From e77a8be9a0a7f2c10151967e3c72c5afcbd41117 Mon Sep 17 00:00:00 2001 From: Arend Van Spriel Date: Fri, 16 Dec 2016 12:15:54 +0000 Subject: nl80211: better describe field in struct nl80211_bss_select_rssi_adjust The two fields in struct nl80211_bss_select_rssi_adjust did not state their type or unit. Adding documentation. Reported-by: Jouni Malinen Signed-off-by: Arend van Spriel Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6b76e3b0c18e..d74e10b1246a 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4964,8 +4964,9 @@ enum nl80211_sched_scan_plan { /** * struct nl80211_bss_select_rssi_adjust - RSSI adjustment parameters. * - * @band: band of BSS that must match for RSSI value adjustment. - * @delta: value used to adjust the RSSI value of matching BSS. + * @band: band of BSS that must match for RSSI value adjustment. The value + * of this field is according to &enum nl80211_band. + * @delta: value used to adjust the RSSI value of matching BSS in dB. */ struct nl80211_bss_select_rssi_adjust { __u8 band; -- cgit v1.3-14-g43fede From 3289025aedc018f8fd9d0e37fb9efa0c6d531ffa Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Mon, 4 Jul 2016 22:35:15 -0700 Subject: RDS: add receive message trace used by application Socket option to tap receive path latency in various stages in nano seconds. It can be enabled on selective sockets using using SO_RDS_MSG_RXPATH_LATENCY socket option. RDS will return the data to application with RDS_CMSG_RXPATH_LATENCY in defined format. Scope is left to add more trace points for future without need of change in the interface. Reviewed-by: Sowmini Varadhan Signed-off-by: Santosh Shilimkar --- include/uapi/linux/rds.h | 33 +++++++++++++++++++++++++++++++++ net/rds/af_rds.c | 28 ++++++++++++++++++++++++++++ net/rds/ib_recv.c | 4 ++++ net/rds/rds.h | 10 ++++++++++ net/rds/recv.c | 32 +++++++++++++++++++++++++++++--- net/rds/tcp_recv.c | 5 +++++ 6 files changed, 109 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index 0f9265cb2a96..3833113ab2c0 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -52,6 +52,13 @@ #define RDS_GET_MR_FOR_DEST 7 #define SO_RDS_TRANSPORT 8 +/* Socket option to tap receive path latency + * SO_RDS: SO_RDS_MSG_RXPATH_LATENCY + * Format used struct rds_rx_trace_so + */ +#define SO_RDS_MSG_RXPATH_LATENCY 10 + + /* supported values for SO_RDS_TRANSPORT */ #define RDS_TRANS_IB 0 #define RDS_TRANS_IWARP 1 @@ -77,6 +84,12 @@ * the same as for the GET_MR setsockopt. * RDS_CMSG_RDMA_STATUS (recvmsg) * Returns the status of a completed RDMA operation. + * RDS_CMSG_RXPATH_LATENCY(recvmsg) + * Returns rds message latencies in various stages of receive + * path in nS. Its set per socket using SO_RDS_MSG_RXPATH_LATENCY + * socket option. Legitimate points are defined in + * enum rds_message_rxpath_latency. More points can be added in + * future. CSMG format is struct rds_cmsg_rx_trace. */ #define RDS_CMSG_RDMA_ARGS 1 #define RDS_CMSG_RDMA_DEST 2 @@ -87,6 +100,7 @@ #define RDS_CMSG_ATOMIC_CSWP 7 #define RDS_CMSG_MASKED_ATOMIC_FADD 8 #define RDS_CMSG_MASKED_ATOMIC_CSWP 9 +#define RDS_CMSG_RXPATH_LATENCY 11 #define RDS_INFO_FIRST 10000 #define RDS_INFO_COUNTERS 10000 @@ -171,6 +185,25 @@ struct rds_info_rdma_connection { uint32_t rdma_mr_size; }; +/* RDS message Receive Path Latency points */ +enum rds_message_rxpath_latency { + RDS_MSG_RX_HDR_TO_DGRAM_START = 0, + RDS_MSG_RX_DGRAM_REASSEMBLE, + RDS_MSG_RX_DGRAM_DELIVERED, + RDS_MSG_RX_DGRAM_TRACE_MAX +}; + +struct rds_rx_trace_so { + u8 rx_traces; + u8 rx_trace_pos[RDS_MSG_RX_DGRAM_TRACE_MAX]; +}; + +struct rds_cmsg_rx_trace { + u8 rx_traces; + u8 rx_trace_pos[RDS_MSG_RX_DGRAM_TRACE_MAX]; + u64 rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX]; +}; + /* * Congestion monitoring. * Congestion control in RDS happens at the host connection diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 2ac1e6194be3..fd8217404162 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -298,6 +298,30 @@ static int rds_enable_recvtstamp(struct sock *sk, char __user *optval, return 0; } +static int rds_recv_track_latency(struct rds_sock *rs, char __user *optval, + int optlen) +{ + struct rds_rx_trace_so trace; + int i; + + if (optlen != sizeof(struct rds_rx_trace_so)) + return -EFAULT; + + if (copy_from_user(&trace, optval, sizeof(trace))) + return -EFAULT; + + rs->rs_rx_traces = trace.rx_traces; + for (i = 0; i < rs->rs_rx_traces; i++) { + if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) { + rs->rs_rx_traces = 0; + return -EFAULT; + } + rs->rs_rx_trace[i] = trace.rx_trace_pos[i]; + } + + return 0; +} + static int rds_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { @@ -338,6 +362,9 @@ static int rds_setsockopt(struct socket *sock, int level, int optname, ret = rds_enable_recvtstamp(sock->sk, optval, optlen); release_sock(sock->sk); break; + case SO_RDS_MSG_RXPATH_LATENCY: + ret = rds_recv_track_latency(rs, optval, optlen); + break; default: ret = -ENOPROTOOPT; } @@ -484,6 +511,7 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol) INIT_LIST_HEAD(&rs->rs_cong_list); spin_lock_init(&rs->rs_rdma_lock); rs->rs_rdma_keys = RB_ROOT; + rs->rs_rx_traces = 0; spin_lock_bh(&rds_sock_lock); list_add_tail(&rs->rs_item, &rds_sock_list); diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 4b0f12679219..e10624aa6959 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -911,8 +911,12 @@ static void rds_ib_process_recv(struct rds_connection *conn, ic->i_ibinc = ibinc; hdr = &ibinc->ii_inc.i_hdr; + ibinc->ii_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] = + local_clock(); memcpy(hdr, ihdr, sizeof(*hdr)); ic->i_recv_data_rem = be32_to_cpu(hdr->h_len); + ibinc->ii_inc.i_rx_lat_trace[RDS_MSG_RX_START] = + local_clock(); rdsdebug("ic %p ibinc %p rem %u flag 0x%x\n", ic, ibinc, ic->i_recv_data_rem, hdr->h_flags); diff --git a/net/rds/rds.h b/net/rds/rds.h index f713194e4620..07fff73dd4f3 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -253,6 +253,11 @@ struct rds_ext_header_rdma_dest { #define RDS_EXTHDR_GEN_NUM 6 #define __RDS_EXTHDR_MAX 16 /* for now */ +#define RDS_RX_MAX_TRACES (RDS_MSG_RX_DGRAM_TRACE_MAX + 1) +#define RDS_MSG_RX_HDR 0 +#define RDS_MSG_RX_START 1 +#define RDS_MSG_RX_END 2 +#define RDS_MSG_RX_CMSG 3 struct rds_incoming { atomic_t i_refcount; @@ -265,6 +270,7 @@ struct rds_incoming { rds_rdma_cookie_t i_rdma_cookie; struct timeval i_rx_tstamp; + u64 i_rx_lat_trace[RDS_RX_MAX_TRACES]; }; struct rds_mr { @@ -575,6 +581,10 @@ struct rds_sock { unsigned char rs_recverr, rs_cong_monitor; u32 rs_hash_initval; + + /* Socket receive path trace points*/ + u8 rs_rx_traces; + u8 rs_rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX]; }; static inline struct rds_sock *rds_sk_to_rs(const struct sock *sk) diff --git a/net/rds/recv.c b/net/rds/recv.c index ba19eeeae85a..8b7e7b7f2c2d 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -43,6 +43,8 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, __be32 saddr) { + int i; + atomic_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = conn; @@ -50,6 +52,9 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, inc->i_rdma_cookie = 0; inc->i_rx_tstamp.tv_sec = 0; inc->i_rx_tstamp.tv_usec = 0; + + for (i = 0; i < RDS_RX_MAX_TRACES; i++) + inc->i_rx_lat_trace[i] = 0; } EXPORT_SYMBOL_GPL(rds_inc_init); @@ -373,6 +378,7 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, if (sock_flag(sk, SOCK_RCVTSTAMP)) do_gettimeofday(&inc->i_rx_tstamp); rds_inc_addref(inc); + inc->i_rx_lat_trace[RDS_MSG_RX_END] = local_clock(); list_add_tail(&inc->i_item, &rs->rs_recv_queue); __rds_wake_sk_sleep(sk); } else { @@ -534,7 +540,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, ret = put_cmsg(msg, SOL_RDS, RDS_CMSG_RDMA_DEST, sizeof(inc->i_rdma_cookie), &inc->i_rdma_cookie); if (ret) - return ret; + goto out; } if ((inc->i_rx_tstamp.tv_sec != 0) && @@ -543,10 +549,30 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, sizeof(struct timeval), &inc->i_rx_tstamp); if (ret) - return ret; + goto out; } - return 0; + if (rs->rs_rx_traces) { + struct rds_cmsg_rx_trace t; + int i, j; + + inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock(); + t.rx_traces = rs->rs_rx_traces; + for (i = 0; i < rs->rs_rx_traces; i++) { + j = rs->rs_rx_trace[i]; + t.rx_trace_pos[i] = j; + t.rx_trace[i] = inc->i_rx_lat_trace[j + 1] - + inc->i_rx_lat_trace[j]; + } + + ret = put_cmsg(msg, SOL_RDS, RDS_CMSG_RXPATH_LATENCY, + sizeof(t), &t); + if (ret) + goto out; + } + +out: + return ret; } int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index ad4892e97f91..e006ef8e6d40 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -180,6 +180,9 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, rdsdebug("alloced tinc %p\n", tinc); rds_inc_path_init(&tinc->ti_inc, cp, cp->cp_conn->c_faddr); + tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] = + local_clock(); + /* * XXX * we might be able to use the __ variants when * we've already serialized at a higher level. @@ -204,6 +207,8 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, /* could be 0 for a 0 len message */ tc->t_tinc_data_rem = be32_to_cpu(tinc->ti_inc.i_hdr.h_len); + tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_START] = + local_clock(); } } -- cgit v1.3-14-g43fede From 237bab6611c607a9e63d50164609923feb8b83b3 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 25 Dec 2016 19:58:58 +0800 Subject: netfilter: nf_tables: add missing descriptions in nft_ct_keys We missed to add descriptions about NFT_CT_LABELS, NFT_CT_PKTS and NFT_CT_BYTES, now add it. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 881d49e94569..5726f90bfc2f 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -860,6 +860,9 @@ enum nft_rt_attributes { * @NFT_CT_PROTOCOL: conntrack layer 4 protocol * @NFT_CT_PROTO_SRC: conntrack layer 4 protocol source * @NFT_CT_PROTO_DST: conntrack layer 4 protocol destination + * @NFT_CT_LABELS: conntrack labels + * @NFT_CT_PKTS: conntrack packets + * @NFT_CT_BYTES: conntrack bytes */ enum nft_ct_keys { NFT_CT_STATE, -- cgit v1.3-14-g43fede From 949a358418aae397d7cf1622aa6515eca766b9e7 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 25 Dec 2016 19:58:59 +0800 Subject: netfilter: nft_ct: add average bytes per packet support Similar to xt_connbytes, user can match how many average bytes per packet a connection has transferred so far. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_ct.c | 22 +++++++++++++++++++++- 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 5726f90bfc2f..b00a05d1ee56 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -863,6 +863,7 @@ enum nft_rt_attributes { * @NFT_CT_LABELS: conntrack labels * @NFT_CT_PKTS: conntrack packets * @NFT_CT_BYTES: conntrack bytes + * @NFT_CT_AVGPKT: conntrack average bytes per packet */ enum nft_ct_keys { NFT_CT_STATE, @@ -881,6 +882,7 @@ enum nft_ct_keys { NFT_CT_LABELS, NFT_CT_PKTS, NFT_CT_BYTES, + NFT_CT_AVGPKT, }; /** diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index e6baeaebe653..d774d7823688 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -129,6 +129,22 @@ static void nft_ct_get_eval(const struct nft_expr *expr, memcpy(dest, &count, sizeof(count)); return; } + case NFT_CT_AVGPKT: { + const struct nf_conn_acct *acct = nf_conn_acct_find(ct); + u64 avgcnt = 0, bcnt = 0, pcnt = 0; + + if (acct) { + pcnt = nft_ct_get_eval_counter(acct->counter, + NFT_CT_PKTS, priv->dir); + bcnt = nft_ct_get_eval_counter(acct->counter, + NFT_CT_BYTES, priv->dir); + if (pcnt != 0) + avgcnt = div64_u64(bcnt, pcnt); + } + + memcpy(dest, &avgcnt, sizeof(avgcnt)); + return; + } case NFT_CT_L3PROTOCOL: *dest = nf_ct_l3num(ct); return; @@ -316,6 +332,7 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, break; case NFT_CT_BYTES: case NFT_CT_PKTS: + case NFT_CT_AVGPKT: /* no direction? return sum of original + reply */ if (tb[NFTA_CT_DIRECTION] == NULL) priv->dir = IP_CT_DIR_MAX; @@ -346,7 +363,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (err < 0) return err; - if (priv->key == NFT_CT_BYTES || priv->key == NFT_CT_PKTS) + if (priv->key == NFT_CT_BYTES || + priv->key == NFT_CT_PKTS || + priv->key == NFT_CT_AVGPKT) nf_ct_set_acct(ctx->net, true); return 0; @@ -445,6 +464,7 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) break; case NFT_CT_BYTES: case NFT_CT_PKTS: + case NFT_CT_AVGPKT: if (priv->dir < IP_CT_DIR_MAX && nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir)) goto nla_put_failure; -- cgit v1.3-14-g43fede From 1708ebc9636a249e104b83c6d105f15244825281 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 3 Jan 2017 12:13:39 +0100 Subject: ipmr, ip6mr: add RTNH_F_UNRESOLVED flag to unresolved cache entries While working with ipmr, we noticed that it is impossible to determine if an entry is actually unresolved or its IIF interface has disappeared (e.g. virtual interface got deleted). These entries look almost identical to user-space when dumping or receiving notifications. So in order to recognize them add a new RTNH_F_UNRESOLVED flag which is set when sending an unresolved cache entry to user-space. Suggested-by: Roopa Prabhu Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 1 + net/ipv4/ipmr.c | 4 +++- net/ipv6/ip6mr.c | 4 +++- 3 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index e14377f2ec27..8c93ad1ef9ab 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -350,6 +350,7 @@ struct rtnexthop { #define RTNH_F_ONLINK 4 /* Gateway is forced on link */ #define RTNH_F_OFFLOAD 8 /* offloaded route */ #define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */ +#define RTNH_F_UNRESOLVED 32 /* The entry is unresolved (ipmr) */ #define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index efc1e76d4977..b35dda57586b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2091,8 +2091,10 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, int ct; /* If cache is unresolved, don't try to parse IIF and OIF */ - if (c->mfc_parent >= MAXVIFS) + if (c->mfc_parent >= MAXVIFS) { + rtm->rtm_flags |= RTNH_F_UNRESOLVED; return -ENOENT; + } if (VIF_EXISTS(mrt, c->mfc_parent) && nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 604d8953c775..e275077e8af2 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2243,8 +2243,10 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, int ct; /* If cache is unresolved, don't try to parse IIF and OIF */ - if (c->mf6c_parent >= MAXMIFS) + if (c->mf6c_parent >= MAXMIFS) { + rtm->rtm_flags |= RTNH_F_UNRESOLVED; return -ENOENT; + } if (MIF_EXISTS(mrt, c->mf6c_parent) && nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0) -- cgit v1.3-14-g43fede From aec745e2c520bf2d046684a284dac11c25d8e717 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 7 Jan 2017 17:06:33 -0500 Subject: net-tc: remove unused tc_verd fields Remove the last reference to tc_verd's munge and redirect ttl bits. These fields are no longer used. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index cb4bcdc58543..c769f71972f5 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -17,10 +17,6 @@ /* verdict bit breakdown * -bit 0: when set -> this packet has been munged already - -bit 1: when set -> It is ok to munge this packet - bit 2,3,4,5: Reclassify counter - sort of reverse TTL - if exceeded assume loop @@ -31,8 +27,6 @@ bit 6,7: Where this packet was last seen bit 8: when set --> Request not to classify on ingress. -bits 9,10,11: redirect counter - redirect TTL. Loop avoidance - * * */ @@ -56,7 +50,6 @@ bits 9,10,11: redirect counter - redirect TTL. Loop avoidance #define SET_TC_AT(v,n) ((V_TC_AT(n)) | (v & ~M_TC_AT)) #define MAX_REC_LOOP 4 -#define MAX_RED_LOOP 4 #endif /* Action attributes */ -- cgit v1.3-14-g43fede From d6264071ce7d100a2b7c1f295167796ab5178caf Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 7 Jan 2017 17:06:34 -0500 Subject: net-tc: make MAX_RECLASSIFY_LOOP local This field is no longer kept in tc_verd. Remove it from the global definition of that struct. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 5 ----- net/sched/sch_api.c | 3 ++- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index c769f71972f5..bba23dbb3ab6 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -17,9 +17,6 @@ /* verdict bit breakdown * -bit 2,3,4,5: Reclassify counter - sort of reverse TTL - if exceeded -assume loop - bit 6,7: Where this packet was last seen 0: Above the transmit example at the socket level 1: on the Ingress @@ -48,8 +45,6 @@ bit 8: when set --> Request not to classify on ingress. #define G_TC_AT(x) _TC_GETVALUE(x,S_TC_AT,M_TC_AT) #define V_TC_AT(x) _TC_MAKEVALUE(x,S_TC_AT) #define SET_TC_AT(v,n) ((V_TC_AT(n)) | (v & ~M_TC_AT)) - -#define MAX_REC_LOOP 4 #endif /* Action attributes */ diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d7b93429f0cc..ef53ede11590 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1861,6 +1861,7 @@ int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, { __be16 protocol = tc_skb_protocol(skb); #ifdef CONFIG_NET_CLS_ACT + const int max_reclassify_loop = 4; const struct tcf_proto *old_tp = tp; int limit = 0; @@ -1885,7 +1886,7 @@ reclassify: return TC_ACT_UNSPEC; /* signal: continue lookup */ #ifdef CONFIG_NET_CLS_ACT reset: - if (unlikely(limit++ >= MAX_REC_LOOP)) { + if (unlikely(limit++ >= max_reclassify_loop)) { net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", tp->q->ops->id, tp->prio & 0xffff, ntohs(tp->protocol)); -- cgit v1.3-14-g43fede From e7246e122aaa99ebbb8ad7da80f35a20577bd8af Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 7 Jan 2017 17:06:35 -0500 Subject: net-tc: extract skip classify bit from tc_verd Packets sent by the IFB device skip subsequent tc classification. A single bit governs this state. Move it out of tc_verd in anticipation of removing that __u16 completely. The new bitfield tc_skip_classify temporarily uses one bit of a hole, until tc_verd is removed completely in a follow-up patch. Remove the bit hole comment. It could be 2, 3, 4 or 5 bits long. With that many options, little value in documenting it. Introduce a helper function to deduplicate the logic in the two sites that check this bit. The field tc_skip_classify is set only in IFB on skbs cloned in act_mirred, so original packet sources do not have to clear the bit when reusing packets (notably, pktgen and octeon). Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- drivers/net/ifb.c | 2 +- include/linux/skbuff.h | 5 ++++- include/net/sch_generic.h | 11 +++++++++++ include/uapi/linux/pkt_cls.h | 6 ------ net/core/dev.c | 10 +++------- net/sched/act_api.c | 11 ++++------- 6 files changed, 23 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 082534e187fc..442c4c4a9606 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -81,7 +81,7 @@ static void ifb_ri_tasklet(unsigned long _txp) u32 from = G_TC_FROM(skb->tc_verd); skb->tc_verd = 0; - skb->tc_verd = SET_TC_NCLS(skb->tc_verd); + skb->tc_skip_classify = 1; u64_stats_update_begin(&txp->tsync); txp->tx_packets++; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b53c0cfd417e..570f60ec6cb4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -589,6 +589,7 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @tc_skip_classify: do not classify packet. set by IFB device * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag @@ -749,7 +750,9 @@ struct sk_buff { #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; #endif - /* 2, 4 or 5 bit hole */ +#ifdef CONFIG_NET_CLS_ACT + __u8 tc_skip_classify:1; +#endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 498f81b229a4..857356f2d74b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -418,6 +418,17 @@ static inline bool skb_at_tc_ingress(const struct sk_buff *skb) #endif } +static inline bool skb_skip_tc_classify(struct sk_buff *skb) +{ +#ifdef CONFIG_NET_CLS_ACT + if (skb->tc_skip_classify) { + skb->tc_skip_classify = 0; + return true; + } +#endif + return false; +} + /* Reset all TX qdiscs greater then index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index bba23dbb3ab6..1eed5d7509bc 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -22,8 +22,6 @@ bit 6,7: Where this packet was last seen 1: on the Ingress 2: on the Egress -bit 8: when set --> Request not to classify on ingress. - * * */ @@ -36,10 +34,6 @@ bit 8: when set --> Request not to classify on ingress. #define AT_INGRESS 0x1 #define AT_EGRESS 0x2 -#define TC_NCLS _TC_MAKEMASK1(8) -#define SET_TC_NCLS(v) ( TC_NCLS | (v & ~TC_NCLS)) -#define CLR_TC_NCLS(v) ( v & ~TC_NCLS) - #define S_TC_AT _TC_MAKE32(12) #define M_TC_AT _TC_MAKEMASK(2,S_TC_AT) #define G_TC_AT(x) _TC_GETVALUE(x,S_TC_AT,M_TC_AT) diff --git a/net/core/dev.c b/net/core/dev.c index 56818f7eab2b..e39e35d2e082 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4093,12 +4093,8 @@ another_round: goto out; } -#ifdef CONFIG_NET_CLS_ACT - if (skb->tc_verd & TC_NCLS) { - skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); - goto ncls; - } -#endif + if (skb_skip_tc_classify(skb)) + goto skip_classify; if (pfmemalloc) goto skip_taps; @@ -4128,8 +4124,8 @@ skip_taps: #endif #ifdef CONFIG_NET_CLS_ACT skb->tc_verd = 0; -ncls: #endif +skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2095c83ce773..f04715a57300 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -426,11 +426,9 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, { int ret = -1, i; - if (skb->tc_verd & TC_NCLS) { - skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); - ret = TC_ACT_OK; - goto exec_done; - } + if (skb_skip_tc_classify(skb)) + return TC_ACT_OK; + for (i = 0; i < nr_actions; i++) { const struct tc_action *a = actions[i]; @@ -439,9 +437,8 @@ repeat: if (ret == TC_ACT_REPEAT) goto repeat; /* we need a ttl - JHS */ if (ret != TC_ACT_PIPE) - goto exec_done; + break; } -exec_done: return ret; } EXPORT_SYMBOL(tcf_action_exec); -- cgit v1.3-14-g43fede From a5135bcfba7345031df45e02cd150a45add47cf8 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 7 Jan 2017 17:06:36 -0500 Subject: net-tc: convert tc_verd to integer bitfields Extract the remaining two fields from tc_verd and remove the __u16 completely. TC_AT and TC_FROM are converted to equivalent two-bit integer fields tc_at and tc_from. Where possible, use existing helper skb_at_tc_ingress when reading tc_at. Introduce helper skb_reset_tc to clear fields. Not documenting tc_from and tc_at, because they will be replaced with single bit fields in follow-on patches. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- drivers/net/ifb.c | 7 +++---- drivers/staging/octeon/ethernet-tx.c | 5 ++--- include/linux/skbuff.h | 6 ++---- include/net/sch_generic.h | 10 +++++++++- include/uapi/linux/pkt_cls.h | 31 ------------------------------- net/core/dev.c | 10 ++++------ net/core/pktgen.c | 4 +--- net/core/skbuff.c | 3 --- net/sched/act_ife.c | 7 +++---- net/sched/act_mirred.c | 9 ++++----- net/sched/sch_netem.c | 2 +- 11 files changed, 29 insertions(+), 65 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 442c4c4a9606..b73b6b6c066b 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -78,9 +78,9 @@ static void ifb_ri_tasklet(unsigned long _txp) } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { - u32 from = G_TC_FROM(skb->tc_verd); + u32 from = skb->tc_from; - skb->tc_verd = 0; + skb_reset_tc(skb); skb->tc_skip_classify = 1; u64_stats_update_begin(&txp->tsync); @@ -239,7 +239,6 @@ static void ifb_setup(struct net_device *dev) static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ifb_dev_private *dp = netdev_priv(dev); - u32 from = G_TC_FROM(skb->tc_verd); struct ifb_q_private *txp = dp->tx_private + skb_get_queue_mapping(skb); u64_stats_update_begin(&txp->rsync); @@ -247,7 +246,7 @@ static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) txp->rx_bytes += skb->len; u64_stats_update_end(&txp->rsync); - if (!(from & (AT_INGRESS|AT_EGRESS)) || !skb->skb_iif) { + if (skb->tc_from == AT_STACK || !skb->skb_iif) { dev_kfree_skb(skb); dev->stats.rx_dropped++; return NETDEV_TX_OK; diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c index 6b4c20872323..0b8053205091 100644 --- a/drivers/staging/octeon/ethernet-tx.c +++ b/drivers/staging/octeon/ethernet-tx.c @@ -23,6 +23,7 @@ #endif /* CONFIG_XFRM */ #include +#include #include @@ -369,9 +370,7 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev) #ifdef CONFIG_NET_SCHED skb->tc_index = 0; -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = 0; -#endif /* CONFIG_NET_CLS_ACT */ + skb_reset_tc(skb); #endif /* CONFIG_NET_SCHED */ #endif /* REUSE_SKBUFFS_WITHOUT_FREE */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 570f60ec6cb4..f738d09947b2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -599,7 +599,6 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index - * @tc_verd: traffic control verdict * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue @@ -752,13 +751,12 @@ struct sk_buff { #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; + __u8 tc_at:2; + __u8 tc_from:2; #endif #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ -#ifdef CONFIG_NET_CLS_ACT - __u16 tc_verd; /* traffic control verdict */ -#endif #endif union { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 857356f2d74b..f80dba516964 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -409,10 +409,18 @@ bool tcf_destroy(struct tcf_proto *tp, bool force); void tcf_destroy_chain(struct tcf_proto __rcu **fl); int skb_do_redirect(struct sk_buff *); +static inline void skb_reset_tc(struct sk_buff *skb) +{ +#ifdef CONFIG_NET_CLS_ACT + skb->tc_at = 0; + skb->tc_from = 0; +#endif +} + static inline bool skb_at_tc_ingress(const struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT - return G_TC_AT(skb->tc_verd) & AT_INGRESS; + return skb->tc_at & AT_INGRESS; #else return false; #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 1eed5d7509bc..cee753a7a40c 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -5,40 +5,9 @@ #include #ifdef __KERNEL__ -/* I think i could have done better macros ; for now this is stolen from - * some arch/mips code - jhs -*/ -#define _TC_MAKE32(x) ((x)) - -#define _TC_MAKEMASK1(n) (_TC_MAKE32(1) << _TC_MAKE32(n)) -#define _TC_MAKEMASK(v,n) (_TC_MAKE32((_TC_MAKE32(1)<<(v))-1) << _TC_MAKE32(n)) -#define _TC_MAKEVALUE(v,n) (_TC_MAKE32(v) << _TC_MAKE32(n)) -#define _TC_GETVALUE(v,n,m) ((_TC_MAKE32(v) & _TC_MAKE32(m)) >> _TC_MAKE32(n)) - -/* verdict bit breakdown - * -bit 6,7: Where this packet was last seen -0: Above the transmit example at the socket level -1: on the Ingress -2: on the Egress - - * - * */ - -#define S_TC_FROM _TC_MAKE32(6) -#define M_TC_FROM _TC_MAKEMASK(2,S_TC_FROM) -#define G_TC_FROM(x) _TC_GETVALUE(x,S_TC_FROM,M_TC_FROM) -#define V_TC_FROM(x) _TC_MAKEVALUE(x,S_TC_FROM) -#define SET_TC_FROM(v,n) ((V_TC_FROM(n)) | (v & ~M_TC_FROM)) #define AT_STACK 0x0 #define AT_INGRESS 0x1 #define AT_EGRESS 0x2 - -#define S_TC_AT _TC_MAKE32(12) -#define M_TC_AT _TC_MAKEMASK(2,S_TC_AT) -#define G_TC_AT(x) _TC_GETVALUE(x,S_TC_AT,M_TC_AT) -#define V_TC_AT(x) _TC_MAKEVALUE(x,S_TC_AT) -#define SET_TC_AT(v,n) ((V_TC_AT(n)) | (v & ~M_TC_AT)) #endif /* Action attributes */ diff --git a/net/core/dev.c b/net/core/dev.c index e39e35d2e082..8b5d6d033473 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3153,7 +3153,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) if (!cl) return skb; - /* skb->tc_verd and qdisc_skb_cb(skb)->pkt_len were already set + /* skb->tc_at and qdisc_skb_cb(skb)->pkt_len were already set * earlier by the caller. */ qdisc_bstats_cpu_update(cl->q, skb); @@ -3320,7 +3320,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); + skb->tc_at = AT_EGRESS; # ifdef CONFIG_NET_EGRESS if (static_key_false(&egress_needed)) { skb = sch_handle_egress(skb, &rc, dev); @@ -3920,7 +3920,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, } qdisc_skb_cb(skb)->pkt_len = skb->len; - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); + skb->tc_at = AT_INGRESS; qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res, false)) { @@ -4122,9 +4122,7 @@ skip_taps: goto out; } #endif -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = 0; -#endif + skb_reset_tc(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 8e69ce472236..96947f5d41e4 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3439,9 +3439,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) /* skb was 'freed' by stack, so clean few * bits and reuse it */ -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = 0; /* reset reclass/redir ttl */ -#endif + skb_reset_tc(skb); } while (--burst > 0); goto out; /* Skips xmit_mode M_START_XMIT */ } else if (pkt_dev->xmit_mode == M_QUEUE_XMIT) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5a03730fbc1a..adec4bf807d8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -878,9 +878,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); -#ifdef CONFIG_NET_CLS_ACT - CHECK_SKB_FIELD(tc_verd); -#endif #endif } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 80b848d3f096..921fb20eaa7c 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -736,12 +736,11 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, u16 metalen = ife_get_sz(skb, ife); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; unsigned int skboff = skb->dev->hard_header_len; - u32 at = G_TC_AT(skb->tc_verd); int new_len = skb->len + hdrm; bool exceed_mtu = false; int err; - if (at & AT_EGRESS) { + if (!skb_at_tc_ingress(skb)) { if (new_len > skb->dev->mtu) exceed_mtu = true; } @@ -773,7 +772,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, return TC_ACT_SHOT; } - if (!(at & AT_EGRESS)) + if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); iethh = (struct ethhdr *)skb->data; @@ -816,7 +815,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, ether_addr_copy(oethh->h_dest, iethh->h_dest); oethh->h_proto = htons(ife->eth_type); - if (!(at & AT_EGRESS)) + if (skb_at_tc_ingress(skb)) skb_pull(skb, skb->dev->hard_header_len); spin_unlock(&ife->tcf_lock); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 2d9fa6e0a1b4..8543279bba49 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -170,7 +170,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, int retval, err = 0; int m_eaction; int mac_len; - u32 at; tcf_lastuse_update(&m->tcf_tm); bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); @@ -191,7 +190,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, goto out; } - at = G_TC_AT(skb->tc_verd); skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) goto out; @@ -200,8 +198,9 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, * and devices expect a mac header on xmit, then mac push/pull is * needed. */ - if (at != tcf_mirred_act_direction(m_eaction) && m_mac_header_xmit) { - if (at & AT_EGRESS) { + if (skb->tc_at != tcf_mirred_act_direction(m_eaction) && + m_mac_header_xmit) { + if (!skb_at_tc_ingress(skb)) { /* caught at egress, act ingress: pull mac */ mac_len = skb_network_header(skb) - skb_mac_header(skb); skb_pull_rcsum(skb2, mac_len); @@ -213,7 +212,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, /* mirror is always swallowed */ if (tcf_mirred_is_act_redirect(m_eaction)) - skb2->tc_verd = SET_TC_FROM(skb2->tc_verd, at); + skb2->tc_from = skb2->tc_at; skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index bcfadfdea8e0..bb5c638b6852 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -626,7 +626,7 @@ deliver: * If it's at ingress let's pretend the delay is * from the network (tstamp will be updated). */ - if (G_TC_FROM(skb->tc_verd) & AT_INGRESS) + if (skb->tc_from & AT_INGRESS) skb->tstamp = 0; #endif -- cgit v1.3-14-g43fede From bc31c905e946b5c55df5d2938335e78ffb3157ca Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 7 Jan 2017 17:06:38 -0500 Subject: net-tc: convert tc_from to tc_from_ingress and tc_redirected The tc_from field fulfills two roles. It encodes whether a packet was redirected by an act_mirred device and, if so, whether act_mirred was called on ingress or egress. Split it into separate fields. The information is needed by the special IFB loop, where packets are taken out of the normal path by act_mirred, forwarded to IFB, then reinjected at their original location (ingress or egress) by IFB. The IFB device cannot use skb->tc_at_ingress, because that may have been overwritten as the packet travels from act_mirred to ifb_xmit, when it passes through tc_classify on the IFB egress path. Cache this value in skb->tc_from_ingress. That field is valid only if a packet arriving at ifb_xmit came from act_mirred. Other packets can be crafted to reach ifb_xmit. These must be dropped. Set tc_redirected on redirection and drop all packets that do not have this bit set. Both fields are set only on cloned skbs in tc actions, so original packet sources do not have to clear the bit when reusing packets (notably, pktgen and octeon). Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- drivers/net/ifb.c | 13 +++++-------- include/linux/skbuff.h | 5 ++++- include/net/sch_generic.h | 2 +- include/uapi/linux/pkt_cls.h | 6 ------ net/sched/act_mirred.c | 6 ++++-- net/sched/sch_netem.c | 2 +- 6 files changed, 15 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index b73b6b6c066b..312fce7302d3 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -78,9 +78,7 @@ static void ifb_ri_tasklet(unsigned long _txp) } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { - u32 from = skb->tc_from; - - skb_reset_tc(skb); + skb->tc_redirected = 0; skb->tc_skip_classify = 1; u64_stats_update_begin(&txp->tsync); @@ -101,13 +99,12 @@ static void ifb_ri_tasklet(unsigned long _txp) rcu_read_unlock(); skb->skb_iif = txp->dev->ifindex; - if (from & AT_EGRESS) { + if (!skb->tc_from_ingress) { dev_queue_xmit(skb); - } else if (from & AT_INGRESS) { + } else { skb_pull(skb, skb->mac_len); netif_receive_skb(skb); - } else - BUG(); + } } if (__netif_tx_trylock(txq)) { @@ -246,7 +243,7 @@ static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) txp->rx_bytes += skb->len; u64_stats_update_end(&txp->rsync); - if (skb->tc_from == AT_STACK || !skb->skb_iif) { + if (!skb->tc_redirected || !skb->skb_iif) { dev_kfree_skb(skb); dev->stats.rx_dropped++; return NETDEV_TX_OK; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fab3f87e9bd1..3149a88de548 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -591,6 +591,8 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1, * @ipvs_property: skbuff is owned by ipvs * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress + * @tc_redirected: packet was redirected by a tc action + * @tc_from_ingress: if tc_redirected, tc_at_ingress at time of redirect * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag @@ -753,7 +755,8 @@ struct sk_buff { #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; __u8 tc_at_ingress:1; - __u8 tc_from:2; + __u8 tc_redirected:1; + __u8 tc_from_ingress:1; #endif #ifdef CONFIG_NET_SCHED diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 4bd6d5387209..e2f426f6d62f 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -412,7 +412,7 @@ int skb_do_redirect(struct sk_buff *); static inline void skb_reset_tc(struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT - skb->tc_from = 0; + skb->tc_redirected = 0; #endif } diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index cee753a7a40c..a081efbd61a2 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -4,12 +4,6 @@ #include #include -#ifdef __KERNEL__ -#define AT_STACK 0x0 -#define AT_INGRESS 0x1 -#define AT_EGRESS 0x2 -#endif - /* Action attributes */ enum { TCA_ACT_UNSPEC, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index e832c62fd705..84682f02b611 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -211,8 +211,10 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, } /* mirror is always swallowed */ - if (tcf_mirred_is_act_redirect(m_eaction)) - skb2->tc_from = skb_at_tc_ingress(skb) ? AT_INGRESS : AT_EGRESS; + if (tcf_mirred_is_act_redirect(m_eaction)) { + skb2->tc_redirected = 1; + skb2->tc_from_ingress = skb2->tc_at_ingress; + } skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index bb5c638b6852..c8bb62a1e744 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -626,7 +626,7 @@ deliver: * If it's at ingress let's pretend the delay is * from the network (tstamp will be updated). */ - if (skb->tc_from & AT_INGRESS) + if (skb->tc_redirected && skb->tc_from_ingress) skb->tstamp = 0; #endif -- cgit v1.3-14-g43fede From bd2522b168847106c1885f0319a2833bdf88bf9a Mon Sep 17 00:00:00 2001 From: Andrzej Zaborowski Date: Fri, 6 Jan 2017 16:33:43 -0500 Subject: cfg80211: NL80211_ATTR_SOCKET_OWNER support for CMD_CONNECT Disconnect or deauthenticate when the owning socket is closed if this flag is supplied to CMD_CONNECT or CMD_ASSOCIATE. This may be used to ensure userspace daemon doesn't leave an unmanaged connection behind. In some situations it would be possible to account for that, to some degree, in the deamon restart code or in the up/down scripts without the use of this attribute. But there will be systems where the daemon can go away for varying periods without a warning due to local resource management. Signed-off-by: Andrew Zaborowski Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 7 +++++++ include/uapi/linux/nl80211.h | 2 ++ net/wireless/core.c | 3 +++ net/wireless/core.h | 1 + net/wireless/mlme.c | 5 +++++ net/wireless/nl80211.c | 26 +++++++++++++++++++++++++- net/wireless/sme.c | 33 +++++++++++++++++++++++++++++++++ 7 files changed, 76 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 41a9ecd82ca0..cb13789ebaef 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3865,6 +3865,9 @@ struct cfg80211_cached_keys; * @conn: (private) cfg80211 software SME connection state machine data * @connect_keys: (private) keys to set after connection is established * @conn_bss_type: connecting/connected BSS type + * @conn_owner_nlportid: (private) connection owner socket port ID + * @disconnect_wk: (private) auto-disconnect work + * @disconnect_bssid: (private) the BSSID to use for auto-disconnect * @ibss_fixed: (private) IBSS is using fixed BSSID * @ibss_dfs_possible: (private) IBSS may change to a DFS channel * @event_list: (private) list for internal event processing @@ -3896,6 +3899,10 @@ struct wireless_dev { struct cfg80211_conn *conn; struct cfg80211_cached_keys *connect_keys; enum ieee80211_bss_type conn_bss_type; + u32 conn_owner_nlportid; + + struct work_struct disconnect_wk; + u8 disconnect_bssid[ETH_ALEN]; struct list_head event_list; spinlock_t event_lock; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d74e10b1246a..174f4b30e804 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1820,6 +1820,8 @@ enum nl80211_commands { * and remove functions. NAN notifications will be sent in unicast to that * socket. Without this attribute, any socket can add functions and the * notifications will be sent to the %NL80211_MCGRP_NAN multicast group. + * If set during %NL80211_CMD_ASSOCIATE or %NL80211_CMD_CONNECT the + * station will deauthenticate when the socket is closed. * * @NL80211_ATTR_TDLS_INITIATOR: flag attribute indicating the current end is * the TDLS link initiator. diff --git a/net/wireless/core.c b/net/wireless/core.c index 158c59ecf90a..903fc419217a 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1142,6 +1142,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr) dev->priv_flags |= IFF_DONT_BRIDGE; + INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); break; case NETDEV_GOING_DOWN: @@ -1230,6 +1232,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, #ifdef CONFIG_CFG80211_WEXT kzfree(wdev->wext.keys); #endif + flush_work(&wdev->disconnect_wk); } /* * synchronise (so that we won't find this netdev diff --git a/net/wireless/core.h b/net/wireless/core.h index bc8ba6e57519..ba42055a036d 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -400,6 +400,7 @@ void __cfg80211_roamed(struct wireless_dev *wdev, const u8 *resp_ie, size_t resp_ie_len); int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); +void cfg80211_autodisconnect_wk(struct work_struct *work); /* SME implementation */ void cfg80211_conn_work(struct work_struct *work); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 4646cf5695b9..1c63a77aea34 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -345,6 +345,11 @@ int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, !ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) return 0; + if (ether_addr_equal(wdev->disconnect_bssid, bssid) || + (wdev->current_bss && + ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) + wdev->conn_owner_nlportid = 0; + return rdev_deauth(rdev, dev, &req); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fed33ec20a71..b378d0a04003 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -8050,8 +8050,17 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) err = nl80211_crypto_settings(rdev, info, &req.crypto, 1); if (!err) { wdev_lock(dev->ieee80211_ptr); + err = cfg80211_mlme_assoc(rdev, dev, chan, bssid, ssid, ssid_len, &req); + + if (!err && info->attrs[NL80211_ATTR_SOCKET_OWNER]) { + dev->ieee80211_ptr->conn_owner_nlportid = + info->snd_portid; + memcpy(dev->ieee80211_ptr->disconnect_bssid, + bssid, ETH_ALEN); + } + wdev_unlock(dev->ieee80211_ptr); } @@ -8770,11 +8779,24 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) } wdev_lock(dev->ieee80211_ptr); + err = cfg80211_connect(rdev, dev, &connect, connkeys, connect.prev_bssid); - wdev_unlock(dev->ieee80211_ptr); if (err) kzfree(connkeys); + + if (!err && info->attrs[NL80211_ATTR_SOCKET_OWNER]) { + dev->ieee80211_ptr->conn_owner_nlportid = info->snd_portid; + if (connect.bssid) + memcpy(dev->ieee80211_ptr->disconnect_bssid, + connect.bssid, ETH_ALEN); + else + memset(dev->ieee80211_ptr->disconnect_bssid, + 0, ETH_ALEN); + } + + wdev_unlock(dev->ieee80211_ptr); + return err; } @@ -14491,6 +14513,8 @@ static int nl80211_netlink_notify(struct notifier_block * nb, if (wdev->owner_nlportid == notify->portid) schedule_destroy_work = true; + else if (wdev->conn_owner_nlportid == notify->portid) + schedule_work(&wdev->disconnect_wk); } spin_lock_bh(&rdev->beacon_registrations_lock); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 5e0d19380302..46693913fcea 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -727,6 +727,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, kzfree(wdev->connect_keys); wdev->connect_keys = NULL; wdev->ssid_len = 0; + wdev->conn_owner_nlportid = 0; if (bss) { cfg80211_unhold_bss(bss_from_pub(bss)); cfg80211_put_bss(wdev->wiphy, bss); @@ -955,6 +956,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, wdev->current_bss = NULL; wdev->ssid_len = 0; + wdev->conn_owner_nlportid = 0; nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); @@ -1098,6 +1100,8 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, kzfree(wdev->connect_keys); wdev->connect_keys = NULL; + wdev->conn_owner_nlportid = 0; + if (wdev->conn) err = cfg80211_sme_disconnect(wdev, reason); else if (!rdev->ops->disconnect) @@ -1107,3 +1111,32 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, return err; } + +/* + * Used to clean up after the connection / connection attempt owner socket + * disconnects + */ +void cfg80211_autodisconnect_wk(struct work_struct *work) +{ + struct wireless_dev *wdev = + container_of(work, struct wireless_dev, disconnect_wk); + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + + wdev_lock(wdev); + + if (wdev->conn_owner_nlportid) { + /* + * Use disconnect_bssid if still connecting and ops->disconnect + * not implemented. Otherwise we can use cfg80211_disconnect. + */ + if (rdev->ops->disconnect || wdev->current_bss) + cfg80211_disconnect(rdev, wdev->netdev, + WLAN_REASON_DEAUTH_LEAVING, true); + else + cfg80211_mlme_deauth(rdev, wdev->netdev, + wdev->disconnect_bssid, NULL, 0, + WLAN_REASON_DEAUTH_LEAVING, false); + } + + wdev_unlock(wdev); +} -- cgit v1.3-14-g43fede From c008b33f3ef0915dfb57432dba1fa0ce34fdcc29 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Mon, 9 Jan 2017 11:24:21 +0100 Subject: net/sched: act_csum: compute crc32c on SCTP packets modify act_csum to compute crc32c on IPv4/IPv6 packets having SCTP in their payload, and extend UAPI definitions accordingly. Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_csum.h | 3 ++- net/sched/act_csum.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tc_act/tc_csum.h b/include/uapi/linux/tc_act/tc_csum.h index 8ac8041ab5f1..a11bb355dbfb 100644 --- a/include/uapi/linux/tc_act/tc_csum.h +++ b/include/uapi/linux/tc_act/tc_csum.h @@ -21,7 +21,8 @@ enum { TCA_CSUM_UPDATE_FLAG_IGMP = 4, TCA_CSUM_UPDATE_FLAG_TCP = 8, TCA_CSUM_UPDATE_FLAG_UDP = 16, - TCA_CSUM_UPDATE_FLAG_UDPLITE = 32 + TCA_CSUM_UPDATE_FLAG_UDPLITE = 32, + TCA_CSUM_UPDATE_FLAG_SCTP = 64, }; struct tc_csum { diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index a0edd80a44db..e978ccd4402c 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -30,6 +30,7 @@ #include #include #include +#include #include @@ -322,6 +323,25 @@ ignore_obscure_skb: return 1; } +static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, + unsigned int ipl) +{ + struct sctphdr *sctph; + + if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) + return 1; + + sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); + if (!sctph) + return 0; + + sctph->checksum = sctp_compute_cksum(skb, + skb_network_offset(skb) + ihl); + skb->ip_summed = CHECKSUM_NONE; + + return 1; +} + static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags) { const struct iphdr *iph; @@ -365,6 +385,11 @@ static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags) ntohs(iph->tot_len), 1)) goto fail; break; + case IPPROTO_SCTP: + if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) && + !tcf_csum_sctp(skb, iph->ihl * 4, ntohs(iph->tot_len))) + goto fail; + break; } if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) { @@ -481,6 +506,11 @@ static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags) pl + sizeof(*ip6h), 1)) goto fail; goto done; + case IPPROTO_SCTP: + if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) && + !tcf_csum_sctp(skb, hl, pl + sizeof(*ip6h))) + goto fail; + goto done; default: goto ignore_skb; } -- cgit v1.3-14-g43fede From 6812baabf24d5c299c13223366a23c269408f4d0 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 9 Jan 2017 16:55:15 +0100 Subject: smc: establish pnet table management Connection creation with SMC-R starts through an internal TCP-connection. The Ethernet interface for this TCP-connection is not restricted to the Ethernet interface of a RoCE device. Any existing Ethernet interface belonging to the same physical net can be used, as long as there is a defined relation between the Ethernet interface and some RoCE devices. This relation is defined with the help of an identification string called "Physical Net ID" or short "pnet ID". Information about defined pnet IDs and their related Ethernet interfaces and RoCE devices is stored in the SMC-R pnet table. A pnet table entry consists of the identifying pnet ID and the associated network and IB device. This patch adds pnet table configuration support using the generic netlink message interface referring to network and IB device by their names. Commands exist to add, delete, and display pnet table entries, and to flush or display the entire pnet table. There are cross-checks to verify whether the ethernet interfaces or infiniband devices really exist in the system. If either device is not available, the pnet ID entry is not created. Loss of network devices and IB devices is also monitored; a pnet ID entry is removed when an associated network or IB device is removed. Signed-off-by: Thomas Richter Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 35 ++++ net/smc/Makefile | 2 +- net/smc/af_smc.c | 11 +- net/smc/smc_ib.c | 2 + net/smc/smc_pnet.c | 534 +++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_pnet.h | 23 ++ 6 files changed, 604 insertions(+), 3 deletions(-) create mode 100644 include/uapi/linux/smc.h create mode 100644 net/smc/smc_pnet.c create mode 100644 net/smc/smc_pnet.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h new file mode 100644 index 000000000000..ab1dea8e53ee --- /dev/null +++ b/include/uapi/linux/smc.h @@ -0,0 +1,35 @@ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for generic netlink based configuration of an SMC-R PNET table + * + * Copyright IBM Corp. 2016 + * + * Author(s): Thomas Richter + */ + +#ifndef _UAPI_LINUX_SMC_H_ +#define _UAPI_LINUX_SMC_H_ + +/* Netlink SMC_PNETID attributes */ +enum { + SMC_PNETID_UNSPEC, + SMC_PNETID_NAME, + SMC_PNETID_ETHNAME, + SMC_PNETID_IBNAME, + SMC_PNETID_IBPORT, + __SMC_PNETID_MAX, + SMC_PNETID_MAX = __SMC_PNETID_MAX - 1 +}; + +enum { /* SMC PNET Table commands */ + SMC_PNETID_GET = 1, + SMC_PNETID_ADD, + SMC_PNETID_DEL, + SMC_PNETID_FLUSH +}; + +#define SMCR_GENL_FAMILY_NAME "SMC_PNETID" +#define SMCR_GENL_FAMILY_VERSION 1 + +#endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/Makefile b/net/smc/Makefile index 56f2170e6f64..50f39ffec8c9 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -1,2 +1,2 @@ obj-$(CONFIG_SMC) += smc.o -smc-y := af_smc.o smc_ib.o +smc-y := af_smc.o smc_pnet.o smc_ib.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 50492ee495ce..8b059b2fc34d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -21,6 +21,7 @@ #include "smc.h" #include "smc_ib.h" +#include "smc_pnet.h" static void smc_set_keepalive(struct sock *sk, int val) { @@ -586,10 +587,14 @@ static int __init smc_init(void) { int rc; + rc = smc_pnet_init(); + if (rc) + return rc; + rc = proto_register(&smc_proto, 1); if (rc) { pr_err("%s: proto_register fails with %d\n", __func__, rc); - goto out; + goto out_pnet; } rc = sock_register(&smc_sock_family_ops); @@ -610,7 +615,8 @@ out_sock: sock_unregister(PF_SMC); out_proto: proto_unregister(&smc_proto); -out: +out_pnet: + smc_pnet_exit(); return rc; } @@ -619,6 +625,7 @@ static void __exit smc_exit(void) smc_ib_unregister_client(); sock_unregister(PF_SMC); proto_unregister(&smc_proto); + smc_pnet_exit(); } module_init(smc_init); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 7222b7ede900..5b037f435bc1 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -14,6 +14,7 @@ #include #include +#include "smc_pnet.h" #include "smc_ib.h" #include "smc.h" @@ -123,6 +124,7 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) spin_lock(&smc_ib_devices.lock); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */ spin_unlock(&smc_ib_devices.lock); + smc_pnet_remove_by_ibdev(smcibdev); kfree(smcibdev); } diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c new file mode 100644 index 000000000000..9d3e7fb8348d --- /dev/null +++ b/net/smc/smc_pnet.c @@ -0,0 +1,534 @@ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Generic netlink support functions to configure an SMC-R PNET table + * + * Copyright IBM Corp. 2016 + * + * Author(s): Thomas Richter + */ + +#include +#include +#include +#include +#include + +#include +#include + +#include + +#include "smc_pnet.h" +#include "smc_ib.h" + +#define SMC_MAX_PNET_ID_LEN 16 /* Max. length of PNET id */ + +static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { + [SMC_PNETID_NAME] = { + .type = NLA_NUL_STRING, + .len = SMC_MAX_PNET_ID_LEN - 1 + }, + [SMC_PNETID_ETHNAME] = { + .type = NLA_NUL_STRING, + .len = IFNAMSIZ - 1 + }, + [SMC_PNETID_IBNAME] = { + .type = NLA_NUL_STRING, + .len = IB_DEVICE_NAME_MAX - 1 + }, + [SMC_PNETID_IBPORT] = { .type = NLA_U8 } +}; + +static struct genl_family smc_pnet_nl_family; + +/** + * struct smc_pnettable - SMC PNET table anchor + * @lock: Lock for list action + * @pnetlist: List of PNETIDs + */ +static struct smc_pnettable { + rwlock_t lock; + struct list_head pnetlist; +} smc_pnettable = { + .pnetlist = LIST_HEAD_INIT(smc_pnettable.pnetlist), + .lock = __RW_LOCK_UNLOCKED(smc_pnettable.lock) +}; + +/** + * struct smc_pnetentry - pnet identifier name entry + * @list: List node. + * @pnet_name: Pnet identifier name + * @ndev: pointer to network device. + * @smcibdev: Pointer to IB device. + */ +struct smc_pnetentry { + struct list_head list; + char pnet_name[SMC_MAX_PNET_ID_LEN + 1]; + struct net_device *ndev; + struct smc_ib_device *smcibdev; + u8 ib_port; +}; + +/* Check if two RDMA device entries are identical. Use device name and port + * number for comparison. + */ +static bool smc_pnet_same_ibname(struct smc_pnetentry *pnetelem, char *ibname, + u8 ibport) +{ + return pnetelem->ib_port == ibport && + !strncmp(pnetelem->smcibdev->ibdev->name, ibname, + sizeof(pnetelem->smcibdev->ibdev->name)); +} + +/* Find a pnetid in the pnet table. + */ +static struct smc_pnetentry *smc_pnet_find_pnetid(char *pnet_name) +{ + struct smc_pnetentry *pnetelem, *found_pnetelem = NULL; + + read_lock(&smc_pnettable.lock); + list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { + if (!strncmp(pnetelem->pnet_name, pnet_name, + sizeof(pnetelem->pnet_name))) { + found_pnetelem = pnetelem; + break; + } + } + read_unlock(&smc_pnettable.lock); + return found_pnetelem; +} + +/* Remove a pnetid from the pnet table. + */ +static int smc_pnet_remove_by_pnetid(char *pnet_name) +{ + struct smc_pnetentry *pnetelem, *tmp_pe; + int rc = -ENOENT; + + write_lock(&smc_pnettable.lock); + list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist, + list) { + if (!strncmp(pnetelem->pnet_name, pnet_name, + sizeof(pnetelem->pnet_name))) { + list_del(&pnetelem->list); + dev_put(pnetelem->ndev); + kfree(pnetelem); + rc = 0; + break; + } + } + write_unlock(&smc_pnettable.lock); + return rc; +} + +/* Remove a pnet entry mentioning a given network device from the pnet table. + */ +static int smc_pnet_remove_by_ndev(struct net_device *ndev) +{ + struct smc_pnetentry *pnetelem, *tmp_pe; + int rc = -ENOENT; + + write_lock(&smc_pnettable.lock); + list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist, + list) { + if (pnetelem->ndev == ndev) { + list_del(&pnetelem->list); + dev_put(pnetelem->ndev); + kfree(pnetelem); + rc = 0; + break; + } + } + write_unlock(&smc_pnettable.lock); + return rc; +} + +/* Remove a pnet entry mentioning a given ib device from the pnet table. + */ +int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev) +{ + struct smc_pnetentry *pnetelem, *tmp_pe; + int rc = -ENOENT; + + write_lock(&smc_pnettable.lock); + list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist, + list) { + if (pnetelem->smcibdev == ibdev) { + list_del(&pnetelem->list); + dev_put(pnetelem->ndev); + kfree(pnetelem); + rc = 0; + break; + } + } + write_unlock(&smc_pnettable.lock); + return rc; +} + +/* Append a pnetid to the end of the pnet table if not already on this list. + */ +static int smc_pnet_enter(struct smc_pnetentry *new_pnetelem) +{ + struct smc_pnetentry *pnetelem; + int rc = -EEXIST; + + write_lock(&smc_pnettable.lock); + list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { + if (!strncmp(pnetelem->pnet_name, new_pnetelem->pnet_name, + sizeof(new_pnetelem->pnet_name)) || + !strncmp(pnetelem->ndev->name, new_pnetelem->ndev->name, + sizeof(new_pnetelem->ndev->name)) || + smc_pnet_same_ibname(pnetelem, + new_pnetelem->smcibdev->ibdev->name, + new_pnetelem->ib_port)) + goto found; + } + list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist); + rc = 0; +found: + write_unlock(&smc_pnettable.lock); + return rc; +} + +/* The limit for pnetid is 16 characters. + * Valid characters should be (single-byte character set) a-z, A-Z, 0-9. + * Lower case letters are converted to upper case. + * Interior blanks should not be used. + */ +static bool smc_pnetid_valid(const char *pnet_name, char *pnetid) +{ + char *bf = skip_spaces(pnet_name); + size_t len = strlen(bf); + char *end = bf + len; + + if (!len) + return false; + while (--end >= bf && isspace(*end)) + ; + if (end - bf >= SMC_MAX_PNET_ID_LEN) + return false; + while (bf <= end) { + if (!isalnum(*bf)) + return false; + *pnetid++ = islower(*bf) ? toupper(*bf) : *bf; + bf++; + } + *pnetid = '\0'; + return true; +} + +/* Find an infiniband device by a given name. The device might not exist. */ +struct smc_ib_device *smc_pnet_find_ib(char *ib_name) +{ + struct smc_ib_device *ibdev; + + spin_lock(&smc_ib_devices.lock); + list_for_each_entry(ibdev, &smc_ib_devices.list, list) { + if (!strncmp(ibdev->ibdev->name, ib_name, + sizeof(ibdev->ibdev->name))) { + goto out; + } + } + ibdev = NULL; +out: + spin_unlock(&smc_ib_devices.lock); + return ibdev; +} + +/* Parse the supplied netlink attributes and fill a pnetentry structure. + * For ethernet and infiniband device names verify that the devices exist. + */ +static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem, + struct nlattr *tb[]) +{ + char *string, *ibname = NULL; + int rc = 0; + + memset(pnetelem, 0, sizeof(*pnetelem)); + INIT_LIST_HEAD(&pnetelem->list); + if (tb[SMC_PNETID_NAME]) { + string = (char *)nla_data(tb[SMC_PNETID_NAME]); + if (!smc_pnetid_valid(string, pnetelem->pnet_name)) { + rc = -EINVAL; + goto error; + } + } + if (tb[SMC_PNETID_ETHNAME]) { + string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); + pnetelem->ndev = dev_get_by_name(net, string); + if (!pnetelem->ndev) + return -ENOENT; + } + if (tb[SMC_PNETID_IBNAME]) { + ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]); + ibname = strim(ibname); + pnetelem->smcibdev = smc_pnet_find_ib(ibname); + if (!pnetelem->smcibdev) { + rc = -ENOENT; + goto error; + } + } + if (tb[SMC_PNETID_IBPORT]) { + pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]); + if (pnetelem->ib_port > SMC_MAX_PORTS) { + rc = -EINVAL; + goto error; + } + } + return 0; + +error: + if (pnetelem->ndev) + dev_put(pnetelem->ndev); + return rc; +} + +/* Convert an smc_pnetentry to a netlink attribute sequence */ +static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem) +{ + if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name) || + nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->ndev->name) || + nla_put_string(msg, SMC_PNETID_IBNAME, + pnetelem->smcibdev->ibdev->name) || + nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port)) + return -1; + return 0; +} + +/* Retrieve one PNETID entry */ +static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info) +{ + struct smc_pnetentry *pnetelem; + struct sk_buff *msg; + void *hdr; + int rc; + + pnetelem = smc_pnet_find_pnetid( + (char *)nla_data(info->attrs[SMC_PNETID_NAME])); + if (!pnetelem) + return -ENOENT; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &smc_pnet_nl_family, 0, SMC_PNETID_GET); + if (!hdr) { + rc = -EMSGSIZE; + goto err_out; + } + + if (smc_pnet_set_nla(msg, pnetelem)) { + rc = -ENOBUFS; + goto err_out; + } + + genlmsg_end(msg, hdr); + return genlmsg_reply(msg, info); + +err_out: + nlmsg_free(msg); + return rc; +} + +static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct smc_pnetentry *pnetelem; + int rc; + + pnetelem = kzalloc(sizeof(*pnetelem), GFP_KERNEL); + if (!pnetelem) + return -ENOMEM; + rc = smc_pnet_fill_entry(net, pnetelem, info->attrs); + if (!rc) + rc = smc_pnet_enter(pnetelem); + if (rc) { + kfree(pnetelem); + return rc; + } + rc = smc_ib_remember_port_attr(pnetelem->smcibdev, pnetelem->ib_port); + if (rc) + smc_pnet_remove_by_pnetid(pnetelem->pnet_name); + return rc; +} + +static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info) +{ + return smc_pnet_remove_by_pnetid( + (char *)nla_data(info->attrs[SMC_PNETID_NAME])); +} + +static int smc_pnet_dump_start(struct netlink_callback *cb) +{ + cb->args[0] = 0; + return 0; +} + +static int smc_pnet_dumpinfo(struct sk_buff *skb, + u32 portid, u32 seq, u32 flags, + struct smc_pnetentry *pnetelem) +{ + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &smc_pnet_nl_family, + flags, SMC_PNETID_GET); + if (!hdr) + return -ENOMEM; + if (smc_pnet_set_nla(skb, pnetelem) < 0) { + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; + } + genlmsg_end(skb, hdr); + return 0; +} + +static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_pnetentry *pnetelem; + int idx = 0; + + read_lock(&smc_pnettable.lock); + list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { + if (idx++ < cb->args[0]) + continue; + if (smc_pnet_dumpinfo(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + pnetelem)) { + --idx; + break; + } + } + cb->args[0] = idx; + read_unlock(&smc_pnettable.lock); + return skb->len; +} + +/* Remove and delete all pnetids from pnet table. + */ +static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) +{ + struct smc_pnetentry *pnetelem, *tmp_pe; + + write_lock(&smc_pnettable.lock); + list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist, + list) { + list_del(&pnetelem->list); + dev_put(pnetelem->ndev); + kfree(pnetelem); + } + write_unlock(&smc_pnettable.lock); + return 0; +} + +/* SMC_PNETID generic netlink operation definition */ +static const struct genl_ops smc_pnet_ops[] = { + { + .cmd = SMC_PNETID_GET, + .flags = GENL_ADMIN_PERM, + .policy = smc_pnet_policy, + .doit = smc_pnet_get, + .dumpit = smc_pnet_dump, + .start = smc_pnet_dump_start + }, + { + .cmd = SMC_PNETID_ADD, + .flags = GENL_ADMIN_PERM, + .policy = smc_pnet_policy, + .doit = smc_pnet_add + }, + { + .cmd = SMC_PNETID_DEL, + .flags = GENL_ADMIN_PERM, + .policy = smc_pnet_policy, + .doit = smc_pnet_del + }, + { + .cmd = SMC_PNETID_FLUSH, + .flags = GENL_ADMIN_PERM, + .policy = smc_pnet_policy, + .doit = smc_pnet_flush + } +}; + +/* SMC_PNETID family definition */ +static struct genl_family smc_pnet_nl_family = { + .hdrsize = 0, + .name = SMCR_GENL_FAMILY_NAME, + .version = SMCR_GENL_FAMILY_VERSION, + .maxattr = SMC_PNETID_MAX, + .netnsok = true, + .module = THIS_MODULE, + .ops = smc_pnet_ops, + .n_ops = ARRAY_SIZE(smc_pnet_ops) +}; + +static int smc_pnet_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + + switch (event) { + case NETDEV_REBOOT: + case NETDEV_UNREGISTER: + smc_pnet_remove_by_ndev(event_dev); + default: + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block smc_netdev_notifier = { + .notifier_call = smc_pnet_netdev_event +}; + +int __init smc_pnet_init(void) +{ + int rc; + + rc = genl_register_family(&smc_pnet_nl_family); + if (rc) + return rc; + rc = register_netdevice_notifier(&smc_netdev_notifier); + if (rc) + genl_unregister_family(&smc_pnet_nl_family); + return rc; +} + +void smc_pnet_exit(void) +{ + smc_pnet_flush(NULL, NULL); + unregister_netdevice_notifier(&smc_netdev_notifier); + genl_unregister_family(&smc_pnet_nl_family); +} + +/* PNET table analysis for a given sock: + * determine ib_device and port belonging to used internal TCP socket + * ethernet interface. + */ +void smc_pnet_find_roce_resource(struct sock *sk, + struct smc_ib_device **smcibdev, u8 *ibport) +{ + struct dst_entry *dst = sk_dst_get(sk); + struct smc_pnetentry *pnetelem; + + *smcibdev = NULL; + *ibport = 0; + + if (!dst) + return; + if (!dst->dev) + goto out_rel; + read_lock(&smc_pnettable.lock); + list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { + if (dst->dev == pnetelem->ndev) { + *smcibdev = pnetelem->smcibdev; + *ibport = pnetelem->ib_port; + break; + } + } + read_unlock(&smc_pnettable.lock); +out_rel: + dst_release(dst); +} diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h new file mode 100644 index 000000000000..32ab3df928ca --- /dev/null +++ b/net/smc/smc_pnet.h @@ -0,0 +1,23 @@ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * PNET table queries + * + * Copyright IBM Corp. 2016 + * + * Author(s): Thomas Richter + */ + +#ifndef _SMC_PNET_H +#define _SMC_PNET_H + +struct smc_ib_device; + +int smc_pnet_init(void) __init; +void smc_pnet_exit(void); +int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev); +struct smc_ib_device *smc_pnet_find_ib(char *ib_name); +void smc_pnet_find_roce_resource(struct sock *sk, + struct smc_ib_device **smcibdev, u8 *ibport); + +#endif -- cgit v1.3-14-g43fede From f16a7dd5cf27eeda187425c9c7d96802a549f9c4 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Mon, 9 Jan 2017 16:55:26 +0100 Subject: smc: netlink interface for SMC sockets Support for SMC socket monitoring via netlink sockets of protocol NETLINK_SOCK_DIAG. Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- include/net/smc.h | 20 ++++ include/net/sock.h | 3 + include/uapi/linux/netlink.h | 1 + include/uapi/linux/smc_diag.h | 85 +++++++++++++++++ net/smc/Kconfig | 9 ++ net/smc/Makefile | 1 + net/smc/af_smc.c | 43 ++++++++- net/smc/smc.h | 2 + net/smc/smc_close.c | 1 + net/smc/smc_diag.c | 215 ++++++++++++++++++++++++++++++++++++++++++ 10 files changed, 379 insertions(+), 1 deletion(-) create mode 100644 include/net/smc.h create mode 100644 include/uapi/linux/smc_diag.h create mode 100644 net/smc/smc_diag.c (limited to 'include/uapi/linux') diff --git a/include/net/smc.h b/include/net/smc.h new file mode 100644 index 000000000000..12d26358ad9f --- /dev/null +++ b/include/net/smc.h @@ -0,0 +1,20 @@ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the SMC module (socket related) + * + * Copyright IBM Corp. 2016 + * + * Author(s): Ursula Braun + */ +#ifndef _SMC_H +#define _SMC_H + +struct smc_hashinfo { + rwlock_t lock; + struct hlist_head ht; +}; + +int smc_hash_sk(struct sock *sk); +void smc_unhash_sk(struct sock *sk); +#endif /* _SMC_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 99deda67eba0..389a0a619b45 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -70,6 +70,7 @@ #include #include #include +#include /* * This structure really needs to be cleaned up. @@ -986,6 +987,7 @@ struct request_sock_ops; struct timewait_sock_ops; struct inet_hashinfo; struct raw_hashinfo; +struct smc_hashinfo; struct module; /* @@ -1094,6 +1096,7 @@ struct proto { struct inet_hashinfo *hashinfo; struct udp_table *udp_table; struct raw_hashinfo *raw_hash; + struct smc_hashinfo *smc_hash; } h; struct module *owner; diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 0dba4e4ed2be..f3946a27bd07 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -27,6 +27,7 @@ #define NETLINK_ECRYPTFS 19 #define NETLINK_RDMA 20 #define NETLINK_CRYPTO 21 /* Crypto layer */ +#define NETLINK_SMC 22 /* SMC monitoring */ #define NETLINK_INET_DIAG NETLINK_SOCK_DIAG diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h new file mode 100644 index 000000000000..0063919fea34 --- /dev/null +++ b/include/uapi/linux/smc_diag.h @@ -0,0 +1,85 @@ +#ifndef _UAPI_SMC_DIAG_H_ +#define _UAPI_SMC_DIAG_H_ + +#include +#include +#include + +/* Request structure */ +struct smc_diag_req { + __u8 diag_family; + __u8 pad[2]; + __u8 diag_ext; /* Query extended information */ + struct inet_diag_sockid id; +}; + +/* Base info structure. It contains socket identity (addrs/ports/cookie) based + * on the internal clcsock, and more SMC-related socket data + */ +struct smc_diag_msg { + __u8 diag_family; + __u8 diag_state; + __u8 diag_fallback; + __u8 diag_shutdown; + struct inet_diag_sockid id; + + __u32 diag_uid; + __u64 diag_inode; +}; + +/* Extensions */ + +enum { + SMC_DIAG_NONE, + SMC_DIAG_CONNINFO, + SMC_DIAG_LGRINFO, + SMC_DIAG_SHUTDOWN, + __SMC_DIAG_MAX, +}; + +#define SMC_DIAG_MAX (__SMC_DIAG_MAX - 1) + +/* SMC_DIAG_CONNINFO */ + +struct smc_diag_cursor { + __u16 reserved; + __u16 wrap; + __u32 count; +}; + +struct smc_diag_conninfo { + __u32 token; /* unique connection id */ + __u32 sndbuf_size; /* size of send buffer */ + __u32 rmbe_size; /* size of RMB element */ + __u32 peer_rmbe_size; /* size of peer RMB element */ + /* local RMB element cursors */ + struct smc_diag_cursor rx_prod; /* received producer cursor */ + struct smc_diag_cursor rx_cons; /* received consumer cursor */ + /* peer RMB element cursors */ + struct smc_diag_cursor tx_prod; /* sent producer cursor */ + struct smc_diag_cursor tx_cons; /* sent consumer cursor */ + __u8 rx_prod_flags; /* received producer flags */ + __u8 rx_conn_state_flags; /* recvd connection flags*/ + __u8 tx_prod_flags; /* sent producer flags */ + __u8 tx_conn_state_flags; /* sent connection flags*/ + /* send buffer cursors */ + struct smc_diag_cursor tx_prep; /* prepared to be sent cursor */ + struct smc_diag_cursor tx_sent; /* sent cursor */ + struct smc_diag_cursor tx_fin; /* confirmed sent cursor */ +}; + +/* SMC_DIAG_LINKINFO */ + +struct smc_diag_linkinfo { + __u8 link_id; /* link identifier */ + __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ + __u8 ibport; /* RDMA device port number */ + __u8 gid[40]; /* local GID */ + __u8 peer_gid[40]; /* peer GID */ +}; + +struct smc_diag_lgrinfo { + struct smc_diag_linkinfo lnk[1]; + __u8 role; +}; +#endif /* _UAPI_SMC_DIAG_H_ */ diff --git a/net/smc/Kconfig b/net/smc/Kconfig index bc029803e728..c717ef0896aa 100644 --- a/net/smc/Kconfig +++ b/net/smc/Kconfig @@ -9,3 +9,12 @@ config SMC a separate socket family SMC. Select this option if you want to run SMC socket applications + +config SMC_DIAG + tristate "SMC: socket monitoring interface" + depends on SMC + ---help--- + Support for SMC socket monitoring interface used by tools such as + smcss. + + if unsure, say Y. diff --git a/net/smc/Makefile b/net/smc/Makefile index 5cf0cafaa208..188104654b54 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_SMC) += smc.o +obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 3f543d58bc5c..5d4208ad029e 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "smc.h" #include "smc_clc.h" @@ -59,13 +60,48 @@ static void smc_set_keepalive(struct sock *sk, int val) smc->clcsock->sk->sk_prot->keepalive(smc->clcsock->sk, val); } -static struct proto smc_proto = { +static struct smc_hashinfo smc_v4_hashinfo = { + .lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock), +}; + +int smc_hash_sk(struct sock *sk) +{ + struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; + struct hlist_head *head; + + head = &h->ht; + + write_lock_bh(&h->lock); + sk_add_node(sk, head); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + write_unlock_bh(&h->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(smc_hash_sk); + +void smc_unhash_sk(struct sock *sk) +{ + struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; + + write_lock_bh(&h->lock); + if (sk_del_node_init(sk)) + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + write_unlock_bh(&h->lock); +} +EXPORT_SYMBOL_GPL(smc_unhash_sk); + +struct proto smc_proto = { .name = "SMC", .owner = THIS_MODULE, .keepalive = smc_set_keepalive, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v4_hashinfo, .slab_flags = SLAB_DESTROY_BY_RCU, }; +EXPORT_SYMBOL_GPL(smc_proto); static int smc_release(struct socket *sock) { @@ -109,6 +145,7 @@ static int smc_release(struct socket *sock) schedule_delayed_work(&smc->sock_put_work, SMC_CLOSE_SOCK_PUT_DELAY); } + sk->sk_prot->unhash(sk); release_sock(sk); sock_put(sk); @@ -144,6 +181,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock) INIT_LIST_HEAD(&smc->accept_q); spin_lock_init(&smc->accept_q_lock); INIT_DELAYED_WORK(&smc->sock_put_work, smc_close_sock_put_work); + sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); return sk; @@ -536,6 +574,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) lsmc->sk.sk_err = -rc; new_sk->sk_state = SMC_CLOSED; sock_set_flag(new_sk, SOCK_DEAD); + sk->sk_prot->unhash(new_sk); sock_put(new_sk); *new_smc = NULL; goto out; @@ -545,6 +584,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) sock_release(new_clcsock); new_sk->sk_state = SMC_CLOSED; sock_set_flag(new_sk, SOCK_DEAD); + sk->sk_prot->unhash(new_sk); sock_put(new_sk); *new_smc = NULL; goto out; @@ -1320,6 +1360,7 @@ static int __init smc_init(void) pr_err("%s: sock_register fails with %d\n", __func__, rc); goto out_proto; } + INIT_HLIST_HEAD(&smc_v4_hashinfo.ht); rc = smc_ib_register_client(); if (rc) { diff --git a/net/smc/smc.h b/net/smc/smc.h index 959a5d2014ab..ee5fbea24549 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -21,6 +21,8 @@ #define SMC_MAX_PORTS 2 /* Max # of ports */ +extern struct proto smc_proto; + #ifdef ATOMIC64_INIT #define KERNEL_HAS_ATOMIC64 #endif diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index d70c05b57021..03dfcc6b7661 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -384,6 +384,7 @@ void smc_close_sock_put_work(struct work_struct *work) struct smc_sock, sock_put_work); + smc->sk.sk_prot->unhash(&smc->sk); sock_put(&smc->sk); } diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c new file mode 100644 index 000000000000..d2d01cf70224 --- /dev/null +++ b/net/smc/smc_diag.c @@ -0,0 +1,215 @@ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Monitoring SMC transport protocol sockets + * + * Copyright IBM Corp. 2016 + * + * Author(s): Ursula Braun + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "smc.h" +#include "smc_core.h" + +static void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) +{ + sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", + be16_to_cpu(((__be16 *)gid_raw)[0]), + be16_to_cpu(((__be16 *)gid_raw)[1]), + be16_to_cpu(((__be16 *)gid_raw)[2]), + be16_to_cpu(((__be16 *)gid_raw)[3]), + be16_to_cpu(((__be16 *)gid_raw)[4]), + be16_to_cpu(((__be16 *)gid_raw)[5]), + be16_to_cpu(((__be16 *)gid_raw)[6]), + be16_to_cpu(((__be16 *)gid_raw)[7])); +} + +static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) +{ + struct smc_sock *smc = smc_sk(sk); + + r->diag_family = sk->sk_family; + if (!smc->clcsock) + return; + r->id.idiag_sport = htons(smc->clcsock->sk->sk_num); + r->id.idiag_dport = smc->clcsock->sk->sk_dport; + r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if; + sock_diag_save_cookie(sk, r->id.idiag_cookie); + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr; + r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr; +} + +static int smc_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, + struct smc_diag_msg *r, + struct user_namespace *user_ns) +{ + if (nla_put_u8(skb, SMC_DIAG_SHUTDOWN, sk->sk_shutdown)) + return 1; + + r->diag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); + r->diag_inode = sock_i_ino(sk); + return 0; +} + +static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, + struct netlink_callback *cb, + const struct smc_diag_req *req, + struct nlattr *bc) +{ + struct smc_sock *smc = smc_sk(sk); + struct user_namespace *user_ns; + struct smc_diag_msg *r; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + cb->nlh->nlmsg_type, sizeof(*r), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + r = nlmsg_data(nlh); + smc_diag_msg_common_fill(r, sk); + r->diag_state = sk->sk_state; + r->diag_fallback = smc->use_fallback; + user_ns = sk_user_ns(NETLINK_CB(cb->skb).sk); + if (smc_diag_msg_attrs_fill(sk, skb, r, user_ns)) + goto errout; + + if ((req->diag_ext & (1 << (SMC_DIAG_CONNINFO - 1))) && smc->conn.lgr) { + struct smc_connection *conn = &smc->conn; + struct smc_diag_conninfo cinfo = { + .token = conn->alert_token_local, + .sndbuf_size = conn->sndbuf_size, + .rmbe_size = conn->rmbe_size, + .peer_rmbe_size = conn->peer_rmbe_size, + + .rx_prod.wrap = conn->local_rx_ctrl.prod.wrap, + .rx_prod.count = conn->local_rx_ctrl.prod.count, + .rx_cons.wrap = conn->local_rx_ctrl.cons.wrap, + .rx_cons.count = conn->local_rx_ctrl.cons.count, + + .tx_prod.wrap = conn->local_tx_ctrl.prod.wrap, + .tx_prod.count = conn->local_tx_ctrl.prod.count, + .tx_cons.wrap = conn->local_tx_ctrl.cons.wrap, + .tx_cons.count = conn->local_tx_ctrl.cons.count, + + .tx_prod_flags = + *(u8 *)&conn->local_tx_ctrl.prod_flags, + .tx_conn_state_flags = + *(u8 *)&conn->local_tx_ctrl.conn_state_flags, + .rx_prod_flags = *(u8 *)&conn->local_rx_ctrl.prod_flags, + .rx_conn_state_flags = + *(u8 *)&conn->local_rx_ctrl.conn_state_flags, + + .tx_prep.wrap = conn->tx_curs_prep.wrap, + .tx_prep.count = conn->tx_curs_prep.count, + .tx_sent.wrap = conn->tx_curs_sent.wrap, + .tx_sent.count = conn->tx_curs_sent.count, + .tx_fin.wrap = conn->tx_curs_fin.wrap, + .tx_fin.count = conn->tx_curs_fin.count, + }; + + if (nla_put(skb, SMC_DIAG_CONNINFO, sizeof(cinfo), &cinfo) < 0) + goto errout; + } + + if ((req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && smc->conn.lgr) { + struct smc_diag_lgrinfo linfo = { + .role = smc->conn.lgr->role, + .lnk[0].ibport = smc->conn.lgr->lnk[0].ibport, + .lnk[0].link_id = smc->conn.lgr->lnk[0].link_id, + }; + + memcpy(linfo.lnk[0].ibname, + smc->conn.lgr->lnk[0].smcibdev->ibdev->name, + sizeof(smc->conn.lgr->lnk[0].smcibdev->ibdev->name)); + smc_gid_be16_convert(linfo.lnk[0].gid, + smc->conn.lgr->lnk[0].gid.raw); + smc_gid_be16_convert(linfo.lnk[0].peer_gid, + smc->conn.lgr->lnk[0].peer_gid); + + if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0) + goto errout; + } + + nlmsg_end(skb, nlh); + return 0; + +errout: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *bc = NULL; + struct hlist_head *head; + struct sock *sk; + int rc = 0; + + read_lock(&smc_proto.h.smc_hash->lock); + head = &smc_proto.h.smc_hash->ht; + if (hlist_empty(head)) + goto out; + + sk_for_each(sk, head) { + if (!net_eq(sock_net(sk), net)) + continue; + rc = __smc_diag_dump(sk, skb, cb, nlmsg_data(cb->nlh), bc); + if (rc) + break; + } + +out: + read_unlock(&smc_proto.h.smc_hash->lock); + return rc; +} + +static int smc_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) +{ + struct net *net = sock_net(skb->sk); + + if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY && + h->nlmsg_flags & NLM_F_DUMP) { + { + struct netlink_dump_control c = { + .dump = smc_diag_dump, + .min_dump_alloc = SKB_WITH_OVERHEAD(32768), + }; + return netlink_dump_start(net->diag_nlsk, skb, h, &c); + } + } + return 0; +} + +static const struct sock_diag_handler smc_diag_handler = { + .family = AF_SMC, + .dump = smc_diag_handler_dump, +}; + +static int __init smc_diag_init(void) +{ + return sock_diag_register(&smc_diag_handler); +} + +static void __exit smc_diag_exit(void) +{ + sock_diag_unregister(&smc_diag_handler); +} + +module_init(smc_diag_init); +module_exit(smc_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 43 /* AF_SMC */); -- cgit v1.3-14-g43fede From 99d31326cbe6951872af5c8a6bc2679388a4d9ef Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 11 Jan 2017 14:05:43 +0100 Subject: net/sched: cls_flower: Support matching on ARP Support matching on ARP operation, and hardware and protocol addresses for Ethernet hardware and IPv4 protocol addresses. Example usage: tc qdisc add dev eth0 ingress tc filter add dev eth0 protocol arp parent ffff: flower indev eth0 \ arp_op request arp_sip 10.0.0.1 action drop tc filter add dev eth0 protocol rarp parent ffff: flower indev eth0 \ arp_op reply arp_tha 52:54:3f:00:00:00/24 action drop Signed-off-by: Simon Horman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 11 ++++++++++ net/sched/cls_flower.c | 51 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 62 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index a081efbd61a2..1e5e1ddfdaca 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -416,6 +416,17 @@ enum { TCA_FLOWER_KEY_ICMPV6_TYPE, /* u8 */ TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */ + TCA_FLOWER_KEY_ARP_SIP, /* be32 */ + TCA_FLOWER_KEY_ARP_SIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_OP, /* u8 */ + TCA_FLOWER_KEY_ARP_OP_MASK, /* u8 */ + TCA_FLOWER_KEY_ARP_SHA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_SHA_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA_MASK, /* ETH_ALEN */ + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 970db7a41684..a3bfda3091a4 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -40,6 +40,7 @@ struct fl_flow_key { }; struct flow_dissector_key_ports tp; struct flow_dissector_key_icmp icmp; + struct flow_dissector_key_arp arp; struct flow_dissector_key_keyid enc_key_id; union { struct flow_dissector_key_ipv4_addrs enc_ipv4; @@ -401,6 +402,16 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ICMPV6_TYPE_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ICMPV6_CODE] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ICMPV6_CODE_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ARP_SIP] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ARP_SIP_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ARP_TIP] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ARP_TIP_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ARP_OP] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ARP_OP_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ARP_SHA] = { .len = ETH_ALEN }, + [TCA_FLOWER_KEY_ARP_SHA_MASK] = { .len = ETH_ALEN }, + [TCA_FLOWER_KEY_ARP_THA] = { .len = ETH_ALEN }, + [TCA_FLOWER_KEY_ARP_THA_MASK] = { .len = ETH_ALEN }, }; static void fl_set_key_val(struct nlattr **tb, @@ -572,6 +583,23 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->icmp.code, TCA_FLOWER_KEY_ICMPV4_CODE_MASK, sizeof(key->icmp.code)); + } else if (key->basic.n_proto == htons(ETH_P_ARP) || + key->basic.n_proto == htons(ETH_P_RARP)) { + fl_set_key_val(tb, &key->arp.sip, TCA_FLOWER_KEY_ARP_SIP, + &mask->arp.sip, TCA_FLOWER_KEY_ARP_SIP_MASK, + sizeof(key->arp.sip)); + fl_set_key_val(tb, &key->arp.tip, TCA_FLOWER_KEY_ARP_TIP, + &mask->arp.tip, TCA_FLOWER_KEY_ARP_TIP_MASK, + sizeof(key->arp.tip)); + fl_set_key_val(tb, &key->arp.op, TCA_FLOWER_KEY_ARP_OP, + &mask->arp.op, TCA_FLOWER_KEY_ARP_OP_MASK, + sizeof(key->arp.op)); + fl_set_key_val(tb, key->arp.sha, TCA_FLOWER_KEY_ARP_SHA, + mask->arp.sha, TCA_FLOWER_KEY_ARP_SHA_MASK, + sizeof(key->arp.sha)); + fl_set_key_val(tb, key->arp.tha, TCA_FLOWER_KEY_ARP_THA, + mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK, + sizeof(key->arp.tha)); } if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] || @@ -688,6 +716,8 @@ static void fl_init_dissector(struct cls_fl_head *head, FLOW_DISSECTOR_KEY_PORTS, tp); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_ICMP, icmp); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_ARP, arp); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_VLAN, vlan); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, @@ -1112,6 +1142,27 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, TCA_FLOWER_KEY_ICMPV6_CODE_MASK, sizeof(key->icmp.code)))) goto nla_put_failure; + else if ((key->basic.n_proto == htons(ETH_P_ARP) || + key->basic.n_proto == htons(ETH_P_RARP)) && + (fl_dump_key_val(skb, &key->arp.sip, + TCA_FLOWER_KEY_ARP_SIP, &mask->arp.sip, + TCA_FLOWER_KEY_ARP_SIP_MASK, + sizeof(key->arp.sip)) || + fl_dump_key_val(skb, &key->arp.tip, + TCA_FLOWER_KEY_ARP_TIP, &mask->arp.tip, + TCA_FLOWER_KEY_ARP_TIP_MASK, + sizeof(key->arp.tip)) || + fl_dump_key_val(skb, &key->arp.op, + TCA_FLOWER_KEY_ARP_OP, &mask->arp.op, + TCA_FLOWER_KEY_ARP_OP_MASK, + sizeof(key->arp.op)) || + fl_dump_key_val(skb, key->arp.sha, TCA_FLOWER_KEY_ARP_SHA, + mask->arp.sha, TCA_FLOWER_KEY_ARP_SHA_MASK, + sizeof(key->arp.sha)) || + fl_dump_key_val(skb, key->arp.tha, TCA_FLOWER_KEY_ARP_THA, + mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK, + sizeof(key->arp.tha)))) + goto nla_put_failure; if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && (fl_dump_key_val(skb, &key->enc_ipv4.src, -- cgit v1.3-14-g43fede From ab5bb2d51ba8da4add4612b529968446cdb504b1 Mon Sep 17 00:00:00 2001 From: vamsi krishna Date: Fri, 13 Jan 2017 01:12:19 +0200 Subject: cfg80211: Add support for randomizing TA of Public Action frames Add support to use a random local address (Address 2 = TA in transmit and the same address in receive functionality) for Public Action frames in order to improve privacy of WLAN clients. Applications fill the random transmit address in the frame buffer in the NL80211_CMD_FRAME command. This can be used only with the drivers that indicate support for random local address by setting the new NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA and/or NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA_CONNECTED in ext_features. The driver needs to configure receive behavior to accept frames to the specified random address during the time the frame exchange is pending and such frames need to be acknowledged similarly to frames sent to the local permanent address when this random address functionality is not used. Signed-off-by: vamsi krishna Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 6 ++++++ net/wireless/mlme.c | 21 +++++++++++++++++++-- 2 files changed, 25 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 174f4b30e804..908886c83894 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4699,6 +4699,10 @@ enum nl80211_feature_flags { * configuration (AP/mesh) with VHT rates. * @NL80211_EXT_FEATURE_FILS_STA: This driver supports Fast Initial Link Setup * with user space SME (NL80211_CMD_AUTHENTICATE) in station mode. + * @NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA: This driver supports randomized TA + * in @NL80211_CMD_FRAME while not associated. + * @NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA_CONNECTED: This driver supports + * randomized TA in @NL80211_CMD_FRAME while associated. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4714,6 +4718,8 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_BEACON_RATE_HT, NL80211_EXT_FEATURE_BEACON_RATE_VHT, NL80211_EXT_FEATURE_FILS_STA, + NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA, + NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA_CONNECTED, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 1c63a77aea34..b876f40c9dad 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -662,8 +662,25 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, return err; } - if (!ether_addr_equal(mgmt->sa, wdev_address(wdev))) - return -EINVAL; + if (!ether_addr_equal(mgmt->sa, wdev_address(wdev))) { + /* Allow random TA to be used with Public Action frames if the + * driver has indicated support for this. Otherwise, only allow + * the local address to be used. + */ + if (!ieee80211_is_action(mgmt->frame_control) || + mgmt->u.action.category != WLAN_CATEGORY_PUBLIC) + return -EINVAL; + if (!wdev->current_bss && + !wiphy_ext_feature_isset( + &rdev->wiphy, + NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA)) + return -EINVAL; + if (wdev->current_bss && + !wiphy_ext_feature_isset( + &rdev->wiphy, + NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA_CONNECTED)) + return -EINVAL; + } /* Transmit the Action frame as requested by user space */ return rdev_mgmt_tx(rdev, wdev, params, cookie); -- cgit v1.3-14-g43fede From bf95ecdba93b98d27ac219e79f773f2074b4ca47 Mon Sep 17 00:00:00 2001 From: vamsi krishna Date: Fri, 13 Jan 2017 01:12:20 +0200 Subject: cfg80211: Add support to sched scan to report better BSSs Enhance sched scan to support option of finding a better BSS while in connected state. Firmware scans the medium and reports when it finds a known BSS which has better RSSI than the current connected BSS. New attributes to specify the relative RSSI (compared to the current BSS) are added to the sched scan to implement this. Signed-off-by: vamsi krishna Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 36 +++++++++++++++++++++++++----------- include/uapi/linux/nl80211.h | 30 ++++++++++++++++++++++++++++++ net/wireless/nl80211.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 99 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cb13789ebaef..4456491132cd 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1619,6 +1619,17 @@ struct cfg80211_sched_scan_plan { u32 iterations; }; +/** + * struct cfg80211_bss_select_adjust - BSS selection with RSSI adjustment. + * + * @band: band of BSS which should match for RSSI level adjustment. + * @delta: value of RSSI level adjustment. + */ +struct cfg80211_bss_select_adjust { + enum nl80211_band band; + s8 delta; +}; + /** * struct cfg80211_sched_scan_request - scheduled scan request description * @@ -1654,6 +1665,16 @@ struct cfg80211_sched_scan_plan { * cycle. The driver may ignore this parameter and start * immediately (or at any other time), if this feature is not * supported. + * @relative_rssi_set: Indicates whether @relative_rssi is set or not. + * @relative_rssi: Relative RSSI threshold in dB to restrict scan result + * reporting in connected state to cases where a matching BSS is determined + * to have better or slightly worse RSSI than the current connected BSS. + * The relative RSSI threshold values are ignored in disconnected state. + * @rssi_adjust: delta dB of RSSI preference to be given to the BSSs that belong + * to the specified band while deciding whether a better BSS is reported + * using @relative_rssi. If delta is a negative number, the BSSs that + * belong to the specified band will be penalized by delta dB in relative + * comparisions. */ struct cfg80211_sched_scan_request { struct cfg80211_ssid *ssids; @@ -1673,6 +1694,10 @@ struct cfg80211_sched_scan_request { u8 mac_addr[ETH_ALEN] __aligned(2); u8 mac_addr_mask[ETH_ALEN] __aligned(2); + bool relative_rssi_set; + s8 relative_rssi; + struct cfg80211_bss_select_adjust rssi_adjust; + /* internal */ struct wiphy *wiphy; struct net_device *dev; @@ -1980,17 +2005,6 @@ struct cfg80211_ibss_params { struct ieee80211_ht_cap ht_capa_mask; }; -/** - * struct cfg80211_bss_select_adjust - BSS selection with RSSI adjustment. - * - * @band: band of BSS which should match for RSSI level adjustment. - * @delta: value of RSSI level adjustment. - */ -struct cfg80211_bss_select_adjust { - enum nl80211_band band; - s8 delta; -}; - /** * struct cfg80211_bss_selection - connection parameters for BSS selection. * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 908886c83894..6b17feb5e839 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1982,6 +1982,20 @@ enum nl80211_commands { * @NL80211_ATTR_BSSID: The BSSID of the AP. Note that %NL80211_ATTR_MAC is also * used in various commands/events for specifying the BSSID. * + * @NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI: Relative RSSI threshold by which + * other BSSs has to be better or slightly worse than the current + * connected BSS so that they get reported to user space. + * This will give an opportunity to userspace to consider connecting to + * other matching BSSs which have better or slightly worse RSSI than + * the current connected BSS by using an offloaded operation to avoid + * unnecessary wakeups. + * + * @NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST: When present the RSSI level for BSSs in + * the specified band is to be adjusted before doing + * %NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI based comparision to figure out + * better BSSs. The attribute value is a packed structure + * value as specified by &struct nl80211_bss_select_rssi_adjust. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2388,6 +2402,9 @@ enum nl80211_attrs { NL80211_ATTR_BSSID, + NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI, + NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3080,6 +3097,13 @@ enum nl80211_reg_rule_attr { * how this API was implemented in the past. Also, due to the same problem, * the only way to create a matchset with only an RSSI filter (with this * attribute) is if there's only a single matchset with the RSSI attribute. + * @NL80211_SCHED_SCAN_MATCH_ATTR_RELATIVE_RSSI: Flag indicating whether + * %NL80211_SCHED_SCAN_MATCH_ATTR_RSSI to be used as absolute RSSI or + * relative to current bss's RSSI. + * @NL80211_SCHED_SCAN_MATCH_ATTR_RSSI_ADJUST: When present the RSSI level for + * BSS-es in the specified band is to be adjusted before doing + * RSSI-based BSS selection. The attribute value is a packed structure + * value as specified by &struct nl80211_bss_select_rssi_adjust. * @NL80211_SCHED_SCAN_MATCH_ATTR_MAX: highest scheduled scan filter * attribute number currently defined * @__NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST: internal use @@ -3089,6 +3113,8 @@ enum nl80211_sched_scan_match_attr { NL80211_SCHED_SCAN_MATCH_ATTR_SSID, NL80211_SCHED_SCAN_MATCH_ATTR_RSSI, + NL80211_SCHED_SCAN_MATCH_ATTR_RELATIVE_RSSI, + NL80211_SCHED_SCAN_MATCH_ATTR_RSSI_ADJUST, /* keep last */ __NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST, @@ -4703,6 +4729,9 @@ enum nl80211_feature_flags { * in @NL80211_CMD_FRAME while not associated. * @NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA_CONNECTED: This driver supports * randomized TA in @NL80211_CMD_FRAME while associated. + * @NL80211_EXT_FEATURE_SCHED_SCAN_RELATIVE_RSSI: The driver supports sched_scan + * for reporting BSSs with better RSSI than the current connected BSS + * (%NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI). * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4720,6 +4749,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_FILS_STA, NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA, NL80211_EXT_FEATURE_MGMT_TX_RANDOM_TA_CONNECTED, + NL80211_EXT_FEATURE_SCHED_SCAN_RELATIVE_RSSI, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b378d0a04003..71c66ff9a702 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -405,6 +405,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_FILS_NONCES] = { .len = 2 * FILS_NONCE_LEN }, [NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED] = { .type = NLA_FLAG, }, [NL80211_ATTR_BSSID] = { .len = ETH_ALEN }, + [NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI] = { .type = NLA_S8 }, + [NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST] = { + .len = sizeof(struct nl80211_bss_select_rssi_adjust) + }, }; /* policy for the key attributes */ @@ -6950,6 +6954,12 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, if (!n_plans || n_plans > wiphy->max_sched_scan_plans) return ERR_PTR(-EINVAL); + if (!wiphy_ext_feature_isset( + wiphy, NL80211_EXT_FEATURE_SCHED_SCAN_RELATIVE_RSSI) && + (attrs[NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI] || + attrs[NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST])) + return ERR_PTR(-EINVAL); + request = kzalloc(sizeof(*request) + sizeof(*request->ssids) * n_ssids + sizeof(*request->match_sets) * n_match_sets @@ -7156,6 +7166,26 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, request->delay = nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_DELAY]); + if (attrs[NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI]) { + request->relative_rssi = nla_get_s8( + attrs[NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI]); + request->relative_rssi_set = true; + } + + if (request->relative_rssi_set && + attrs[NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST]) { + struct nl80211_bss_select_rssi_adjust *rssi_adjust; + + rssi_adjust = nla_data( + attrs[NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST]); + request->rssi_adjust.band = rssi_adjust->band; + request->rssi_adjust.delta = rssi_adjust->delta; + if (!is_band_valid(wiphy, request->rssi_adjust.band)) { + err = -EINVAL; + goto out_free; + } + } + err = nl80211_parse_sched_scan_plans(wiphy, n_plans, request, attrs); if (err) goto out_free; @@ -9692,6 +9722,20 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_DELAY, req->delay)) return -ENOBUFS; + if (req->relative_rssi_set) { + struct nl80211_bss_select_rssi_adjust rssi_adjust; + + if (nla_put_s8(msg, NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI, + req->relative_rssi)) + return -ENOBUFS; + + rssi_adjust.band = req->rssi_adjust.band; + rssi_adjust.delta = req->rssi_adjust.delta; + if (nla_put(msg, NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST, + sizeof(rssi_adjust), &rssi_adjust)) + return -ENOBUFS; + } + freqs = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES); if (!freqs) return -ENOBUFS; -- cgit v1.3-14-g43fede From 3093ebbeabcdddc9a982950052f2151df43c7aa2 Mon Sep 17 00:00:00 2001 From: Purushottam Kushwaha Date: Fri, 13 Jan 2017 01:12:21 +0200 Subject: cfg80211: Specify the reason for connect timeout This enhances the connect timeout API to also carry the reason for the timeout. These reason codes for the connect time out are represented by enum nl80211_timeout_reason and are passed to user space through a new attribute NL80211_ATTR_TIMEOUT_REASON (u32). Signed-off-by: Purushottam Kushwaha Signed-off-by: Jouni Malinen [keep gfp_t argument last] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 18 ++++++++++++++---- include/uapi/linux/nl80211.h | 21 +++++++++++++++++++++ net/wireless/core.h | 4 +++- net/wireless/mlme.c | 3 ++- net/wireless/nl80211.c | 9 +++++++-- net/wireless/nl80211.h | 4 +++- net/wireless/sme.c | 39 +++++++++++++++++++++++++++------------ net/wireless/util.c | 2 +- 8 files changed, 78 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4456491132cd..9b3427c8d1db 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5090,6 +5090,12 @@ static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp) * %WLAN_STATUS_UNSPECIFIED_FAILURE if your device cannot give you * the real status code for failures. * @gfp: allocation flags + * @timeout_reason: reason for connection timeout. This is used when the + * connection fails due to a timeout instead of an explicit rejection from + * the AP. %NL80211_TIMEOUT_UNSPECIFIED is used when the timeout reason is + * not known. This value is used only if @status < 0 to indicate that the + * failure is due to a timeout and not due to explicit rejection by the AP. + * This value is ignored in other cases (@status >= 0). * * It should be called by the underlying driver whenever connect() has * succeeded. This is similar to cfg80211_connect_result(), but with the @@ -5099,7 +5105,8 @@ static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp) void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid, struct cfg80211_bss *bss, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, - size_t resp_ie_len, int status, gfp_t gfp); + size_t resp_ie_len, int status, gfp_t gfp, + enum nl80211_timeout_reason timeout_reason); /** * cfg80211_connect_result - notify cfg80211 of connection result @@ -5125,7 +5132,8 @@ cfg80211_connect_result(struct net_device *dev, const u8 *bssid, u16 status, gfp_t gfp) { cfg80211_connect_bss(dev, bssid, NULL, req_ie, req_ie_len, resp_ie, - resp_ie_len, status, gfp); + resp_ie_len, status, gfp, + NL80211_TIMEOUT_UNSPECIFIED); } /** @@ -5136,6 +5144,7 @@ cfg80211_connect_result(struct net_device *dev, const u8 *bssid, * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @gfp: allocation flags + * @timeout_reason: reason for connection timeout. * * It should be called by the underlying driver whenever connect() has failed * in a sequence where no explicit authentication/association rejection was @@ -5145,10 +5154,11 @@ cfg80211_connect_result(struct net_device *dev, const u8 *bssid, */ static inline void cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, - const u8 *req_ie, size_t req_ie_len, gfp_t gfp) + const u8 *req_ie, size_t req_ie_len, gfp_t gfp, + enum nl80211_timeout_reason timeout_reason) { cfg80211_connect_bss(dev, bssid, NULL, req_ie, req_ie_len, NULL, 0, -1, - gfp); + gfp, timeout_reason); } /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6b17feb5e839..c51b40cc0645 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1996,6 +1996,10 @@ enum nl80211_commands { * better BSSs. The attribute value is a packed structure * value as specified by &struct nl80211_bss_select_rssi_adjust. * + * @NL80211_ATTR_TIMEOUT_REASON: The reason for which an operation timed out. + * u32 attribute with an &enum nl80211_timeout_reason value. This is used, + * e.g., with %NL80211_CMD_CONNECT event. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2405,6 +2409,8 @@ enum nl80211_attrs { NL80211_ATTR_SCHED_SCAN_RELATIVE_RSSI, NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST, + NL80211_ATTR_TIMEOUT_REASON, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -4788,6 +4794,21 @@ enum nl80211_connect_failed_reason { NL80211_CONN_FAIL_BLOCKED_CLIENT, }; +/** + * enum nl80211_timeout_reason - timeout reasons + * + * @NL80211_TIMEOUT_UNSPECIFIED: Timeout reason unspecified. + * @NL80211_TIMEOUT_SCAN: Scan (AP discovery) timed out. + * @NL80211_TIMEOUT_AUTH: Authentication timed out. + * @NL80211_TIMEOUT_ASSOC: Association timed out. + */ +enum nl80211_timeout_reason { + NL80211_TIMEOUT_UNSPECIFIED, + NL80211_TIMEOUT_SCAN, + NL80211_TIMEOUT_AUTH, + NL80211_TIMEOUT_ASSOC, +}; + /** * enum nl80211_scan_flags - scan request control flags * diff --git a/net/wireless/core.h b/net/wireless/core.h index ba42055a036d..58ca206982fe 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -228,6 +228,7 @@ struct cfg80211_event { size_t resp_ie_len; struct cfg80211_bss *bss; int status; /* -1 = failed; 0..65535 = status code */ + enum nl80211_timeout_reason timeout_reason; } cr; struct { const u8 *req_ie; @@ -388,7 +389,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, size_t resp_ie_len, int status, bool wextev, - struct cfg80211_bss *bss); + struct cfg80211_bss *bss, + enum nl80211_timeout_reason timeout_reason); void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap); int cfg80211_disconnect(struct cfg80211_registered_device *rdev, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index b876f40c9dad..22b3d9990065 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -48,7 +48,8 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss, /* update current_bss etc., consumes the bss reference */ __cfg80211_connect_result(dev, mgmt->bssid, NULL, 0, ie, len - ieoffs, status_code, - status_code == WLAN_STATUS_SUCCESS, bss); + status_code == WLAN_STATUS_SUCCESS, bss, + NL80211_TIMEOUT_UNSPECIFIED); } EXPORT_SYMBOL(cfg80211_rx_assoc_resp); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 71c66ff9a702..b4e7bdd673e0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -409,6 +409,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_SCHED_SCAN_RSSI_ADJUST] = { .len = sizeof(struct nl80211_bss_select_rssi_adjust) }, + [NL80211_ATTR_TIMEOUT_REASON] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -13231,7 +13232,9 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, size_t resp_ie_len, - int status, gfp_t gfp) + int status, + enum nl80211_timeout_reason timeout_reason, + gfp_t gfp) { struct sk_buff *msg; void *hdr; @@ -13252,7 +13255,9 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, nla_put_u16(msg, NL80211_ATTR_STATUS_CODE, status < 0 ? WLAN_STATUS_UNSPECIFIED_FAILURE : status) || - (status < 0 && nla_put_flag(msg, NL80211_ATTR_TIMED_OUT)) || + (status < 0 && + (nla_put_flag(msg, NL80211_ATTR_TIMED_OUT) || + nla_put_u32(msg, NL80211_ATTR_TIMEOUT_REASON, timeout_reason))) || (req_ie && nla_put(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie)) || (resp_ie && diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 75f82520211d..e488dca87423 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -56,7 +56,9 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, size_t resp_ie_len, - int status, gfp_t gfp); + int status, + enum nl80211_timeout_reason timeout_reason, + gfp_t gfp); void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid, const u8 *req_ie, size_t req_ie_len, diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 46693913fcea..b347e63d7aaa 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -34,10 +34,11 @@ struct cfg80211_conn { CFG80211_CONN_SCAN_AGAIN, CFG80211_CONN_AUTHENTICATE_NEXT, CFG80211_CONN_AUTHENTICATING, - CFG80211_CONN_AUTH_FAILED, + CFG80211_CONN_AUTH_FAILED_TIMEOUT, CFG80211_CONN_ASSOCIATE_NEXT, CFG80211_CONN_ASSOCIATING, CFG80211_CONN_ASSOC_FAILED, + CFG80211_CONN_ASSOC_FAILED_TIMEOUT, CFG80211_CONN_DEAUTH, CFG80211_CONN_ABANDON, CFG80211_CONN_CONNECTED, @@ -140,7 +141,8 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) return err; } -static int cfg80211_conn_do_work(struct wireless_dev *wdev) +static int cfg80211_conn_do_work(struct wireless_dev *wdev, + enum nl80211_timeout_reason *treason) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_connect_params *params; @@ -171,7 +173,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) NULL, 0, params->key, params->key_len, params->key_idx, NULL, 0); - case CFG80211_CONN_AUTH_FAILED: + case CFG80211_CONN_AUTH_FAILED_TIMEOUT: + *treason = NL80211_TIMEOUT_AUTH; return -ENOTCONN; case CFG80211_CONN_ASSOCIATE_NEXT: if (WARN_ON(!rdev->ops->assoc)) @@ -198,6 +201,9 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) WLAN_REASON_DEAUTH_LEAVING, false); return err; + case CFG80211_CONN_ASSOC_FAILED_TIMEOUT: + *treason = NL80211_TIMEOUT_ASSOC; + /* fall through */ case CFG80211_CONN_ASSOC_FAILED: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, @@ -223,6 +229,7 @@ void cfg80211_conn_work(struct work_struct *work) container_of(work, struct cfg80211_registered_device, conn_work); struct wireless_dev *wdev; u8 bssid_buf[ETH_ALEN], *bssid = NULL; + enum nl80211_timeout_reason treason; rtnl_lock(); @@ -244,10 +251,12 @@ void cfg80211_conn_work(struct work_struct *work) memcpy(bssid_buf, wdev->conn->params.bssid, ETH_ALEN); bssid = bssid_buf; } - if (cfg80211_conn_do_work(wdev)) { + treason = NL80211_TIMEOUT_UNSPECIFIED; + if (cfg80211_conn_do_work(wdev, &treason)) { __cfg80211_connect_result( wdev->netdev, bssid, - NULL, 0, NULL, 0, -1, false, NULL); + NULL, 0, NULL, 0, -1, false, NULL, + treason); } wdev_unlock(wdev); } @@ -352,7 +361,8 @@ void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len) } else if (status_code != WLAN_STATUS_SUCCESS) { __cfg80211_connect_result(wdev->netdev, mgmt->bssid, NULL, 0, NULL, 0, - status_code, false, NULL); + status_code, false, NULL, + NL80211_TIMEOUT_UNSPECIFIED); } else if (wdev->conn->state == CFG80211_CONN_AUTHENTICATING) { wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; schedule_work(&rdev->conn_work); @@ -400,7 +410,7 @@ void cfg80211_sme_auth_timeout(struct wireless_dev *wdev) if (!wdev->conn) return; - wdev->conn->state = CFG80211_CONN_AUTH_FAILED; + wdev->conn->state = CFG80211_CONN_AUTH_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } @@ -422,7 +432,7 @@ void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev) if (!wdev->conn) return; - wdev->conn->state = CFG80211_CONN_ASSOC_FAILED; + wdev->conn->state = CFG80211_CONN_ASSOC_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } @@ -564,7 +574,9 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, /* we're good if we have a matching bss struct */ if (bss) { - err = cfg80211_conn_do_work(wdev); + enum nl80211_timeout_reason treason; + + err = cfg80211_conn_do_work(wdev, &treason); cfg80211_put_bss(wdev->wiphy, bss); } else { /* otherwise we'll need to scan for the AP first */ @@ -661,7 +673,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, size_t resp_ie_len, int status, bool wextev, - struct cfg80211_bss *bss) + struct cfg80211_bss *bss, + enum nl80211_timeout_reason timeout_reason) { struct wireless_dev *wdev = dev->ieee80211_ptr; const u8 *country_ie; @@ -680,7 +693,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev, bssid, req_ie, req_ie_len, resp_ie, resp_ie_len, - status, GFP_KERNEL); + status, timeout_reason, GFP_KERNEL); #ifdef CONFIG_CFG80211_WEXT if (wextev) { @@ -771,7 +784,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid, struct cfg80211_bss *bss, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, - size_t resp_ie_len, int status, gfp_t gfp) + size_t resp_ie_len, int status, gfp_t gfp, + enum nl80211_timeout_reason timeout_reason) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -811,6 +825,7 @@ void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid, cfg80211_hold_bss(bss_from_pub(bss)); ev->cr.bss = bss; ev->cr.status = status; + ev->cr.timeout_reason = timeout_reason; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); diff --git a/net/wireless/util.c b/net/wireless/util.c index cd8a7ae55e7d..1b9296882dcd 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -951,7 +951,7 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) ev->cr.resp_ie, ev->cr.resp_ie_len, ev->cr.status, ev->cr.status == WLAN_STATUS_SUCCESS, - ev->cr.bss); + ev->cr.bss, ev->cr.timeout_reason); break; case EVENT_ROAMED: __cfg80211_roamed(wdev, ev->rm.bss, ev->rm.req_ie, -- cgit v1.3-14-g43fede From a50a05f497a2a6e772900ffe93246fb7243d86d8 Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Sun, 15 Jan 2017 15:26:16 +0100 Subject: ipv6: sr: add missing Kbuild export for header files Add missing IPv6-SR header files in include/uapi/linux/Kbuild. Also, prevent seg6_lwt_headroom() from being exported and add missing linux/types.h include. Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/uapi/linux/Kbuild | 4 ++++ include/uapi/linux/seg6.h | 2 ++ include/uapi/linux/seg6_hmac.h | 1 + include/uapi/linux/seg6_iptunnel.h | 4 ++++ 4 files changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index f330ba4547cf..e600b50be77e 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -379,6 +379,10 @@ header-y += sctp.h header-y += sdla.h header-y += seccomp.h header-y += securebits.h +header-y += seg6_genl.h +header-y += seg6.h +header-y += seg6_hmac.h +header-y += seg6_iptunnel.h header-y += selinux_netlink.h header-y += sem.h header-y += serial_core.h diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h index c396a8052f73..33496595064c 100644 --- a/include/uapi/linux/seg6.h +++ b/include/uapi/linux/seg6.h @@ -14,6 +14,8 @@ #ifndef _UAPI_LINUX_SEG6_H #define _UAPI_LINUX_SEG6_H +#include + /* * SRH */ diff --git a/include/uapi/linux/seg6_hmac.h b/include/uapi/linux/seg6_hmac.h index b652dfd51bc5..e691c753fc3f 100644 --- a/include/uapi/linux/seg6_hmac.h +++ b/include/uapi/linux/seg6_hmac.h @@ -1,6 +1,7 @@ #ifndef _UAPI_LINUX_SEG6_HMAC_H #define _UAPI_LINUX_SEG6_HMAC_H +#include #include #define SEG6_HMAC_SECRET_LEN 64 diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h index 0f7dbd280a9c..7a7183d4062a 100644 --- a/include/uapi/linux/seg6_iptunnel.h +++ b/include/uapi/linux/seg6_iptunnel.h @@ -33,6 +33,8 @@ enum { SEG6_IPTUN_MODE_ENCAP, }; +#ifdef __KERNEL__ + static inline size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) { int encap = (tuninfo->mode == SEG6_IPTUN_MODE_ENCAP); @@ -42,3 +44,5 @@ static inline size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) } #endif + +#endif -- cgit v1.3-14-g43fede From aefb4d4ad83b608cb8e0cab8d3cd8e57d3f91feb Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Mon, 16 Jan 2017 14:16:36 +0000 Subject: net: AF-specific RTM_GETSTATS attributes Add the functionality for including address-family-specific per-link stats in RTM_GETSTATS messages. This is done through adding a new IFLA_STATS_AF_SPEC attribute under which address family attributes are nested and then the AF-specific attributes can be further nested. This follows the model of IFLA_AF_SPEC on RTM_*LINK messages and it has the advantage of presenting an easily extended hierarchy. The rtnl_af_ops structure is extended to provide AFs with the opportunity to fill and provide the size of their stats attributes. One alternative would have been to provide AFs with the ability to add attributes directly into the RTM_GETSTATS message without a nested hierarchy. I discounted this approach as it increases the rate at which the 32 attribute number space is used up and it makes implementation a little more tricky for stats dump resuming (at the moment the order in which attributes are added to the message has to match the numeric order of the attributes). Another alternative would have been to register per-AF RTM_GETSTATS handlers. I discounted this approach as I perceived a common use-case to be getting all the stats for an interface and this approach would necessitate multiple requests/dumps to retrieve them all. Signed-off-by: Robert Shearman Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 4 ++++ include/uapi/linux/if_link.h | 1 + net/core/rtnetlink.c | 50 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 55 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 4113916cc1bb..106de5f7bf06 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -139,6 +139,10 @@ struct rtnl_af_ops { const struct nlattr *attr); int (*set_link_af)(struct net_device *dev, const struct nlattr *attr); + + int (*fill_stats_af)(struct sk_buff *skb, + const struct net_device *dev); + size_t (*get_stats_af_size)(const struct net_device *dev); }; void __rtnl_af_unregister(struct rtnl_af_ops *ops); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6b13e591abc9..184b16ed2b84 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -847,6 +847,7 @@ enum { IFLA_STATS_LINK_XSTATS, IFLA_STATS_LINK_XSTATS_SLAVE, IFLA_STATS_LINK_OFFLOAD_XSTATS, + IFLA_STATS_AF_SPEC, __IFLA_STATS_MAX, }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 75e3ea7bda08..f538f764fca6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3829,6 +3829,39 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, *idxattr = 0; } + if (stats_attr_valid(filter_mask, IFLA_STATS_AF_SPEC, *idxattr)) { + struct rtnl_af_ops *af_ops; + + *idxattr = IFLA_STATS_AF_SPEC; + attr = nla_nest_start(skb, IFLA_STATS_AF_SPEC); + if (!attr) + goto nla_put_failure; + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->fill_stats_af) { + struct nlattr *af; + int err; + + af = nla_nest_start(skb, af_ops->family); + if (!af) + goto nla_put_failure; + + err = af_ops->fill_stats_af(skb, dev); + + if (err == -ENODATA) + nla_nest_cancel(skb, af); + else if (err < 0) + goto nla_put_failure; + + nla_nest_end(skb, af); + } + } + + nla_nest_end(skb, attr); + + *idxattr = 0; + } + nlmsg_end(skb, nlh); return 0; @@ -3885,6 +3918,23 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, 0)) size += rtnl_get_offload_stats_size(dev); + if (stats_attr_valid(filter_mask, IFLA_STATS_AF_SPEC, 0)) { + struct rtnl_af_ops *af_ops; + + /* for IFLA_STATS_AF_SPEC */ + size += nla_total_size(0); + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->get_stats_af_size) { + size += nla_total_size( + af_ops->get_stats_af_size(dev)); + + /* for AF_* */ + size += nla_total_size(0); + } + } + } + return size; } -- cgit v1.3-14-g43fede From 27d691056bde4a6feca5e83fd92b787332c46302 Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Mon, 16 Jan 2017 14:16:37 +0000 Subject: mpls: Packet stats Having MPLS packet stats is useful for observing network operation and for diagnosing network problems. In the absence of anything better, RFC2863 and RFC3813 are used for guidance for which stats to expose and the semantics of them. In particular rx_noroutes maps to in unknown protos in RFC2863. The stats are exposed to userspace via AF_MPLS attributes embedded in the IFLA_STATS_AF_SPEC attribute of RTM_GETSTATS messages. All the introduced fields are 64-bit, even error ones, to ensure no overflow with long uptimes. Per-CPU counters are used to avoid cache-line contention on the commonly used fields. The other fields have also been made per-CPU for code to avoid performance problems in error conditions on the assumption that on some platforms the cost of atomic operations could be more expensive than sending the packet (which is what would be done in the success case). If that's not the case, we could instead not use per-CPU counters for these fields. Only unicast and non-fragment are exposed at the moment, but other counters can be exposed in the future either by adding to the end of struct mpls_link_stats or by additional netlink attributes in the AF_MPLS IFLA_STATS_AF_SPEC nested attribute. Signed-off-by: Robert Shearman Signed-off-by: David S. Miller --- include/uapi/linux/mpls.h | 30 ++++++++ net/mpls/af_mpls.c | 181 ++++++++++++++++++++++++++++++++++++++++------ net/mpls/internal.h | 58 ++++++++++++++- net/mpls/mpls_iptunnel.c | 11 ++- 4 files changed, 252 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h index 24a6cb1aec86..77a19dfe3990 100644 --- a/include/uapi/linux/mpls.h +++ b/include/uapi/linux/mpls.h @@ -43,4 +43,34 @@ struct mpls_label { #define MPLS_LABEL_FIRST_UNRESERVED 16 /* RFC3032 */ +/* These are embedded into IFLA_STATS_AF_SPEC: + * [IFLA_STATS_AF_SPEC] + * -> [AF_MPLS] + * -> [MPLS_STATS_xxx] + * + * Attributes: + * [MPLS_STATS_LINK] = { + * struct mpls_link_stats + * } + */ +enum { + MPLS_STATS_UNSPEC, /* also used as 64bit pad attribute */ + MPLS_STATS_LINK, + __MPLS_STATS_MAX, +}; + +#define MPLS_STATS_MAX (__MPLS_STATS_MAX - 1) + +struct mpls_link_stats { + __u64 rx_packets; /* total packets received */ + __u64 tx_packets; /* total packets transmitted */ + __u64 rx_bytes; /* total bytes received */ + __u64 tx_bytes; /* total bytes transmitted */ + __u64 rx_errors; /* bad packets received */ + __u64 tx_errors; /* packet transmit problems */ + __u64 rx_dropped; /* packet dropped on receive */ + __u64 tx_dropped; /* packet dropped on transmit */ + __u64 rx_noroute; /* no route for packet dest */ +}; + #endif /* _UAPI_MPLS_H */ diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 15fe97644ffe..4dc81963af8f 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -17,8 +18,8 @@ #include #if IS_ENABLED(CONFIG_IPV6) #include -#include #endif +#include #include #include "internal.h" @@ -48,11 +49,6 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) return rt; } -static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) -{ - return rcu_dereference_rtnl(dev->mpls_ptr); -} - bool mpls_output_possible(const struct net_device *dev) { return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); @@ -98,6 +94,31 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) } EXPORT_SYMBOL_GPL(mpls_pkt_too_big); +void mpls_stats_inc_outucastpkts(struct net_device *dev, + const struct sk_buff *skb) +{ + struct mpls_dev *mdev; + + if (skb->protocol == htons(ETH_P_MPLS_UC)) { + mdev = mpls_dev_get(dev); + if (mdev) + MPLS_INC_STATS_LEN(mdev, skb->len, + tx_packets, + tx_bytes); + } else if (skb->protocol == htons(ETH_P_IP)) { + IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); +#if IS_ENABLED(CONFIG_IPV6) + } else if (skb->protocol == htons(ETH_P_IPV6)) { + struct inet6_dev *in6dev = __in6_dev_get(dev); + + if (in6dev) + IP6_UPD_PO_STATS(dev_net(dev), in6dev, + IPSTATS_MIB_OUT, skb->len); +#endif + } +} +EXPORT_SYMBOL_GPL(mpls_stats_inc_outucastpkts); + static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb, bool bos) { @@ -253,6 +274,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, struct mpls_nh *nh; struct mpls_entry_decoded dec; struct net_device *out_dev; + struct mpls_dev *out_mdev; struct mpls_dev *mdev; unsigned int hh_len; unsigned int new_header_size; @@ -262,17 +284,25 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, /* Careful this entire function runs inside of an rcu critical section */ mdev = mpls_dev_get(dev); - if (!mdev || !mdev->input_enabled) + if (!mdev) goto drop; - if (skb->pkt_type != PACKET_HOST) + MPLS_INC_STATS_LEN(mdev, skb->len, rx_packets, + rx_bytes); + + if (!mdev->input_enabled) { + MPLS_INC_STATS(mdev, rx_dropped); goto drop; + } + + if (skb->pkt_type != PACKET_HOST) + goto err; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) - goto drop; + goto err; if (!pskb_may_pull(skb, sizeof(*hdr))) - goto drop; + goto err; /* Read and decode the label */ hdr = mpls_hdr(skb); @@ -285,33 +315,35 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, skb_orphan(skb); rt = mpls_route_input_rcu(net, dec.label); - if (!rt) + if (!rt) { + MPLS_INC_STATS(mdev, rx_noroute); goto drop; + } nh = mpls_select_multipath(rt, skb, dec.bos); if (!nh) - goto drop; - - /* Find the output device */ - out_dev = rcu_dereference(nh->nh_dev); - if (!mpls_output_possible(out_dev)) - goto drop; + goto err; if (skb_warn_if_lro(skb)) - goto drop; + goto err; skb_forward_csum(skb); /* Verify ttl is valid */ if (dec.ttl <= 1) - goto drop; + goto err; dec.ttl -= 1; + /* Find the output device */ + out_dev = rcu_dereference(nh->nh_dev); + if (!mpls_output_possible(out_dev)) + goto tx_err; + /* Verify the destination can hold the packet */ new_header_size = mpls_nh_header_size(nh); mtu = mpls_dev_mtu(out_dev); if (mpls_pkt_too_big(skb, mtu - new_header_size)) - goto drop; + goto tx_err; hh_len = LL_RESERVED_SPACE(out_dev); if (!out_dev->header_ops) @@ -319,7 +351,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, /* Ensure there is enough space for the headers in the skb */ if (skb_cow(skb, hh_len + new_header_size)) - goto drop; + goto tx_err; skb->dev = out_dev; skb->protocol = htons(ETH_P_MPLS_UC); @@ -327,7 +359,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ if (!mpls_egress(rt, skb, dec)) - goto drop; + goto err; } else { bool bos; int i; @@ -343,6 +375,8 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, } } + mpls_stats_inc_outucastpkts(out_dev, skb); + /* If via wasn't specified then send out using device address */ if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC) err = neigh_xmit(NEIGH_LINK_TABLE, out_dev, @@ -355,6 +389,13 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, __func__, err); return 0; +tx_err: + out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL; + if (out_mdev) + MPLS_INC_STATS(out_mdev, tx_errors); + goto drop; +err: + MPLS_INC_STATS(mdev, rx_errors); drop: kfree_skb(skb); return NET_RX_DROP; @@ -853,6 +894,70 @@ errout: return err; } +static void mpls_get_stats(struct mpls_dev *mdev, + struct mpls_link_stats *stats) +{ + struct mpls_pcpu_stats *p; + int i; + + memset(stats, 0, sizeof(*stats)); + + for_each_possible_cpu(i) { + struct mpls_link_stats local; + unsigned int start; + + p = per_cpu_ptr(mdev->stats, i); + do { + start = u64_stats_fetch_begin(&p->syncp); + local = p->stats; + } while (u64_stats_fetch_retry(&p->syncp, start)); + + stats->rx_packets += local.rx_packets; + stats->rx_bytes += local.rx_bytes; + stats->tx_packets += local.tx_packets; + stats->tx_bytes += local.tx_bytes; + stats->rx_errors += local.rx_errors; + stats->tx_errors += local.tx_errors; + stats->rx_dropped += local.rx_dropped; + stats->tx_dropped += local.tx_dropped; + stats->rx_noroute += local.rx_noroute; + } +} + +static int mpls_fill_stats_af(struct sk_buff *skb, + const struct net_device *dev) +{ + struct mpls_link_stats *stats; + struct mpls_dev *mdev; + struct nlattr *nla; + + mdev = mpls_dev_get(dev); + if (!mdev) + return -ENODATA; + + nla = nla_reserve_64bit(skb, MPLS_STATS_LINK, + sizeof(struct mpls_link_stats), + MPLS_STATS_UNSPEC); + if (!nla) + return -EMSGSIZE; + + stats = nla_data(nla); + mpls_get_stats(mdev, stats); + + return 0; +} + +static size_t mpls_get_stats_af_size(const struct net_device *dev) +{ + struct mpls_dev *mdev; + + mdev = mpls_dev_get(dev); + if (!mdev) + return 0; + + return nla_total_size_64bit(sizeof(struct mpls_link_stats)); +} + #define MPLS_PERDEV_SYSCTL_OFFSET(field) \ (&((struct mpls_dev *)0)->field) @@ -911,6 +1016,7 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev) { struct mpls_dev *mdev; int err = -ENOMEM; + int i; ASSERT_RTNL(); @@ -918,6 +1024,17 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev) if (!mdev) return ERR_PTR(err); + mdev->stats = alloc_percpu(struct mpls_pcpu_stats); + if (!mdev->stats) + goto free; + + for_each_possible_cpu(i) { + struct mpls_pcpu_stats *mpls_stats; + + mpls_stats = per_cpu_ptr(mdev->stats, i); + u64_stats_init(&mpls_stats->syncp); + } + err = mpls_dev_sysctl_register(dev, mdev); if (err) goto free; @@ -927,10 +1044,19 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev) return mdev; free: + free_percpu(mdev->stats); kfree(mdev); return ERR_PTR(err); } +static void mpls_dev_destroy_rcu(struct rcu_head *head) +{ + struct mpls_dev *mdev = container_of(head, struct mpls_dev, rcu); + + free_percpu(mdev->stats); + kfree(mdev); +} + static void mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; @@ -1045,7 +1171,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, if (mdev) { mpls_dev_sysctl_unregister(mdev); RCU_INIT_POINTER(dev->mpls_ptr, NULL); - kfree_rcu(mdev, rcu); + call_rcu(&mdev->rcu, mpls_dev_destroy_rcu); } break; case NETDEV_CHANGENAME: @@ -1706,6 +1832,12 @@ static struct pernet_operations mpls_net_ops = { .exit = mpls_net_exit, }; +static struct rtnl_af_ops mpls_af_ops __read_mostly = { + .family = AF_MPLS, + .fill_stats_af = mpls_fill_stats_af, + .get_stats_af_size = mpls_get_stats_af_size, +}; + static int __init mpls_init(void) { int err; @@ -1722,6 +1854,8 @@ static int __init mpls_init(void) dev_add_pack(&mpls_packet_type); + rtnl_af_register(&mpls_af_ops); + rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, NULL); rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, NULL); rtnl_register(PF_MPLS, RTM_GETROUTE, NULL, mpls_dump_routes, NULL); @@ -1738,6 +1872,7 @@ module_init(mpls_init); static void __exit mpls_exit(void) { rtnl_unregister_all(PF_MPLS); + rtnl_af_unregister(&mpls_af_ops); dev_remove_pack(&mpls_packet_type); unregister_netdevice_notifier(&mpls_dev_notifier); unregister_pernet_subsys(&mpls_net_ops); diff --git a/net/mpls/internal.h b/net/mpls/internal.h index bdfef6c3271a..d97243034605 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -9,13 +9,58 @@ struct mpls_entry_decoded { u8 bos; }; +struct mpls_pcpu_stats { + struct mpls_link_stats stats; + struct u64_stats_sync syncp; +}; + struct mpls_dev { - int input_enabled; + int input_enabled; - struct ctl_table_header *sysctl; - struct rcu_head rcu; + struct mpls_pcpu_stats __percpu *stats; + + struct ctl_table_header *sysctl; + struct rcu_head rcu; }; +#if BITS_PER_LONG == 32 + +#define MPLS_INC_STATS_LEN(mdev, len, pkts_field, bytes_field) \ + do { \ + __typeof__(*(mdev)->stats) *ptr = \ + raw_cpu_ptr((mdev)->stats); \ + local_bh_disable(); \ + u64_stats_update_begin(&ptr->syncp); \ + ptr->stats.pkts_field++; \ + ptr->stats.bytes_field += (len); \ + u64_stats_update_end(&ptr->syncp); \ + local_bh_enable(); \ + } while (0) + +#define MPLS_INC_STATS(mdev, field) \ + do { \ + __typeof__(*(mdev)->stats) *ptr = \ + raw_cpu_ptr((mdev)->stats); \ + local_bh_disable(); \ + u64_stats_update_begin(&ptr->syncp); \ + ptr->stats.field++; \ + u64_stats_update_end(&ptr->syncp); \ + local_bh_enable(); \ + } while (0) + +#else + +#define MPLS_INC_STATS_LEN(mdev, len, pkts_field, bytes_field) \ + do { \ + this_cpu_inc((mdev)->stats->stats.pkts_field); \ + this_cpu_add((mdev)->stats->stats.bytes_field, (len)); \ + } while (0) + +#define MPLS_INC_STATS(mdev, field) \ + this_cpu_inc((mdev)->stats->stats.field) + +#endif + struct sk_buff; #define LABEL_NOT_SPECIFIED (1 << 20) @@ -114,6 +159,11 @@ static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr * return result; } +static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) +{ + return rcu_dereference_rtnl(dev->mpls_ptr); +} + int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]); int nla_get_labels(const struct nlattr *nla, u32 max_labels, u8 *labels, @@ -123,5 +173,7 @@ int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table, bool mpls_output_possible(const struct net_device *dev); unsigned int mpls_dev_mtu(const struct net_device *dev); bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu); +void mpls_stats_inc_outucastpkts(struct net_device *dev, + const struct sk_buff *skb); #endif /* MPLS_INTERNAL_H */ diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 2f7ccd934416..02531284bc49 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -48,11 +48,15 @@ static int mpls_xmit(struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct rtable *rt = NULL; struct rt6_info *rt6 = NULL; + struct mpls_dev *out_mdev; int err = 0; bool bos; int i; unsigned int ttl; + /* Find the output device */ + out_dev = dst->dev; + /* Obtain the ttl */ if (dst->ops->family == AF_INET) { ttl = ip_hdr(skb)->ttl; @@ -66,8 +70,6 @@ static int mpls_xmit(struct sk_buff *skb) skb_orphan(skb); - /* Find the output device */ - out_dev = dst->dev; if (!mpls_output_possible(out_dev) || !dst->lwtstate || skb_warn_if_lro(skb)) goto drop; @@ -109,6 +111,8 @@ static int mpls_xmit(struct sk_buff *skb) bos = false; } + mpls_stats_inc_outucastpkts(out_dev, skb); + if (rt) err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway, skb); @@ -122,6 +126,9 @@ static int mpls_xmit(struct sk_buff *skb) return LWTUNNEL_XMIT_DONE; drop: + out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL; + if (out_mdev) + MPLS_INC_STATS(out_mdev, tx_errors); kfree_skb(skb); return -EINVAL; } -- cgit v1.3-14-g43fede From 53631a5f9c6669264adb7b4e92fd95d1d6ffa7d3 Mon Sep 17 00:00:00 2001 From: Lance Richardson Date: Mon, 16 Jan 2017 18:11:35 -0500 Subject: bridge: sparse fixes in br_ip6_multicast_alloc_query() Changed type of csum field in struct igmpv3_query from __be16 to __sum16 to eliminate type warning, made same change in struct igmpv3_report for consistency. Fixed up an ntohs() where htons() should have been used instead. Signed-off-by: Lance Richardson Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/uapi/linux/igmp.h | 4 ++-- net/bridge/br_multicast.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/igmp.h b/include/uapi/linux/igmp.h index ccbb32aa6704..a97f9a7568cf 100644 --- a/include/uapi/linux/igmp.h +++ b/include/uapi/linux/igmp.h @@ -53,7 +53,7 @@ struct igmpv3_grec { struct igmpv3_report { __u8 type; __u8 resv1; - __be16 csum; + __sum16 csum; __be16 resv2; __be16 ngrec; struct igmpv3_grec grec[0]; @@ -62,7 +62,7 @@ struct igmpv3_report { struct igmpv3_query { __u8 type; __u8 code; - __be16 csum; + __sum16 csum; __be32 group; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 qrv:3, diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index b30e77e8427c..f66346122dc4 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -540,7 +540,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, break; case 2: mld2q = (struct mld2_query *)icmp6_hdr(skb); - mld2q->mld2q_mrc = ntohs((u16)jiffies_to_msecs(interval)); + mld2q->mld2q_mrc = htons((u16)jiffies_to_msecs(interval)); mld2q->mld2q_type = ICMPV6_MGM_QUERY; mld2q->mld2q_code = 0; mld2q->mld2q_cksum = 0; -- cgit v1.3-14-g43fede From 9fb657aec0e20b4ed4401c44a4140f8d7b7a9ca0 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 18 Jan 2017 00:44:46 +0800 Subject: sctp: add sockopt SCTP_ENABLE_STREAM_RESET This patch is to add sockopt SCTP_ENABLE_STREAM_RESET to get/set strreset_enable to indicate which reconf request type it supports, which is described in rfc6525 section 6.3.1. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 4 +++ include/uapi/linux/sctp.h | 7 ++++ net/sctp/associola.c | 1 + net/sctp/socket.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 96 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index ee037ef15d65..d99b76e33b2e 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1257,6 +1257,8 @@ struct sctp_endpoint { __u8 auth_enable:1, prsctp_enable:1, reconf_enable:1; + + __u8 strreset_enable; }; /* Recover the outter endpoint structure. */ @@ -1872,6 +1874,8 @@ struct sctp_association { prsctp_enable:1, reconf_enable:1; + __u8 strreset_enable; + __u32 strreset_outseq; /* Update after receiving response */ __u32 strreset_inseq; /* Update after receiving request */ diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index a406adcc0793..867be0f32fd7 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -115,6 +115,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_PR_SUPPORTED 113 #define SCTP_DEFAULT_PRINFO 114 #define SCTP_PR_ASSOC_STATUS 115 +#define SCTP_ENABLE_STREAM_RESET 118 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -138,6 +139,12 @@ typedef __s32 sctp_assoc_t; #define SCTP_PR_RTX_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_RTX) #define SCTP_PR_PRIO_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_PRIO) +/* For enable stream reset */ +#define SCTP_ENABLE_RESET_STREAM_REQ 0x01 +#define SCTP_ENABLE_RESET_ASSOC_REQ 0x02 +#define SCTP_ENABLE_CHANGE_ASSOC_REQ 0x04 +#define SCTP_ENABLE_STRRESET_MASK 0x07 + /* These are bit fields for msghdr->msg_flags. See section 5.1. */ /* On user space Linux, these live in as an enum. */ enum sctp_msg_flags { diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 68b99adc21a3..e50dc6d7543f 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -271,6 +271,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->active_key_id = ep->active_key_id; asoc->prsctp_enable = ep->prsctp_enable; asoc->reconf_enable = ep->reconf_enable; + asoc->strreset_enable = ep->strreset_enable; /* Save the hmacs and chunks list into this association */ if (ep->auth_hmacs_list) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 635e03412693..0a9bc984b6c8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3750,6 +3750,42 @@ out: return retval; } +static int sctp_setsockopt_enable_strreset(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EINVAL; + + if (optlen != sizeof(params)) + goto out; + + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + if (params.assoc_value & (~SCTP_ENABLE_STRRESET_MASK)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + asoc->strreset_enable = params.assoc_value; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + sp->ep->strreset_enable = params.assoc_value; + } else { + goto out; + } + + retval = 0; + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -3916,6 +3952,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_DEFAULT_PRINFO: retval = sctp_setsockopt_default_prinfo(sk, optval, optlen); break; + case SCTP_ENABLE_STREAM_RESET: + retval = sctp_setsockopt_enable_strreset(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -6400,6 +6439,47 @@ out: return retval; } +static int sctp_getsockopt_enable_strreset(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + params.assoc_value = asoc->strreset_enable; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + params.assoc_value = sp->ep->strreset_enable; + } else { + retval = -EINVAL; + goto out; + } + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, ¶ms, len)) + goto out; + + retval = 0; + +out: + return retval; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -6567,6 +6647,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_pr_assocstatus(sk, len, optval, optlen); break; + case SCTP_ENABLE_STREAM_RESET: + retval = sctp_getsockopt_enable_strreset(sk, len, optval, + optlen); + break; default: retval = -ENOPROTOOPT; break; -- cgit v1.3-14-g43fede From 7f9d68ac944e24ee5f9ac8d059ca00b1c1d34137 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 18 Jan 2017 00:44:47 +0800 Subject: sctp: implement sender-side procedures for SSN Reset Request Parameter This patch is to implement sender-side procedures for the Outgoing and Incoming SSN Reset Request Parameter described in rfc6525 section 5.1.2 and 5.1.3. It is also add sockopt SCTP_RESET_STREAMS in rfc6525 section 6.3.2 for users. Note that the new asoc member strreset_outstanding is to make sure only one reconf request chunk on the fly as rfc6525 section 5.1.1 demands. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 6 ++++ include/net/sctp/structs.h | 1 + include/uapi/linux/sctp.h | 11 +++++++ net/sctp/outqueue.c | 33 +++++++++++++------ net/sctp/socket.c | 29 +++++++++++++++++ net/sctp/stream.c | 79 ++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 149 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index bc0e049b1474..3cfd365bcfbc 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -193,6 +193,12 @@ void sctp_remaddr_proc_exit(struct net *net); */ int sctp_offload_init(void); +/* + * sctp/stream.c + */ +int sctp_send_reset_streams(struct sctp_association *asoc, + struct sctp_reset_streams *params); + /* * Module global variables */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d99b76e33b2e..231fa9ac50bd 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1875,6 +1875,7 @@ struct sctp_association { reconf_enable:1; __u8 strreset_enable; + __u8 strreset_outstanding; /* request param count on the fly */ __u32 strreset_outseq; /* Update after receiving response */ __u32 strreset_inseq; /* Update after receiving request */ diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 867be0f32fd7..03c27cefffb1 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -116,6 +116,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_DEFAULT_PRINFO 114 #define SCTP_PR_ASSOC_STATUS 115 #define SCTP_ENABLE_STREAM_RESET 118 +#define SCTP_RESET_STREAMS 119 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -145,6 +146,9 @@ typedef __s32 sctp_assoc_t; #define SCTP_ENABLE_CHANGE_ASSOC_REQ 0x04 #define SCTP_ENABLE_STRRESET_MASK 0x07 +#define SCTP_STREAM_RESET_INCOMING 0x01 +#define SCTP_STREAM_RESET_OUTGOING 0x02 + /* These are bit fields for msghdr->msg_flags. See section 5.1. */ /* On user space Linux, these live in as an enum. */ enum sctp_msg_flags { @@ -1015,4 +1019,11 @@ struct sctp_info { __u32 __reserved3; }; +struct sctp_reset_streams { + sctp_assoc_t srs_assoc_id; + uint16_t srs_flags; + uint16_t srs_number_streams; /* 0 == ALL */ + uint16_t srs_stream_list[]; /* list if srs_num_streams is not 0 */ +}; + #endif /* _UAPI_SCTP_H */ diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 34efaa4ef2f6..65abe22d8691 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -915,22 +915,28 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) case SCTP_CID_ECN_ECNE: case SCTP_CID_ASCONF: case SCTP_CID_FWD_TSN: + case SCTP_CID_RECONF: status = sctp_packet_transmit_chunk(packet, chunk, one_packet, gfp); if (status != SCTP_XMIT_OK) { /* put the chunk back */ list_add(&chunk->list, &q->control_chunk_list); - } else { - asoc->stats.octrlchunks++; - /* PR-SCTP C5) If a FORWARD TSN is sent, the - * sender MUST assure that at least one T3-rtx - * timer is running. - */ - if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN) { - sctp_transport_reset_t3_rtx(transport); - transport->last_time_sent = jiffies; - } + break; + } + + asoc->stats.octrlchunks++; + /* PR-SCTP C5) If a FORWARD TSN is sent, the + * sender MUST assure that at least one T3-rtx + * timer is running. + */ + if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN) { + sctp_transport_reset_t3_rtx(transport); + transport->last_time_sent = jiffies; } + + if (chunk == asoc->strreset_chunk) + sctp_transport_reset_reconf_timer(transport); + break; default: @@ -1016,6 +1022,8 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) /* Finally, transmit new packets. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { + __u32 sid = ntohs(chunk->subh.data_hdr->stream); + /* RFC 2960 6.5 Every DATA chunk MUST carry a valid * stream identifier. */ @@ -1038,6 +1046,11 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) continue; } + if (asoc->stream->out[sid].state == SCTP_STREAM_CLOSED) { + sctp_outq_head_data(q, chunk); + goto sctp_flush_out; + } + /* If there is a specified transport, use it. * Otherwise, we want to use the active path. */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0a9bc984b6c8..bee4dd3feabb 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3786,6 +3786,32 @@ out: return retval; } +static int sctp_setsockopt_reset_streams(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_reset_streams *params; + struct sctp_association *asoc; + int retval = -EINVAL; + + if (optlen < sizeof(struct sctp_reset_streams)) + return -EINVAL; + + params = memdup_user(optval, optlen); + if (IS_ERR(params)) + return PTR_ERR(params); + + asoc = sctp_id2assoc(sk, params->srs_assoc_id); + if (!asoc) + goto out; + + retval = sctp_send_reset_streams(asoc, params); + +out: + kfree(params); + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -3955,6 +3981,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_ENABLE_STREAM_RESET: retval = sctp_setsockopt_enable_strreset(sk, optval, optlen); break; + case SCTP_RESET_STREAMS: + retval = sctp_setsockopt_reset_streams(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index f86de43cbbe5..13d5e07dcd7d 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -33,6 +33,7 @@ */ #include +#include struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp) { @@ -83,3 +84,81 @@ void sctp_stream_clear(struct sctp_stream *stream) for (i = 0; i < stream->incnt; i++) stream->in[i].ssn = 0; } + +static int sctp_send_reconf(struct sctp_association *asoc, + struct sctp_chunk *chunk) +{ + struct net *net = sock_net(asoc->base.sk); + int retval = 0; + + retval = sctp_primitive_RECONF(net, asoc, chunk); + if (retval) + sctp_chunk_free(chunk); + + return retval; +} + +int sctp_send_reset_streams(struct sctp_association *asoc, + struct sctp_reset_streams *params) +{ + struct sctp_stream *stream = asoc->stream; + __u16 i, str_nums, *str_list; + struct sctp_chunk *chunk; + int retval = -EINVAL; + bool out, in; + + if (!asoc->peer.reconf_capable || + !(asoc->strreset_enable & SCTP_ENABLE_RESET_STREAM_REQ)) { + retval = -ENOPROTOOPT; + goto out; + } + + if (asoc->strreset_outstanding) { + retval = -EINPROGRESS; + goto out; + } + + out = params->srs_flags & SCTP_STREAM_RESET_OUTGOING; + in = params->srs_flags & SCTP_STREAM_RESET_INCOMING; + if (!out && !in) + goto out; + + str_nums = params->srs_number_streams; + str_list = params->srs_stream_list; + if (out && str_nums) + for (i = 0; i < str_nums; i++) + if (str_list[i] >= stream->outcnt) + goto out; + + if (in && str_nums) + for (i = 0; i < str_nums; i++) + if (str_list[i] >= stream->incnt) + goto out; + + chunk = sctp_make_strreset_req(asoc, str_nums, str_list, out, in); + if (!chunk) + goto out; + + if (out) { + if (str_nums) + for (i = 0; i < str_nums; i++) + stream->out[str_list[i]].state = + SCTP_STREAM_CLOSED; + else + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_CLOSED; + } + + asoc->strreset_outstanding = out + in; + asoc->strreset_chunk = chunk; + sctp_chunk_hold(asoc->strreset_chunk); + + retval = sctp_send_reconf(asoc, chunk); + if (retval) { + sctp_chunk_put(asoc->strreset_chunk); + asoc->strreset_chunk = NULL; + } + +out: + return retval; +} -- cgit v1.3-14-g43fede From a5e8c07059d0f0b31737408711d44794928ac218 Mon Sep 17 00:00:00 2001 From: Gianluca Borello Date: Wed, 18 Jan 2017 17:55:49 +0000 Subject: bpf: add bpf_probe_read_str helper Provide a simple helper with the same semantics of strncpy_from_unsafe(): int bpf_probe_read_str(void *dst, int size, const void *unsafe_addr) This gives more flexibility to a bpf program. A typical use case is intercepting a file name during sys_open(). The current approach is: SEC("kprobe/sys_open") void bpf_sys_open(struct pt_regs *ctx) { char buf[PATHLEN]; // PATHLEN is defined to 256 bpf_probe_read(buf, sizeof(buf), ctx->di); /* consume buf */ } This is suboptimal because the size of the string needs to be estimated at compile time, causing more memory to be copied than often necessary, and can become more problematic if further processing on buf is done, for example by pushing it to userspace via bpf_perf_event_output(), since the real length of the string is unknown and the entire buffer must be copied (and defining an unrolled strnlen() inside the bpf program is a very inefficient and unfeasible approach). With the new helper, the code can easily operate on the actual string length rather than the buffer size: SEC("kprobe/sys_open") void bpf_sys_open(struct pt_regs *ctx) { char buf[PATHLEN]; // PATHLEN is defined to 256 int res = bpf_probe_read_str(buf, sizeof(buf), ctx->di); /* consume buf, for example push it to userspace via * bpf_perf_event_output(), but this time we can use * res (the string length) as event size, after checking * its boundaries. */ } Another useful use case is when parsing individual process arguments or individual environment variables navigating current->mm->arg_start and current->mm->env_start: using this helper and the return value, one can quickly iterate at the right offset of the memory area. The code changes simply leverage the already existent strncpy_from_unsafe() kernel function, which is safe to be called from a bpf program as it is used in bpf_trace_printk(). Signed-off-by: Gianluca Borello Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 15 ++++++++++++++- kernel/trace/bpf_trace.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0eb0e87dbe9f..54a5894bb4ea 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -430,6 +430,18 @@ union bpf_attr { * @xdp_md: pointer to xdp_md * @delta: An positive/negative integer to be added to xdp_md.data * Return: 0 on success or negative on error + * + * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) + * Copy a NUL terminated string from unsafe address. In case the string + * length is smaller than size, the target is not padded with further NUL + * bytes. In case the string length is larger than size, just count-1 + * bytes are copied and the last byte is set to NUL. + * @dst: destination address + * @size: maximum number of bytes to copy, including the trailing NUL + * @unsafe_ptr: unsafe address + * Return: + * > 0 length of the string including the trailing NUL on success + * < 0 error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -476,7 +488,8 @@ union bpf_attr { FN(set_hash_invalid), \ FN(get_numa_node_id), \ FN(skb_change_head), \ - FN(xdp_adjust_head), + FN(xdp_adjust_head), \ + FN(probe_read_str), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c22a961d1a42..424daa4586d1 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -395,6 +395,36 @@ static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size, + const void *, unsafe_ptr) +{ + int ret; + + /* + * The strncpy_from_unsafe() call will likely not fill the entire + * buffer, but that's okay in this circumstance as we're probing + * arbitrary memory anyway similar to bpf_probe_read() and might + * as well probe the stack. Thus, memory is explicitly cleared + * only in error case, so that improper users ignoring return + * code altogether don't copy garbage; otherwise length of string + * is returned that can be used for bpf_perf_event_output() et al. + */ + ret = strncpy_from_unsafe(dst, unsafe_ptr, size); + if (unlikely(ret < 0)) + memset(dst, 0, size); + + return ret; +} + +static const struct bpf_func_proto bpf_probe_read_str_proto = { + .func = bpf_probe_read_str, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -432,6 +462,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; + case BPF_FUNC_probe_read_str: + return &bpf_probe_read_str_proto; default: return NULL; } -- cgit v1.3-14-g43fede From 01fd12bb189a0772301dd37e9b31e53761269a1b Mon Sep 17 00:00:00 2001 From: Jon Paul Maloy Date: Wed, 18 Jan 2017 13:50:53 -0500 Subject: tipc: make replicast a user selectable option If the bearer carrying multicast messages supports broadcast, those messages will be sent to all cluster nodes, irrespective of whether these nodes host any actual destinations socket or not. This is clearly wasteful if the cluster is large and there are only a few real destinations for the message being sent. In this commit we extend the eligibility of the newly introduced "replicast" transmit option. We now make it possible for a user to select which method he wants to be used, either as a mandatory setting via setsockopt(), or as a relative setting where we let the broadcast layer decide which method to use based on the ratio between cluster size and the message's actual number of destination nodes. In the latter case, a sending socket must stick to a previously selected method until it enters an idle period of at least 5 seconds. This eliminates the risk of message reordering caused by method change, i.e., when changes to cluster size or number of destinations would otherwise mandate a new method to be used. Reviewed-by: Parthasarathy Bhuvaragan Acked-by: Ying Xue Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- include/uapi/linux/tipc.h | 6 +++-- net/tipc/bcast.c | 62 ++++++++++++++++++++++++++++++++++++++++++----- net/tipc/bcast.h | 17 ++++++++++++- net/tipc/link.c | 4 +++ net/tipc/node.h | 4 ++- net/tipc/socket.c | 36 +++++++++++++++++++++------ 6 files changed, 112 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index bf049e8fe31b..5351b08c897a 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -1,7 +1,7 @@ /* * include/uapi/linux/tipc.h: Header for TIPC socket interface * - * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2003-2006, 2015-2016 Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * @@ -220,7 +220,7 @@ struct sockaddr_tipc { #define TIPC_DESTNAME 3 /* destination name */ /* - * TIPC-specific socket option values + * TIPC-specific socket option names */ #define TIPC_IMPORTANCE 127 /* Default: TIPC_LOW_IMPORTANCE */ @@ -229,6 +229,8 @@ struct sockaddr_tipc { #define TIPC_CONN_TIMEOUT 130 /* Default: 8000 (ms) */ #define TIPC_NODE_RECVQ_DEPTH 131 /* Default: none (read only) */ #define TIPC_SOCK_RECVQ_DEPTH 132 /* Default: none (read only) */ +#define TIPC_MCAST_BROADCAST 133 /* Default: TIPC selects. No arg */ +#define TIPC_MCAST_REPLICAST 134 /* Default: TIPC selects. No arg */ /* * Maximum sizes of TIPC bearer-related names (including terminating NULL) diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 672e6ef93cab..7d99029df342 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -54,6 +54,9 @@ const char tipc_bclink_name[] = "broadcast-link"; * @dest: array keeping number of reachable destinations per bearer * @primary_bearer: a bearer having links to all broadcast destinations, if any * @bcast_support: indicates if primary bearer, if any, supports broadcast + * @rcast_support: indicates if all peer nodes support replicast + * @rc_ratio: dest count as percentage of cluster size where send method changes + * @bc_threshold: calculated drom rc_ratio; if dests > threshold use broadcast */ struct tipc_bc_base { struct tipc_link *link; @@ -61,6 +64,9 @@ struct tipc_bc_base { int dests[MAX_BEARERS]; int primary_bearer; bool bcast_support; + bool rcast_support; + int rc_ratio; + int bc_threshold; }; static struct tipc_bc_base *tipc_bc_base(struct net *net) @@ -73,6 +79,19 @@ int tipc_bcast_get_mtu(struct net *net) return tipc_link_mtu(tipc_bc_sndlink(net)) - INT_H_SIZE; } +void tipc_bcast_disable_rcast(struct net *net) +{ + tipc_bc_base(net)->rcast_support = false; +} + +static void tipc_bcbase_calc_bc_threshold(struct net *net) +{ + struct tipc_bc_base *bb = tipc_bc_base(net); + int cluster_size = tipc_link_bc_peers(tipc_bc_sndlink(net)); + + bb->bc_threshold = 1 + (cluster_size * bb->rc_ratio / 100); +} + /* tipc_bcbase_select_primary(): find a bearer with links to all destinations, * if any, and make it primary bearer */ @@ -175,6 +194,31 @@ static void tipc_bcbase_xmit(struct net *net, struct sk_buff_head *xmitq) __skb_queue_purge(&_xmitq); } +static void tipc_bcast_select_xmit_method(struct net *net, int dests, + struct tipc_mc_method *method) +{ + struct tipc_bc_base *bb = tipc_bc_base(net); + unsigned long exp = method->expires; + + /* Broadcast supported by used bearer/bearers? */ + if (!bb->bcast_support) { + method->rcast = true; + return; + } + /* Any destinations which don't support replicast ? */ + if (!bb->rcast_support) { + method->rcast = false; + return; + } + /* Can current method be changed ? */ + method->expires = jiffies + TIPC_METHOD_EXPIRE; + if (method->mandatory || time_before(jiffies, exp)) + return; + + /* Determine method to use now */ + method->rcast = dests <= bb->bc_threshold; +} + /* tipc_bcast_xmit - broadcast the buffer chain to all external nodes * @net: the applicable net namespace * @pkts: chain of buffers containing message @@ -237,16 +281,16 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, * and to identified node local sockets * @net: the applicable net namespace * @pkts: chain of buffers containing message - * @dests: destination nodes for message. Not consumed. + * @method: send method to be used + * @dests: destination nodes for message. * @cong_link_cnt: returns number of encountered congested destination links - * @cong_links: returns identities of congested links * Consumes buffer chain. * Returns 0 if success, otherwise errno */ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, - struct tipc_nlist *dests, u16 *cong_link_cnt) + struct tipc_mc_method *method, struct tipc_nlist *dests, + u16 *cong_link_cnt) { - struct tipc_bc_base *bb = tipc_bc_base(net); struct sk_buff_head inputq, localq; int rc = 0; @@ -258,9 +302,10 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, rc = -ENOMEM; goto exit; } - + /* Send according to determined transmit method */ if (dests->remote) { - if (!bb->bcast_support) + tipc_bcast_select_xmit_method(net, dests->remote, method); + if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); else rc = tipc_bcast_xmit(net, pkts, cong_link_cnt); @@ -269,6 +314,7 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, if (dests->local) tipc_sk_mcast_rcv(net, &localq, &inputq); exit: + /* This queue should normally be empty by now */ __skb_queue_purge(pkts); return rc; } @@ -377,6 +423,7 @@ void tipc_bcast_add_peer(struct net *net, struct tipc_link *uc_l, tipc_bcast_lock(net); tipc_link_add_bc_peer(snd_l, uc_l, xmitq); tipc_bcbase_select_primary(net); + tipc_bcbase_calc_bc_threshold(net); tipc_bcast_unlock(net); } @@ -395,6 +442,7 @@ void tipc_bcast_remove_peer(struct net *net, struct tipc_link *rcv_l) tipc_bcast_lock(net); tipc_link_remove_bc_peer(snd_l, rcv_l, &xmitq); tipc_bcbase_select_primary(net); + tipc_bcbase_calc_bc_threshold(net); tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); @@ -477,6 +525,8 @@ int tipc_bcast_init(struct net *net) goto enomem; bb->link = l; tn->bcl = l; + bb->rc_ratio = 25; + bb->rcast_support = true; return 0; enomem: kfree(bb); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index dd772e6f6fa4..751530ab0c49 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -46,6 +46,8 @@ struct tipc_nlist; struct tipc_nitem; extern const char tipc_bclink_name[]; +#define TIPC_METHOD_EXPIRE msecs_to_jiffies(5000) + struct tipc_nlist { struct list_head list; u32 self; @@ -58,6 +60,17 @@ void tipc_nlist_purge(struct tipc_nlist *nl); void tipc_nlist_add(struct tipc_nlist *nl, u32 node); void tipc_nlist_del(struct tipc_nlist *nl, u32 node); +/* Cookie to be used between socket and broadcast layer + * @rcast: replicast (instead of broadcast) was used at previous xmit + * @mandatory: broadcast/replicast indication was set by user + * @expires: re-evaluate non-mandatory transmit method if we are past this + */ +struct tipc_mc_method { + bool rcast; + bool mandatory; + unsigned long expires; +}; + int tipc_bcast_init(struct net *net); void tipc_bcast_stop(struct net *net); void tipc_bcast_add_peer(struct net *net, struct tipc_link *l, @@ -66,8 +79,10 @@ void tipc_bcast_remove_peer(struct net *net, struct tipc_link *rcv_bcl); void tipc_bcast_inc_bearer_dst_cnt(struct net *net, int bearer_id); void tipc_bcast_dec_bearer_dst_cnt(struct net *net, int bearer_id); int tipc_bcast_get_mtu(struct net *net); +void tipc_bcast_disable_rcast(struct net *net); int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, - struct tipc_nlist *dests, u16 *cong_link_cnt); + struct tipc_mc_method *method, struct tipc_nlist *dests, + u16 *cong_link_cnt); int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb); void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l, struct tipc_msg *hdr); diff --git a/net/tipc/link.c b/net/tipc/link.c index b17b9e155469..ddd2dd6f77aa 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -515,6 +515,10 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, if (link_is_bc_sndlink(l)) l->state = LINK_ESTABLISHED; + /* Disable replicast if even a single peer doesn't support it */ + if (link_is_bc_rcvlink(l) && !(peer_caps & TIPC_BCAST_RCAST)) + tipc_bcast_disable_rcast(net); + return true; } diff --git a/net/tipc/node.h b/net/tipc/node.h index 39ef54c1f2ad..898c22916984 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -47,11 +47,13 @@ enum { TIPC_BCAST_SYNCH = (1 << 1), TIPC_BCAST_STATE_NACK = (1 << 2), - TIPC_BLOCK_FLOWCTL = (1 << 3) + TIPC_BLOCK_FLOWCTL = (1 << 3), + TIPC_BCAST_RCAST = (1 << 4) }; #define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \ TIPC_BCAST_STATE_NACK | \ + TIPC_BCAST_RCAST | \ TIPC_BLOCK_FLOWCTL) #define INVALID_BEARER_ID -1 diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 93b6ae3154c9..5bec8aac5008 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -79,6 +79,7 @@ enum { * @rcv_unacked: # messages read by user, but not yet acked back to peer * @peer: 'connected' peer for dgram/rdm * @node: hash table node + * @mc_method: cookie for use between socket and broadcast layer * @rcu: rcu struct for tipc_sock */ struct tipc_sock { @@ -103,6 +104,7 @@ struct tipc_sock { u16 rcv_win; struct sockaddr_tipc peer; struct rhash_head node; + struct tipc_mc_method mc_method; struct rcu_head rcu; }; @@ -740,6 +742,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_msg *hdr = &tsk->phdr; struct net *net = sock_net(sk); int mtu = tipc_bcast_get_mtu(net); + struct tipc_mc_method *method = &tsk->mc_method; u32 domain = addr_domain(net, TIPC_CLUSTER_SCOPE); struct sk_buff_head pkts; struct tipc_nlist dsts; @@ -773,7 +776,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, /* Send message if build was successful */ if (unlikely(rc == dlen)) - rc = tipc_mcast_xmit(net, &pkts, &dsts, + rc = tipc_mcast_xmit(net, &pkts, method, &dsts, &tsk->cong_link_cnt); tipc_nlist_purge(&dsts); @@ -2344,18 +2347,29 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); - u32 value; + u32 value = 0; int res; if ((lvl == IPPROTO_TCP) && (sock->type == SOCK_STREAM)) return 0; if (lvl != SOL_TIPC) return -ENOPROTOOPT; - if (ol < sizeof(value)) - return -EINVAL; - res = get_user(value, (u32 __user *)ov); - if (res) - return res; + + switch (opt) { + case TIPC_IMPORTANCE: + case TIPC_SRC_DROPPABLE: + case TIPC_DEST_DROPPABLE: + case TIPC_CONN_TIMEOUT: + if (ol < sizeof(value)) + return -EINVAL; + res = get_user(value, (u32 __user *)ov); + if (res) + return res; + break; + default: + if (ov || ol) + return -EINVAL; + } lock_sock(sk); @@ -2376,6 +2390,14 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, tipc_sk(sk)->conn_timeout = value; /* no need to set "res", since already 0 at this point */ break; + case TIPC_MCAST_BROADCAST: + tsk->mc_method.rcast = false; + tsk->mc_method.mandatory = true; + break; + case TIPC_MCAST_REPLICAST: + tsk->mc_method.rcast = true; + tsk->mc_method.mandatory = true; + break; default: res = -EINVAL; } -- cgit v1.3-14-g43fede From b95a5c4db09bc7c253636cb84dc9b12c577fd5a0 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Sat, 21 Jan 2017 17:26:11 +0100 Subject: bpf: add a longest prefix match trie map implementation This trie implements a longest prefix match algorithm that can be used to match IP addresses to a stored set of ranges. Internally, data is stored in an unbalanced trie of nodes that has a maximum height of n, where n is the prefixlen the trie was created with. Tries may be created with prefix lengths that are multiples of 8, in the range from 8 to 2048. The key used for lookup and update operations is a struct bpf_lpm_trie_key, and the value is a uint64_t. The code carries more information about the internal implementation. Signed-off-by: Daniel Mack Reviewed-by: David Herrmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 7 + kernel/bpf/Makefile | 2 +- kernel/bpf/lpm_trie.c | 503 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 511 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/lpm_trie.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 54a5894bb4ea..bd3068485410 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -63,6 +63,12 @@ struct bpf_insn { __s32 imm; /* signed immediate constant */ }; +/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ +struct bpf_lpm_trie_key { + __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ + __u8 data[0]; /* Arbitrary size */ +}; + /* BPF syscall commands, see bpf(2) man-page for details. */ enum bpf_cmd { BPF_MAP_CREATE, @@ -89,6 +95,7 @@ enum bpf_map_type { BPF_MAP_TYPE_CGROUP_ARRAY, BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH, + BPF_MAP_TYPE_LPM_TRIE, }; enum bpf_prog_type { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 1276474ac3cd..e1ce4f4fd7fd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,7 +1,7 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o -obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o +obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c new file mode 100644 index 000000000000..ba19241d1979 --- /dev/null +++ b/kernel/bpf/lpm_trie.c @@ -0,0 +1,503 @@ +/* + * Longest prefix match list implementation + * + * Copyright (c) 2016,2017 Daniel Mack + * Copyright (c) 2016 David Herrmann + * + * This file is subject to the terms and conditions of version 2 of the GNU + * General Public License. See the file COPYING in the main directory of the + * Linux distribution for more details. + */ + +#include +#include +#include +#include +#include +#include + +/* Intermediate node */ +#define LPM_TREE_NODE_FLAG_IM BIT(0) + +struct lpm_trie_node; + +struct lpm_trie_node { + struct rcu_head rcu; + struct lpm_trie_node __rcu *child[2]; + u32 prefixlen; + u32 flags; + u8 data[0]; +}; + +struct lpm_trie { + struct bpf_map map; + struct lpm_trie_node __rcu *root; + size_t n_entries; + size_t max_prefixlen; + size_t data_size; + raw_spinlock_t lock; +}; + +/* This trie implements a longest prefix match algorithm that can be used to + * match IP addresses to a stored set of ranges. + * + * Data stored in @data of struct bpf_lpm_key and struct lpm_trie_node is + * interpreted as big endian, so data[0] stores the most significant byte. + * + * Match ranges are internally stored in instances of struct lpm_trie_node + * which each contain their prefix length as well as two pointers that may + * lead to more nodes containing more specific matches. Each node also stores + * a value that is defined by and returned to userspace via the update_elem + * and lookup functions. + * + * For instance, let's start with a trie that was created with a prefix length + * of 32, so it can be used for IPv4 addresses, and one single element that + * matches 192.168.0.0/16. The data array would hence contain + * [0xc0, 0xa8, 0x00, 0x00] in big-endian notation. This documentation will + * stick to IP-address notation for readability though. + * + * As the trie is empty initially, the new node (1) will be places as root + * node, denoted as (R) in the example below. As there are no other node, both + * child pointers are %NULL. + * + * +----------------+ + * | (1) (R) | + * | 192.168.0.0/16 | + * | value: 1 | + * | [0] [1] | + * +----------------+ + * + * Next, let's add a new node (2) matching 192.168.0.0/24. As there is already + * a node with the same data and a smaller prefix (ie, a less specific one), + * node (2) will become a child of (1). In child index depends on the next bit + * that is outside of what (1) matches, and that bit is 0, so (2) will be + * child[0] of (1): + * + * +----------------+ + * | (1) (R) | + * | 192.168.0.0/16 | + * | value: 1 | + * | [0] [1] | + * +----------------+ + * | + * +----------------+ + * | (2) | + * | 192.168.0.0/24 | + * | value: 2 | + * | [0] [1] | + * +----------------+ + * + * The child[1] slot of (1) could be filled with another node which has bit #17 + * (the next bit after the ones that (1) matches on) set to 1. For instance, + * 192.168.128.0/24: + * + * +----------------+ + * | (1) (R) | + * | 192.168.0.0/16 | + * | value: 1 | + * | [0] [1] | + * +----------------+ + * | | + * +----------------+ +------------------+ + * | (2) | | (3) | + * | 192.168.0.0/24 | | 192.168.128.0/24 | + * | value: 2 | | value: 3 | + * | [0] [1] | | [0] [1] | + * +----------------+ +------------------+ + * + * Let's add another node (4) to the game for 192.168.1.0/24. In order to place + * it, node (1) is looked at first, and because (4) of the semantics laid out + * above (bit #17 is 0), it would normally be attached to (1) as child[0]. + * However, that slot is already allocated, so a new node is needed in between. + * That node does not have a value attached to it and it will never be + * returned to users as result of a lookup. It is only there to differentiate + * the traversal further. It will get a prefix as wide as necessary to + * distinguish its two children: + * + * +----------------+ + * | (1) (R) | + * | 192.168.0.0/16 | + * | value: 1 | + * | [0] [1] | + * +----------------+ + * | | + * +----------------+ +------------------+ + * | (4) (I) | | (3) | + * | 192.168.0.0/23 | | 192.168.128.0/24 | + * | value: --- | | value: 3 | + * | [0] [1] | | [0] [1] | + * +----------------+ +------------------+ + * | | + * +----------------+ +----------------+ + * | (2) | | (5) | + * | 192.168.0.0/24 | | 192.168.1.0/24 | + * | value: 2 | | value: 5 | + * | [0] [1] | | [0] [1] | + * +----------------+ +----------------+ + * + * 192.168.1.1/32 would be a child of (5) etc. + * + * An intermediate node will be turned into a 'real' node on demand. In the + * example above, (4) would be re-used if 192.168.0.0/23 is added to the trie. + * + * A fully populated trie would have a height of 32 nodes, as the trie was + * created with a prefix length of 32. + * + * The lookup starts at the root node. If the current node matches and if there + * is a child that can be used to become more specific, the trie is traversed + * downwards. The last node in the traversal that is a non-intermediate one is + * returned. + */ + +static inline int extract_bit(const u8 *data, size_t index) +{ + return !!(data[index / 8] & (1 << (7 - (index % 8)))); +} + +/** + * longest_prefix_match() - determine the longest prefix + * @trie: The trie to get internal sizes from + * @node: The node to operate on + * @key: The key to compare to @node + * + * Determine the longest prefix of @node that matches the bits in @key. + */ +static size_t longest_prefix_match(const struct lpm_trie *trie, + const struct lpm_trie_node *node, + const struct bpf_lpm_trie_key *key) +{ + size_t prefixlen = 0; + size_t i; + + for (i = 0; i < trie->data_size; i++) { + size_t b; + + b = 8 - fls(node->data[i] ^ key->data[i]); + prefixlen += b; + + if (prefixlen >= node->prefixlen || prefixlen >= key->prefixlen) + return min(node->prefixlen, key->prefixlen); + + if (b < 8) + break; + } + + return prefixlen; +} + +/* Called from syscall or from eBPF program */ +static void *trie_lookup_elem(struct bpf_map *map, void *_key) +{ + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct lpm_trie_node *node, *found = NULL; + struct bpf_lpm_trie_key *key = _key; + + /* Start walking the trie from the root node ... */ + + for (node = rcu_dereference(trie->root); node;) { + unsigned int next_bit; + size_t matchlen; + + /* Determine the longest prefix of @node that matches @key. + * If it's the maximum possible prefix for this trie, we have + * an exact match and can return it directly. + */ + matchlen = longest_prefix_match(trie, node, key); + if (matchlen == trie->max_prefixlen) { + found = node; + break; + } + + /* If the number of bits that match is smaller than the prefix + * length of @node, bail out and return the node we have seen + * last in the traversal (ie, the parent). + */ + if (matchlen < node->prefixlen) + break; + + /* Consider this node as return candidate unless it is an + * artificially added intermediate one. + */ + if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) + found = node; + + /* If the node match is fully satisfied, let's see if we can + * become more specific. Determine the next bit in the key and + * traverse down. + */ + next_bit = extract_bit(key->data, node->prefixlen); + node = rcu_dereference(node->child[next_bit]); + } + + if (!found) + return NULL; + + return found->data + trie->data_size; +} + +static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, + const void *value) +{ + struct lpm_trie_node *node; + size_t size = sizeof(struct lpm_trie_node) + trie->data_size; + + if (value) + size += trie->map.value_size; + + node = kmalloc(size, GFP_ATOMIC | __GFP_NOWARN); + if (!node) + return NULL; + + node->flags = 0; + + if (value) + memcpy(node->data + trie->data_size, value, + trie->map.value_size); + + return node; +} + +/* Called from syscall or from eBPF program */ +static int trie_update_elem(struct bpf_map *map, + void *_key, void *value, u64 flags) +{ + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct lpm_trie_node *node, *im_node, *new_node = NULL; + struct lpm_trie_node __rcu **slot; + struct bpf_lpm_trie_key *key = _key; + unsigned long irq_flags; + unsigned int next_bit; + size_t matchlen = 0; + int ret = 0; + + if (unlikely(flags > BPF_EXIST)) + return -EINVAL; + + if (key->prefixlen > trie->max_prefixlen) + return -EINVAL; + + raw_spin_lock_irqsave(&trie->lock, irq_flags); + + /* Allocate and fill a new node */ + + if (trie->n_entries == trie->map.max_entries) { + ret = -ENOSPC; + goto out; + } + + new_node = lpm_trie_node_alloc(trie, value); + if (!new_node) { + ret = -ENOMEM; + goto out; + } + + trie->n_entries++; + + new_node->prefixlen = key->prefixlen; + RCU_INIT_POINTER(new_node->child[0], NULL); + RCU_INIT_POINTER(new_node->child[1], NULL); + memcpy(new_node->data, key->data, trie->data_size); + + /* Now find a slot to attach the new node. To do that, walk the tree + * from the root and match as many bits as possible for each node until + * we either find an empty slot or a slot that needs to be replaced by + * an intermediate node. + */ + slot = &trie->root; + + while ((node = rcu_dereference_protected(*slot, + lockdep_is_held(&trie->lock)))) { + matchlen = longest_prefix_match(trie, node, key); + + if (node->prefixlen != matchlen || + node->prefixlen == key->prefixlen || + node->prefixlen == trie->max_prefixlen) + break; + + next_bit = extract_bit(key->data, node->prefixlen); + slot = &node->child[next_bit]; + } + + /* If the slot is empty (a free child pointer or an empty root), + * simply assign the @new_node to that slot and be done. + */ + if (!node) { + rcu_assign_pointer(*slot, new_node); + goto out; + } + + /* If the slot we picked already exists, replace it with @new_node + * which already has the correct data array set. + */ + if (node->prefixlen == matchlen) { + new_node->child[0] = node->child[0]; + new_node->child[1] = node->child[1]; + + if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) + trie->n_entries--; + + rcu_assign_pointer(*slot, new_node); + kfree_rcu(node, rcu); + + goto out; + } + + /* If the new node matches the prefix completely, it must be inserted + * as an ancestor. Simply insert it between @node and *@slot. + */ + if (matchlen == key->prefixlen) { + next_bit = extract_bit(node->data, matchlen); + rcu_assign_pointer(new_node->child[next_bit], node); + rcu_assign_pointer(*slot, new_node); + goto out; + } + + im_node = lpm_trie_node_alloc(trie, NULL); + if (!im_node) { + ret = -ENOMEM; + goto out; + } + + im_node->prefixlen = matchlen; + im_node->flags |= LPM_TREE_NODE_FLAG_IM; + memcpy(im_node->data, node->data, trie->data_size); + + /* Now determine which child to install in which slot */ + if (extract_bit(key->data, matchlen)) { + rcu_assign_pointer(im_node->child[0], node); + rcu_assign_pointer(im_node->child[1], new_node); + } else { + rcu_assign_pointer(im_node->child[0], new_node); + rcu_assign_pointer(im_node->child[1], node); + } + + /* Finally, assign the intermediate node to the determined spot */ + rcu_assign_pointer(*slot, im_node); + +out: + if (ret) { + if (new_node) + trie->n_entries--; + + kfree(new_node); + kfree(im_node); + } + + raw_spin_unlock_irqrestore(&trie->lock, irq_flags); + + return ret; +} + +static int trie_delete_elem(struct bpf_map *map, void *key) +{ + /* TODO */ + return -ENOSYS; +} + +static struct bpf_map *trie_alloc(union bpf_attr *attr) +{ + size_t cost, cost_per_node; + struct lpm_trie *trie; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || + attr->map_flags != BPF_F_NO_PREALLOC || + attr->key_size < sizeof(struct bpf_lpm_trie_key) + 1 || + attr->key_size > sizeof(struct bpf_lpm_trie_key) + 256 || + attr->value_size == 0) + return ERR_PTR(-EINVAL); + + trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN); + if (!trie) + return ERR_PTR(-ENOMEM); + + /* copy mandatory map attributes */ + trie->map.map_type = attr->map_type; + trie->map.key_size = attr->key_size; + trie->map.value_size = attr->value_size; + trie->map.max_entries = attr->max_entries; + trie->data_size = attr->key_size - + offsetof(struct bpf_lpm_trie_key, data); + trie->max_prefixlen = trie->data_size * 8; + + cost_per_node = sizeof(struct lpm_trie_node) + + attr->value_size + trie->data_size; + cost = sizeof(*trie) + attr->max_entries * cost_per_node; + trie->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + ret = bpf_map_precharge_memlock(trie->map.pages); + if (ret) { + kfree(trie); + return ERR_PTR(ret); + } + + raw_spin_lock_init(&trie->lock); + + return &trie->map; +} + +static void trie_free(struct bpf_map *map) +{ + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct lpm_trie_node __rcu **slot; + struct lpm_trie_node *node; + + raw_spin_lock(&trie->lock); + + /* Always start at the root and walk down to a node that has no + * children. Then free that node, nullify its reference in the parent + * and start over. + */ + + for (;;) { + slot = &trie->root; + + for (;;) { + node = rcu_dereference_protected(*slot, + lockdep_is_held(&trie->lock)); + if (!node) + goto unlock; + + if (rcu_access_pointer(node->child[0])) { + slot = &node->child[0]; + continue; + } + + if (rcu_access_pointer(node->child[1])) { + slot = &node->child[1]; + continue; + } + + kfree(node); + RCU_INIT_POINTER(*slot, NULL); + break; + } + } + +unlock: + raw_spin_unlock(&trie->lock); +} + +static const struct bpf_map_ops trie_ops = { + .map_alloc = trie_alloc, + .map_free = trie_free, + .map_lookup_elem = trie_lookup_elem, + .map_update_elem = trie_update_elem, + .map_delete_elem = trie_delete_elem, +}; + +static struct bpf_map_type_list trie_type __read_mostly = { + .ops = &trie_ops, + .type = BPF_MAP_TYPE_LPM_TRIE, +}; + +static int __init register_trie_map(void) +{ + bpf_register_map_type(&trie_type); + return 0; +} +late_initcall(register_trie_map); -- cgit v1.3-14-g43fede From 12a6075cabc0d9ffbc0366b44daa22f278606312 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Tue, 10 Jan 2017 18:52:06 +0100 Subject: can: dev: add CAN interface termination API This patch adds a netlink interface to configure the CAN bus termination of CAN interfaces. Inside the driver an array of supported termination values is defined: const u16 drvname_termination[] = { 60, 120, CAN_TERMINATION_DISABLED }; struct drvname_priv *priv; priv = netdev_priv(dev); priv->termination_const = drvname_termination; priv->termination_const_cnt = ARRAY_SIZE(drvname_termination); priv->termination = CAN_TERMINATION_DISABLED; And the funtion to set the value has to be defined: priv->do_set_termination = drvname_set_termination; Signed-off-by: Oliver Hartkopp Reviewed-by: Ramesh Shanmugasundaram Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 49 +++++++++++++++++++++++++++++++++++++++- include/linux/can/dev.h | 4 ++++ include/uapi/linux/can/netlink.h | 5 ++++ 3 files changed, 57 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 8d6208c0b400..fefe2cd17721 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -958,6 +958,30 @@ static int can_changelink(struct net_device *dev, } } + if (data[IFLA_CAN_TERMINATION]) { + const u16 termval = nla_get_u16(data[IFLA_CAN_TERMINATION]); + const unsigned int num_term = priv->termination_const_cnt; + unsigned int i; + + if (!priv->do_set_termination) + return -EOPNOTSUPP; + + /* check whether given value is supported by the interface */ + for (i = 0; i < num_term; i++) { + if (termval == priv->termination_const[i]) + break; + } + if (i >= num_term) + return -EINVAL; + + /* Finally, set the termination value */ + err = priv->do_set_termination(dev, termval); + if (err) + return err; + + priv->termination = termval; + } + return 0; } @@ -980,6 +1004,11 @@ static size_t can_get_size(const struct net_device *dev) size += nla_total_size(sizeof(struct can_bittiming)); if (priv->data_bittiming_const) /* IFLA_CAN_DATA_BITTIMING_CONST */ size += nla_total_size(sizeof(struct can_bittiming_const)); + if (priv->termination_const) { + size += nla_total_size(sizeof(priv->termination)); /* IFLA_CAN_TERMINATION */ + size += nla_total_size(sizeof(*priv->termination_const) * /* IFLA_CAN_TERMINATION_CONST */ + priv->termination_const_cnt); + } return size; } @@ -1018,7 +1047,15 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) (priv->data_bittiming_const && nla_put(skb, IFLA_CAN_DATA_BITTIMING_CONST, sizeof(*priv->data_bittiming_const), - priv->data_bittiming_const))) + priv->data_bittiming_const)) || + + (priv->termination_const && + (nla_put_u16(skb, IFLA_CAN_TERMINATION, priv->termination) || + nla_put(skb, IFLA_CAN_TERMINATION_CONST, + sizeof(*priv->termination_const) * + priv->termination_const_cnt, + priv->termination_const)))) + return -EMSGSIZE; return 0; @@ -1073,6 +1110,16 @@ static struct rtnl_link_ops can_link_ops __read_mostly = { */ int register_candev(struct net_device *dev) { + struct can_priv *priv = netdev_priv(dev); + + /* Ensure termination_const, termination_const_cnt and + * do_set_termination consistency. All must be either set or + * unset. + */ + if ((!priv->termination_const != !priv->termination_const_cnt) || + (!priv->termination_const != !priv->do_set_termination)) + return -EINVAL; + dev->rtnl_link_ops = &can_link_ops; return register_netdev(dev); } diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 5f5270941ba0..f6a57f322f00 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -38,6 +38,9 @@ struct can_priv { struct can_bittiming bittiming, data_bittiming; const struct can_bittiming_const *bittiming_const, *data_bittiming_const; + const u16 *termination_const; + unsigned int termination_const_cnt; + u16 termination; struct can_clock clock; enum can_state state; @@ -53,6 +56,7 @@ struct can_priv { int (*do_set_bittiming)(struct net_device *dev); int (*do_set_data_bittiming)(struct net_device *dev); int (*do_set_mode)(struct net_device *dev, enum can_mode mode); + int (*do_set_termination)(struct net_device *dev, u16 term); int (*do_get_state)(const struct net_device *dev, enum can_state *state); int (*do_get_berr_counter)(const struct net_device *dev, diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 94ffe0c83ce7..7414771926fb 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -127,9 +127,14 @@ enum { IFLA_CAN_BERR_COUNTER, IFLA_CAN_DATA_BITTIMING, IFLA_CAN_DATA_BITTIMING_CONST, + IFLA_CAN_TERMINATION, + IFLA_CAN_TERMINATION_CONST, __IFLA_CAN_MAX }; #define IFLA_CAN_MAX (__IFLA_CAN_MAX - 1) +/* u16 termination range: 1..65535 Ohms */ +#define CAN_TERMINATION_DISABLED 0 + #endif /* !_UAPI_CAN_NETLINK_H */ -- cgit v1.3-14-g43fede From 431af779256cd6cb8328ac23c5696bae63c33a51 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 11 Jan 2017 17:05:35 +0100 Subject: can: dev: add CAN interface API for fixed bitrates Some CAN interfaces only support fixed fixed bitrates. This patch adds a netlink interface to get the list of the CAN interface's fixed bitrates and data bitrates. Inside the driver arrays of supported data- bitrate values are defined. const u32 drvname_bitrate[] = { 20000, 50000, 100000 }; const u32 drvname_data_bitrate[] = { 200000, 500000, 1000000 }; struct drvname_priv *priv; priv = netdev_priv(dev); priv->bitrate_const = drvname_bitrate; priv->bitrate_const_cnt = ARRAY_SIZE(drvname_bitrate); priv->data_bitrate_const = drvname_data_bitrate; priv->data_bitrate_const_cnt = ARRAY_SIZE(drvname_data_bitrate); Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 81 ++++++++++++++++++++++++++++++++-------- include/linux/can/dev.h | 4 ++ include/uapi/linux/can/netlink.h | 2 + 3 files changed, 71 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index afcf487382c9..611d16a7061d 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -279,8 +279,29 @@ static int can_fixup_bittiming(struct net_device *dev, struct can_bittiming *bt, return 0; } +/* Checks the validity of predefined bitrate settings */ +static int can_validate_bitrate(struct net_device *dev, struct can_bittiming *bt, + const u32 *bitrate_const, + const unsigned int bitrate_const_cnt) +{ + struct can_priv *priv = netdev_priv(dev); + unsigned int i; + + for (i = 0; i < bitrate_const_cnt; i++) { + if (bt->bitrate == bitrate_const[i]) + break; + } + + if (i >= priv->bitrate_const_cnt) + return -EINVAL; + + return 0; +} + static int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt, - const struct can_bittiming_const *btc) + const struct can_bittiming_const *btc, + const u32 *bitrate_const, + const unsigned int bitrate_const_cnt) { int err; @@ -290,10 +311,13 @@ static int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt, * alternatively the CAN timing parameters (tq, prop_seg, etc.) are * provided directly which are then checked and fixed up. */ - if (!bt->tq && bt->bitrate) + if (!bt->tq && bt->bitrate && btc) err = can_calc_bittiming(dev, bt, btc); - else if (bt->tq && !bt->bitrate) + else if (bt->tq && !bt->bitrate && btc) err = can_fixup_bittiming(dev, bt, btc); + else if (!bt->tq && bt->bitrate && bitrate_const) + err = can_validate_bitrate(dev, bt, bitrate_const, + bitrate_const_cnt); else err = -EINVAL; @@ -878,12 +902,12 @@ static int can_changelink(struct net_device *dev, return -EOPNOTSUPP; memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt)); - if (priv->bittiming_const) { - err = can_get_bittiming(dev, &bt, - priv->bittiming_const); - if (err) - return err; - } + err = can_get_bittiming(dev, &bt, + priv->bittiming_const, + priv->bitrate_const, + priv->bitrate_const_cnt); + if (err) + return err; memcpy(&priv->bittiming, &bt, sizeof(bt)); if (priv->do_set_bittiming) { @@ -962,12 +986,12 @@ static int can_changelink(struct net_device *dev, memcpy(&dbt, nla_data(data[IFLA_CAN_DATA_BITTIMING]), sizeof(dbt)); - if (priv->data_bittiming_const) { - err = can_get_bittiming(dev, &dbt, - priv->data_bittiming_const); - if (err) - return err; - } + err = can_get_bittiming(dev, &dbt, + priv->data_bittiming_const, + priv->data_bitrate_const, + priv->data_bitrate_const_cnt); + if (err) + return err; memcpy(&priv->data_bittiming, &dbt, sizeof(dbt)); if (priv->do_set_data_bittiming) { @@ -1029,6 +1053,12 @@ static size_t can_get_size(const struct net_device *dev) size += nla_total_size(sizeof(*priv->termination_const) * /* IFLA_CAN_TERMINATION_CONST */ priv->termination_const_cnt); } + if (priv->bitrate_const) /* IFLA_CAN_BITRATE_CONST */ + size += nla_total_size(sizeof(*priv->bitrate_const) * + priv->bitrate_const_cnt); + if (priv->data_bitrate_const) /* IFLA_CAN_DATA_BITRATE_CONST */ + size += nla_total_size(sizeof(*priv->data_bitrate_const) * + priv->data_bitrate_const_cnt); return size; } @@ -1074,7 +1104,20 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put(skb, IFLA_CAN_TERMINATION_CONST, sizeof(*priv->termination_const) * priv->termination_const_cnt, - priv->termination_const)))) + priv->termination_const))) || + + (priv->bitrate_const && + nla_put(skb, IFLA_CAN_BITRATE_CONST, + sizeof(*priv->bitrate_const) * + priv->bitrate_const_cnt, + priv->bitrate_const)) || + + (priv->data_bitrate_const && + nla_put(skb, IFLA_CAN_DATA_BITRATE_CONST, + sizeof(*priv->data_bitrate_const) * + priv->data_bitrate_const_cnt, + priv->data_bitrate_const)) + ) return -EMSGSIZE; @@ -1140,6 +1183,12 @@ int register_candev(struct net_device *dev) (!priv->termination_const != !priv->do_set_termination)) return -EINVAL; + if (!priv->bitrate_const != !priv->bitrate_const_cnt) + return -EINVAL; + + if (!priv->data_bitrate_const != !priv->data_bitrate_const_cnt) + return -EINVAL; + dev->rtnl_link_ops = &can_link_ops; return register_netdev(dev); } diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index f6a57f322f00..141b05aade81 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -41,6 +41,10 @@ struct can_priv { const u16 *termination_const; unsigned int termination_const_cnt; u16 termination; + const u32 *bitrate_const; + unsigned int bitrate_const_cnt; + const u32 *data_bitrate_const; + unsigned int data_bitrate_const_cnt; struct can_clock clock; enum can_state state; diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 7414771926fb..fdf75f74fdaf 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -129,6 +129,8 @@ enum { IFLA_CAN_DATA_BITTIMING_CONST, IFLA_CAN_TERMINATION, IFLA_CAN_TERMINATION_CONST, + IFLA_CAN_BITRATE_CONST, + IFLA_CAN_DATA_BITRATE_CONST, __IFLA_CAN_MAX }; -- cgit v1.3-14-g43fede From 6db6f0eae6052b70885562e1733896647ec1d807 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Sat, 21 Jan 2017 21:01:32 +0100 Subject: bridge: multicast to unicast MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implements an optional, per bridge port flag and feature to deliver multicast packets to any host on the according port via unicast individually. This is done by copying the packet per host and changing the multicast destination MAC to a unicast one accordingly. multicast-to-unicast works on top of the multicast snooping feature of the bridge. Which means unicast copies are only delivered to hosts which are interested in it and signalized this via IGMP/MLD reports previously. This feature is intended for interface types which have a more reliable and/or efficient way to deliver unicast packets than broadcast ones (e.g. wifi). However, it should only be enabled on interfaces where no IGMPv2/MLDv1 report suppression takes place. This feature is disabled by default. The initial patch and idea is from Felix Fietkau. Signed-off-by: Felix Fietkau [linus.luessing@c0d3.blue: various bug + style fixes, commit message] Signed-off-by: Linus Lüssing Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 1 + net/bridge/br_forward.c | 39 ++++++++++++++++++- net/bridge/br_mdb.c | 2 +- net/bridge/br_multicast.c | 90 ++++++++++++++++++++++++++++++++------------ net/bridge/br_netlink.c | 5 +++ net/bridge/br_private.h | 3 +- net/bridge/br_sysfs_if.c | 2 + 8 files changed, 114 insertions(+), 29 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index c6587c01d951..debc9d5904e5 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -46,6 +46,7 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) #define BR_MCAST_FLOOD BIT(11) +#define BR_MULTICAST_TO_UNICAST BIT(12) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 184b16ed2b84..b9aa5641ebe5 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -321,6 +321,7 @@ enum { IFLA_BRPORT_MULTICAST_ROUTER, IFLA_BRPORT_PAD, IFLA_BRPORT_MCAST_FLOOD, + IFLA_BRPORT_MCAST_TO_UCAST, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 7cb41aee4c82..a0f9d0037d24 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -174,6 +174,31 @@ out: return p; } +static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, + const unsigned char *addr, bool local_orig) +{ + struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev; + const unsigned char *src = eth_hdr(skb)->h_source; + + if (!should_deliver(p, skb)) + return; + + /* Even with hairpin, no soliloquies - prevent breaking IPv6 DAD */ + if (skb->dev == p->dev && ether_addr_equal(src, addr)) + return; + + skb = skb_copy(skb, GFP_ATOMIC); + if (!skb) { + dev->stats.tx_dropped++; + return; + } + + if (!is_broadcast_ether_addr(addr)) + memcpy(eth_hdr(skb)->h_dest, addr, ETH_ALEN); + + __br_forward(p, skb, local_orig); +} + /* called under rcu_read_lock */ void br_flood(struct net_bridge *br, struct sk_buff *skb, enum br_pkt_type pkt_type, bool local_rcv, bool local_orig) @@ -241,10 +266,20 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) : NULL; - port = (unsigned long)lport > (unsigned long)rport ? - lport : rport; + if ((unsigned long)lport > (unsigned long)rport) { + port = lport; + + if (port->flags & BR_MULTICAST_TO_UNICAST) { + maybe_deliver_addr(lport, skb, p->eth_addr, + local_orig); + goto delivered; + } + } else { + port = rport; + } prev = maybe_deliver(prev, port, skb, local_orig); +delivered: if (IS_ERR(prev)) goto out; if (prev == port) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 7dbc80d01eb0..056e6ac49d8f 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -531,7 +531,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, break; } - p = br_multicast_new_port_group(port, group, *pp, state); + p = br_multicast_new_port_group(port, group, *pp, state, NULL); if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index f66346122dc4..1de3438e36bf 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -43,12 +43,14 @@ static void br_multicast_add_router(struct net_bridge *br, static void br_ip4_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, - __u16 vid); + __u16 vid, + const unsigned char *src); + #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, const struct in6_addr *group, - __u16 vid); + __u16 vid, const unsigned char *src); #endif unsigned int br_mdb_rehash_seq; @@ -711,7 +713,8 @@ struct net_bridge_port_group *br_multicast_new_port_group( struct net_bridge_port *port, struct br_ip *group, struct net_bridge_port_group __rcu *next, - unsigned char flags) + unsigned char flags, + const unsigned char *src) { struct net_bridge_port_group *p; @@ -726,12 +729,32 @@ struct net_bridge_port_group *br_multicast_new_port_group( hlist_add_head(&p->mglist, &port->mglist); setup_timer(&p->timer, br_multicast_port_group_expired, (unsigned long)p); + + if (src) + memcpy(p->eth_addr, src, ETH_ALEN); + else + memset(p->eth_addr, 0xff, ETH_ALEN); + return p; } +static bool br_port_group_equal(struct net_bridge_port_group *p, + struct net_bridge_port *port, + const unsigned char *src) +{ + if (p->port != port) + return false; + + if (!(port->flags & BR_MULTICAST_TO_UNICAST)) + return true; + + return ether_addr_equal(src, p->eth_addr); +} + static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, - struct br_ip *group) + struct br_ip *group, + const unsigned char *src) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; @@ -758,13 +781,13 @@ static int br_multicast_add_group(struct net_bridge *br, for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { - if (p->port == port) + if (br_port_group_equal(p, port, src)) goto found; if ((unsigned long)p->port < (unsigned long)port) break; } - p = br_multicast_new_port_group(port, group, *pp, 0); + p = br_multicast_new_port_group(port, group, *pp, 0, src); if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); @@ -783,7 +806,8 @@ err: static int br_ip4_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, - __u16 vid) + __u16 vid, + const unsigned char *src) { struct br_ip br_group; @@ -794,14 +818,15 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, br_group.proto = htons(ETH_P_IP); br_group.vid = vid; - return br_multicast_add_group(br, port, &br_group); + return br_multicast_add_group(br, port, &br_group, src); } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, const struct in6_addr *group, - __u16 vid) + __u16 vid, + const unsigned char *src) { struct br_ip br_group; @@ -812,7 +837,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; - return br_multicast_add_group(br, port, &br_group); + return br_multicast_add_group(br, port, &br_group, src); } #endif @@ -1081,6 +1106,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + const unsigned char *src; struct igmpv3_report *ih; struct igmpv3_grec *grec; int i; @@ -1121,12 +1147,14 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, continue; } + src = eth_hdr(skb)->h_source; if ((type == IGMPV3_CHANGE_TO_INCLUDE || type == IGMPV3_MODE_IS_INCLUDE) && ntohs(grec->grec_nsrcs) == 0) { - br_ip4_multicast_leave_group(br, port, group, vid); + br_ip4_multicast_leave_group(br, port, group, vid, src); } else { - err = br_ip4_multicast_add_group(br, port, group, vid); + err = br_ip4_multicast_add_group(br, port, group, vid, + src); if (err) break; } @@ -1141,6 +1169,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + const unsigned char *src; struct icmp6hdr *icmp6h; struct mld2_grec *grec; int i; @@ -1188,14 +1217,16 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, continue; } + src = eth_hdr(skb)->h_source; if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE || grec->grec_type == MLD2_MODE_IS_INCLUDE) && ntohs(*nsrcs) == 0) { br_ip6_multicast_leave_group(br, port, &grec->grec_mca, - vid); + vid, src); } else { err = br_ip6_multicast_add_group(br, port, - &grec->grec_mca, vid); + &grec->grec_mca, vid, + src); if (err) break; } @@ -1511,7 +1542,8 @@ br_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group, struct bridge_mcast_other_query *other_query, - struct bridge_mcast_own_query *own_query) + struct bridge_mcast_own_query *own_query, + const unsigned char *src) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; @@ -1535,7 +1567,7 @@ br_multicast_leave_group(struct net_bridge *br, for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { - if (p->port != port) + if (!br_port_group_equal(p, port, src)) continue; rcu_assign_pointer(*pp, p->next); @@ -1566,7 +1598,7 @@ br_multicast_leave_group(struct net_bridge *br, for (p = mlock_dereference(mp->ports, br); p != NULL; p = mlock_dereference(p->next, br)) { - if (p->port != port) + if (!br_port_group_equal(p, port, src)) continue; if (!hlist_unhashed(&p->mglist) && @@ -1617,7 +1649,8 @@ out: static void br_ip4_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, - __u16 vid) + __u16 vid, + const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; @@ -1632,14 +1665,15 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, br_group.vid = vid; br_multicast_leave_group(br, port, &br_group, &br->ip4_other_query, - own_query); + own_query, src); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, const struct in6_addr *group, - __u16 vid) + __u16 vid, + const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; @@ -1654,7 +1688,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, br_group.vid = vid; br_multicast_leave_group(br, port, &br_group, &br->ip6_other_query, - own_query); + own_query, src); } #endif @@ -1712,6 +1746,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, u16 vid) { struct sk_buff *skb_trimmed = NULL; + const unsigned char *src; struct igmphdr *ih; int err; @@ -1731,13 +1766,14 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, } ih = igmp_hdr(skb); + src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->igmp = ih->type; switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - err = br_ip4_multicast_add_group(br, port, ih->group, vid); + err = br_ip4_multicast_add_group(br, port, ih->group, vid, src); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: err = br_ip4_multicast_igmp3_report(br, port, skb_trimmed, vid); @@ -1746,7 +1782,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = br_ip4_multicast_query(br, port, skb_trimmed, vid); break; case IGMP_HOST_LEAVE_MESSAGE: - br_ip4_multicast_leave_group(br, port, ih->group, vid); + br_ip4_multicast_leave_group(br, port, ih->group, vid, src); break; } @@ -1766,6 +1802,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, u16 vid) { struct sk_buff *skb_trimmed = NULL; + const unsigned char *src; struct mld_msg *mld; int err; @@ -1785,8 +1822,10 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, switch (mld->mld_type) { case ICMPV6_MGM_REPORT: + src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid); + err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid, + src); break; case ICMPV6_MLD2_REPORT: err = br_ip6_multicast_mld2_report(br, port, skb_trimmed, vid); @@ -1795,7 +1834,8 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, err = br_ip6_multicast_query(br, port, skb_trimmed, vid); break; case ICMPV6_MGM_REDUCTION: - br_ip6_multicast_leave_group(br, port, &mld->mld_mca, vid); + src = eth_hdr(skb)->h_source; + br_ip6_multicast_leave_group(br, port, &mld->mld_mca, vid, src); break; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 71c7453268c1..6c087cd049b9 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -123,6 +123,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + + nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ @@ -173,6 +174,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, !!(p->flags & BR_ROOT_BLOCK)) || nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || + nla_put_u8(skb, IFLA_BRPORT_MCAST_TO_UCAST, + !!(p->flags & BR_MULTICAST_TO_UNICAST)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) || nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || @@ -586,6 +589,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, + [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ @@ -636,6 +640,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); + br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 8ce621e8345c..0b82a227fc34 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -177,6 +177,7 @@ struct net_bridge_port_group { struct timer_list timer; struct br_ip addr; unsigned char flags; + unsigned char eth_addr[ETH_ALEN]; }; struct net_bridge_mdb_entry @@ -599,7 +600,7 @@ void br_multicast_free_pg(struct rcu_head *head); struct net_bridge_port_group * br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, struct net_bridge_port_group __rcu *next, - unsigned char flags); + unsigned char flags, const unsigned char *src); void br_mdb_init(void); void br_mdb_uninit(void); void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 8bd569695e76..05e8946ccc03 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -188,6 +188,7 @@ static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router, store_multicast_router); BRPORT_ATTR_FLAG(multicast_fast_leave, BR_MULTICAST_FAST_LEAVE); +BRPORT_ATTR_FLAG(multicast_to_unicast, BR_MULTICAST_TO_UNICAST); #endif static const struct brport_attribute *brport_attrs[] = { @@ -214,6 +215,7 @@ static const struct brport_attribute *brport_attrs[] = { #ifdef CONFIG_BRIDGE_IGMP_SNOOPING &brport_attr_multicast_router, &brport_attr_multicast_fast_leave, + &brport_attr_multicast_to_unicast, #endif &brport_attr_proxyarp, &brport_attr_proxyarp_wifi, -- cgit v1.3-14-g43fede From 6ae0a6286171154661b74f7f550f9441c6008424 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Mon, 23 Jan 2017 11:07:08 +0100 Subject: net: Introduce psample, a new genetlink channel for packet sampling Add a general way for kernel modules to sample packets, without being tied to any specific subsystem. This netlink channel can be used by tc, iptables, etc. and allow to standardize packet sampling in the kernel. For every sampled packet, the psample module adds the following metadata fields: PSAMPLE_ATTR_IIFINDEX - the packets input ifindex, if applicable PSAMPLE_ATTR_OIFINDEX - the packet output ifindex, if applicable PSAMPLE_ATTR_ORIGSIZE - the packet's original size, in case it has been truncated during sampling PSAMPLE_ATTR_SAMPLE_GROUP - the packet's sample group, which is set by the user who initiated the sampling. This field allows the user to differentiate between several samplers working simultaneously and filter packets relevant to him PSAMPLE_ATTR_GROUP_SEQ - sequence counter of last sent packet. The sequence is kept for each group PSAMPLE_ATTR_SAMPLE_RATE - the sampling rate used for sampling the packets PSAMPLE_ATTR_DATA - the actual packet bits The sampled packets are sent to the PSAMPLE_NL_MCGRP_SAMPLE multicast group. In addition, add the GET_GROUPS netlink command which allows the user to see the current sample groups, their refcount and sequence number. This command currently supports only netlink dump mode. Signed-off-by: Yotam Gigi Signed-off-by: Jiri Pirko Reviewed-by: Jamal Hadi Salim Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- MAINTAINERS | 7 + include/net/psample.h | 36 ++++++ include/uapi/linux/Kbuild | 1 + include/uapi/linux/psample.h | 35 +++++ net/Kconfig | 1 + net/Makefile | 1 + net/psample/Kconfig | 15 +++ net/psample/Makefile | 5 + net/psample/psample.c | 301 +++++++++++++++++++++++++++++++++++++++++++ 9 files changed, 402 insertions(+) create mode 100644 include/net/psample.h create mode 100644 include/uapi/linux/psample.h create mode 100644 net/psample/Kconfig create mode 100644 net/psample/Makefile create mode 100644 net/psample/psample.c (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 3c84a8fecc09..d76fccd09266 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9957,6 +9957,13 @@ L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/block/ps3vram.c +PSAMPLE PACKET SAMPLING SUPPORT: +M: Yotam Gigi +S: Maintained +F: net/psample +F: include/net/psample.h +F: include/uapi/linux/psample.h + PSTORE FILESYSTEM M: Anton Vorontsov M: Colin Cross diff --git a/include/net/psample.h b/include/net/psample.h new file mode 100644 index 000000000000..8888b0e1a82e --- /dev/null +++ b/include/net/psample.h @@ -0,0 +1,36 @@ +#ifndef __NET_PSAMPLE_H +#define __NET_PSAMPLE_H + +#include +#include +#include + +struct psample_group { + struct list_head list; + struct net *net; + u32 group_num; + u32 refcount; + u32 seq; +}; + +struct psample_group *psample_group_get(struct net *net, u32 group_num); +void psample_group_put(struct psample_group *group); + +#if IS_ENABLED(CONFIG_PSAMPLE) + +void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, + u32 trunc_size, int in_ifindex, int out_ifindex, + u32 sample_rate); + +#else + +static inline void psample_sample_packet(struct psample_group *group, + struct sk_buff *skb, u32 trunc_size, + int in_ifindex, int out_ifindex, + u32 sample_rate) +{ +} + +#endif + +#endif /* __NET_PSAMPLE_H */ diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index e600b50be77e..80ad741a42fa 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -305,6 +305,7 @@ header-y += netrom.h header-y += net_namespace.h header-y += net_tstamp.h header-y += nfc.h +header-y += psample.h header-y += nfs2.h header-y += nfs3.h header-y += nfs4.h diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h new file mode 100644 index 000000000000..ed48996ec0e8 --- /dev/null +++ b/include/uapi/linux/psample.h @@ -0,0 +1,35 @@ +#ifndef __UAPI_PSAMPLE_H +#define __UAPI_PSAMPLE_H + +enum { + /* sampled packet metadata */ + PSAMPLE_ATTR_IIFINDEX, + PSAMPLE_ATTR_OIFINDEX, + PSAMPLE_ATTR_ORIGSIZE, + PSAMPLE_ATTR_SAMPLE_GROUP, + PSAMPLE_ATTR_GROUP_SEQ, + PSAMPLE_ATTR_SAMPLE_RATE, + PSAMPLE_ATTR_DATA, + + /* commands attributes */ + PSAMPLE_ATTR_GROUP_REFCOUNT, + + __PSAMPLE_ATTR_MAX +}; + +enum psample_command { + PSAMPLE_CMD_SAMPLE, + PSAMPLE_CMD_GET_GROUP, + PSAMPLE_CMD_NEW_GROUP, + PSAMPLE_CMD_DEL_GROUP, +}; + +/* Can be overridden at runtime by module option */ +#define PSAMPLE_ATTR_MAX (__PSAMPLE_ATTR_MAX - 1) + +#define PSAMPLE_NL_MCGRP_CONFIG_NAME "config" +#define PSAMPLE_NL_MCGRP_SAMPLE_NAME "packets" +#define PSAMPLE_GENL_NAME "psample" +#define PSAMPLE_GENL_VERSION 1 + +#endif diff --git a/net/Kconfig b/net/Kconfig index 92ae1500d9e1..ce4aee69fc0d 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -390,6 +390,7 @@ source "net/9p/Kconfig" source "net/caif/Kconfig" source "net/ceph/Kconfig" source "net/nfc/Kconfig" +source "net/psample/Kconfig" config LWTUNNEL bool "Network light weight tunnels" diff --git a/net/Makefile b/net/Makefile index 5d6e0e5ff7f8..7d41de48310e 100644 --- a/net/Makefile +++ b/net/Makefile @@ -70,6 +70,7 @@ obj-$(CONFIG_DNS_RESOLVER) += dns_resolver/ obj-$(CONFIG_CEPH_LIB) += ceph/ obj-$(CONFIG_BATMAN_ADV) += batman-adv/ obj-$(CONFIG_NFC) += nfc/ +obj-$(CONFIG_PSAMPLE) += psample/ obj-$(CONFIG_OPENVSWITCH) += openvswitch/ obj-$(CONFIG_VSOCKETS) += vmw_vsock/ obj-$(CONFIG_MPLS) += mpls/ diff --git a/net/psample/Kconfig b/net/psample/Kconfig new file mode 100644 index 000000000000..d850246a6059 --- /dev/null +++ b/net/psample/Kconfig @@ -0,0 +1,15 @@ +# +# psample packet sampling configuration +# + +menuconfig PSAMPLE + depends on NET + tristate "Packet-sampling netlink channel" + default n + help + Say Y here to add support for packet-sampling netlink channel + This netlink channel allows transferring packets alongside some + metadata to userspace. + + To compile this support as a module, choose M here: the module will + be called psample. diff --git a/net/psample/Makefile b/net/psample/Makefile new file mode 100644 index 000000000000..609b0a79c9f3 --- /dev/null +++ b/net/psample/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the psample netlink channel +# + +obj-$(CONFIG_PSAMPLE) += psample.o diff --git a/net/psample/psample.c b/net/psample/psample.c new file mode 100644 index 000000000000..8aa58a918783 --- /dev/null +++ b/net/psample/psample.c @@ -0,0 +1,301 @@ +/* + * net/psample/psample.c - Netlink channel for packet sampling + * Copyright (c) 2017 Yotam Gigi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define PSAMPLE_MAX_PACKET_SIZE 0xffff + +static LIST_HEAD(psample_groups_list); +static DEFINE_SPINLOCK(psample_groups_lock); + +/* multicast groups */ +enum psample_nl_multicast_groups { + PSAMPLE_NL_MCGRP_CONFIG, + PSAMPLE_NL_MCGRP_SAMPLE, +}; + +static const struct genl_multicast_group psample_nl_mcgrps[] = { + [PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME }, + [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME }, +}; + +static struct genl_family psample_nl_family __ro_after_init; + +static int psample_group_nl_fill(struct sk_buff *msg, + struct psample_group *group, + enum psample_command cmd, u32 portid, u32 seq, + int flags) +{ + void *hdr; + int ret; + + hdr = genlmsg_put(msg, portid, seq, &psample_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + ret = nla_put_u32(msg, PSAMPLE_ATTR_SAMPLE_GROUP, group->group_num); + if (ret < 0) + goto error; + + ret = nla_put_u32(msg, PSAMPLE_ATTR_GROUP_REFCOUNT, group->refcount); + if (ret < 0) + goto error; + + ret = nla_put_u32(msg, PSAMPLE_ATTR_GROUP_SEQ, group->seq); + if (ret < 0) + goto error; + + genlmsg_end(msg, hdr); + return 0; + +error: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int psample_nl_cmd_get_group_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct psample_group *group; + int start = cb->args[0]; + int idx = 0; + int err; + + spin_lock(&psample_groups_lock); + list_for_each_entry(group, &psample_groups_list, list) { + if (!net_eq(group->net, sock_net(msg->sk))) + continue; + if (idx < start) { + idx++; + continue; + } + err = psample_group_nl_fill(msg, group, PSAMPLE_CMD_NEW_GROUP, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + if (err) + break; + idx++; + } + + spin_unlock(&psample_groups_lock); + cb->args[0] = idx; + return msg->len; +} + +static const struct genl_ops psample_nl_ops[] = { + { + .cmd = PSAMPLE_CMD_GET_GROUP, + .dumpit = psample_nl_cmd_get_group_dumpit, + /* can be retrieved by unprivileged users */ + } +}; + +static struct genl_family psample_nl_family __ro_after_init = { + .name = PSAMPLE_GENL_NAME, + .version = PSAMPLE_GENL_VERSION, + .maxattr = PSAMPLE_ATTR_MAX, + .netnsok = true, + .module = THIS_MODULE, + .mcgrps = psample_nl_mcgrps, + .ops = psample_nl_ops, + .n_ops = ARRAY_SIZE(psample_nl_ops), + .n_mcgrps = ARRAY_SIZE(psample_nl_mcgrps), +}; + +static void psample_group_notify(struct psample_group *group, + enum psample_command cmd) +{ + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!msg) + return; + + err = psample_group_nl_fill(msg, group, cmd, 0, 0, NLM_F_MULTI); + if (!err) + genlmsg_multicast_netns(&psample_nl_family, group->net, msg, 0, + PSAMPLE_NL_MCGRP_CONFIG, GFP_ATOMIC); + else + nlmsg_free(msg); +} + +static struct psample_group *psample_group_create(struct net *net, + u32 group_num) +{ + struct psample_group *group; + + group = kzalloc(sizeof(*group), GFP_ATOMIC); + if (!group) + return NULL; + + group->net = net; + group->group_num = group_num; + list_add_tail(&group->list, &psample_groups_list); + + psample_group_notify(group, PSAMPLE_CMD_NEW_GROUP); + return group; +} + +static void psample_group_destroy(struct psample_group *group) +{ + psample_group_notify(group, PSAMPLE_CMD_DEL_GROUP); + list_del(&group->list); + kfree(group); +} + +static struct psample_group * +psample_group_lookup(struct net *net, u32 group_num) +{ + struct psample_group *group; + + list_for_each_entry(group, &psample_groups_list, list) + if ((group->group_num == group_num) && (group->net == net)) + return group; + return NULL; +} + +struct psample_group *psample_group_get(struct net *net, u32 group_num) +{ + struct psample_group *group; + + spin_lock(&psample_groups_lock); + + group = psample_group_lookup(net, group_num); + if (!group) { + group = psample_group_create(net, group_num); + if (!group) + goto out; + } + group->refcount++; + +out: + spin_unlock(&psample_groups_lock); + return group; +} +EXPORT_SYMBOL_GPL(psample_group_get); + +void psample_group_put(struct psample_group *group) +{ + spin_lock(&psample_groups_lock); + + if (--group->refcount == 0) + psample_group_destroy(group); + + spin_unlock(&psample_groups_lock); +} +EXPORT_SYMBOL_GPL(psample_group_put); + +void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, + u32 trunc_size, int in_ifindex, int out_ifindex, + u32 sample_rate) +{ + struct sk_buff *nl_skb; + int data_len; + int meta_len; + void *data; + int ret; + + meta_len = (in_ifindex ? nla_total_size(sizeof(u16)) : 0) + + (out_ifindex ? nla_total_size(sizeof(u16)) : 0) + + nla_total_size(sizeof(u32)) + /* sample_rate */ + nla_total_size(sizeof(u32)) + /* orig_size */ + nla_total_size(sizeof(u32)) + /* group_num */ + nla_total_size(sizeof(u32)); /* seq */ + + data_len = min(skb->len, trunc_size); + if (meta_len + nla_total_size(data_len) > PSAMPLE_MAX_PACKET_SIZE) + data_len = PSAMPLE_MAX_PACKET_SIZE - meta_len - NLA_HDRLEN + - NLA_ALIGNTO; + + nl_skb = genlmsg_new(meta_len + data_len, GFP_ATOMIC); + if (unlikely(!nl_skb)) + return; + + data = genlmsg_put(nl_skb, 0, 0, &psample_nl_family, 0, + PSAMPLE_CMD_SAMPLE); + if (unlikely(!data)) + goto error; + + if (in_ifindex) { + ret = nla_put_u16(nl_skb, PSAMPLE_ATTR_IIFINDEX, in_ifindex); + if (unlikely(ret < 0)) + goto error; + } + + if (out_ifindex) { + ret = nla_put_u16(nl_skb, PSAMPLE_ATTR_OIFINDEX, out_ifindex); + if (unlikely(ret < 0)) + goto error; + } + + ret = nla_put_u32(nl_skb, PSAMPLE_ATTR_SAMPLE_RATE, sample_rate); + if (unlikely(ret < 0)) + goto error; + + ret = nla_put_u32(nl_skb, PSAMPLE_ATTR_ORIGSIZE, skb->len); + if (unlikely(ret < 0)) + goto error; + + ret = nla_put_u32(nl_skb, PSAMPLE_ATTR_SAMPLE_GROUP, group->group_num); + if (unlikely(ret < 0)) + goto error; + + ret = nla_put_u32(nl_skb, PSAMPLE_ATTR_GROUP_SEQ, group->seq++); + if (unlikely(ret < 0)) + goto error; + + if (data_len) { + int nla_len = nla_total_size(data_len); + struct nlattr *nla; + + nla = (struct nlattr *)skb_put(nl_skb, nla_len); + nla->nla_type = PSAMPLE_ATTR_DATA; + nla->nla_len = nla_attr_size(data_len); + + if (skb_copy_bits(skb, 0, nla_data(nla), data_len)) + goto error; + } + + genlmsg_end(nl_skb, data); + genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, + PSAMPLE_NL_MCGRP_SAMPLE, GFP_ATOMIC); + + return; +error: + pr_err_ratelimited("Could not create psample log message\n"); + nlmsg_free(nl_skb); +} +EXPORT_SYMBOL_GPL(psample_sample_packet); + +static int __init psample_module_init(void) +{ + return genl_register_family(&psample_nl_family); +} + +static void __exit psample_module_exit(void) +{ + genl_unregister_family(&psample_nl_family); +} + +module_init(psample_module_init); +module_exit(psample_module_exit); + +MODULE_AUTHOR("Yotam Gigi "); +MODULE_DESCRIPTION("netlink channel for packet sampling"); +MODULE_LICENSE("GPL v2"); -- cgit v1.3-14-g43fede From 5c5670fae43027778e84b9d9ff3b9d91a10a8131 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Mon, 23 Jan 2017 11:07:09 +0100 Subject: net/sched: Introduce sample tc action This action allows the user to sample traffic matched by tc classifier. The sampling consists of choosing packets randomly and sampling them using the psample module. The user can configure the psample group number, the sampling rate and the packet's truncation (to save kernel-user traffic). Example: To sample ingress traffic from interface eth1, one may use the commands: tc qdisc add dev eth1 handle ffff: ingress tc filter add dev eth1 parent ffff: \ matchall action sample rate 12 group 4 Where the first command adds an ingress qdisc and the second starts sampling randomly with an average of one sampled packet per 12 packets on dev eth1 to psample group 4. Signed-off-by: Yotam Gigi Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/tc_act/tc_sample.h | 50 +++++++ include/uapi/linux/tc_act/Kbuild | 1 + include/uapi/linux/tc_act/tc_sample.h | 26 ++++ net/sched/Kconfig | 12 ++ net/sched/Makefile | 1 + net/sched/act_sample.c | 274 ++++++++++++++++++++++++++++++++++ 6 files changed, 364 insertions(+) create mode 100644 include/net/tc_act/tc_sample.h create mode 100644 include/uapi/linux/tc_act/tc_sample.h create mode 100644 net/sched/act_sample.c (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_sample.h b/include/net/tc_act/tc_sample.h new file mode 100644 index 000000000000..89e9305be880 --- /dev/null +++ b/include/net/tc_act/tc_sample.h @@ -0,0 +1,50 @@ +#ifndef __NET_TC_SAMPLE_H +#define __NET_TC_SAMPLE_H + +#include +#include +#include + +struct tcf_sample { + struct tc_action common; + u32 rate; + bool truncate; + u32 trunc_size; + struct psample_group __rcu *psample_group; + u32 psample_group_num; + struct list_head tcfm_list; + struct rcu_head rcu; +}; +#define to_sample(a) ((struct tcf_sample *)a) + +static inline bool is_tcf_sample(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + return a->ops && a->ops->type == TCA_ACT_SAMPLE; +#else + return false; +#endif +} + +static inline __u32 tcf_sample_rate(const struct tc_action *a) +{ + return to_sample(a)->rate; +} + +static inline bool tcf_sample_truncate(const struct tc_action *a) +{ + return to_sample(a)->truncate; +} + +static inline int tcf_sample_trunc_size(const struct tc_action *a) +{ + return to_sample(a)->trunc_size; +} + +static inline struct psample_group * +tcf_sample_psample_group(const struct tc_action *a) +{ + return rcu_dereference(to_sample(a)->psample_group); +} + +#endif /* __NET_TC_SAMPLE_H */ diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild index e3db7403296f..ba62ddf0e58a 100644 --- a/include/uapi/linux/tc_act/Kbuild +++ b/include/uapi/linux/tc_act/Kbuild @@ -4,6 +4,7 @@ header-y += tc_defact.h header-y += tc_gact.h header-y += tc_ipt.h header-y += tc_mirred.h +header-y += tc_sample.h header-y += tc_nat.h header-y += tc_pedit.h header-y += tc_skbedit.h diff --git a/include/uapi/linux/tc_act/tc_sample.h b/include/uapi/linux/tc_act/tc_sample.h new file mode 100644 index 000000000000..edc9058bb30d --- /dev/null +++ b/include/uapi/linux/tc_act/tc_sample.h @@ -0,0 +1,26 @@ +#ifndef __LINUX_TC_SAMPLE_H +#define __LINUX_TC_SAMPLE_H + +#include +#include +#include + +#define TCA_ACT_SAMPLE 26 + +struct tc_sample { + tc_gen; +}; + +enum { + TCA_SAMPLE_UNSPEC, + TCA_SAMPLE_TM, + TCA_SAMPLE_PARMS, + TCA_SAMPLE_RATE, + TCA_SAMPLE_TRUNC_SIZE, + TCA_SAMPLE_PSAMPLE_GROUP, + TCA_SAMPLE_PAD, + __TCA_SAMPLE_MAX +}; +#define TCA_SAMPLE_MAX (__TCA_SAMPLE_MAX - 1) + +#endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index a9aa38d43fa7..72cfa3a6bac0 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -650,6 +650,18 @@ config NET_ACT_MIRRED To compile this code as a module, choose M here: the module will be called act_mirred. +config NET_ACT_SAMPLE + tristate "Traffic Sampling" + depends on NET_CLS_ACT + select PSAMPLE + ---help--- + Say Y here to allow packet sampling tc action. The packet sample + action consists of statistically choosing packets and sampling + them using the psample module. + + To compile this code as a module, choose M here: the + module will be called act_sample. + config NET_ACT_IPT tristate "IPtables targets" depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES diff --git a/net/sched/Makefile b/net/sched/Makefile index 4bdda3634e0b..7b915d226de7 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -10,6 +10,7 @@ obj-$(CONFIG_NET_CLS_ACT) += act_api.o obj-$(CONFIG_NET_ACT_POLICE) += act_police.o obj-$(CONFIG_NET_ACT_GACT) += act_gact.o obj-$(CONFIG_NET_ACT_MIRRED) += act_mirred.o +obj-$(CONFIG_NET_ACT_SAMPLE) += act_sample.o obj-$(CONFIG_NET_ACT_IPT) += act_ipt.o obj-$(CONFIG_NET_ACT_NAT) += act_nat.o obj-$(CONFIG_NET_ACT_PEDIT) += act_pedit.o diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c new file mode 100644 index 000000000000..39229756de07 --- /dev/null +++ b/net/sched/act_sample.c @@ -0,0 +1,274 @@ +/* + * net/sched/act_sample.c - Packet sampling tc action + * Copyright (c) 2017 Yotam Gigi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define SAMPLE_TAB_MASK 7 +static unsigned int sample_net_id; +static struct tc_action_ops act_sample_ops; + +static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { + [TCA_SAMPLE_PARMS] = { .len = sizeof(struct tc_sample) }, + [TCA_SAMPLE_RATE] = { .type = NLA_U32 }, + [TCA_SAMPLE_TRUNC_SIZE] = { .type = NLA_U32 }, + [TCA_SAMPLE_PSAMPLE_GROUP] = { .type = NLA_U32 }, +}; + +static int tcf_sample_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, int ovr, + int bind) +{ + struct tc_action_net *tn = net_generic(net, sample_net_id); + struct nlattr *tb[TCA_SAMPLE_MAX + 1]; + struct psample_group *psample_group; + struct tc_sample *parm; + struct tcf_sample *s; + bool exists = false; + int ret; + + if (!nla) + return -EINVAL; + ret = nla_parse_nested(tb, TCA_SAMPLE_MAX, nla, sample_policy); + if (ret < 0) + return ret; + if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] || + !tb[TCA_SAMPLE_PSAMPLE_GROUP]) + return -EINVAL; + + parm = nla_data(tb[TCA_SAMPLE_PARMS]); + + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; + + if (!exists) { + ret = tcf_hash_create(tn, parm->index, est, a, + &act_sample_ops, bind, false); + if (ret) + return ret; + ret = ACT_P_CREATED; + } else { + tcf_hash_release(*a, bind); + if (!ovr) + return -EEXIST; + } + s = to_sample(*a); + + ASSERT_RTNL(); + s->tcf_action = parm->action; + s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); + psample_group = psample_group_get(net, s->psample_group_num); + if (!psample_group) + return -ENOMEM; + RCU_INIT_POINTER(s->psample_group, psample_group); + + if (tb[TCA_SAMPLE_TRUNC_SIZE]) { + s->truncate = true; + s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]); + } + + if (ret == ACT_P_CREATED) + tcf_hash_insert(tn, *a); + return ret; +} + +static void tcf_sample_cleanup_rcu(struct rcu_head *rcu) +{ + struct tcf_sample *s = container_of(rcu, struct tcf_sample, rcu); + struct psample_group *psample_group; + + psample_group = rcu_dereference_protected(s->psample_group, 1); + RCU_INIT_POINTER(s->psample_group, NULL); + psample_group_put(psample_group); +} + +static void tcf_sample_cleanup(struct tc_action *a, int bind) +{ + struct tcf_sample *s = to_sample(a); + + call_rcu(&s->rcu, tcf_sample_cleanup_rcu); +} + +static bool tcf_sample_dev_ok_push(struct net_device *dev) +{ + switch (dev->type) { + case ARPHRD_TUNNEL: + case ARPHRD_TUNNEL6: + case ARPHRD_SIT: + case ARPHRD_IPGRE: + case ARPHRD_VOID: + case ARPHRD_NONE: + return false; + default: + return true; + } +} + +static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_sample *s = to_sample(a); + struct psample_group *psample_group; + int retval; + int size; + int iif; + int oif; + + tcf_lastuse_update(&s->tcf_tm); + bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb); + retval = READ_ONCE(s->tcf_action); + + rcu_read_lock(); + psample_group = rcu_dereference(s->psample_group); + + /* randomly sample packets according to rate */ + if (psample_group && (prandom_u32() % s->rate == 0)) { + if (!skb_at_tc_ingress(skb)) { + iif = skb->skb_iif; + oif = skb->dev->ifindex; + } else { + iif = skb->dev->ifindex; + oif = 0; + } + + /* on ingress, the mac header gets popped, so push it back */ + if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) + skb_push(skb, skb->mac_len); + + size = s->truncate ? s->trunc_size : skb->len; + psample_sample_packet(psample_group, skb, size, iif, oif, + s->rate); + + if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) + skb_pull(skb, skb->mac_len); + } + + rcu_read_unlock(); + return retval; +} + +static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tcf_sample *s = to_sample(a); + struct tc_sample opt = { + .index = s->tcf_index, + .action = s->tcf_action, + .refcnt = s->tcf_refcnt - ref, + .bindcnt = s->tcf_bindcnt - bind, + }; + struct tcf_t t; + + if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + tcf_tm_dump(&t, &s->tcf_tm); + if (nla_put_64bit(skb, TCA_SAMPLE_TM, sizeof(t), &t, TCA_SAMPLE_PAD)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_SAMPLE_RATE, s->rate)) + goto nla_put_failure; + + if (s->truncate) + if (nla_put_u32(skb, TCA_SAMPLE_TRUNC_SIZE, s->trunc_size)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num)) + goto nla_put_failure; + return skb->len; + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static int tcf_sample_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + const struct tc_action_ops *ops) +{ + struct tc_action_net *tn = net_generic(net, sample_net_id); + + return tcf_generic_walker(tn, skb, cb, type, ops); +} + +static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, sample_net_id); + + return tcf_hash_search(tn, a, index); +} + +static struct tc_action_ops act_sample_ops = { + .kind = "sample", + .type = TCA_ACT_SAMPLE, + .owner = THIS_MODULE, + .act = tcf_sample_act, + .dump = tcf_sample_dump, + .init = tcf_sample_init, + .cleanup = tcf_sample_cleanup, + .walk = tcf_sample_walker, + .lookup = tcf_sample_search, + .size = sizeof(struct tcf_sample), +}; + +static __net_init int sample_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, sample_net_id); + + return tc_action_net_init(tn, &act_sample_ops, SAMPLE_TAB_MASK); +} + +static void __net_exit sample_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, sample_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations sample_net_ops = { + .init = sample_init_net, + .exit = sample_exit_net, + .id = &sample_net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init sample_init_module(void) +{ + return tcf_register_action(&act_sample_ops, &sample_net_ops); +} + +static void __exit sample_cleanup_module(void) +{ + tcf_unregister_action(&act_sample_ops, &sample_net_ops); +} + +module_init(sample_init_module); +module_exit(sample_cleanup_module); + +MODULE_AUTHOR("Yotam Gigi "); +MODULE_DESCRIPTION("Packet sampling action"); +MODULE_LICENSE("GPL v2"); -- cgit v1.3-14-g43fede From d1b662adcdb87944b7f6f7bd2f95cbb1404dbf18 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 24 Jan 2017 01:06:28 +0100 Subject: bpf: allow option for setting bpf_l4_csum_replace from scratch When programs need to calculate the csum from scratch for small UDP packets and use bpf_l4_csum_replace() to feed the result from helpers like bpf_csum_diff(), then we need a flag besides BPF_F_MARK_MANGLED_0 that would ignore the case of current csum being 0, and which would still allow for the helper to set the csum and transform when needed to CSUM_MANGLED_0. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 7 ++++--- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bd3068485410..e07fd5a324e6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -522,6 +522,7 @@ enum bpf_func_id { /* BPF_FUNC_l4_csum_replace flags. */ #define BPF_F_PSEUDO_HDR (1ULL << 4) #define BPF_F_MARK_MANGLED_0 (1ULL << 5) +#define BPF_F_MARK_ENFORCE (1ULL << 6) /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ #define BPF_F_INGRESS (1ULL << 0) diff --git a/net/core/filter.c b/net/core/filter.c index e2263da505be..1e00737e3bc3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1522,10 +1522,11 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, { bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; + bool do_mforce = flags & BPF_F_MARK_ENFORCE; __sum16 *ptr; - if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | - BPF_F_HDR_FIELD_MASK))) + if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE | + BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; @@ -1533,7 +1534,7 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, return -EFAULT; ptr = (__sum16 *)(skb->data + offset); - if (is_mmzero && !*ptr) + if (is_mmzero && !do_mforce && !*ptr) return 0; switch (flags & BPF_F_HDR_FIELD_MASK) { -- cgit v1.3-14-g43fede From 1045ba77a5962a22bce7777678ef46714107ea63 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 24 Jan 2017 07:02:41 -0500 Subject: net sched actions: Add support for user cookies Introduce optional 128-bit action cookie. Like all other cookie schemes in the networking world (eg in protocols like http or existing kernel fib protocol field, etc) the idea is to save user state that when retrieved serves as a correlator. The kernel _should not_ intepret it. The user can store whatever they wish in the 128 bits. Sample exercise(showing variable length use of cookie) .. create an accept action with cookie a1b2c3d4 sudo $TC actions add action ok index 1 cookie a1b2c3d4 .. dump all gact actions.. sudo $TC -s actions ls action gact action order 0: gact action pass random type none pass val 0 index 1 ref 1 bind 0 installed 5 sec used 5 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 cookie a1b2c3d4 .. bind the accept action to a filter.. sudo $TC filter add dev lo parent ffff: protocol ip prio 1 \ u32 match ip dst 127.0.0.1/32 flowid 1:1 action gact index 1 ... send some traffic.. $ ping 127.0.0.1 -c 3 PING 127.0.0.1 (127.0.0.1) 56(84) bytes of data. 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.020 ms 64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.027 ms 64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=0.038 ms Signed-off-by: David S. Miller --- include/net/act_api.h | 1 + include/net/pkt_cls.h | 8 ++++++++ include/uapi/linux/pkt_cls.h | 3 +++ net/sched/act_api.c | 45 ++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 57 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/act_api.h b/include/net/act_api.h index 1d716449209e..cfa2ae33da9a 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -41,6 +41,7 @@ struct tc_action { struct rcu_head tcfa_rcu; struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; + struct tc_cookie *act_cookie; }; #define tcf_head common.tcfa_head #define tcf_index common.tcfa_index diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index f0a051480c6c..b43077e47d35 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -515,4 +515,12 @@ struct tc_cls_bpf_offload { u32 gen_flags; }; + +/* This structure holds cookie structure that is passed from user + * to the kernel for actions and classifiers + */ +struct tc_cookie { + u8 *data; + u32 len; +}; #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index fd373ebd5a44..345551e71410 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -4,6 +4,8 @@ #include #include +#define TC_COOKIE_MAX_SIZE 16 + /* Action attributes */ enum { TCA_ACT_UNSPEC, @@ -12,6 +14,7 @@ enum { TCA_ACT_INDEX, TCA_ACT_STATS, TCA_ACT_PAD, + TCA_ACT_COOKIE, __TCA_ACT_MAX }; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index cd08df91351d..3c5e29ba6594 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -33,6 +34,12 @@ static void free_tcf(struct rcu_head *head) free_percpu(p->cpu_bstats); free_percpu(p->cpu_qstats); + + if (p->act_cookie) { + kfree(p->act_cookie->data); + kfree(p->act_cookie); + } + kfree(p); } @@ -475,6 +482,12 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) goto nla_put_failure; if (tcf_action_copy_stats(skb, a, 0)) goto nla_put_failure; + if (a->act_cookie) { + if (nla_put(skb, TCA_ACT_COOKIE, a->act_cookie->len, + a->act_cookie->data)) + goto nla_put_failure; + } + nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -516,6 +529,22 @@ errout: return err; } +int nla_memdup_cookie(struct tc_action *a, struct nlattr **tb) +{ + a->act_cookie = kzalloc(sizeof(*a->act_cookie), GFP_KERNEL); + if (!a->act_cookie) + return -ENOMEM; + + a->act_cookie->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL); + if (!a->act_cookie->data) { + kfree(a->act_cookie); + return -ENOMEM; + } + a->act_cookie->len = nla_len(tb[TCA_ACT_COOKIE]); + + return 0; +} + struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind) @@ -575,6 +604,22 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, if (err < 0) goto err_mod; + if (tb[TCA_ACT_COOKIE]) { + int cklen = nla_len(tb[TCA_ACT_COOKIE]); + + if (cklen > TC_COOKIE_MAX_SIZE) { + err = -EINVAL; + tcf_hash_release(a, bind); + goto err_mod; + } + + err = nla_memdup_cookie(a, tb); + if (err < 0) { + tcf_hash_release(a, bind); + goto err_mod; + } + } + /* module count goes up only when brand new policy is created * if it exists and is only bound to in a_o->init() then * ACT_P_CREATED is not returned (a zero is). -- cgit v1.3-14-g43fede From 19f6d3f3c8422d65b5e3d2162e30ef07c6e21ea2 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Mon, 23 Jan 2017 10:59:22 -0800 Subject: net/tcp-fastopen: Add new API support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a new socket option, TCP_FASTOPEN_CONNECT, as an alternative way to perform Fast Open on the active side (client). Prior to this patch, a client needs to replace the connect() call with sendto(MSG_FASTOPEN). This can be cumbersome for applications who want to use Fast Open: these socket operations are often done in lower layer libraries used by many other applications. Changing these libraries and/or the socket call sequences are not trivial. A more convenient approach is to perform Fast Open by simply enabling a socket option when the socket is created w/o changing other socket calls sequence: s = socket() create a new socket setsockopt(s, IPPROTO_TCP, TCP_FASTOPEN_CONNECT …); newly introduced sockopt If set, new functionality described below will be used. Return ENOTSUPP if TFO is not supported or not enabled in the kernel. connect() With cookie present, return 0 immediately. With no cookie, initiate 3WHS with TFO cookie-request option and return -1 with errno = EINPROGRESS. write()/sendmsg() With cookie present, send out SYN with data and return the number of bytes buffered. With no cookie, and 3WHS not yet completed, return -1 with errno = EINPROGRESS. No MSG_FASTOPEN flag is needed. read() Return -1 with errno = EWOULDBLOCK/EAGAIN if connect() is called but write() is not called yet. Return -1 with errno = EWOULDBLOCK/EAGAIN if connection is established but no msg is received yet. Return number of bytes read if socket is established and there is msg received. The new API simplifies life for applications that always perform a write() immediately after a successful connect(). Such applications can now take advantage of Fast Open by merely making one new setsockopt() call at the time of creating the socket. Nothing else about the application's socket call sequence needs to change. Signed-off-by: Wei Wang Acked-by: Eric Dumazet Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- include/net/inet_sock.h | 6 +++++- include/net/tcp.h | 1 + include/uapi/linux/tcp.h | 1 + net/ipv4/af_inet.c | 31 ++++++++++++++++++++++++------- net/ipv4/tcp.c | 35 ++++++++++++++++++++++++++++++++++- net/ipv4/tcp_fastopen.c | 33 +++++++++++++++++++++++++++++++++ net/ipv4/tcp_ipv4.c | 7 ++++++- net/ipv6/tcp_ipv6.c | 5 +++++ 9 files changed, 111 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 5371b3d70cfe..f88f4649ba6f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -222,7 +222,8 @@ struct tcp_sock { u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ - unused:5; + fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ + unused:4; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ unused1 : 1, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c9cff977a7fb..aa95053dfc78 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -206,7 +206,11 @@ struct inet_sock { transparent:1, mc_all:1, nodefrag:1; - __u8 bind_address_no_port:1; + __u8 bind_address_no_port:1, + defer_connect:1; /* Indicates that fastopen_connect is set + * and cookie exists so we defer connect + * until first data frame is written + */ __u8 rcv_tos; __u8 convert_csum; int uc_index; diff --git a/include/net/tcp.h b/include/net/tcp.h index de67541d7adf..6ec4ea652f3f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1495,6 +1495,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, void tcp_fastopen_init_key_once(bool publish); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); +bool tcp_fastopen_defer_connect(struct sock *sk, int *err); #define TCP_FASTOPEN_KEY_LENGTH 16 /* Fastopen key context */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index c53de2691cec..6ff35eb48d10 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -116,6 +116,7 @@ enum { #define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */ #define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */ #define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */ +#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */ struct tcp_repair_opt { __u32 opt_code; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 28fe8da4e1ac..92e7f3e957fa 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -576,13 +576,24 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int err; long timeo; - if (addr_len < sizeof(uaddr->sa_family)) - return -EINVAL; + /* + * uaddr can be NULL and addr_len can be 0 if: + * sk is a TCP fastopen active socket and + * TCP_FASTOPEN_CONNECT sockopt is set and + * we already have a valid cookie for this socket. + * In this case, user can call write() after connect(). + * write() will invoke tcp_sendmsg_fastopen() which calls + * __inet_stream_connect(). + */ + if (uaddr) { + if (addr_len < sizeof(uaddr->sa_family)) + return -EINVAL; - if (uaddr->sa_family == AF_UNSPEC) { - err = sk->sk_prot->disconnect(sk, flags); - sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; - goto out; + if (uaddr->sa_family == AF_UNSPEC) { + err = sk->sk_prot->disconnect(sk, flags); + sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; + goto out; + } } switch (sock->state) { @@ -593,7 +604,10 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = -EISCONN; goto out; case SS_CONNECTING: - err = -EALREADY; + if (inet_sk(sk)->defer_connect) + err = -EINPROGRESS; + else + err = -EALREADY; /* Fall out of switch with err, set for this state */ break; case SS_UNCONNECTED: @@ -607,6 +621,9 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTING; + if (!err && inet_sk(sk)->defer_connect) + goto out; + /* Just entered SS_CONNECTING state; the only * difference is that return value in non-blocking * case is EINPROGRESS, rather than EALREADY. diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c43eb1a831d7..d9735b76d073 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -533,6 +533,12 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tp->urg_data & TCP_URG_VALID) mask |= POLLPRI; + } else if (sk->sk_state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { + /* Active TCP fastopen socket with defer_connect + * Return POLLOUT so application can call write() + * in order for kernel to generate SYN+data + */ + mask |= POLLOUT | POLLWRNORM; } /* This barrier is coupled with smp_wmb() in tcp_reset() */ smp_rmb(); @@ -1071,6 +1077,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); + struct inet_sock *inet = inet_sk(sk); int err, flags; if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE)) @@ -1085,9 +1092,19 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, tp->fastopen_req->data = msg; tp->fastopen_req->size = size; + if (inet->defer_connect) { + err = tcp_connect(sk); + /* Same failure procedure as in tcp_v4/6_connect */ + if (err) { + tcp_set_state(sk, TCP_CLOSE); + inet->inet_dport = 0; + sk->sk_route_caps = 0; + } + } flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags); + inet->defer_connect = 0; *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); return err; @@ -1107,7 +1124,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) lock_sock(sk); flags = msg->msg_flags; - if (flags & MSG_FASTOPEN) { + if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; @@ -2656,6 +2673,18 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = -EINVAL; } break; + case TCP_FASTOPEN_CONNECT: + if (val > 1 || val < 0) { + err = -EINVAL; + } else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { + if (sk->sk_state == TCP_CLOSE) + tp->fastopen_connect = val; + else + err = -EINVAL; + } else { + err = -EOPNOTSUPP; + } + break; case TCP_TIMESTAMP: if (!tp->repair) err = -EPERM; @@ -3016,6 +3045,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = icsk->icsk_accept_queue.fastopenq.max_qlen; break; + case TCP_FASTOPEN_CONNECT: + val = tp->fastopen_connect; + break; + case TCP_TIMESTAMP: val = tcp_time_stamp + tp->tsoffset; break; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index f90e09e1ff4c..9674bec4a0f8 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -346,3 +346,36 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, } return cookie->len > 0; } + +/* This function checks if we want to defer sending SYN until the first + * write(). We defer under the following conditions: + * 1. fastopen_connect sockopt is set + * 2. we have a valid cookie + * Return value: return true if we want to defer until application writes data + * return false if we want to send out SYN immediately + */ +bool tcp_fastopen_defer_connect(struct sock *sk, int *err) +{ + struct tcp_fastopen_cookie cookie = { .len = 0 }; + struct tcp_sock *tp = tcp_sk(sk); + u16 mss; + + if (tp->fastopen_connect && !tp->fastopen_req) { + if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) { + inet_sk(sk)->defer_connect = 1; + return true; + } + + /* Alloc fastopen_req in order for FO option to be included + * in SYN + */ + tp->fastopen_req = kzalloc(sizeof(*tp->fastopen_req), + sk->sk_allocation); + if (tp->fastopen_req) + tp->fastopen_req->cookie = cookie; + else + *err = -ENOBUFS; + } + return false; +} +EXPORT_SYMBOL(tcp_fastopen_defer_connect); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a90b4540c11e..8c9e9aa17d66 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -232,6 +232,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); + rt = NULL; if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr, @@ -242,9 +243,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_id = tp->write_seq ^ jiffies; + if (tcp_fastopen_defer_connect(sk, &err)) + return err; + if (err) + goto failure; + err = tcp_connect(sk); - rt = NULL; if (err) goto failure; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0b7cd3d009b6..95c05e5293b1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -287,6 +287,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, inet->inet_dport, &tp->tsoffset); + if (tcp_fastopen_defer_connect(sk, &err)) + return err; + if (err) + goto late_failure; + err = tcp_connect(sk); if (err) goto late_failure; -- cgit v1.3-14-g43fede From e60bf3ea67673fc6dd2645946e6dcf135fd7e30c Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 11 Dec 2016 13:16:07 +0100 Subject: uapi: install batman_adv.h header 09748a22f4ab ("batman-adv: add generic netlink family for batman-adv") introduced the new batman_adv.h which describes the netlink attributes and commands of batman-adv. But the Kbuild entry to install the header was not added. All currently known tools ship their own copy of batman_adv.h but it should be installed anyway to later be able to migrate to the system batman_adv.h. Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index a8b93e685239..7fdceb2ac5b7 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -64,6 +64,7 @@ header-y += auto_fs.h header-y += auxvec.h header-y += ax25.h header-y += b1lli.h +header-y += batman_adv.h header-y += baycom.h header-y += bcm933xx_hcs.h header-y += bfs_fs.h -- cgit v1.3-14-g43fede From ac79cbb96b58614ce13c4fccc00a9b4d43c2f79b Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 1 Jan 2017 00:00:00 +0100 Subject: batman-adv: update copyright years for 2017 Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/batman_adv.h | 2 +- net/batman-adv/Makefile | 2 +- net/batman-adv/bat_algo.c | 2 +- net/batman-adv/bat_algo.h | 2 +- net/batman-adv/bat_iv_ogm.c | 2 +- net/batman-adv/bat_iv_ogm.h | 2 +- net/batman-adv/bat_v.c | 2 +- net/batman-adv/bat_v.h | 2 +- net/batman-adv/bat_v_elp.c | 2 +- net/batman-adv/bat_v_elp.h | 2 +- net/batman-adv/bat_v_ogm.c | 2 +- net/batman-adv/bat_v_ogm.h | 2 +- net/batman-adv/bitarray.c | 2 +- net/batman-adv/bitarray.h | 2 +- net/batman-adv/bridge_loop_avoidance.c | 2 +- net/batman-adv/bridge_loop_avoidance.h | 2 +- net/batman-adv/debugfs.c | 2 +- net/batman-adv/debugfs.h | 2 +- net/batman-adv/distributed-arp-table.c | 2 +- net/batman-adv/distributed-arp-table.h | 2 +- net/batman-adv/fragmentation.c | 2 +- net/batman-adv/fragmentation.h | 2 +- net/batman-adv/gateway_client.c | 2 +- net/batman-adv/gateway_client.h | 2 +- net/batman-adv/gateway_common.c | 2 +- net/batman-adv/gateway_common.h | 2 +- net/batman-adv/hard-interface.c | 2 +- net/batman-adv/hard-interface.h | 2 +- net/batman-adv/hash.c | 2 +- net/batman-adv/hash.h | 2 +- net/batman-adv/icmp_socket.c | 2 +- net/batman-adv/icmp_socket.h | 2 +- net/batman-adv/log.c | 2 +- net/batman-adv/log.h | 2 +- net/batman-adv/main.c | 2 +- net/batman-adv/main.h | 2 +- net/batman-adv/multicast.c | 2 +- net/batman-adv/multicast.h | 2 +- net/batman-adv/netlink.c | 2 +- net/batman-adv/netlink.h | 2 +- net/batman-adv/network-coding.c | 2 +- net/batman-adv/network-coding.h | 2 +- net/batman-adv/originator.c | 2 +- net/batman-adv/originator.h | 2 +- net/batman-adv/packet.h | 2 +- net/batman-adv/routing.c | 2 +- net/batman-adv/routing.h | 2 +- net/batman-adv/send.c | 2 +- net/batman-adv/send.h | 2 +- net/batman-adv/soft-interface.c | 2 +- net/batman-adv/soft-interface.h | 2 +- net/batman-adv/sysfs.c | 2 +- net/batman-adv/sysfs.h | 2 +- net/batman-adv/tp_meter.c | 2 +- net/batman-adv/tp_meter.h | 2 +- net/batman-adv/translation-table.c | 2 +- net/batman-adv/translation-table.h | 2 +- net/batman-adv/tvlv.c | 2 +- net/batman-adv/tvlv.h | 2 +- net/batman-adv/types.h | 2 +- 60 files changed, 60 insertions(+), 60 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 734fe83ab645..a83ddb7b63db 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2017 B.A.T.M.A.N. contributors: * * Matthias Schiffer * diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index f724d3c98a81..915987bc6d29 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # -# Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index 623d04302aa2..44fd073b7546 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 3b5b69cdd12b..29f6312f9bf1 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index f00f666e2ccd..7c3d994e90d8 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h index b9f3550faaf7..ae2ab526bdb1 100644 --- a/net/batman-adv/bat_iv_ogm.h +++ b/net/batman-adv/bat_iv_ogm.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 2ac612d7bab4..0acd081dd286 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h index 83b77639729e..dd7c4b647e6b 100644 --- a/net/batman-adv/bat_v.h +++ b/net/batman-adv/bat_v.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing * diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index f2fb2f05b6bf..b90c9903e246 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index be17c0b1369e..376ead280ab9 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 38b9aab83fc0..03a35c9f456d 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index 4c4d45caa422..2068770b542d 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 032271421a20..2b070c7e31da 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2017 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 0e6e9d09078c..cc262c9d97e0 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2017 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index e7f690b571ea..2d22fd5ba96c 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 2827cd3c13d2..e157986bd01c 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 77925504379d..5406148b9497 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index e49121ee55f6..9c5d4a65b98c 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 49576c5a3fe3..dab466f97ccf 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index 813ecea96cf9..ec364a3c1c66 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 9c561e683f4b..42bfbd801a1b 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: * * Martin Hundebøll * diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index b95f619606af..1a2d6c308745 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2013-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: * * Martin Hundebøll * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 52b8bd6ec431..de9955d5224d 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 859166d03561..3baa3d466e5e 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 21184810d89f..5db2e43e3775 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 8a5e1ddf1175..0a6a97d201f2 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 61a431a9772b..e348f76ea8c1 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index d6309a423629..9f9890ff7a22 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index a0a0fdb85805..b5f7e13918ac 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2017 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 557a7044cfbc..0c905e91c5e2 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2017 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index b310f381ae02..6308c9f0fd96 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index e44a7da51431..f3fec40aae86 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index c73c31769aba..4ef4bde2cc2d 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index 3284a7b0325d..7a2b9f4da078 100644 --- a/net/batman-adv/log.h +++ b/net/batman-adv/log.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index d46415edd3be..5000c540614d 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 8683542067ba..57a8103dbce7 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 090a69fc342e..952ba81a565b 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2014-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2017 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 2cddaf52a21d..2a78cddab0e9 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2014-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2017 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 062738163bdc..ab13b4d58733 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2017 B.A.T.M.A.N. contributors: * * Matthias Schiffer * diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index 52eb16281aba..f1cd8c5da966 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2017 B.A.T.M.A.N. contributors: * * Matthias Schiffer * diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index ab5a3bf0765f..e1f6fc72fe3e 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2017 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index d6d7fb4ec5d5..c66efb81d2f4 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2017 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 8f3b2969cc4e..8e2a4b205257 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index ebc56183f358..d94220a6d21a 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 7a36bcfa0ba0..8e8a5db197cb 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 6713bdf414cd..5f050fbdfff7 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 05c3ff42e181..5ede16c32f15 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 49021b7124f3..d7308263b8fa 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index a94e1e8639ca..f21166d10323 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 1f55b4b9181c..4a9923a95e8a 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index ec303ddbf647..639c3abb214a 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 17c844196eb2..0ae8b30e4eaa 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index c76021b4e198..e487412e256b 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 981e8c5b07e9..07f64b60b528 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2017 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli * diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index ba922c425e56..a8ada5c123bd 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2017 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 30ecbfb40adf..941afad92121 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 783fdba84db2..411d586191da 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index a783420356ae..1d9e267caec9 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index e4369b547b43..4d01400ada30 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index e913aee28c98..8f64a5c01345 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * -- cgit v1.3-14-g43fede From d35a00b8e33dab7385f724e713ae71c8be0a49f4 Mon Sep 17 00:00:00 2001 From: Felix Jia Date: Thu, 26 Jan 2017 16:59:17 +1300 Subject: net/ipv6: allow sysctl to change link-local address generation mode The address generation mode for IPv6 link-local can only be configured by netlink messages. This patch adds the ability to change the address generation mode via sysctl. v1 -> v2 Removed the rtnl lock and switch to use RCU lock to iterate through the netdev list. v2 -> v3 Removed the addrgenmode variable from the idev structure and use the systcl storage for the flag. Simplifed the logic for sysctl handling by removing the supported for all operation. Added support for more types of tunnel interfaces for link-local address generation. Based the patches from net-next. v3 -> v4 Removed unnecessary whitespace changes. Signed-off-by: Felix Jia Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/net/if_inet6.h | 1 - include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 104 +++++++++++++++++++++++++++++++++++++--------- 4 files changed, 86 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 671d014e6429..71be5b330d21 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -69,6 +69,7 @@ struct ipv6_devconf { __s32 seg6_require_hmac; #endif __u32 enhanced_dad; + __u32 addr_gen_mode; struct ctl_table_header *sysctl_header; }; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 0fa4c324b713..f656f9051aca 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -205,7 +205,6 @@ struct inet6_dev { __s32 rs_interval; /* in jiffies */ __u8 rs_probes; - __u8 addr_gen_mode; unsigned long tstamp; /* ipv6InterfaceTable update timestamp */ struct rcu_head rcu; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index eaf65dc82e22..8ef9e75e004e 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -182,6 +182,7 @@ enum { DEVCONF_SEG6_ENABLED, DEVCONF_SEG6_REQUIRE_HMAC, DEVCONF_ENHANCED_DAD, + DEVCONF_ADDR_GEN_MODE, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ac9bd5620f81..e35259dd17ba 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -243,6 +243,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .seg6_require_hmac = 0, #endif .enhanced_dad = 1, + .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -294,6 +295,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .seg6_require_hmac = 0, #endif .enhanced_dad = 1, + .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, }; /* Check if a valid qdisc is available */ @@ -386,9 +388,9 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); if (ndev->cnf.stable_secret.initialized) - ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; else - ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64; + ndev->cnf.addr_gen_mode = ipv6_devconf_dflt.addr_gen_mode; ndev->cnf.mtu6 = dev->mtu; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); @@ -2387,8 +2389,8 @@ static void manage_tempaddrs(struct inet6_dev *idev, static bool is_addr_mode_generate_stable(struct inet6_dev *idev) { - return idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY || - idev->addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM; + return idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY || + idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM; } int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, @@ -3152,7 +3154,7 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - switch (idev->addr_gen_mode) { + switch (idev->cnf.addr_gen_mode) { case IN6_ADDR_GEN_MODE_RANDOM: ipv6_gen_mode_random_init(idev); /* fallthrough */ @@ -3204,8 +3206,8 @@ static void addrconf_dev_config(struct net_device *dev) /* this device type has no EUI support */ if (dev->type == ARPHRD_NONE && - idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) - idev->addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM; + idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) + idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM; addrconf_addr_gen(idev, false); } @@ -4982,6 +4984,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_SEG6_REQUIRE_HMAC] = cnf->seg6_require_hmac; #endif array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; + array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; } static inline size_t inet6_ifla6_size(void) @@ -5093,7 +5096,7 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, if (!nla) goto nla_put_failure; - if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->addr_gen_mode)) + if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode)) goto nla_put_failure; read_lock_bh(&idev->lock); @@ -5211,6 +5214,26 @@ static int inet6_validate_link_af(const struct net_device *dev, return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy); } +static int check_addr_gen_mode(int mode) +{ + if (mode != IN6_ADDR_GEN_MODE_EUI64 && + mode != IN6_ADDR_GEN_MODE_NONE && + mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + mode != IN6_ADDR_GEN_MODE_RANDOM) + return -EINVAL; + return 1; +} + +static int check_stable_privacy(struct inet6_dev *idev, struct net *net, + int mode) +{ + if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + !idev->cnf.stable_secret.initialized && + !net->ipv6.devconf_dflt->stable_secret.initialized) + return -EINVAL; + return 1; +} + static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) { int err = -EINVAL; @@ -5232,18 +5255,11 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) if (tb[IFLA_INET6_ADDR_GEN_MODE]) { u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); - if (mode != IN6_ADDR_GEN_MODE_EUI64 && - mode != IN6_ADDR_GEN_MODE_NONE && - mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY && - mode != IN6_ADDR_GEN_MODE_RANDOM) - return -EINVAL; - - if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY && - !idev->cnf.stable_secret.initialized && - !dev_net(dev)->ipv6.devconf_dflt->stable_secret.initialized) + if (check_addr_gen_mode(mode) < 0 || + check_stable_privacy(idev, dev_net(dev), mode) < 0) return -EINVAL; - idev->addr_gen_mode = mode; + idev->cnf.addr_gen_mode = mode; err = 0; } @@ -5652,6 +5668,47 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, return ret; } +static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret = 0; + int new_val; + struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1; + struct net *net = (struct net *)ctl->extra2; + + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + if (write) { + new_val = *((int *)ctl->data); + + if (check_addr_gen_mode(new_val) < 0) + return -EINVAL; + + /* request for default */ + if (&net->ipv6.devconf_dflt->addr_gen_mode == ctl->data) { + ipv6_devconf_dflt.addr_gen_mode = new_val; + + /* request for individual net device */ + } else { + if (!idev) + return ret; + + if (check_stable_privacy(idev, net, new_val) < 0) + return -EINVAL; + + if (idev->cnf.addr_gen_mode != new_val) { + idev->cnf.addr_gen_mode = new_val; + rtnl_lock(); + addrconf_dev_config(idev->dev); + rtnl_unlock(); + } + } + } + + return ret; +} + static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -5702,14 +5759,14 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, struct inet6_dev *idev = __in6_dev_get(dev); if (idev) { - idev->addr_gen_mode = + idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; } } } else { struct inet6_dev *idev = ctl->extra1; - idev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; } out: @@ -6096,6 +6153,13 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "addr_gen_mode", + .data = &ipv6_devconf.addr_gen_mode, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_addr_gen_mode, + }, { /* sentinel */ } -- cgit v1.3-14-g43fede From 7e98102f489775d8c000884fca8a0d995ea688a9 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 27 Jan 2017 16:24:38 -0800 Subject: tcp: record pkts sent and retransmistted Add two stats in SCM_TIMESTAMPING_OPT_STATS: TCP_NLA_DATA_SEGS_OUT: total data packets sent including retransmission TCP_NLA_TOTAL_RETRANS: total data packets retransmitted The names are picked to be consistent with corresponding fields in TCP_INFO. This allows applications that are using the timestamping API to measure latency stats to also retrive retransmission rate of application write. Signed-off-by: Yuchung Cheng Signed-off-by: Soheil Hassas Yeganeh Acked-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 6ff35eb48d10..38a2b07afdff 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -227,6 +227,8 @@ enum { TCP_NLA_BUSY, /* Time (usec) busy sending data */ TCP_NLA_RWND_LIMITED, /* Time (usec) limited by receive window */ TCP_NLA_SNDBUF_LIMITED, /* Time (usec) limited by send buffer */ + TCP_NLA_DATA_SEGS_OUT, /* Data pkts sent including retransmission */ + TCP_NLA_TOTAL_RETRANS, /* Data pkts retransmitted */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2ed472ebf3b5..b751abc56935 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2870,7 +2870,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) struct sk_buff *stats; struct tcp_info info; - stats = alloc_skb(3 * nla_total_size_64bit(sizeof(u64)), GFP_ATOMIC); + stats = alloc_skb(5 * nla_total_size_64bit(sizeof(u64)), GFP_ATOMIC); if (!stats) return NULL; @@ -2881,6 +2881,10 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) info.tcpi_rwnd_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED, info.tcpi_sndbuf_limited, TCP_NLA_PAD); + nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT, + tp->data_segs_out, TCP_NLA_PAD); + nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS, + tp->total_retrans, TCP_NLA_PAD); return stats; } -- cgit v1.3-14-g43fede From ba94f3088b792b16ea576a256a6030feddc87f24 Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Wed, 1 Feb 2017 11:00:45 -0800 Subject: unix: add ioctl to open a unix socket file with O_PATH This ioctl opens a file to which a socket is bound and returns a file descriptor. The caller has to have CAP_NET_ADMIN in the socket network namespace. Currently it is impossible to get a path and a mount point for a socket file. socket_diag reports address, device ID and inode number for unix sockets. An address can contain a relative path or a file may be moved somewhere. And these properties say nothing about a mount namespace and a mount point of a socket file. With the introduced ioctl, we can get a path by reading /proc/self/fd/X and get mnt_id from /proc/self/fdinfo/X. In CRIU we are going to use this ioctl to dump and restore unix socket. Here is an example how it can be used: $ strace -e socket,bind,ioctl ./test /tmp/test_sock socket(AF_UNIX, SOCK_STREAM, 0) = 3 bind(3, {sa_family=AF_UNIX, sun_path="test_sock"}, 11) = 0 ioctl(3, SIOCUNIXFILE, 0) = 4 ^Z $ ss -a | grep test_sock u_str LISTEN 0 1 test_sock 17798 * 0 $ ls -l /proc/760/fd/{3,4} lrwx------ 1 root root 64 Feb 1 09:41 3 -> 'socket:[17798]' l--------- 1 root root 64 Feb 1 09:41 4 -> /tmp/test_sock $ cat /proc/760/fdinfo/4 pos: 0 flags: 012000000 mnt_id: 40 $ cat /proc/self/mountinfo | grep "^40\s" 40 19 0:37 / /tmp rw shared:23 - tmpfs tmpfs rw Signed-off-by: Andrei Vagin Signed-off-by: David S. Miller --- include/uapi/linux/un.h | 2 ++ net/unix/af_unix.c | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/un.h b/include/uapi/linux/un.h index 3ed3e46c1b1f..4f0ab3a548ad 100644 --- a/include/uapi/linux/un.h +++ b/include/uapi/linux/un.h @@ -10,4 +10,6 @@ struct sockaddr_un { char sun_path[UNIX_PATH_MAX]; /* pathname */ }; +#define SIOCUNIXFILE (SIOCPROTOPRIVATE + 0) /* open a socket file with O_PATH */ + #endif /* _LINUX_UN_H */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index cef79873b09d..e2d18b9f910f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -117,6 +117,7 @@ #include #include #include +#include struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; EXPORT_SYMBOL_GPL(unix_socket_table); @@ -2592,6 +2593,43 @@ long unix_outq_len(struct sock *sk) } EXPORT_SYMBOL_GPL(unix_outq_len); +static int unix_open_file(struct sock *sk) +{ + struct path path; + struct file *f; + int fd; + + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + unix_state_lock(sk); + path = unix_sk(sk)->path; + if (!path.dentry) { + unix_state_unlock(sk); + return -ENOENT; + } + + path_get(&path); + unix_state_unlock(sk); + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + goto out; + + f = dentry_open(&path, O_PATH, current_cred()); + if (IS_ERR(f)) { + put_unused_fd(fd); + fd = PTR_ERR(f); + goto out; + } + + fd_install(fd, f); +out: + path_put(&path); + + return fd; +} + static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; @@ -2610,6 +2648,9 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) else err = put_user(amount, (int __user *)arg); break; + case SIOCUNIXFILE: + err = unix_open_file(sk); + break; default: err = -ENOIOCTLCMD; break; -- cgit v1.3-14-g43fede From 8fe809a992639b2013c0d8da2ba55cdea28a959a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 1 Feb 2017 20:47:59 -0800 Subject: net: add LINUX_MIB_PFMEMALLOCDROP counter Debugging issues caused by pfmemalloc is often tedious. Add a new SNMP counter to more easily diagnose these problems. Signed-off-by: Eric Dumazet Cc: Josef Bacik Acked-by: Josef Bacik Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 1 + net/core/filter.c | 5 +++-- net/ipv4/proc.c | 1 + 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index e7a31f830690..3b2bed7ca9a4 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -240,6 +240,7 @@ enum LINUX_MIB_SACKMERGED, LINUX_MIB_SACKSHIFTFALLBACK, LINUX_MIB_TCPBACKLOGDROP, + LINUX_MIB_PFMEMALLOCDROP, LINUX_MIB_TCPMINTTLDROP, /* RFC 5082 */ LINUX_MIB_TCPDEFERACCEPTDROP, LINUX_MIB_IPRPFILTER, /* IP Reverse Path Filter (rp_filter) */ diff --git a/net/core/filter.c b/net/core/filter.c index 1e00737e3bc3..0b753cbb2536 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -76,9 +76,10 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ - if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); return -ENOMEM; - + } err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb); if (err) return err; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index a9deeb90dd36..69cf49e8356d 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -262,6 +262,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSackMerged", LINUX_MIB_SACKMERGED), SNMP_MIB_ITEM("TCPSackShiftFallback", LINUX_MIB_SACKSHIFTFALLBACK), SNMP_MIB_ITEM("TCPBacklogDrop", LINUX_MIB_TCPBACKLOGDROP), + SNMP_MIB_ITEM("PFMemallocDrop", LINUX_MIB_PFMEMALLOCDROP), SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP), SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP), SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER), -- cgit v1.3-14-g43fede From 1ce8460496c05379c66edc178c3c55ca4e953044 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 1 Feb 2017 15:30:02 +0200 Subject: net: Introduce ife encapsulation module This module is responsible for the ife encapsulation protocol encode/decode logics. That module can: - ife_encode: encode skb and reserve space for the ife meta header - ife_decode: decode skb and extract the meta header size - ife_tlv_meta_encode - encodes one tlv entry into the reserved ife header space. - ife_tlv_meta_decode - decodes one tlv entry from the packet - ife_tlv_meta_next - advance to the next tlv Reviewed-by: Jiri Pirko Signed-off-by: Yotam Gigi Signed-off-by: Jamal Hadi Salim Signed-off-by: Roman Mashak Signed-off-by: David S. Miller --- MAINTAINERS | 7 +++ include/net/ife.h | 51 +++++++++++++++++ include/uapi/linux/Kbuild | 1 + include/uapi/linux/ife.h | 18 ++++++ net/Kconfig | 1 + net/Makefile | 1 + net/ife/Kconfig | 16 ++++++ net/ife/Makefile | 5 ++ net/ife/ife.c | 142 ++++++++++++++++++++++++++++++++++++++++++++++ 9 files changed, 242 insertions(+) create mode 100644 include/net/ife.h create mode 100644 include/uapi/linux/ife.h create mode 100644 net/ife/Kconfig create mode 100644 net/ife/Makefile create mode 100644 net/ife/ife.c (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 5e637e2b3ff9..2abda6cb3150 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6250,6 +6250,13 @@ F: include/net/cfg802154.h F: include/net/ieee802154_netdev.h F: Documentation/networking/ieee802154.txt +IFE PROTOCOL +M: Yotam Gigi +M: Jamal Hadi Salim +F: net/ife +F: include/net/ife.h +F: include/uapi/linux/ife.h + IGORPLUG-USB IR RECEIVER M: Sean Young L: linux-media@vger.kernel.org diff --git a/include/net/ife.h b/include/net/ife.h new file mode 100644 index 000000000000..2d87d6898b0a --- /dev/null +++ b/include/net/ife.h @@ -0,0 +1,51 @@ +#ifndef __NET_IFE_H +#define __NET_IFE_H + +#include +#include +#include +#include + +#if IS_ENABLED(CONFIG_NET_IFE) + +void *ife_encode(struct sk_buff *skb, u16 metalen); +void *ife_decode(struct sk_buff *skb, u16 *metalen); + +void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen); +int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, + const void *dval); + +void *ife_tlv_meta_next(void *skbdata); + +#else + +static inline void *ife_encode(struct sk_buff *skb, u16 metalen) +{ + return NULL; +} + +static inline void *ife_decode(struct sk_buff *skb, u16 *metalen) +{ + return NULL; +} + +static inline void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, + u16 *totlen) +{ + return NULL; +} + +static inline int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, + const void *dval) +{ + return 0; +} + +static inline void *ife_tlv_meta_next(void *skbdata) +{ + return NULL; +} + +#endif + +#endif /* __NET_IFE_H */ diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 486e050e64c5..a2e90722a4c4 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -195,6 +195,7 @@ header-y += if_tun.h header-y += if_tunnel.h header-y += if_vlan.h header-y += if_x25.h +header-y += ife.h header-y += igmp.h header-y += ila.h header-y += in6.h diff --git a/include/uapi/linux/ife.h b/include/uapi/linux/ife.h new file mode 100644 index 000000000000..2954da32e012 --- /dev/null +++ b/include/uapi/linux/ife.h @@ -0,0 +1,18 @@ +#ifndef __UAPI_IFE_H +#define __UAPI_IFE_H + +#define IFE_METAHDRLEN 2 + +enum { + IFE_META_SKBMARK = 1, + IFE_META_HASHID, + IFE_META_PRIO, + IFE_META_QMAP, + IFE_META_TCINDEX, + __IFE_META_MAX +}; + +/*Can be overridden at runtime by module option*/ +#define IFE_META_MAX (__IFE_META_MAX - 1) + +#endif diff --git a/net/Kconfig b/net/Kconfig index ce4aee69fc0d..2f2842d2d3ed 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -391,6 +391,7 @@ source "net/caif/Kconfig" source "net/ceph/Kconfig" source "net/nfc/Kconfig" source "net/psample/Kconfig" +source "net/ife/Kconfig" config LWTUNNEL bool "Network light weight tunnels" diff --git a/net/Makefile b/net/Makefile index 7d41de48310e..9b681550e3a3 100644 --- a/net/Makefile +++ b/net/Makefile @@ -71,6 +71,7 @@ obj-$(CONFIG_CEPH_LIB) += ceph/ obj-$(CONFIG_BATMAN_ADV) += batman-adv/ obj-$(CONFIG_NFC) += nfc/ obj-$(CONFIG_PSAMPLE) += psample/ +obj-$(CONFIG_NET_IFE) += ife/ obj-$(CONFIG_OPENVSWITCH) += openvswitch/ obj-$(CONFIG_VSOCKETS) += vmw_vsock/ obj-$(CONFIG_MPLS) += mpls/ diff --git a/net/ife/Kconfig b/net/ife/Kconfig new file mode 100644 index 000000000000..31e48b652c7c --- /dev/null +++ b/net/ife/Kconfig @@ -0,0 +1,16 @@ +# +# IFE subsystem configuration +# + +menuconfig NET_IFE + depends on NET + tristate "Inter-FE based on IETF ForCES InterFE LFB" + default n + help + Say Y here to add support of IFE encapsulation protocol + For details refer to netdev01 paper: + "Distributing Linux Traffic Control Classifier-Action Subsystem" + Authors: Jamal Hadi Salim and Damascene M. Joachimpillai + + To compile this support as a module, choose M here: the module will + be called ife. diff --git a/net/ife/Makefile b/net/ife/Makefile new file mode 100644 index 000000000000..2a90d97746cc --- /dev/null +++ b/net/ife/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the IFE encapsulation protocol +# + +obj-$(CONFIG_NET_IFE) += ife.o diff --git a/net/ife/ife.c b/net/ife/ife.c new file mode 100644 index 000000000000..f360341c72eb --- /dev/null +++ b/net/ife/ife.c @@ -0,0 +1,142 @@ +/* + * net/ife/ife.c - Inter-FE protocol based on ForCES WG InterFE LFB + * Copyright (c) 2015 Jamal Hadi Salim + * Copyright (c) 2017 Yotam Gigi + * + * Refer to: draft-ietf-forces-interfelfb-03 and netdev01 paper: + * "Distributing Linux Traffic Control Classifier-Action Subsystem" + * Authors: Jamal Hadi Salim and Damascene M. Joachimpillai + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct ifeheadr { + __be16 metalen; + u8 tlv_data[]; +}; + +void *ife_encode(struct sk_buff *skb, u16 metalen) +{ + /* OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA + * where ORIGDATA = original ethernet header ... + */ + int hdrm = metalen + IFE_METAHDRLEN; + int total_push = hdrm + skb->dev->hard_header_len; + struct ifeheadr *ifehdr; + struct ethhdr *iethh; /* inner ether header */ + int skboff = 0; + int err; + + err = skb_cow_head(skb, total_push); + if (unlikely(err)) + return NULL; + + iethh = (struct ethhdr *) skb->data; + + __skb_push(skb, total_push); + memcpy(skb->data, iethh, skb->dev->hard_header_len); + skb_reset_mac_header(skb); + skboff += skb->dev->hard_header_len; + + /* total metadata length */ + ifehdr = (struct ifeheadr *) (skb->data + skboff); + metalen += IFE_METAHDRLEN; + ifehdr->metalen = htons(metalen); + + return ifehdr->tlv_data; +} +EXPORT_SYMBOL_GPL(ife_encode); + +void *ife_decode(struct sk_buff *skb, u16 *metalen) +{ + struct ifeheadr *ifehdr; + int total_pull; + u16 ifehdrln; + + ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len); + ifehdrln = ntohs(ifehdr->metalen); + total_pull = skb->dev->hard_header_len + ifehdrln; + + if (unlikely(ifehdrln < 2)) + return NULL; + + if (unlikely(!pskb_may_pull(skb, total_pull))) + return NULL; + + skb_set_mac_header(skb, total_pull); + __skb_pull(skb, total_pull); + *metalen = ifehdrln - IFE_METAHDRLEN; + + return &ifehdr->tlv_data; +} +EXPORT_SYMBOL_GPL(ife_decode); + +struct meta_tlvhdr { + __be16 type; + __be16 len; +}; + +/* Caller takes care of presenting data in network order + */ +void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen) +{ + struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata; + + *dlen = ntohs(tlv->len) - NLA_HDRLEN; + *attrtype = ntohs(tlv->type); + + if (totlen) + *totlen = nla_total_size(*dlen); + + return skbdata + sizeof(struct meta_tlvhdr); +} +EXPORT_SYMBOL_GPL(ife_tlv_meta_decode); + +void *ife_tlv_meta_next(void *skbdata) +{ + struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata; + u16 tlvlen = ntohs(tlv->len); + + tlvlen = NLA_ALIGN(tlvlen); + + return skbdata + tlvlen; +} +EXPORT_SYMBOL_GPL(ife_tlv_meta_next); + +/* Caller takes care of presenting data in network order + */ +int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) +{ + __be32 *tlv = (__be32 *) (skbdata); + u16 totlen = nla_total_size(dlen); /*alignment + hdr */ + char *dptr = (char *) tlv + NLA_HDRLEN; + u32 htlv = attrtype << 16 | (dlen + NLA_HDRLEN); + + *tlv = htonl(htlv); + memset(dptr, 0, totlen - NLA_HDRLEN); + memcpy(dptr, dval, dlen); + + return totlen; +} +EXPORT_SYMBOL_GPL(ife_tlv_meta_encode); + +MODULE_AUTHOR("Jamal Hadi Salim "); +MODULE_AUTHOR("Yotam Gigi "); +MODULE_DESCRIPTION("Inter-FE LFB action"); +MODULE_LICENSE("GPL"); -- cgit v1.3-14-g43fede From 295a6e06d21e1f469c9f38b00125a13b60ad4e7c Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 1 Feb 2017 15:30:03 +0200 Subject: net/sched: act_ife: Change to use ife module Use the encode/decode functionality from the ife module instead of using implementation inside the act_ife. Reviewed-by: Jiri Pirko Signed-off-by: Yotam Gigi Signed-off-by: Jamal Hadi Salim Signed-off-by: Roman Mashak Signed-off-by: David S. Miller --- include/net/tc_act/tc_ife.h | 1 - include/uapi/linux/tc_act/tc_ife.h | 10 +--- net/sched/Kconfig | 1 + net/sched/act_ife.c | 110 +++++++++++-------------------------- 4 files changed, 34 insertions(+), 88 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index f37e7516ab28..30ba459ddd34 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -6,7 +6,6 @@ #include #include -#define IFE_METAHDRLEN 2 struct tcf_ife_info { struct tc_action common; u8 eth_dst[ETH_ALEN]; diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h index cd18360eca24..7c2817866c97 100644 --- a/include/uapi/linux/tc_act/tc_ife.h +++ b/include/uapi/linux/tc_act/tc_ife.h @@ -3,6 +3,7 @@ #include #include +#include #define TCA_ACT_IFE 25 /* Flag bits for now just encoding/decoding; mutually exclusive */ @@ -28,13 +29,4 @@ enum { }; #define TCA_IFE_MAX (__TCA_IFE_MAX - 1) -#define IFE_META_SKBMARK 1 -#define IFE_META_HASHID 2 -#define IFE_META_PRIO 3 -#define IFE_META_QMAP 4 -#define IFE_META_TCINDEX 5 -/*Can be overridden at runtime by module option*/ -#define __IFE_META_MAX 6 -#define IFE_META_MAX (__IFE_META_MAX - 1) - #endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 72cfa3a6bac0..403790cce7d2 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -776,6 +776,7 @@ config NET_ACT_SKBMOD config NET_ACT_IFE tristate "Inter-FE action based on IETF ForCES InterFE LFB" depends on NET_CLS_ACT + select NET_IFE ---help--- Say Y here to allow for sourcing and terminating metadata For details refer to netdev01 paper: diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 70148c10ede9..71e7ff22f7c9 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -32,6 +32,7 @@ #include #include #include +#include #define IFE_TAB_MASK 15 @@ -46,23 +47,6 @@ static const struct nla_policy ife_policy[TCA_IFE_MAX + 1] = { [TCA_IFE_TYPE] = { .type = NLA_U16}, }; -/* Caller takes care of presenting data in network order -*/ -static int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, - const void *dval) -{ - u32 *tlv = (u32 *)(skbdata); - u16 totlen = nla_total_size(dlen); /*alignment + hdr */ - char *dptr = (char *)tlv + NLA_HDRLEN; - u32 htlv = attrtype << 16 | (dlen + NLA_HDRLEN); - - *tlv = htonl(htlv); - memset(dptr, 0, totlen - NLA_HDRLEN); - memcpy(dptr, dval, dlen); - - return totlen; -} - int ife_encode_meta_u16(u16 metaval, void *skbdata, struct tcf_meta_info *mi) { u16 edata = 0; @@ -637,69 +621,59 @@ int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, return 0; } -struct ifeheadr { - __be16 metalen; - u8 tlv_data[]; -}; - -struct meta_tlvhdr { - __be16 type; - __be16 len; -}; - static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; - struct ifeheadr *ifehdr = (struct ifeheadr *)skb->data; - int ifehdrln = (int)ifehdr->metalen; - struct meta_tlvhdr *tlv = (struct meta_tlvhdr *)(ifehdr->tlv_data); + u8 *ifehdr_end; + u8 *tlv_data; + u16 metalen; spin_lock(&ife->tcf_lock); bstats_update(&ife->tcf_bstats, skb); tcf_lastuse_update(&ife->tcf_tm); spin_unlock(&ife->tcf_lock); - ifehdrln = ntohs(ifehdrln); - if (unlikely(!pskb_may_pull(skb, ifehdrln))) { + if (skb_at_tc_ingress(skb)) + skb_push(skb, skb->dev->hard_header_len); + + tlv_data = ife_decode(skb, &metalen); + if (unlikely(!tlv_data)) { spin_lock(&ife->tcf_lock); ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); return TC_ACT_SHOT; } - skb_set_mac_header(skb, ifehdrln); - __skb_pull(skb, ifehdrln); - skb->protocol = eth_type_trans(skb, skb->dev); - ifehdrln -= IFE_METAHDRLEN; - - while (ifehdrln > 0) { - u8 *tlvdata = (u8 *)tlv; - u16 mtype = tlv->type; - u16 mlen = tlv->len; - u16 alen; + ifehdr_end = tlv_data + metalen; + for (; tlv_data < ifehdr_end; tlv_data = ife_tlv_meta_next(tlv_data)) { + u8 *curr_data; + u16 mtype; + u16 dlen; - mtype = ntohs(mtype); - mlen = ntohs(mlen); - alen = NLA_ALIGN(mlen); + curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL); - if (find_decode_metaid(skb, ife, mtype, (mlen - NLA_HDRLEN), - (void *)(tlvdata + NLA_HDRLEN))) { + if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ - pr_info_ratelimited("Unknown metaid %d alnlen %d\n", - mtype, mlen); + pr_info_ratelimited("Unknown metaid %d dlen %d\n", + mtype, dlen); ife->tcf_qstats.overlimits++; } + } - tlvdata += alen; - ifehdrln -= alen; - tlv = (struct meta_tlvhdr *)tlvdata; + if (WARN_ON(tlv_data != ifehdr_end)) { + spin_lock(&ife->tcf_lock); + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; } + skb->protocol = eth_type_trans(skb, skb->dev); skb_reset_network_header(skb); + return action; } @@ -727,7 +701,6 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; struct ethhdr *oethh; /* outer ether header */ - struct ethhdr *iethh; /* inner eth header */ struct tcf_meta_info *e; /* OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA @@ -735,10 +708,11 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, */ u16 metalen = ife_get_sz(skb, ife); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; - unsigned int skboff = skb->dev->hard_header_len; + unsigned int skboff = 0; int new_len = skb->len + hdrm; bool exceed_mtu = false; - int err; + void *ife_meta; + int err = 0; if (!skb_at_tc_ingress(skb)) { if (new_len > skb->dev->mtu) @@ -765,27 +739,10 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, return TC_ACT_SHOT; } - err = skb_cow_head(skb, hdrm); - if (unlikely(err)) { - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); - return TC_ACT_SHOT; - } - if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); - iethh = (struct ethhdr *)skb->data; - __skb_push(skb, hdrm); - memcpy(skb->data, iethh, skb->mac_len); - skb_reset_mac_header(skb); - oethh = eth_hdr(skb); - - /*total metadata length */ - metalen += IFE_METAHDRLEN; - metalen = htons(metalen); - memcpy((skb->data + skboff), &metalen, IFE_METAHDRLEN); - skboff += IFE_METAHDRLEN; + ife_meta = ife_encode(skb, metalen); /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by @@ -793,7 +750,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, */ list_for_each_entry(e, &ife->metalist, metalist) { if (e->ops->encode) { - err = e->ops->encode(skb, (void *)(skb->data + skboff), + err = e->ops->encode(skb, (void *)(ife_meta + skboff), e); } if (err < 0) { @@ -804,15 +761,12 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, } skboff += err; } + oethh = (struct ethhdr *)skb->data; if (!is_zero_ether_addr(ife->eth_src)) ether_addr_copy(oethh->h_source, ife->eth_src); - else - ether_addr_copy(oethh->h_source, iethh->h_source); if (!is_zero_ether_addr(ife->eth_dst)) ether_addr_copy(oethh->h_dest, ife->eth_dst); - else - ether_addr_copy(oethh->h_dest, iethh->h_dest); oethh->h_proto = htons(ife->eth_type); if (skb_at_tc_ingress(skb)) -- cgit v1.3-14-g43fede From 3ad7a4b141ebd6091494913672d7166d5c2764e4 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Tue, 31 Jan 2017 22:59:52 -0800 Subject: vxlan: support fdb and learning in COLLECT_METADATA mode Vxlan COLLECT_METADATA mode today solves the per-vni netdev scalability problem in l3 networks. It expects all forwarding information to be present in dst_metadata. This patch series enhances collect metadata mode to include the case where only vni is present in dst_metadata, and the vxlan driver can then use the rest of the forwarding information datbase to make forwarding decisions. There is no change to default COLLECT_METADATA behaviour. These changes only apply to COLLECT_METADATA when used with the bridging use-case with a special dst_metadata tunnel info flag (eg: where vxlan device is part of a bridge). For all this to work, the vxlan driver will need to now support a single fdb table hashed by mac + vni. This series essentially makes this happen. use-case and workflow: vxlan collect metadata device participates in bridging vlan to vn-segments. Bridge driver above the vxlan device, sends the vni corresponding to the vlan in the dst_metadata. vxlan driver will lookup forwarding database with (mac + vni) for the required remote destination information to forward the packet. Changes introduced by this patch: - allow learning and forwarding database state in vxlan netdev in COLLECT_METADATA mode. Current behaviour is not changed by default. tunnel info flag IP_TUNNEL_INFO_BRIDGE is used to support the new bridge friendly mode. - A single fdb table hashed by (mac, vni) to allow fdb entries with multiple vnis in the same fdb table - rx path already has the vni - tx path expects a vni in the packet with dst_metadata - prior to this series, fdb remote_dsts carried remote vni and the vxlan device carrying the fdb table represented the source vni. With the vxlan device now representing multiple vnis, this patch adds a src vni attribute to the fdb entry. The remote vni already uses NDA_VNI attribute. This patch introduces NDA_SRC_VNI netlink attribute to represent the src vni in a multi vni fdb table. iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's. before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metadata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 196 ++++++++++++++++++++++++++--------------- include/uapi/linux/neighbour.h | 1 + 2 files changed, 126 insertions(+), 71 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 2e48ce22eabf..2374a75dcb55 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -75,6 +75,7 @@ struct vxlan_fdb { struct list_head remotes; u8 eth_addr[ETH_ALEN]; u16 state; /* see ndm_state */ + __be32 vni; u8 flags; /* see ndm_flags */ }; @@ -302,6 +303,10 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, if (rdst->remote_vni != vxlan->default_dst.remote_vni && nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) goto nla_put_failure; + if ((vxlan->flags & VXLAN_F_COLLECT_METADATA) && fdb->vni && + nla_put_u32(skb, NDA_SRC_VNI, + be32_to_cpu(fdb->vni))) + goto nla_put_failure; if (rdst->remote_ifindex && nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) goto nla_put_failure; @@ -400,34 +405,51 @@ static u32 eth_hash(const unsigned char *addr) return hash_64(value, FDB_HASH_BITS); } +static u32 eth_vni_hash(const unsigned char *addr, __be32 vni) +{ + /* use 1 byte of OUI and 3 bytes of NIC */ + u32 key = get_unaligned((u32 *)(addr + 2)); + + return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1); +} + /* Hash chain to use given mac address */ static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, - const u8 *mac) + const u8 *mac, __be32 vni) { - return &vxlan->fdb_head[eth_hash(mac)]; + if (vxlan->flags & VXLAN_F_COLLECT_METADATA) + return &vxlan->fdb_head[eth_vni_hash(mac, vni)]; + else + return &vxlan->fdb_head[eth_hash(mac)]; } /* Look up Ethernet address in forwarding table */ static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan, - const u8 *mac) + const u8 *mac, __be32 vni) { - struct hlist_head *head = vxlan_fdb_head(vxlan, mac); + struct hlist_head *head = vxlan_fdb_head(vxlan, mac, vni); struct vxlan_fdb *f; hlist_for_each_entry_rcu(f, head, hlist) { - if (ether_addr_equal(mac, f->eth_addr)) - return f; + if (ether_addr_equal(mac, f->eth_addr)) { + if (vxlan->flags & VXLAN_F_COLLECT_METADATA) { + if (vni == f->vni) + return f; + } else { + return f; + } + } } return NULL; } static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, - const u8 *mac) + const u8 *mac, __be32 vni) { struct vxlan_fdb *f; - f = __vxlan_find_mac(vxlan, mac); + f = __vxlan_find_mac(vxlan, mac, vni); if (f) f->used = jiffies; @@ -605,15 +627,15 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) static int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, - __be16 port, __be32 vni, __u32 ifindex, - __u8 ndm_flags) + __be16 port, __be32 src_vni, __be32 vni, + __u32 ifindex, __u8 ndm_flags) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int notify = 0; int rc; - f = __vxlan_find_mac(vxlan, mac); + f = __vxlan_find_mac(vxlan, mac, src_vni); if (f) { if (flags & NLM_F_EXCL) { netdev_dbg(vxlan->dev, @@ -670,6 +692,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, f->state = state; f->flags = ndm_flags; f->updated = f->used = jiffies; + f->vni = src_vni; INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); @@ -681,7 +704,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, - vxlan_fdb_head(vxlan, mac)); + vxlan_fdb_head(vxlan, mac, src_vni)); } if (notify) { @@ -718,8 +741,8 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f) } static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, - union vxlan_addr *ip, __be16 *port, __be32 *vni, - u32 *ifindex) + union vxlan_addr *ip, __be16 *port, __be32 *src_vni, + __be32 *vni, u32 *ifindex) { struct net *net = dev_net(vxlan->dev); int err; @@ -757,6 +780,14 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, *vni = vxlan->default_dst.remote_vni; } + if (tb[NDA_SRC_VNI]) { + if (nla_len(tb[NDA_SRC_VNI]) != sizeof(u32)) + return -EINVAL; + *src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); + } else { + *src_vni = vxlan->default_dst.remote_vni; + } + if (tb[NDA_IFINDEX]) { struct net_device *tdev; @@ -782,7 +813,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], /* struct net *net = dev_net(vxlan->dev); */ union vxlan_addr ip; __be16 port; - __be32 vni; + __be32 src_vni, vni; u32 ifindex; int err; @@ -795,7 +826,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], if (tb[NDA_DST] == NULL) return -EINVAL; - err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &vni, &ifindex); + err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex); if (err) return err; @@ -804,36 +835,24 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], spin_lock_bh(&vxlan->hash_lock); err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags, - port, vni, ifindex, ndm->ndm_flags); + port, src_vni, vni, ifindex, ndm->ndm_flags); spin_unlock_bh(&vxlan->hash_lock); return err; } -/* Delete entry (via netlink) */ -static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid) +static int __vxlan_fdb_delete(struct vxlan_dev *vxlan, + const unsigned char *addr, union vxlan_addr ip, + __be16 port, __be32 src_vni, u32 vni, u32 ifindex, + u16 vid) { - struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; struct vxlan_rdst *rd = NULL; - union vxlan_addr ip; - __be16 port; - __be32 vni; - u32 ifindex; - int err; + int err = -ENOENT; - err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &vni, &ifindex); - if (err) - return err; - - err = -ENOENT; - - spin_lock_bh(&vxlan->hash_lock); - f = vxlan_find_mac(vxlan, addr); + f = vxlan_find_mac(vxlan, addr, src_vni); if (!f) - goto out; + return err; if (!vxlan_addr_any(&ip)) { rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex); @@ -841,8 +860,6 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], goto out; } - err = 0; - /* remove a destination if it's not the only one on the list, * otherwise destroy the fdb entry */ @@ -856,6 +873,28 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], vxlan_fdb_destroy(vxlan, f); out: + return 0; +} + +/* Delete entry (via netlink) */ +static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + union vxlan_addr ip; + __be32 src_vni, vni; + __be16 port; + u32 ifindex; + int err; + + err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex); + if (err) + return err; + + spin_lock_bh(&vxlan->hash_lock); + err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex, + vid); spin_unlock_bh(&vxlan->hash_lock); return err; @@ -901,12 +940,13 @@ out: * Return true if packet is bogus and should be dropped. */ static bool vxlan_snoop(struct net_device *dev, - union vxlan_addr *src_ip, const u8 *src_mac) + union vxlan_addr *src_ip, const u8 *src_mac, + __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; - f = vxlan_find_mac(vxlan, src_mac); + f = vxlan_find_mac(vxlan, src_mac, vni); if (likely(f)) { struct vxlan_rdst *rdst = first_remote_rcu(f); @@ -935,6 +975,7 @@ static bool vxlan_snoop(struct net_device *dev, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, + vni, vxlan->default_dst.remote_vni, 0, NTF_SELF); spin_unlock(&vxlan->hash_lock); @@ -1202,7 +1243,7 @@ static bool vxlan_parse_gpe_hdr(struct vxlanhdr *unparsed, static bool vxlan_set_mac(struct vxlan_dev *vxlan, struct vxlan_sock *vs, - struct sk_buff *skb) + struct sk_buff *skb, __be32 vni) { union vxlan_addr saddr; @@ -1226,7 +1267,7 @@ static bool vxlan_set_mac(struct vxlan_dev *vxlan, } if ((vxlan->flags & VXLAN_F_LEARN) && - vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source)) + vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source, vni)) return false; return true; @@ -1268,6 +1309,7 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) __be16 protocol = htons(ETH_P_TEB); bool raw_proto = false; void *oiph; + __be32 vni = 0; /* Need UDP and VXLAN header to be present */ if (!pskb_may_pull(skb, VXLAN_HLEN)) @@ -1289,7 +1331,12 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) if (!vs) goto drop; - vxlan = vxlan_vs_find_vni(vs, vxlan_vni(vxlan_hdr(skb)->vx_vni)); + vni = vxlan_vni(vxlan_hdr(skb)->vx_vni); + + if ((vs->flags & VXLAN_F_COLLECT_METADATA) && !vni) + goto drop; + + vxlan = vxlan_vs_find_vni(vs, vni); if (!vxlan) goto drop; @@ -1307,7 +1354,6 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) goto drop; if (vxlan_collect_metadata(vs)) { - __be32 vni = vxlan_vni(vxlan_hdr(skb)->vx_vni); struct metadata_dst *tun_dst; tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY, @@ -1345,7 +1391,7 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) } if (!raw_proto) { - if (!vxlan_set_mac(vxlan, vs, skb)) + if (!vxlan_set_mac(vxlan, vs, skb, vni)) goto drop; } else { skb_reset_mac_header(skb); @@ -1377,7 +1423,7 @@ drop: return 0; } -static int arp_reduce(struct net_device *dev, struct sk_buff *skb) +static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct arphdr *parp; @@ -1424,7 +1470,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) goto out; } - f = vxlan_find_mac(vxlan, n->ha); + f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); @@ -1548,7 +1594,7 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request, return reply; } -static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) +static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct nd_msg *msg; @@ -1585,7 +1631,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) goto out; } - f = vxlan_find_mac(vxlan, n->ha); + f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); @@ -1906,7 +1952,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, - struct vxlan_dev *dst_vxlan) + struct vxlan_dev *dst_vxlan, __be32 vni) { struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; @@ -1932,7 +1978,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, } if (dst_vxlan->flags & VXLAN_F_LEARN) - vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source); + vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, vni); u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; @@ -1976,7 +2022,7 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, return -ENOENT; } - vxlan_encap_bypass(skb, vxlan, dst_vxlan); + vxlan_encap_bypass(skb, vxlan, dst_vxlan, vni); return 1; } @@ -1984,7 +2030,8 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, } static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, - struct vxlan_rdst *rdst, bool did_rsc) + __be32 default_vni, struct vxlan_rdst *rdst, + bool did_rsc) { struct dst_cache *dst_cache; struct ip_tunnel_info *info; @@ -2011,14 +2058,14 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (vxlan_addr_any(dst)) { if (did_rsc) { /* short-circuited back to local bridge */ - vxlan_encap_bypass(skb, vxlan, vxlan); + vxlan_encap_bypass(skb, vxlan, vxlan, default_vni); return; } goto drop; } dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; - vni = rdst->remote_vni; + vni = (rdst->remote_vni) ? : default_vni; src = &vxlan->cfg.saddr; dst_cache = &rdst->dst_cache; md->gbp = skb->mark; @@ -2173,23 +2220,29 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) bool did_rsc = false; struct vxlan_rdst *rdst, *fdst = NULL; struct vxlan_fdb *f; + __be32 vni = 0; info = skb_tunnel_info(skb); skb_reset_mac_header(skb); if (vxlan->flags & VXLAN_F_COLLECT_METADATA) { - if (info && info->mode & IP_TUNNEL_INFO_TX) - vxlan_xmit_one(skb, dev, NULL, false); - else - kfree_skb(skb); - return NETDEV_TX_OK; + if (info && info->mode & IP_TUNNEL_INFO_BRIDGE && + info->mode & IP_TUNNEL_INFO_TX) { + vni = tunnel_id_to_key32(info->key.tun_id); + } else { + if (info && info->mode & IP_TUNNEL_INFO_TX) + vxlan_xmit_one(skb, dev, vni, NULL, false); + else + kfree_skb(skb); + return NETDEV_TX_OK; + } } if (vxlan->flags & VXLAN_F_PROXY) { eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_ARP) - return arp_reduce(dev, skb); + return arp_reduce(dev, skb, vni); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && pskb_may_pull(skb, sizeof(struct ipv6hdr) @@ -2200,13 +2253,13 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) msg = (struct nd_msg *)skb_transport_header(skb); if (msg->icmph.icmp6_code == 0 && msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) - return neigh_reduce(dev, skb); + return neigh_reduce(dev, skb, vni); } #endif } eth = eth_hdr(skb); - f = vxlan_find_mac(vxlan, eth->h_dest); + f = vxlan_find_mac(vxlan, eth->h_dest, vni); did_rsc = false; if (f && (f->flags & NTF_ROUTER) && (vxlan->flags & VXLAN_F_RSC) && @@ -2214,11 +2267,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) ntohs(eth->h_proto) == ETH_P_IPV6)) { did_rsc = route_shortcircuit(dev, skb); if (did_rsc) - f = vxlan_find_mac(vxlan, eth->h_dest); + f = vxlan_find_mac(vxlan, eth->h_dest, vni); } if (f == NULL) { - f = vxlan_find_mac(vxlan, all_zeros_mac); + f = vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f == NULL) { if ((vxlan->flags & VXLAN_F_L2MISS) && !is_multicast_ether_addr(eth->h_dest)) @@ -2239,11 +2292,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) } skb1 = skb_clone(skb, GFP_ATOMIC); if (skb1) - vxlan_xmit_one(skb1, dev, rdst, did_rsc); + vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc); } if (fdst) - vxlan_xmit_one(skb, dev, fdst, did_rsc); + vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); else kfree_skb(skb); return NETDEV_TX_OK; @@ -2307,12 +2360,12 @@ static int vxlan_init(struct net_device *dev) return 0; } -static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan) +static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) { struct vxlan_fdb *f; spin_lock_bh(&vxlan->hash_lock); - f = __vxlan_find_mac(vxlan, all_zeros_mac); + f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f) vxlan_fdb_destroy(vxlan, f); spin_unlock_bh(&vxlan->hash_lock); @@ -2322,7 +2375,7 @@ static void vxlan_uninit(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); - vxlan_fdb_delete_default(vxlan); + vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); free_percpu(dev->tstats); } @@ -2923,6 +2976,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, vxlan->default_dst.remote_vni, + vxlan->default_dst.remote_vni, vxlan->default_dst.remote_ifindex, NTF_SELF); if (err) @@ -2931,7 +2985,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, err = register_netdevice(dev); if (err) { - vxlan_fdb_delete_default(vxlan); + vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); return err; } diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index bd99a8d80f36..f3d16dbe09d6 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -26,6 +26,7 @@ enum { NDA_IFINDEX, NDA_MASTER, NDA_LINK_NETNSID, + NDA_SRC_VNI, __NDA_MAX }; -- cgit v1.3-14-g43fede From b3c7ef0adadc5768e0baa786213c6bd1ce521a77 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Tue, 31 Jan 2017 22:59:53 -0800 Subject: bridge: uapi: add per vlan tunnel info New nested netlink attribute to associate tunnel info per vlan. This is used by bridge driver to send tunnel metadata to bridge ports in vlan tunnel mode. This patch also adds new per port flag IFLA_BRPORT_VLAN_TUNNEL to enable vlan tunnel mode. off by default. One example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). User can configure per-vlan tunnel information which the bridge driver can use to bridge vlan into the corresponding vn-segment. Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_bridge.h | 11 +++++++++++ include/uapi/linux/if_link.h | 1 + 3 files changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index debc9d5904e5..c5847dc75a93 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -47,6 +47,7 @@ struct br_ip_list { #define BR_PROXYARP_WIFI BIT(10) #define BR_MCAST_FLOOD BIT(11) #define BR_MULTICAST_TO_UNICAST BIT(12) +#define BR_VLAN_TUNNEL BIT(13) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index ab92bca6d448..a9e6244ce438 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -118,6 +118,7 @@ enum { IFLA_BRIDGE_FLAGS, IFLA_BRIDGE_MODE, IFLA_BRIDGE_VLAN_INFO, + IFLA_BRIDGE_VLAN_TUNNEL_INFO, __IFLA_BRIDGE_MAX, }; #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1) @@ -134,6 +135,16 @@ struct bridge_vlan_info { __u16 vid; }; +enum { + IFLA_BRIDGE_VLAN_TUNNEL_UNSPEC, + IFLA_BRIDGE_VLAN_TUNNEL_ID, + IFLA_BRIDGE_VLAN_TUNNEL_VID, + IFLA_BRIDGE_VLAN_TUNNEL_FLAGS, + __IFLA_BRIDGE_VLAN_TUNNEL_MAX, +}; + +#define IFLA_BRIDGE_VLAN_TUNNEL_MAX (__IFLA_BRIDGE_VLAN_TUNNEL_MAX - 1) + struct bridge_vlan_xstats { __u64 rx_bytes; __u64 rx_packets; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b9aa5641ebe5..320fc1e747ee 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -322,6 +322,7 @@ enum { IFLA_BRPORT_PAD, IFLA_BRPORT_MCAST_FLOOD, IFLA_BRPORT_MCAST_TO_UCAST, + IFLA_BRPORT_VLAN_TUNNEL, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.3-14-g43fede From bee427b86217b78a0a5fc85575cc155e4c32bbf9 Mon Sep 17 00:00:00 2001 From: Andrzej Zaborowski Date: Wed, 25 Jan 2017 12:43:41 +0100 Subject: cfg80211: Pass new RSSI level in CQM RSSI notification Update the drivers to pass the RSSI level as a cfg80211_cqm_rssi_notify parameter and pass this value to userspace in a new nl80211 attribute. This helps both userspace and also helps in the implementation of the multiple RSSI thresholds CQM mechanism. Note for marvell/mwifiex I pass 0 for the RSSI value because the new RSSI value is not available to the driver at the time of the cfg80211_cqm_rssi_notify call, but the driver queries the new value immediately after that, so it is actually available just a moment later if we wanted to defer caling cfg80211_cqm_rssi_notify until that moment. Without this, the new cfg80211 code (patch 3) will call .get_station which will send a duplicate HostCmd_CMD_RSSI_INFO command to the hardware. Signed-off-by: Andrew Zaborowski Signed-off-by: Johannes Berg --- drivers/net/wireless/marvell/mwifiex/sta_event.c | 4 ++-- drivers/net/wireless/rndis_wlan.c | 2 +- include/net/cfg80211.h | 3 ++- include/uapi/linux/nl80211.h | 3 +++ net/mac80211/mlme.c | 2 +- net/wireless/nl80211.c | 9 +++++++-- net/wireless/trace.h | 11 +++++++---- 7 files changed, 23 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c index 9df0c4dc06ed..5cc3aa7c31cd 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_event.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c @@ -824,7 +824,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv) case EVENT_RSSI_LOW: cfg80211_cqm_rssi_notify(priv->netdev, NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW, - GFP_KERNEL); + 0, GFP_KERNEL); mwifiex_send_cmd(priv, HostCmd_CMD_RSSI_INFO, HostCmd_ACT_GEN_GET, 0, NULL, false); priv->subsc_evt_rssi_state = RSSI_LOW_RECVD; @@ -839,7 +839,7 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv) case EVENT_RSSI_HIGH: cfg80211_cqm_rssi_notify(priv->netdev, NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH, - GFP_KERNEL); + 0, GFP_KERNEL); mwifiex_send_cmd(priv, HostCmd_CMD_RSSI_INFO, HostCmd_ACT_GEN_GET, 0, NULL, false); priv->subsc_evt_rssi_state = RSSI_HIGH_RECVD; diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 603c90470225..785334f7a538 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -3187,7 +3187,7 @@ static void rndis_do_cqm(struct usbnet *usbdev, s32 rssi) return; priv->last_cqm_event_rssi = rssi; - cfg80211_cqm_rssi_notify(usbdev->net, event, GFP_KERNEL); + cfg80211_cqm_rssi_notify(usbdev->net, event, rssi, GFP_KERNEL); } #define DEVICE_POLLER_JIFFIES (HZ) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5cfd2806a078..a2c18b53e053 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5390,6 +5390,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event * @dev: network device * @rssi_event: the triggered RSSI event + * @rssi_level: new RSSI level value or 0 if not available * @gfp: context flags * * This function is called when a configured connection quality monitoring @@ -5397,7 +5398,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, */ void cfg80211_cqm_rssi_notify(struct net_device *dev, enum nl80211_cqm_rssi_threshold_event rssi_event, - gfp_t gfp); + s32 rssi_level, gfp_t gfp); /** * cfg80211_cqm_pktloss_notify - notify userspace about packetloss to peer diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d6c62ee9bd1d..cd547b864595 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3952,6 +3952,8 @@ enum nl80211_ps_state { * %NL80211_CMD_NOTIFY_CQM. Set to 0 to turn off TX error reporting. * @NL80211_ATTR_CQM_BEACON_LOSS_EVENT: flag attribute that's set in a beacon * loss event + * @NL80211_ATTR_CQM_RSSI_LEVEL: the RSSI value in dBm that triggered the + * RSSI threshold event. * @__NL80211_ATTR_CQM_AFTER_LAST: internal * @NL80211_ATTR_CQM_MAX: highest key attribute */ @@ -3965,6 +3967,7 @@ enum nl80211_attr_cqm { NL80211_ATTR_CQM_TXE_PKTS, NL80211_ATTR_CQM_TXE_INTVL, NL80211_ATTR_CQM_BEACON_LOSS_EVENT, + NL80211_ATTR_CQM_RSSI_LEVEL, /* keep last */ __NL80211_ATTR_CQM_AFTER_LAST, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index ee423688c92e..6e90301154d5 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5048,7 +5048,7 @@ void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif, trace_api_cqm_rssi_notify(sdata, rssi_event, rssi_level); - cfg80211_cqm_rssi_notify(sdata->dev, rssi_event, gfp); + cfg80211_cqm_rssi_notify(sdata->dev, rssi_event, rssi_level, gfp); } EXPORT_SYMBOL(ieee80211_cqm_rssi_notify); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b455898df63c..9d738f75bd4e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9474,6 +9474,7 @@ nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] = { [NL80211_ATTR_CQM_TXE_RATE] = { .type = NLA_U32 }, [NL80211_ATTR_CQM_TXE_PKTS] = { .type = NLA_U32 }, [NL80211_ATTR_CQM_TXE_INTVL] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM_RSSI_LEVEL] = { .type = NLA_S32 }, }; static int nl80211_set_cqm_txe(struct genl_info *info, @@ -13959,11 +13960,11 @@ static void cfg80211_send_cqm(struct sk_buff *msg, gfp_t gfp) void cfg80211_cqm_rssi_notify(struct net_device *dev, enum nl80211_cqm_rssi_threshold_event rssi_event, - gfp_t gfp) + s32 rssi_level, gfp_t gfp) { struct sk_buff *msg; - trace_cfg80211_cqm_rssi_notify(dev, rssi_event); + trace_cfg80211_cqm_rssi_notify(dev, rssi_event, rssi_level); if (WARN_ON(rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW && rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH)) @@ -13977,6 +13978,10 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, rssi_event)) goto nla_put_failure; + if (rssi_level && nla_put_s32(msg, NL80211_ATTR_CQM_RSSI_LEVEL, + rssi_level)) + goto nla_put_failure; + cfg80211_send_cqm(msg, gfp); return; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index ea1b47e04fa4..2419c390f150 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2490,18 +2490,21 @@ TRACE_EVENT(cfg80211_mgmt_tx_status, TRACE_EVENT(cfg80211_cqm_rssi_notify, TP_PROTO(struct net_device *netdev, - enum nl80211_cqm_rssi_threshold_event rssi_event), - TP_ARGS(netdev, rssi_event), + enum nl80211_cqm_rssi_threshold_event rssi_event, + s32 rssi_level), + TP_ARGS(netdev, rssi_event, rssi_level), TP_STRUCT__entry( NETDEV_ENTRY __field(enum nl80211_cqm_rssi_threshold_event, rssi_event) + __field(s32, rssi_level) ), TP_fast_assign( NETDEV_ASSIGN; __entry->rssi_event = rssi_event; + __entry->rssi_level = rssi_level; ), - TP_printk(NETDEV_PR_FMT ", rssi event: %d", - NETDEV_PR_ARG, __entry->rssi_event) + TP_printk(NETDEV_PR_FMT ", rssi event: %d, level: %d", + NETDEV_PR_ARG, __entry->rssi_event, __entry->rssi_level) ); TRACE_EVENT(cfg80211_reg_can_beacon, -- cgit v1.3-14-g43fede From c078ca3b0c5bf82c2b31906c446d6e2ad8ea0783 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Tue, 17 Jan 2017 22:51:26 +0100 Subject: netfilter: nft_exthdr: Add support for existence check If NFT_EXTHDR_F_PRESENT is set, exthdr will not copy any header field data into *dest, but instead set it to 1 if the header is found and 0 otherwise. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 6 ++++++ net/netfilter/nft_exthdr.c | 22 ++++++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 7b730cab99bd..53aac8b8ed6b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -704,6 +704,10 @@ enum nft_payload_attributes { }; #define NFTA_PAYLOAD_MAX (__NFTA_PAYLOAD_MAX - 1) +enum nft_exthdr_flags { + NFT_EXTHDR_F_PRESENT = (1 << 0), +}; + /** * enum nft_exthdr_attributes - nf_tables IPv6 extension header expression netlink attributes * @@ -711,6 +715,7 @@ enum nft_payload_attributes { * @NFTA_EXTHDR_TYPE: extension header type (NLA_U8) * @NFTA_EXTHDR_OFFSET: extension header offset (NLA_U32) * @NFTA_EXTHDR_LEN: extension header length (NLA_U32) + * @NFTA_EXTHDR_FLAGS: extension header flags (NLA_U32) */ enum nft_exthdr_attributes { NFTA_EXTHDR_UNSPEC, @@ -718,6 +723,7 @@ enum nft_exthdr_attributes { NFTA_EXTHDR_TYPE, NFTA_EXTHDR_OFFSET, NFTA_EXTHDR_LEN, + NFTA_EXTHDR_FLAGS, __NFTA_EXTHDR_MAX }; #define NFTA_EXTHDR_MAX (__NFTA_EXTHDR_MAX - 1) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 47beb3abcc9d..a89e5ab150db 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -23,6 +23,7 @@ struct nft_exthdr { u8 offset; u8 len; enum nft_registers dreg:8; + u8 flags; }; static void nft_exthdr_eval(const struct nft_expr *expr, @@ -35,8 +36,12 @@ static void nft_exthdr_eval(const struct nft_expr *expr, int err; err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); - if (err < 0) + if (priv->flags & NFT_EXTHDR_F_PRESENT) { + *dest = (err >= 0); + return; + } else if (err < 0) { goto err; + } offset += priv->offset; dest[priv->len / NFT_REG32_SIZE] = 0; @@ -52,6 +57,7 @@ static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 }, [NFTA_EXTHDR_OFFSET] = { .type = NLA_U32 }, [NFTA_EXTHDR_LEN] = { .type = NLA_U32 }, + [NFTA_EXTHDR_FLAGS] = { .type = NLA_U32 }, }; static int nft_exthdr_init(const struct nft_ctx *ctx, @@ -59,7 +65,7 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_exthdr *priv = nft_expr_priv(expr); - u32 offset, len; + u32 offset, len, flags = 0; int err; if (tb[NFTA_EXTHDR_DREG] == NULL || @@ -76,10 +82,20 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, if (err < 0) return err; + if (tb[NFTA_EXTHDR_FLAGS]) { + err = nft_parse_u32_check(tb[NFTA_EXTHDR_FLAGS], U8_MAX, &flags); + if (err < 0) + return err; + + if (flags & ~NFT_EXTHDR_F_PRESENT) + return -EINVAL; + } + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); priv->offset = offset; priv->len = len; priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); + priv->flags = flags; return nft_validate_register_store(ctx, priv->dreg, NULL, NFT_DATA_VALUE, priv->len); @@ -97,6 +113,8 @@ static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; if (nla_put_be32(skb, NFTA_EXTHDR_LEN, htonl(priv->len))) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_EXTHDR_FLAGS, htonl(priv->flags))) + goto nla_put_failure; return 0; nla_put_failure: -- cgit v1.3-14-g43fede From ab23821f7ecfb022a4aec78fb6f4fd0f6aa1ccab Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 3 Feb 2017 13:35:48 +0100 Subject: netfilter: nft_ct: add zone id get support Just like with counters the direction attribute is optional. We set priv->dir to MAX unconditionally to avoid duplicating the assignment for all keys with optional direction. For keys where direction is mandatory, existing code already returns an error. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_ct.c | 22 +++++++++++++++++++--- 2 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 53aac8b8ed6b..3e60ed78c538 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -870,6 +870,7 @@ enum nft_rt_attributes { * @NFT_CT_PKTS: conntrack packets * @NFT_CT_BYTES: conntrack bytes * @NFT_CT_AVGPKT: conntrack average bytes per packet + * @NFT_CT_ZONE: conntrack zone */ enum nft_ct_keys { NFT_CT_STATE, @@ -889,6 +890,7 @@ enum nft_ct_keys { NFT_CT_PKTS, NFT_CT_BYTES, NFT_CT_AVGPKT, + NFT_CT_ZONE, }; /** diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 66a2377510e1..5bd4cdfdcda5 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -151,6 +151,18 @@ static void nft_ct_get_eval(const struct nft_expr *expr, case NFT_CT_PROTOCOL: *dest = nf_ct_protonum(ct); return; +#ifdef CONFIG_NF_CONNTRACK_ZONES + case NFT_CT_ZONE: { + const struct nf_conntrack_zone *zone = nf_ct_zone(ct); + + if (priv->dir < IP_CT_DIR_MAX) + *dest = nf_ct_zone_id(zone, priv->dir); + else + *dest = zone->id; + + return; + } +#endif default: break; } @@ -266,6 +278,7 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, int err; priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); + priv->dir = IP_CT_DIR_MAX; switch (priv->key) { case NFT_CT_DIRECTION: if (tb[NFTA_CT_DIRECTION] != NULL) @@ -333,11 +346,13 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, case NFT_CT_BYTES: case NFT_CT_PKTS: case NFT_CT_AVGPKT: - /* no direction? return sum of original + reply */ - if (tb[NFTA_CT_DIRECTION] == NULL) - priv->dir = IP_CT_DIR_MAX; len = sizeof(u64); break; +#ifdef CONFIG_NF_CONNTRACK_ZONES + case NFT_CT_ZONE: + len = sizeof(u16); + break; +#endif default: return -EOPNOTSUPP; } @@ -465,6 +480,7 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) case NFT_CT_BYTES: case NFT_CT_PKTS: case NFT_CT_AVGPKT: + case NFT_CT_ZONE: if (priv->dir < IP_CT_DIR_MAX && nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir)) goto nla_put_failure; -- cgit v1.3-14-g43fede From 935b7f643018878bd9d4193eea8b575aff736b9b Mon Sep 17 00:00:00 2001 From: Manuel Messner Date: Tue, 7 Feb 2017 03:14:53 +0100 Subject: netfilter: nft_exthdr: add TCP option matching This patch implements the kernel side of the TCP option patch. Signed-off-by: Manuel Messner Reviewed-by: Florian Westphal Acked-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 17 ++++- net/netfilter/Kconfig | 4 +- net/netfilter/nft_exthdr.c | 119 +++++++++++++++++++++++++++---- 3 files changed, 124 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 3e60ed78c538..207951516ede 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -709,13 +709,27 @@ enum nft_exthdr_flags { }; /** - * enum nft_exthdr_attributes - nf_tables IPv6 extension header expression netlink attributes + * enum nft_exthdr_op - nf_tables match options + * + * @NFT_EXTHDR_OP_IPV6: match against ipv6 extension headers + * @NFT_EXTHDR_OP_TCP: match against tcp options + */ +enum nft_exthdr_op { + NFT_EXTHDR_OP_IPV6, + NFT_EXTHDR_OP_TCPOPT, + __NFT_EXTHDR_OP_MAX +}; +#define NFT_EXTHDR_OP_MAX (__NFT_EXTHDR_OP_MAX - 1) + +/** + * enum nft_exthdr_attributes - nf_tables extension header expression netlink attributes * * @NFTA_EXTHDR_DREG: destination register (NLA_U32: nft_registers) * @NFTA_EXTHDR_TYPE: extension header type (NLA_U8) * @NFTA_EXTHDR_OFFSET: extension header offset (NLA_U32) * @NFTA_EXTHDR_LEN: extension header length (NLA_U32) * @NFTA_EXTHDR_FLAGS: extension header flags (NLA_U32) + * @NFTA_EXTHDR_OP: option match type (NLA_U8) */ enum nft_exthdr_attributes { NFTA_EXTHDR_UNSPEC, @@ -724,6 +738,7 @@ enum nft_exthdr_attributes { NFTA_EXTHDR_OFFSET, NFTA_EXTHDR_LEN, NFTA_EXTHDR_FLAGS, + NFTA_EXTHDR_OP, __NFTA_EXTHDR_MAX }; #define NFTA_EXTHDR_MAX (__NFTA_EXTHDR_MAX - 1) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index ea479ed43373..9b28864cc36a 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -467,10 +467,10 @@ config NF_TABLES_NETDEV This option enables support for the "netdev" table. config NFT_EXTHDR - tristate "Netfilter nf_tables IPv6 exthdr module" + tristate "Netfilter nf_tables exthdr module" help This option adds the "exthdr" expression that you can use to match - IPv6 extension headers. + IPv6 extension headers and tcp options. config NFT_META tristate "Netfilter nf_tables meta module" diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a89e5ab150db..c308920b194c 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -15,20 +15,29 @@ #include #include #include -// FIXME: -#include +#include struct nft_exthdr { u8 type; u8 offset; u8 len; + u8 op; enum nft_registers dreg:8; u8 flags; }; -static void nft_exthdr_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static unsigned int optlen(const u8 *opt, unsigned int offset) +{ + /* Beware zero-length options: make finite progress */ + if (opt[offset] <= TCPOPT_NOP || opt[offset + 1] == 0) + return 1; + else + return opt[offset + 1]; +} + +static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { struct nft_exthdr *priv = nft_expr_priv(expr); u32 *dest = ®s->data[priv->dreg]; @@ -52,6 +61,53 @@ err: regs->verdict.code = NFT_BREAK; } +static void nft_exthdr_tcp_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + u8 buff[sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE]; + struct nft_exthdr *priv = nft_expr_priv(expr); + unsigned int i, optl, tcphdr_len, offset; + u32 *dest = ®s->data[priv->dreg]; + struct tcphdr *tcph; + u8 *opt; + + if (!pkt->tprot_set || pkt->tprot != IPPROTO_TCP) + goto err; + + tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, sizeof(*tcph), buff); + if (!tcph) + goto err; + + tcphdr_len = __tcp_hdrlen(tcph); + if (tcphdr_len < sizeof(*tcph)) + goto err; + + tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, tcphdr_len, buff); + if (!tcph) + goto err; + + opt = (u8 *)tcph; + for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) { + optl = optlen(opt, i); + + if (priv->type != opt[i]) + continue; + + if (i + optl > tcphdr_len || priv->len + priv->offset > optl) + goto err; + + offset = i + priv->offset; + dest[priv->len / NFT_REG32_SIZE] = 0; + memcpy(dest, opt + offset, priv->len); + + return; + } + +err: + regs->verdict.code = NFT_BREAK; +} + static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_DREG] = { .type = NLA_U32 }, [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 }, @@ -65,13 +121,13 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_exthdr *priv = nft_expr_priv(expr); - u32 offset, len, flags = 0; + u32 offset, len, flags = 0, op = NFT_EXTHDR_OP_IPV6; int err; - if (tb[NFTA_EXTHDR_DREG] == NULL || - tb[NFTA_EXTHDR_TYPE] == NULL || - tb[NFTA_EXTHDR_OFFSET] == NULL || - tb[NFTA_EXTHDR_LEN] == NULL) + if (!tb[NFTA_EXTHDR_DREG] || + !tb[NFTA_EXTHDR_TYPE] || + !tb[NFTA_EXTHDR_OFFSET] || + !tb[NFTA_EXTHDR_LEN]) return -EINVAL; err = nft_parse_u32_check(tb[NFTA_EXTHDR_OFFSET], U8_MAX, &offset); @@ -91,11 +147,18 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, return -EINVAL; } + if (tb[NFTA_EXTHDR_OP]) { + err = nft_parse_u32_check(tb[NFTA_EXTHDR_OP], U8_MAX, &op); + if (err < 0) + return err; + } + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); priv->offset = offset; priv->len = len; priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); priv->flags = flags; + priv->op = op; return nft_validate_register_store(ctx, priv->dreg, NULL, NFT_DATA_VALUE, priv->len); @@ -115,6 +178,8 @@ static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; if (nla_put_be32(skb, NFTA_EXTHDR_FLAGS, htonl(priv->flags))) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_EXTHDR_OP, htonl(priv->op))) + goto nla_put_failure; return 0; nla_put_failure: @@ -122,17 +187,45 @@ nla_put_failure: } static struct nft_expr_type nft_exthdr_type; -static const struct nft_expr_ops nft_exthdr_ops = { +static const struct nft_expr_ops nft_exthdr_ipv6_ops = { + .type = &nft_exthdr_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), + .eval = nft_exthdr_ipv6_eval, + .init = nft_exthdr_init, + .dump = nft_exthdr_dump, +}; + +static const struct nft_expr_ops nft_exthdr_tcp_ops = { .type = &nft_exthdr_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), - .eval = nft_exthdr_eval, + .eval = nft_exthdr_tcp_eval, .init = nft_exthdr_init, .dump = nft_exthdr_dump, }; +static const struct nft_expr_ops * +nft_exthdr_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + u32 op; + + if (!tb[NFTA_EXTHDR_OP]) + return &nft_exthdr_ipv6_ops; + + op = ntohl(nla_get_u32(tb[NFTA_EXTHDR_OP])); + switch (op) { + case NFT_EXTHDR_OP_TCPOPT: + return &nft_exthdr_tcp_ops; + case NFT_EXTHDR_OP_IPV6: + return &nft_exthdr_ipv6_ops; + } + + return ERR_PTR(-EOPNOTSUPP); +} + static struct nft_expr_type nft_exthdr_type __read_mostly = { .name = "exthdr", - .ops = &nft_exthdr_ops, + .select_ops = &nft_exthdr_select_ops, .policy = nft_exthdr_policy, .maxattr = NFTA_EXTHDR_MAX, .owner = THIS_MODULE, -- cgit v1.3-14-g43fede From 8585989d146c61dd073d2135c5bb11d0f979d576 Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Wed, 8 Feb 2017 15:00:34 +0200 Subject: cfg80211: fix NAN bands definition The nl80211_nan_dual_band_conf enumeration doesn't make much sense. The default value is assigned to a bit, which makes it weird if the default bit and other bits are set at the same time. To improve this, get rid of NL80211_NAN_BAND_DEFAULT and add a wiphy configuration to let the drivers define which bands are supported. This is exposed to the userspace, which then can make a decision on which band(s) to use. Additionally, rename all "dual_band" elements to "bands", to make things clearer. Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 18 ++++++++++---- include/uapi/linux/nl80211.h | 57 ++++++++++++++++++++------------------------ net/mac80211/cfg.c | 4 ++-- net/mac80211/trace.h | 16 ++++++------- net/wireless/core.c | 3 ++- net/wireless/nl80211.c | 35 ++++++++++++++++++++------- net/wireless/trace.h | 16 ++++++------- 7 files changed, 86 insertions(+), 63 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a2c18b53e053..c92dc03c8528 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5,7 +5,7 @@ * * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright 2015-2016 Intel Deutschland GmbH + * Copyright 2015-2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2416,11 +2416,13 @@ struct cfg80211_qos_map { * This struct defines NAN configuration parameters * * @master_pref: master preference (1 - 255) - * @dual: dual band operation mode, see &enum nl80211_nan_dual_band_conf + * @bands: operating bands, a bitmap of &enum nl80211_band values. + * For instance, for NL80211_BAND_2GHZ, bit 0 would be set + * (i.e. BIT(NL80211_BAND_2GHZ)). */ struct cfg80211_nan_conf { u8 master_pref; - u8 dual; + u8 bands; }; /** @@ -2428,11 +2430,11 @@ struct cfg80211_nan_conf { * configuration * * @CFG80211_NAN_CONF_CHANGED_PREF: master preference - * @CFG80211_NAN_CONF_CHANGED_DUAL: dual band operation + * @CFG80211_NAN_CONF_CHANGED_BANDS: operating bands */ enum cfg80211_nan_conf_changes { CFG80211_NAN_CONF_CHANGED_PREF = BIT(0), - CFG80211_NAN_CONF_CHANGED_DUAL = BIT(1), + CFG80211_NAN_CONF_CHANGED_BANDS = BIT(1), }; /** @@ -3596,6 +3598,10 @@ struct wiphy_iftype_ext_capab { * attribute indices defined in &enum nl80211_bss_select_attr. * * @cookie_counter: unique generic cookie counter, used to identify objects. + * @nan_supported_bands: bands supported by the device in NAN mode, a + * bitmap of &enum nl80211_band values. For instance, for + * NL80211_BAND_2GHZ, bit 0 would be set + * (i.e. BIT(NL80211_BAND_2GHZ)). */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -3727,6 +3733,8 @@ struct wiphy { u64 cookie_counter; + u8 nan_supported_bands; + char priv[0] __aligned(NETDEV_ALIGN); }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index cd547b864595..5ed257c4cd4e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -10,7 +10,7 @@ * Copyright 2008, 2009 Luis R. Rodriguez * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe - * Copyright 2015 Intel Deutschland GmbH + * Copyright 2015-2017 Intel Deutschland GmbH * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -854,12 +854,15 @@ * cfg80211_scan_done(). * * @NL80211_CMD_START_NAN: Start NAN operation, identified by its - * %NL80211_ATTR_WDEV interface. This interface must have been previously - * created with %NL80211_CMD_NEW_INTERFACE. After it has been started, the - * NAN interface will create or join a cluster. This command must have a - * valid %NL80211_ATTR_NAN_MASTER_PREF attribute and optional - * %NL80211_ATTR_NAN_DUAL attributes. - * After this command NAN functions can be added. + * %NL80211_ATTR_WDEV interface. This interface must have been + * previously created with %NL80211_CMD_NEW_INTERFACE. After it + * has been started, the NAN interface will create or join a + * cluster. This command must have a valid + * %NL80211_ATTR_NAN_MASTER_PREF attribute and optional + * %NL80211_ATTR_BANDS attributes. If %NL80211_ATTR_BANDS is + * omitted or set to 0, it means don't-care and the device will + * decide what to use. After this command NAN functions can be + * added. * @NL80211_CMD_STOP_NAN: Stop the NAN operation, identified by * its %NL80211_ATTR_WDEV interface. * @NL80211_CMD_ADD_NAN_FUNCTION: Add a NAN function. The function is defined @@ -880,10 +883,14 @@ * This command is also used as a notification sent when a NAN function is * terminated. This will contain a %NL80211_ATTR_NAN_FUNC_INST_ID * and %NL80211_ATTR_COOKIE attributes. - * @NL80211_CMD_CHANGE_NAN_CONFIG: Change current NAN configuration. NAN - * must be operational (%NL80211_CMD_START_NAN was executed). - * It must contain at least one of the following attributes: - * %NL80211_ATTR_NAN_MASTER_PREF, %NL80211_ATTR_NAN_DUAL. + * @NL80211_CMD_CHANGE_NAN_CONFIG: Change current NAN + * configuration. NAN must be operational (%NL80211_CMD_START_NAN + * was executed). It must contain at least one of the following + * attributes: %NL80211_ATTR_NAN_MASTER_PREF, + * %NL80211_ATTR_BANDS. If %NL80211_ATTR_BANDS is omitted, the + * current configuration is not changed. If it is present but + * set to zero, the configuration is changed to don't-care + * (i.e. the device can decide what to do). * @NL80211_CMD_NAN_FUNC_MATCH: Notification sent when a match is reported. * This will contain a %NL80211_ATTR_NAN_MATCH nested attribute and * %NL80211_ATTR_COOKIE. @@ -1963,10 +1970,13 @@ enum nl80211_commands { * %NL80211_CMD_CHANGE_NAN_CONFIG. Its type is u8 and it can't be 0. * Also, values 1 and 255 are reserved for certification purposes and * should not be used during a normal device operation. - * @NL80211_ATTR_NAN_DUAL: NAN dual band operation config (see - * &enum nl80211_nan_dual_band_conf). This attribute is used with - * %NL80211_CMD_START_NAN and optionally with - * %NL80211_CMD_CHANGE_NAN_CONFIG. + * @NL80211_ATTR_BANDS: operating bands configuration. This is a u32 + * bitmask of BIT(NL80211_BAND_*) as described in %enum + * nl80211_band. For instance, for NL80211_BAND_2GHZ, bit 0 + * would be set. This attribute is used with + * %NL80211_CMD_START_NAN and %NL80211_CMD_CHANGE_NAN_CONFIG, and + * it is optional. If no bands are set, it means don't-care and + * the device will decide what to use. * @NL80211_ATTR_NAN_FUNC: a function that can be added to NAN. See * &enum nl80211_nan_func_attributes for description of this nested * attribute. @@ -2397,7 +2407,7 @@ enum nl80211_attrs { NL80211_ATTR_MESH_PEER_AID, NL80211_ATTR_NAN_MASTER_PREF, - NL80211_ATTR_NAN_DUAL, + NL80211_ATTR_BANDS, NL80211_ATTR_NAN_FUNC, NL80211_ATTR_NAN_MATCH, @@ -5070,21 +5080,6 @@ enum nl80211_bss_select_attr { NL80211_BSS_SELECT_ATTR_MAX = __NL80211_BSS_SELECT_ATTR_AFTER_LAST - 1 }; -/** - * enum nl80211_nan_dual_band_conf - NAN dual band configuration - * - * Defines the NAN dual band mode of operation - * - * @NL80211_NAN_BAND_DEFAULT: device default mode - * @NL80211_NAN_BAND_2GHZ: 2.4GHz mode - * @NL80211_NAN_BAND_5GHZ: 5GHz mode - */ -enum nl80211_nan_dual_band_conf { - NL80211_NAN_BAND_DEFAULT = 1 << 0, - NL80211_NAN_BAND_2GHZ = 1 << 1, - NL80211_NAN_BAND_5GHZ = 1 << 2, -}; - /** * enum nl80211_nan_function_type - NAN function type * diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index a0be2f6cd121..ac879bb17870 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -208,8 +208,8 @@ static int ieee80211_nan_change_conf(struct wiphy *wiphy, if (changes & CFG80211_NAN_CONF_CHANGED_PREF) new_conf.master_pref = conf->master_pref; - if (changes & CFG80211_NAN_CONF_CHANGED_DUAL) - new_conf.dual = conf->dual; + if (changes & CFG80211_NAN_CONF_CHANGED_BANDS) + new_conf.bands = conf->bands; ret = drv_nan_change_conf(sdata->local, sdata, &new_conf, changes); if (!ret) diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index f78d9f4f8711..0d645bc148d0 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -1736,21 +1736,21 @@ TRACE_EVENT(drv_start_nan, LOCAL_ENTRY VIF_ENTRY __field(u8, master_pref) - __field(u8, dual) + __field(u8, bands) ), TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; __entry->master_pref = conf->master_pref; - __entry->dual = conf->dual; + __entry->bands = conf->bands; ), TP_printk( LOCAL_PR_FMT VIF_PR_FMT - ", master preference: %u, dual: %d", + ", master preference: %u, bands: 0x%0x", LOCAL_PR_ARG, VIF_PR_ARG, __entry->master_pref, - __entry->dual + __entry->bands ) ); @@ -1787,7 +1787,7 @@ TRACE_EVENT(drv_nan_change_conf, LOCAL_ENTRY VIF_ENTRY __field(u8, master_pref) - __field(u8, dual) + __field(u8, bands) __field(u32, changes) ), @@ -1795,15 +1795,15 @@ TRACE_EVENT(drv_nan_change_conf, LOCAL_ASSIGN; VIF_ASSIGN; __entry->master_pref = conf->master_pref; - __entry->dual = conf->dual; + __entry->bands = conf->bands; __entry->changes = changes; ), TP_printk( LOCAL_PR_FMT VIF_PR_FMT - ", master preference: %u, dual: %d, changes: 0x%x", + ", master preference: %u, bands: 0x%0x, changes: 0x%x", LOCAL_PR_ARG, VIF_PR_ARG, __entry->master_pref, - __entry->dual, __entry->changes + __entry->bands, __entry->changes ) ); diff --git a/net/wireless/core.c b/net/wireless/core.c index 903fc419217a..e55e05bc4805 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -626,7 +626,8 @@ int wiphy_register(struct wiphy *wiphy) if (WARN_ON((wiphy->interface_modes & BIT(NL80211_IFTYPE_NAN)) && (!rdev->ops->start_nan || !rdev->ops->stop_nan || - !rdev->ops->add_nan_func || !rdev->ops->del_nan_func))) + !rdev->ops->add_nan_func || !rdev->ops->del_nan_func || + !(wiphy->nan_supported_bands & BIT(NL80211_BAND_2GHZ))))) return -EINVAL; #ifndef CONFIG_WIRELESS_WDS diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9d738f75bd4e..b5f755b3ac5d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -398,7 +398,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { }, [NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR] = { .len = ETH_ALEN }, [NL80211_ATTR_NAN_MASTER_PREF] = { .type = NLA_U8 }, - [NL80211_ATTR_NAN_DUAL] = { .type = NLA_U8 }, + [NL80211_ATTR_BANDS] = { .type = NLA_U32 }, [NL80211_ATTR_NAN_FUNC] = { .type = NLA_NESTED }, [NL80211_ATTR_FILS_KEK] = { .type = NLA_BINARY, .len = FILS_MAX_KEK_LEN }, @@ -1886,6 +1886,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, } } + if (nla_put_u32(msg, NL80211_ATTR_BANDS, + rdev->wiphy.nan_supported_bands)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -10777,15 +10781,22 @@ static int nl80211_start_nan(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL80211_ATTR_NAN_MASTER_PREF]) return -EINVAL; - if (!info->attrs[NL80211_ATTR_NAN_DUAL]) - return -EINVAL; - conf.master_pref = nla_get_u8(info->attrs[NL80211_ATTR_NAN_MASTER_PREF]); if (!conf.master_pref) return -EINVAL; - conf.dual = nla_get_u8(info->attrs[NL80211_ATTR_NAN_DUAL]); + if (info->attrs[NL80211_ATTR_BANDS]) { + u32 bands = nla_get_u32(info->attrs[NL80211_ATTR_BANDS]); + + if (bands & ~(u32)wdev->wiphy->nan_supported_bands) + return -EOPNOTSUPP; + + if (bands && !(bands & BIT(NL80211_BAND_2GHZ))) + return -EINVAL; + + conf.bands = bands; + } err = rdev_start_nan(rdev, wdev, &conf); if (err) @@ -11150,9 +11161,17 @@ static int nl80211_nan_change_config(struct sk_buff *skb, changed |= CFG80211_NAN_CONF_CHANGED_PREF; } - if (info->attrs[NL80211_ATTR_NAN_DUAL]) { - conf.dual = nla_get_u8(info->attrs[NL80211_ATTR_NAN_DUAL]); - changed |= CFG80211_NAN_CONF_CHANGED_DUAL; + if (info->attrs[NL80211_ATTR_BANDS]) { + u32 bands = nla_get_u32(info->attrs[NL80211_ATTR_BANDS]); + + if (bands & ~(u32)wdev->wiphy->nan_supported_bands) + return -EOPNOTSUPP; + + if (bands && !(bands & BIT(NL80211_BAND_2GHZ))) + return -EINVAL; + + conf.bands = bands; + changed |= CFG80211_NAN_CONF_CHANGED_BANDS; } if (!changed) diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 2419c390f150..776e80cef9b4 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1915,18 +1915,18 @@ TRACE_EVENT(rdev_start_nan, WIPHY_ENTRY WDEV_ENTRY __field(u8, master_pref) - __field(u8, dual); + __field(u8, bands); ), TP_fast_assign( WIPHY_ASSIGN; WDEV_ASSIGN; __entry->master_pref = conf->master_pref; - __entry->dual = conf->dual; + __entry->bands = conf->bands; ), TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT - ", master preference: %u, dual: %d", + ", master preference: %u, bands: 0x%0x", WIPHY_PR_ARG, WDEV_PR_ARG, __entry->master_pref, - __entry->dual) + __entry->bands) ); TRACE_EVENT(rdev_nan_change_conf, @@ -1937,20 +1937,20 @@ TRACE_EVENT(rdev_nan_change_conf, WIPHY_ENTRY WDEV_ENTRY __field(u8, master_pref) - __field(u8, dual); + __field(u8, bands); __field(u32, changes); ), TP_fast_assign( WIPHY_ASSIGN; WDEV_ASSIGN; __entry->master_pref = conf->master_pref; - __entry->dual = conf->dual; + __entry->bands = conf->bands; __entry->changes = changes; ), TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT - ", master preference: %u, dual: %d, changes: %x", + ", master preference: %u, bands: 0x%0x, changes: %x", WIPHY_PR_ARG, WDEV_PR_ARG, __entry->master_pref, - __entry->dual, __entry->changes) + __entry->bands, __entry->changes) ); DEFINE_EVENT(wiphy_wdev_evt, rdev_stop_nan, -- cgit v1.3-14-g43fede From a92ce1a42dde1caaee4afae67531e3e7acecf6e4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 9 Feb 2017 01:18:18 +0800 Subject: sctp: implement sender-side procedures for SSN/TSN Reset Request Parameter This patch is to implement Sender-Side Procedures for the SSN/TSN Reset Request Parameter descibed in rfc6525 section 5.1.4. It is also to add sockopt SCTP_RESET_ASSOC in rfc6525 section 6.3.3 for users. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 1 + include/uapi/linux/sctp.h | 1 + net/sctp/socket.c | 29 +++++++++++++++++++++++++++++ net/sctp/stream.c | 40 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 71 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 480b65a24aff..b60ca14068d8 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -198,6 +198,7 @@ int sctp_offload_init(void); */ int sctp_send_reset_streams(struct sctp_association *asoc, struct sctp_reset_streams *params); +int sctp_send_reset_assoc(struct sctp_association *asoc); /* * Module global variables diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 03c27cefffb1..c0bd8c3d565a 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -117,6 +117,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_PR_ASSOC_STATUS 115 #define SCTP_ENABLE_STREAM_RESET 118 #define SCTP_RESET_STREAMS 119 +#define SCTP_RESET_ASSOC 120 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a8b4252fe084..45a7c417eb7f 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3818,6 +3818,32 @@ out: return retval; } +static int sctp_setsockopt_reset_assoc(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_association *asoc; + sctp_assoc_t associd; + int retval = -EINVAL; + + if (optlen != sizeof(associd)) + goto out; + + if (copy_from_user(&associd, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + asoc = sctp_id2assoc(sk, associd); + if (!asoc) + goto out; + + retval = sctp_send_reset_assoc(asoc); + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -3990,6 +4016,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_RESET_STREAMS: retval = sctp_setsockopt_reset_streams(sk, optval, optlen); break; + case SCTP_RESET_ASSOC: + retval = sctp_setsockopt_reset_assoc(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 6a686e330c57..53e49fc2f0a3 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -177,3 +177,43 @@ int sctp_send_reset_streams(struct sctp_association *asoc, out: return retval; } + +int sctp_send_reset_assoc(struct sctp_association *asoc) +{ + struct sctp_chunk *chunk = NULL; + int retval; + __u16 i; + + if (!asoc->peer.reconf_capable || + !(asoc->strreset_enable & SCTP_ENABLE_RESET_ASSOC_REQ)) + return -ENOPROTOOPT; + + if (asoc->strreset_outstanding) + return -EINPROGRESS; + + chunk = sctp_make_strreset_tsnreq(asoc); + if (!chunk) + return -ENOMEM; + + /* Block further xmit of data until this request is completed */ + for (i = 0; i < asoc->stream->outcnt; i++) + asoc->stream->out[i].state = SCTP_STREAM_CLOSED; + + asoc->strreset_chunk = chunk; + sctp_chunk_hold(asoc->strreset_chunk); + + retval = sctp_send_reconf(asoc, chunk); + if (retval) { + sctp_chunk_put(asoc->strreset_chunk); + asoc->strreset_chunk = NULL; + + for (i = 0; i < asoc->stream->outcnt; i++) + asoc->stream->out[i].state = SCTP_STREAM_OPEN; + + return retval; + } + + asoc->strreset_outstanding = 1; + + return 0; +} -- cgit v1.3-14-g43fede From 242bd2d519d7194633e309286ba7ba29a1ad63e8 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 9 Feb 2017 01:18:20 +0800 Subject: sctp: implement sender-side procedures for Add Incoming/Outgoing Streams Request Parameter This patch is to implement Sender-Side Procedures for the Add Outgoing and Incoming Streams Request Parameter described in rfc6525 section 5.1.5-5.1.6. It is also to add sockopt SCTP_ADD_STREAMS in rfc6525 section 6.3.4 for users. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 2 ++ include/uapi/linux/sctp.h | 7 +++++ net/sctp/socket.c | 29 ++++++++++++++++++ net/sctp/stream.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 115 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index b60ca14068d8..6dfc5536a3e6 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -199,6 +199,8 @@ int sctp_offload_init(void); int sctp_send_reset_streams(struct sctp_association *asoc, struct sctp_reset_streams *params); int sctp_send_reset_assoc(struct sctp_association *asoc); +int sctp_send_add_streams(struct sctp_association *asoc, + struct sctp_add_streams *params); /* * Module global variables diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index c0bd8c3d565a..a91a9cccbae6 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -118,6 +118,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_ENABLE_STREAM_RESET 118 #define SCTP_RESET_STREAMS 119 #define SCTP_RESET_ASSOC 120 +#define SCTP_ADD_STREAMS 121 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -1027,4 +1028,10 @@ struct sctp_reset_streams { uint16_t srs_stream_list[]; /* list if srs_num_streams is not 0 */ }; +struct sctp_add_streams { + sctp_assoc_t sas_assoc_id; + uint16_t sas_instrms; + uint16_t sas_outstrms; +}; + #endif /* _UAPI_SCTP_H */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 45a7c417eb7f..75f35cea4371 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3844,6 +3844,32 @@ out: return retval; } +static int sctp_setsockopt_add_streams(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_add_streams params; + int retval = -EINVAL; + + if (optlen != sizeof(params)) + goto out; + + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + asoc = sctp_id2assoc(sk, params.sas_assoc_id); + if (!asoc) + goto out; + + retval = sctp_send_add_streams(asoc, ¶ms); + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4019,6 +4045,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_RESET_ASSOC: retval = sctp_setsockopt_reset_assoc(sk, optval, optlen); break; + case SCTP_ADD_STREAMS: + retval = sctp_setsockopt_add_streams(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 53e49fc2f0a3..eb02490245ba 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -217,3 +217,80 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) return 0; } + +int sctp_send_add_streams(struct sctp_association *asoc, + struct sctp_add_streams *params) +{ + struct sctp_stream *stream = asoc->stream; + struct sctp_chunk *chunk = NULL; + int retval = -ENOMEM; + __u32 outcnt, incnt; + __u16 out, in; + + if (!asoc->peer.reconf_capable || + !(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ)) { + retval = -ENOPROTOOPT; + goto out; + } + + if (asoc->strreset_outstanding) { + retval = -EINPROGRESS; + goto out; + } + + out = params->sas_outstrms; + in = params->sas_instrms; + outcnt = stream->outcnt + out; + incnt = stream->incnt + in; + if (outcnt > SCTP_MAX_STREAM || incnt > SCTP_MAX_STREAM || + (!out && !in)) { + retval = -EINVAL; + goto out; + } + + if (out) { + struct sctp_stream_out *streamout; + + streamout = krealloc(stream->out, outcnt * sizeof(*streamout), + GFP_KERNEL); + if (!streamout) + goto out; + + memset(streamout + stream->outcnt, 0, out * sizeof(*streamout)); + stream->out = streamout; + } + + if (in) { + struct sctp_stream_in *streamin; + + streamin = krealloc(stream->in, incnt * sizeof(*streamin), + GFP_KERNEL); + if (!streamin) + goto out; + + memset(streamin + stream->incnt, 0, in * sizeof(*streamin)); + stream->in = streamin; + } + + chunk = sctp_make_strreset_addstrm(asoc, out, in); + if (!chunk) + goto out; + + asoc->strreset_chunk = chunk; + sctp_chunk_hold(asoc->strreset_chunk); + + retval = sctp_send_reconf(asoc, chunk); + if (retval) { + sctp_chunk_put(asoc->strreset_chunk); + asoc->strreset_chunk = NULL; + goto out; + } + + stream->incnt = incnt; + stream->outcnt = outcnt; + + asoc->strreset_outstanding = !!out + !!in; + +out: + return retval; +} -- cgit v1.3-14-g43fede From cb80d58fae76d8ea93555149b2b16e19b89a1f4f Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Thu, 9 Feb 2017 11:21:55 -0800 Subject: openvswitch: Unionize ovs_key_ct_label with a u32 array. Make the array of labels in struct ovs_key_ct_label an union, adding a u32 array of the same byte size as the existing u8 array. It is faster to loop through the labels 32 bits at the time, which is also the alignment of netlink attributes. Signed-off-by: Jarno Rajahalme Acked-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 8 ++++++-- net/openvswitch/conntrack.c | 15 ++++++++------- 2 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 375d812fea36..96aee34ef55f 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -446,9 +446,13 @@ struct ovs_key_nd { __u8 nd_tll[ETH_ALEN]; }; -#define OVS_CT_LABELS_LEN 16 +#define OVS_CT_LABELS_LEN_32 4 +#define OVS_CT_LABELS_LEN (OVS_CT_LABELS_LEN_32 * sizeof(__u32)) struct ovs_key_ct_labels { - __u8 ct_labels[OVS_CT_LABELS_LEN]; + union { + __u8 ct_labels[OVS_CT_LABELS_LEN]; + __u32 ct_labels_32[OVS_CT_LABELS_LEN_32]; + }; }; /* OVS_KEY_ATTR_CT_STATE flags */ diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index a6ff374d57d3..f23934ccce20 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -281,20 +281,21 @@ static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key, /* Triggers a change event, which makes sense only for * confirmed connections. */ - int err = nf_connlabels_replace(ct, (u32 *)labels, (u32 *)mask, - OVS_CT_LABELS_LEN / sizeof(u32)); + int err = nf_connlabels_replace(ct, labels->ct_labels_32, + mask->ct_labels_32, + OVS_CT_LABELS_LEN_32); if (err) return err; } else { u32 *dst = (u32 *)cl->bits; - const u32 *msk = (const u32 *)mask->ct_labels; - const u32 *lbl = (const u32 *)labels->ct_labels; + const u32 *msk = mask->ct_labels_32; + const u32 *lbl = labels->ct_labels_32; int i; /* No-one else has access to the non-confirmed entry, copy * labels over, keeping any bits we are not explicitly setting. */ - for (i = 0; i < OVS_CT_LABELS_LEN / sizeof(u32); i++) + for (i = 0; i < OVS_CT_LABELS_LEN_32; i++) dst[i] = (dst[i] & ~msk[i]) | (lbl[i] & msk[i]); } @@ -866,8 +867,8 @@ static bool labels_nonzero(const struct ovs_key_ct_labels *labels) { size_t i; - for (i = 0; i < sizeof(*labels); i++) - if (labels->ct_labels[i]) + for (i = 0; i < OVS_CT_LABELS_LEN_32; i++) + if (labels->ct_labels_32[i]) return true; return false; -- cgit v1.3-14-g43fede From 9dd7f8907c3705dc7a7a375d1c6e30b06e6daffc Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Thu, 9 Feb 2017 11:21:59 -0800 Subject: openvswitch: Add original direction conntrack tuple to sw_flow_key. Add the fields of the conntrack original direction 5-tuple to struct sw_flow_key. The new fields are initially marked as non-existent, and are populated whenever a conntrack action is executed and either finds or generates a conntrack entry. This means that these fields exist for all packets that were not rejected by conntrack as untrackable. The original tuple fields in the sw_flow_key are filled from the original direction tuple of the conntrack entry relating to the current packet, or from the original direction tuple of the master conntrack entry, if the current conntrack entry has a master. Generally, expected connections of connections having an assigned helper (e.g., FTP), have a master conntrack entry. The main purpose of the new conntrack original tuple fields is to allow matching on them for policy decision purposes, with the premise that the admissibility of tracked connections reply packets (as well as original direction packets), and both direction packets of any related connections may be based on ACL rules applying to the master connection's original direction 5-tuple. This also makes it easier to make policy decisions when the actual packet headers might have been transformed by NAT, as the original direction 5-tuple represents the packet headers before any such transformation. When using the original direction 5-tuple the admissibility of return and/or related packets need not be based on the mere existence of a conntrack entry, allowing separation of admission policy from the established conntrack state. While existence of a conntrack entry is required for admission of the return or related packets, policy changes can render connections that were initially admitted to be rejected or dropped afterwards. If the admission of the return and related packets was based on mere conntrack state (e.g., connection being in an established state), a policy change that would make the connection rejected or dropped would need to find and delete all conntrack entries affected by such a change. When using the original direction 5-tuple matching the affected conntrack entries can be allowed to time out instead, as the established state of the connection would not need to be the basis for packet admission any more. It should be noted that the directionality of related connections may be the same or different than that of the master connection, and neither the original direction 5-tuple nor the conntrack state bits carry this information. If needed, the directionality of the master connection can be stored in master's conntrack mark or labels, which are automatically inherited by the expected related connections. The fact that neither ARP nor ND packets are trackable by conntrack allows mutual exclusion between ARP/ND and the new conntrack original tuple fields. Hence, the IP addresses are overlaid in union with ARP and ND fields. This allows the sw_flow_key to not grow much due to this patch, but it also means that we must be careful to never use the new key fields with ARP or ND packets. ARP is easy to distinguish and keep mutually exclusive based on the ethernet type, but ND being an ICMPv6 protocol requires a bit more attention. Signed-off-by: Jarno Rajahalme Acked-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 20 +++++++++- net/openvswitch/actions.c | 2 + net/openvswitch/conntrack.c | 86 +++++++++++++++++++++++++++++++++++++--- net/openvswitch/conntrack.h | 10 ++++- net/openvswitch/flow.c | 34 +++++++++++++--- net/openvswitch/flow.h | 49 ++++++++++++++++++----- net/openvswitch/flow_netlink.c | 85 +++++++++++++++++++++++++++++---------- net/openvswitch/flow_netlink.h | 7 +++- 8 files changed, 246 insertions(+), 47 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 96aee34ef55f..90af8b8e10f8 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -1,6 +1,6 @@ /* - * Copyright (c) 2007-2013 Nicira, Inc. + * Copyright (c) 2007-2017 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -331,6 +331,8 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_ZONE, /* u16 connection tracking zone. */ OVS_KEY_ATTR_CT_MARK, /* u32 connection tracking mark */ OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */ + OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */ + OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */ #ifdef __KERNEL__ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ @@ -472,6 +474,22 @@ struct ovs_key_ct_labels { #define OVS_CS_F_NAT_MASK (OVS_CS_F_SRC_NAT | OVS_CS_F_DST_NAT) +struct ovs_key_ct_tuple_ipv4 { + __be32 ipv4_src; + __be32 ipv4_dst; + __be16 src_port; + __be16 dst_port; + __u8 ipv4_proto; +}; + +struct ovs_key_ct_tuple_ipv6 { + __be32 ipv6_src[4]; + __be32 ipv6_dst[4]; + __be16 src_port; + __be16 dst_port; + __u8 ipv6_proto; +}; + /** * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. * @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index efa9a8858cc6..b1beb2b94ec7 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1074,6 +1074,8 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_ZONE: case OVS_KEY_ATTR_CT_MARK: case OVS_KEY_ATTR_CT_LABELS: + case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4: + case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6: err = -EINVAL; break; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index f989ccf38eab..bfd7606c8be1 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -147,6 +147,20 @@ static void ovs_ct_get_labels(const struct nf_conn *ct, memset(labels, 0, OVS_CT_LABELS_LEN); } +static void __ovs_ct_update_key_orig_tp(struct sw_flow_key *key, + const struct nf_conntrack_tuple *orig, + u8 icmp_proto) +{ + key->ct.orig_proto = orig->dst.protonum; + if (orig->dst.protonum == icmp_proto) { + key->ct.orig_tp.src = htons(orig->dst.u.icmp.type); + key->ct.orig_tp.dst = htons(orig->dst.u.icmp.code); + } else { + key->ct.orig_tp.src = orig->src.u.all; + key->ct.orig_tp.dst = orig->dst.u.all; + } +} + static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, const struct nf_conntrack_zone *zone, const struct nf_conn *ct) @@ -155,6 +169,35 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, key->ct.zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); ovs_ct_get_labels(ct, &key->ct.labels); + + if (ct) { + const struct nf_conntrack_tuple *orig; + + /* Use the master if we have one. */ + if (ct->master) + ct = ct->master; + orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + + /* IP version must match with the master connection. */ + if (key->eth.type == htons(ETH_P_IP) && + nf_ct_l3num(ct) == NFPROTO_IPV4) { + key->ipv4.ct_orig.src = orig->src.u3.ip; + key->ipv4.ct_orig.dst = orig->dst.u3.ip; + __ovs_ct_update_key_orig_tp(key, orig, IPPROTO_ICMP); + return; + } else if (key->eth.type == htons(ETH_P_IPV6) && + !sw_flow_key_is_nd(key) && + nf_ct_l3num(ct) == NFPROTO_IPV6) { + key->ipv6.ct_orig.src = orig->src.u3.in6; + key->ipv6.ct_orig.dst = orig->dst.u3.in6; + __ovs_ct_update_key_orig_tp(key, orig, NEXTHDR_ICMP); + return; + } + } + /* Clear 'ct.orig_proto' to mark the non-existence of conntrack + * original direction key fields. + */ + key->ct.orig_proto = 0; } /* Update 'key' based on skb->_nfct. If 'post_ct' is true, then OVS has @@ -208,24 +251,55 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) ovs_ct_update_key(skb, NULL, key, false, false); } -int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) +#define IN6_ADDR_INITIALIZER(ADDR) \ + { (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \ + (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] } + +int ovs_ct_put_key(const struct sw_flow_key *swkey, + const struct sw_flow_key *output, struct sk_buff *skb) { - if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) + if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct.state)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && - nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, key->ct.zone)) + nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct.zone)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && - nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, key->ct.mark)) + nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, output->ct.mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(key->ct.labels), - &key->ct.labels)) + nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(output->ct.labels), + &output->ct.labels)) return -EMSGSIZE; + if (swkey->ct.orig_proto) { + if (swkey->eth.type == htons(ETH_P_IP)) { + struct ovs_key_ct_tuple_ipv4 orig = { + output->ipv4.ct_orig.src, + output->ipv4.ct_orig.dst, + output->ct.orig_tp.src, + output->ct.orig_tp.dst, + output->ct.orig_proto, + }; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, + sizeof(orig), &orig)) + return -EMSGSIZE; + } else if (swkey->eth.type == htons(ETH_P_IPV6)) { + struct ovs_key_ct_tuple_ipv6 orig = { + IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src), + IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst), + output->ct.orig_tp.src, + output->ct.orig_tp.dst, + output->ct.orig_proto, + }; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, + sizeof(orig), &orig)) + return -EMSGSIZE; + } + } + return 0; } diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 8f6230bd6183..9e92445dc092 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -32,7 +32,8 @@ int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, const struct ovs_conntrack_info *); void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); -int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb); +int ovs_ct_put_key(const struct sw_flow_key *swkey, + const struct sw_flow_key *output, struct sk_buff *skb); void ovs_ct_free_action(const struct nlattr *a); #define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \ @@ -79,9 +80,14 @@ static inline void ovs_ct_fill_key(const struct sk_buff *skb, key->ct.zone = 0; key->ct.mark = 0; memset(&key->ct.labels, 0, sizeof(key->ct.labels)); + /* Clear 'ct.orig_proto' to mark the non-existence of original + * direction key fields. + */ + key->ct.orig_proto = 0; } -static inline int ovs_ct_put_key(const struct sw_flow_key *key, +static inline int ovs_ct_put_key(const struct sw_flow_key *swkey, + const struct sw_flow_key *output, struct sk_buff *skb) { return 0; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 2c0a00f7f1b7..9d4bb8eb63f2 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -765,7 +765,7 @@ static int key_extract_mac_proto(struct sk_buff *skb) int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key) { - int res; + int res, err; /* Extract metadata from packet. */ if (tun_info) { @@ -792,7 +792,6 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, key->phy.priority = skb->priority; key->phy.in_port = OVS_CB(skb)->input_vport->port_no; key->phy.skb_mark = skb->mark; - ovs_ct_fill_key(skb, key); key->ovs_flow_hash = 0; res = key_extract_mac_proto(skb); if (res < 0) @@ -800,17 +799,26 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, key->mac_proto = res; key->recirc_id = 0; - return key_extract(skb, key); + err = key_extract(skb, key); + if (!err) + ovs_ct_fill_key(skb, key); /* Must be after key_extract(). */ + return err; } int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr, struct sk_buff *skb, struct sw_flow_key *key, bool log) { + const struct nlattr *a[OVS_KEY_ATTR_MAX + 1]; + u64 attrs = 0; int err; + err = parse_flow_nlattrs(attr, a, &attrs, log); + if (err) + return -EINVAL; + /* Extract metadata from netlink attributes. */ - err = ovs_nla_get_flow_metadata(net, attr, key, log); + err = ovs_nla_get_flow_metadata(net, a, attrs, key, log); if (err) return err; @@ -824,5 +832,21 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr, */ skb->protocol = key->eth.type; - return key_extract(skb, key); + err = key_extract(skb, key); + if (err) + return err; + + /* Check that we have conntrack original direction tuple metadata only + * for packets for which it makes sense. Otherwise the key may be + * corrupted due to overlapping key fields. + */ + if (attrs & (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4) && + key->eth.type != htons(ETH_P_IP)) + return -EINVAL; + if (attrs & (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6) && + (key->eth.type != htons(ETH_P_IPV6) || + sw_flow_key_is_nd(key))) + return -EINVAL; + + return 0; } diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index f61cae7f9030..76e05b25f030 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2014 Nicira, Inc. + * Copyright (c) 2007-2017 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -107,10 +107,16 @@ struct sw_flow_key { __be32 src; /* IP source address. */ __be32 dst; /* IP destination address. */ } addr; - struct { - u8 sha[ETH_ALEN]; /* ARP source hardware address. */ - u8 tha[ETH_ALEN]; /* ARP target hardware address. */ - } arp; + union { + struct { + __be32 src; + __be32 dst; + } ct_orig; /* Conntrack original direction fields. */ + struct { + u8 sha[ETH_ALEN]; /* ARP source hardware address. */ + u8 tha[ETH_ALEN]; /* ARP target hardware address. */ + } arp; + }; } ipv4; struct { struct { @@ -118,23 +124,44 @@ struct sw_flow_key { struct in6_addr dst; /* IPv6 destination address. */ } addr; __be32 label; /* IPv6 flow label. */ - struct { - struct in6_addr target; /* ND target address. */ - u8 sll[ETH_ALEN]; /* ND source link layer address. */ - u8 tll[ETH_ALEN]; /* ND target link layer address. */ - } nd; + union { + struct { + struct in6_addr src; + struct in6_addr dst; + } ct_orig; /* Conntrack original direction fields. */ + struct { + struct in6_addr target; /* ND target address. */ + u8 sll[ETH_ALEN]; /* ND source link layer address. */ + u8 tll[ETH_ALEN]; /* ND target link layer address. */ + } nd; + }; } ipv6; }; struct { /* Connection tracking fields. */ + u8 state; + u8 orig_proto; /* CT orig tuple IP protocol. */ u16 zone; u32 mark; - u8 state; + struct { + __be16 src; /* CT orig tuple tp src port. */ + __be16 dst; /* CT orig tuple tp dst port. */ + } orig_tp; + struct ovs_key_ct_labels labels; } ct; } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */ +static inline bool sw_flow_key_is_nd(const struct sw_flow_key *key) +{ + return key->eth.type == htons(ETH_P_IPV6) && + key->ip.proto == NEXTHDR_ICMP && + key->tp.dst == 0 && + (key->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) || + key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)); +} + struct sw_flow_key_range { unsigned short int start; unsigned short int end; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index c87d359b9b37..989f38f120bb 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -129,7 +129,9 @@ static bool match_validate(const struct sw_flow_match *match, /* The following mask attributes allowed only if they * pass the validation tests. */ mask_allowed &= ~((1 << OVS_KEY_ATTR_IPV4) + | (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4) | (1 << OVS_KEY_ATTR_IPV6) + | (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6) | (1 << OVS_KEY_ATTR_TCP) | (1 << OVS_KEY_ATTR_TCP_FLAGS) | (1 << OVS_KEY_ATTR_UDP) @@ -161,8 +163,10 @@ static bool match_validate(const struct sw_flow_match *match, if (match->key->eth.type == htons(ETH_P_IP)) { key_expected |= 1 << OVS_KEY_ATTR_IPV4; - if (match->mask && (match->mask->key.eth.type == htons(0xffff))) + if (match->mask && match->mask->key.eth.type == htons(0xffff)) { mask_allowed |= 1 << OVS_KEY_ATTR_IPV4; + mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4; + } if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) { if (match->key->ip.proto == IPPROTO_UDP) { @@ -196,8 +200,10 @@ static bool match_validate(const struct sw_flow_match *match, if (match->key->eth.type == htons(ETH_P_IPV6)) { key_expected |= 1 << OVS_KEY_ATTR_IPV6; - if (match->mask && (match->mask->key.eth.type == htons(0xffff))) + if (match->mask && match->mask->key.eth.type == htons(0xffff)) { mask_allowed |= 1 << OVS_KEY_ATTR_IPV6; + mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6; + } if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) { if (match->key->ip.proto == IPPROTO_UDP) { @@ -230,6 +236,12 @@ static bool match_validate(const struct sw_flow_match *match, htons(NDISC_NEIGHBOUR_SOLICITATION) || match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) { key_expected |= 1 << OVS_KEY_ATTR_ND; + /* Original direction conntrack tuple + * uses the same space as the ND fields + * in the key, so both are not allowed + * at the same time. + */ + mask_allowed &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6); if (match->mask && (match->mask->key.tp.src == htons(0xff))) mask_allowed |= 1 << OVS_KEY_ATTR_ND; } @@ -282,7 +294,7 @@ size_t ovs_key_attr_size(void) /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ - BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 26); + BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 28); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ @@ -295,6 +307,7 @@ size_t ovs_key_attr_size(void) + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */ + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + + nla_total_size(40) /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -355,6 +368,10 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) }, [OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) }, + [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4] = { + .len = sizeof(struct ovs_key_ct_tuple_ipv4) }, + [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = { + .len = sizeof(struct ovs_key_ct_tuple_ipv6) }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -430,9 +447,8 @@ static int parse_flow_mask_nlattrs(const struct nlattr *attr, return __parse_flow_nlattrs(attr, a, attrsp, log, true); } -static int parse_flow_nlattrs(const struct nlattr *attr, - const struct nlattr *a[], u64 *attrsp, - bool log) +int parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[], + u64 *attrsp, bool log) { return __parse_flow_nlattrs(attr, a, attrsp, log, false); } @@ -1082,6 +1098,34 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, sizeof(*cl), is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS); } + if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4)) { + const struct ovs_key_ct_tuple_ipv4 *ct; + + ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4]); + + SW_FLOW_KEY_PUT(match, ipv4.ct_orig.src, ct->ipv4_src, is_mask); + SW_FLOW_KEY_PUT(match, ipv4.ct_orig.dst, ct->ipv4_dst, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_proto, ct->ipv4_proto, is_mask); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4); + } + if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6)) { + const struct ovs_key_ct_tuple_ipv6 *ct; + + ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6]); + + SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.src, &ct->ipv6_src, + sizeof(match->key->ipv6.ct_orig.src), + is_mask); + SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.dst, &ct->ipv6_dst, + sizeof(match->key->ipv6.ct_orig.dst), + is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask); + SW_FLOW_KEY_PUT(match, ct.orig_proto, ct->ipv6_proto, is_mask); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6); + } /* For layer 3 packets the Ethernet type is provided * and treated as metadata but no MAC addresses are provided. @@ -1493,9 +1537,12 @@ u32 ovs_nla_get_ufid_flags(const struct nlattr *attr) /** * ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key. - * @key: Receives extracted in_port, priority, tun_key and skb_mark. - * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute - * sequence. + * @net: Network namespace. + * @key: Receives extracted in_port, priority, tun_key, skb_mark and conntrack + * metadata. + * @a: Array of netlink attributes holding parsed %OVS_KEY_ATTR_* Netlink + * attributes. + * @attrs: Bit mask for the netlink attributes included in @a. * @log: Boolean to allow kernel error logging. Normally true, but when * probing for feature compatibility this should be passed in as false to * suppress unnecessary error logging. @@ -1504,25 +1551,23 @@ u32 ovs_nla_get_ufid_flags(const struct nlattr *attr) * take the same form accepted by flow_from_nlattrs(), but only enough of it to * get the metadata, that is, the parts of the flow key that cannot be * extracted from the packet itself. + * + * This must be called before the packet key fields are filled in 'key'. */ -int ovs_nla_get_flow_metadata(struct net *net, const struct nlattr *attr, - struct sw_flow_key *key, - bool log) +int ovs_nla_get_flow_metadata(struct net *net, + const struct nlattr *a[OVS_KEY_ATTR_MAX + 1], + u64 attrs, struct sw_flow_key *key, bool log) { - const struct nlattr *a[OVS_KEY_ATTR_MAX + 1]; struct sw_flow_match match; - u64 attrs = 0; - int err; - - err = parse_flow_nlattrs(attr, a, &attrs, log); - if (err) - return -EINVAL; memset(&match, 0, sizeof(match)); match.key = key; memset(&key->ct, 0, sizeof(key->ct)); + memset(&key->ipv4.ct_orig, 0, sizeof(key->ipv4.ct_orig)); + memset(&key->ipv6.ct_orig, 0, sizeof(key->ipv6.ct_orig)); + key->phy.in_port = DP_MAX_PORTS; return metadata_from_nlattrs(net, &match, &attrs, a, false, log); @@ -1584,7 +1629,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if (nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, output->phy.skb_mark)) goto nla_put_failure; - if (ovs_ct_put_key(output, skb)) + if (ovs_ct_put_key(swkey, output, skb)) goto nla_put_failure; if (ovs_key_mac_proto(swkey) == MAC_PROTO_ETHERNET) { diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 45f9769e5aac..929c665ac3aa 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -46,8 +46,11 @@ void ovs_match_init(struct sw_flow_match *match, int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *, int attr, bool is_mask, struct sk_buff *); -int ovs_nla_get_flow_metadata(struct net *, const struct nlattr *, - struct sw_flow_key *, bool log); +int parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[], + u64 *attrsp, bool log); +int ovs_nla_get_flow_metadata(struct net *net, + const struct nlattr *a[OVS_KEY_ATTR_MAX + 1], + u64 attrs, struct sw_flow_key *key, bool log); int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb); -- cgit v1.3-14-g43fede From dd41d33f0b033885211a5d6f3ee19e73238aa9ee Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Thu, 9 Feb 2017 11:22:00 -0800 Subject: openvswitch: Add force commit. Stateful network admission policy may allow connections to one direction and reject connections initiated in the other direction. After policy change it is possible that for a new connection an overlapping conntrack entry already exists, where the original direction of the existing connection is opposed to the new connection's initial packet. Most importantly, conntrack state relating to the current packet gets the "reply" designation based on whether the original direction tuple or the reply direction tuple matched. If this "directionality" is wrong w.r.t. to the stateful network admission policy it may happen that packets in neither direction are correctly admitted. This patch adds a new "force commit" option to the OVS conntrack action that checks the original direction of an existing conntrack entry. If that direction is opposed to the current packet, the existing conntrack entry is deleted and a new one is subsequently created in the correct direction. Signed-off-by: Jarno Rajahalme Acked-by: Pravin B Shelar Acked-by: Joe Stringer Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 5 +++++ net/openvswitch/conntrack.c | 26 ++++++++++++++++++++++++-- 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 90af8b8e10f8..7f41f7d0000f 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -674,6 +674,10 @@ struct ovs_action_hash { * @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG. * @OVS_CT_ATTR_NAT: Nested OVS_NAT_ATTR_* for performing L3 network address * translation (NAT) on the packet. + * @OVS_CT_ATTR_FORCE_COMMIT: Like %OVS_CT_ATTR_COMMIT, but instead of doing + * nothing if the connection is already committed will check that the current + * packet is in conntrack entry's original direction. If directionality does + * not match, will delete the existing conntrack entry and commit a new one. */ enum ovs_ct_attr { OVS_CT_ATTR_UNSPEC, @@ -684,6 +688,7 @@ enum ovs_ct_attr { OVS_CT_ATTR_HELPER, /* netlink helper to assist detection of related connections. */ OVS_CT_ATTR_NAT, /* Nested OVS_NAT_ATTR_* */ + OVS_CT_ATTR_FORCE_COMMIT, /* No argument */ __OVS_CT_ATTR_MAX }; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index bfd7606c8be1..8b15bab70583 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -65,6 +65,7 @@ struct ovs_conntrack_info { struct nf_conn *ct; u8 commit : 1; u8 nat : 3; /* enum ovs_ct_nat */ + u8 force : 1; u16 family; struct md_mark mark; struct md_labels labels; @@ -613,10 +614,13 @@ static bool skb_nfct_cached(struct net *net, */ if (!ct && key->ct.state & OVS_CS_F_TRACKED && !(key->ct.state & OVS_CS_F_INVALID) && - key->ct.zone == info->zone.id) + key->ct.zone == info->zone.id) { ct = ovs_ct_find_existing(net, &info->zone, info->family, skb, !!(key->ct.state & OVS_CS_F_NAT_MASK)); + if (ct) + nf_ct_get(skb, &ctinfo); + } if (!ct) return false; if (!net_eq(net, read_pnet(&ct->ct_net))) @@ -630,6 +634,18 @@ static bool skb_nfct_cached(struct net *net, if (help && rcu_access_pointer(help->helper) != info->helper) return false; } + /* Force conntrack entry direction to the current packet? */ + if (info->force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { + /* Delete the conntrack entry if confirmed, else just release + * the reference. + */ + if (nf_ct_is_confirmed(ct)) + nf_ct_delete(ct, 0, 0); + else + nf_conntrack_put(&ct->ct_general); + nf_ct_set(skb, NULL, 0); + return false; + } return true; } @@ -1207,6 +1223,7 @@ static int parse_nat(const struct nlattr *attr, static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 }, + [OVS_CT_ATTR_FORCE_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), .maxlen = sizeof(u16) }, [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), @@ -1246,6 +1263,9 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, } switch (type) { + case OVS_CT_ATTR_FORCE_COMMIT: + info->force = true; + /* fall through. */ case OVS_CT_ATTR_COMMIT: info->commit = true; break; @@ -1472,7 +1492,9 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, if (!start) return -EMSGSIZE; - if (ct_info->commit && nla_put_flag(skb, OVS_CT_ATTR_COMMIT)) + if (ct_info->commit && nla_put_flag(skb, ct_info->force + ? OVS_CT_ATTR_FORCE_COMMIT + : OVS_CT_ATTR_COMMIT)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) -- cgit v1.3-14-g43fede From 71d0ed7079dffbc5cd0941d77d9b84e04109c9bb Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 7 Feb 2017 09:56:07 +0200 Subject: net/act_pedit: Support using offset relative to the conventional network headers Extend pedit to enable the user setting offset relative to network headers. This change would enable to work with more complex header schemes (vs the simple IPv4 case) where setting a fixed offset relative to the network header is not enough. After this patch, the action has information about the exact header type and field inside this header. This information could be used later on for hardware offloading of pedit. Backward compatibility was being kept: 1. Old kernel <-> new userspace 2. New kernel <-> old userspace 3. add rule using new userspace <-> dump using old userspace 4. add rule using old userspace <-> dump using new userspace When using the extended api, new netlink attributes are being used. This way, operation will fail in (1) and (3) - and no malformed rule be added or dumped. Of course, new user space that doesn't need the new functionality can use the old netlink attributes and operation will succeed. Since action can support both api's, (2) should work, and it is easy to write the new user space to have (4) work. The action is having a strict check that only header types and commands it can handle are accepted. This way future additions will be much easier. Usage example: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower \ ip_proto tcp \ dst_port 80 \ action pedit munge tcp dport set 8080 pipe \ action mirred egress redirect dev veth0 Will forward tcp port whose original dest port is 80, while modifying the destination port to 8080. Signed-off-by: Amir Vadai Reviewed-by: Or Gerlitz Signed-off-by: David S. Miller --- include/net/tc_act/tc_pedit.h | 5 + include/uapi/linux/tc_act/tc_pedit.h | 23 ++++ net/sched/act_pedit.c | 196 ++++++++++++++++++++++++++++++++--- 3 files changed, 208 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 29e38d6823df..e076f22035a5 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -3,11 +3,16 @@ #include +struct tcf_pedit_key_ex { + enum pedit_header_type htype; +}; + struct tcf_pedit { struct tc_action common; unsigned char tcfp_nkeys; unsigned char tcfp_flags; struct tc_pedit_key *tcfp_keys; + struct tcf_pedit_key_ex *tcfp_keys_ex; }; #define to_pedit(a) ((struct tcf_pedit *)a) diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h index 6389959a5157..22f19eeda997 100644 --- a/include/uapi/linux/tc_act/tc_pedit.h +++ b/include/uapi/linux/tc_act/tc_pedit.h @@ -11,10 +11,33 @@ enum { TCA_PEDIT_TM, TCA_PEDIT_PARMS, TCA_PEDIT_PAD, + TCA_PEDIT_PARMS_EX, + TCA_PEDIT_KEYS_EX, + TCA_PEDIT_KEY_EX, __TCA_PEDIT_MAX }; #define TCA_PEDIT_MAX (__TCA_PEDIT_MAX - 1) +enum { + TCA_PEDIT_KEY_EX_HTYPE = 1, + __TCA_PEDIT_KEY_EX_MAX +}; +#define TCA_PEDIT_KEY_EX_MAX (__TCA_PEDIT_KEY_EX_MAX - 1) + + /* TCA_PEDIT_KEY_EX_HDR_TYPE_NETWROK is a special case for legacy users. It + * means no specific header type - offset is relative to the network layer + */ +enum pedit_header_type { + TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK = 0, + TCA_PEDIT_KEY_EX_HDR_TYPE_ETH = 1, + TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 = 2, + TCA_PEDIT_KEY_EX_HDR_TYPE_IP6 = 3, + TCA_PEDIT_KEY_EX_HDR_TYPE_TCP = 4, + TCA_PEDIT_KEY_EX_HDR_TYPE_UDP = 5, + __PEDIT_HDR_TYPE_MAX, +}; +#define TCA_PEDIT_HDR_TYPE_MAX (__PEDIT_HDR_TYPE_MAX - 1) + struct tc_pedit_key { __u32 mask; /* AND */ __u32 val; /*XOR */ diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index b27c4daec88f..fdd012bd3602 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -22,6 +22,7 @@ #include #include #include +#include #define PEDIT_TAB_MASK 15 @@ -30,18 +31,112 @@ static struct tc_action_ops act_pedit_ops; static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, + [TCA_PEDIT_KEYS_EX] = { .type = NLA_NESTED }, }; +static const struct nla_policy pedit_key_ex_policy[TCA_PEDIT_KEY_EX_MAX + 1] = { + [TCA_PEDIT_KEY_EX_HTYPE] = { .type = NLA_U16 }, +}; + +static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, + u8 n) +{ + struct tcf_pedit_key_ex *keys_ex; + struct tcf_pedit_key_ex *k; + const struct nlattr *ka; + int err = -EINVAL; + int rem; + + if (!nla || !n) + return NULL; + + keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL); + if (!keys_ex) + return ERR_PTR(-ENOMEM); + + k = keys_ex; + + nla_for_each_nested(ka, nla, rem) { + struct nlattr *tb[TCA_PEDIT_KEY_EX_MAX + 1]; + + if (!n) { + err = -EINVAL; + goto err_out; + } + n--; + + if (nla_type(ka) != TCA_PEDIT_KEY_EX) { + err = -EINVAL; + goto err_out; + } + + err = nla_parse_nested(tb, TCA_PEDIT_KEY_EX_MAX, ka, + pedit_key_ex_policy); + if (err) + goto err_out; + + if (!tb[TCA_PEDIT_KEY_EX_HTYPE]) { + err = -EINVAL; + goto err_out; + } + + k->htype = nla_get_u16(tb[TCA_PEDIT_KEY_EX_HTYPE]); + + if (k->htype > TCA_PEDIT_HDR_TYPE_MAX) { + err = -EINVAL; + goto err_out; + } + + k++; + } + + if (n) + goto err_out; + + return keys_ex; + +err_out: + kfree(keys_ex); + return ERR_PTR(err); +} + +static int tcf_pedit_key_ex_dump(struct sk_buff *skb, + struct tcf_pedit_key_ex *keys_ex, int n) +{ + struct nlattr *keys_start = nla_nest_start(skb, TCA_PEDIT_KEYS_EX); + + for (; n > 0; n--) { + struct nlattr *key_start; + + key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX); + + if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype)) { + nlmsg_trim(skb, keys_start); + return -EINVAL; + } + + nla_nest_end(skb, key_start); + + keys_ex++; + } + + nla_nest_end(skb, keys_start); + + return 0; +} + static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind) { struct tc_action_net *tn = net_generic(net, pedit_net_id); struct nlattr *tb[TCA_PEDIT_MAX + 1]; + struct nlattr *pattr; struct tc_pedit *parm; int ret = 0, err; struct tcf_pedit *p; struct tc_pedit_key *keys = NULL; + struct tcf_pedit_key_ex *keys_ex; int ksize; if (nla == NULL) @@ -51,13 +146,21 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (err < 0) return err; - if (tb[TCA_PEDIT_PARMS] == NULL) + pattr = tb[TCA_PEDIT_PARMS]; + if (!pattr) + pattr = tb[TCA_PEDIT_PARMS_EX]; + if (!pattr) return -EINVAL; - parm = nla_data(tb[TCA_PEDIT_PARMS]); + + parm = nla_data(pattr); ksize = parm->nkeys * sizeof(struct tc_pedit_key); - if (nla_len(tb[TCA_PEDIT_PARMS]) < sizeof(*parm) + ksize) + if (nla_len(pattr) < sizeof(*parm) + ksize) return -EINVAL; + keys_ex = tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys); + if (IS_ERR(keys_ex)) + return PTR_ERR(keys_ex); + if (!tcf_hash_check(tn, parm->index, a, bind)) { if (!parm->nkeys) return -EINVAL; @@ -69,6 +172,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { tcf_hash_cleanup(*a, est); + kfree(keys_ex); return -ENOMEM; } ret = ACT_P_CREATED; @@ -81,8 +185,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, p = to_pedit(*a); if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) { keys = kmalloc(ksize, GFP_KERNEL); - if (keys == NULL) + if (!keys) { + kfree(keys_ex); return -ENOMEM; + } } } @@ -95,6 +201,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, p->tcfp_nkeys = parm->nkeys; } memcpy(p->tcfp_keys, parm->keys, ksize); + + kfree(p->tcfp_keys_ex); + p->tcfp_keys_ex = keys_ex; + spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) tcf_hash_insert(tn, *a); @@ -106,6 +216,7 @@ static void tcf_pedit_cleanup(struct tc_action *a, int bind) struct tcf_pedit *p = to_pedit(a); struct tc_pedit_key *keys = p->tcfp_keys; kfree(keys); + kfree(p->tcfp_keys_ex); } static bool offset_valid(struct sk_buff *skb, int offset) @@ -119,38 +230,84 @@ static bool offset_valid(struct sk_buff *skb, int offset) return true; } +static int pedit_skb_hdr_offset(struct sk_buff *skb, + enum pedit_header_type htype, int *hoffset) +{ + int ret = -EINVAL; + + switch (htype) { + case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: + if (skb_mac_header_was_set(skb)) { + *hoffset = skb_mac_offset(skb); + ret = 0; + } + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK: + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: + *hoffset = skb_network_offset(skb); + ret = 0; + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: + case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: + if (skb_transport_header_was_set(skb)) { + *hoffset = skb_transport_offset(skb); + ret = 0; + } + break; + default: + ret = -EINVAL; + break; + }; + + return ret; +} + static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_pedit *p = to_pedit(a); int i; - unsigned int off; if (skb_unclone(skb, GFP_ATOMIC)) return p->tcf_action; - off = skb_network_offset(skb); - spin_lock(&p->tcf_lock); tcf_lastuse_update(&p->tcf_tm); if (p->tcfp_nkeys > 0) { struct tc_pedit_key *tkey = p->tcfp_keys; + struct tcf_pedit_key_ex *tkey_ex = p->tcfp_keys_ex; + enum pedit_header_type htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; for (i = p->tcfp_nkeys; i > 0; i--, tkey++) { u32 *ptr, _data; int offset = tkey->off; + int hoffset; + int rc; + + if (tkey_ex) { + htype = tkey_ex->htype; + tkey_ex++; + } + + rc = pedit_skb_hdr_offset(skb, htype, &hoffset); + if (rc) { + pr_info("tc filter pedit bad header type specified (0x%x)\n", + htype); + goto bad; + } if (tkey->offmask) { char *d, _d; - if (!offset_valid(skb, off + tkey->at)) { + if (!offset_valid(skb, hoffset + tkey->at)) { pr_info("tc filter pedit 'at' offset %d out of bounds\n", - off + tkey->at); + hoffset + tkey->at); goto bad; } - d = skb_header_pointer(skb, off + tkey->at, 1, + d = skb_header_pointer(skb, hoffset + tkey->at, 1, &_d); if (!d) goto bad; @@ -163,19 +320,19 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, goto bad; } - if (!offset_valid(skb, off + offset)) { + if (!offset_valid(skb, hoffset + offset)) { pr_info("tc filter pedit offset %d out of bounds\n", - offset); + hoffset + offset); goto bad; } - ptr = skb_header_pointer(skb, off + offset, 4, &_data); + ptr = skb_header_pointer(skb, hoffset + offset, 4, &_data); if (!ptr) goto bad; /* just do it, baby */ *ptr = ((*ptr & tkey->mask) ^ tkey->val); if (ptr == &_data) - skb_store_bits(skb, off + offset, ptr, 4); + skb_store_bits(skb, hoffset + offset, ptr, 4); } goto done; @@ -215,8 +372,15 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, opt->refcnt = p->tcf_refcnt - ref; opt->bindcnt = p->tcf_bindcnt - bind; - if (nla_put(skb, TCA_PEDIT_PARMS, s, opt)) - goto nla_put_failure; + if (p->tcfp_keys_ex) { + tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys); + + if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt)) + goto nla_put_failure; + } else { + if (nla_put(skb, TCA_PEDIT_PARMS, s, opt)) + goto nla_put_failure; + } tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_PEDIT_TM, sizeof(t), &t, TCA_PEDIT_PAD)) -- cgit v1.3-14-g43fede From 853a14ba4682f820266469979c9297debc05f60c Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 7 Feb 2017 09:56:08 +0200 Subject: net/act_pedit: Introduce 'add' operation This command could be useful to inc/dec fields. For example, to forward any TCP packet and decrease its TTL: $ tc filter add dev enp0s9 protocol ip parent ffff: \ flower ip_proto tcp \ action pedit munge ip ttl add 0xff pipe \ action mirred egress redirect dev veth0 In the example above, adding 0xff to this u8 field is actually decreasing it by one, since the operation is masked. Signed-off-by: Amir Vadai Reviewed-by: Or Gerlitz Signed-off-by: David S. Miller --- include/net/tc_act/tc_pedit.h | 1 + include/uapi/linux/tc_act/tc_pedit.h | 8 ++++++++ net/sched/act_pedit.c | 30 ++++++++++++++++++++++++++---- 3 files changed, 35 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index e076f22035a5..dfbd6ee0bc7c 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -5,6 +5,7 @@ struct tcf_pedit_key_ex { enum pedit_header_type htype; + enum pedit_cmd cmd; }; struct tcf_pedit { diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h index 22f19eeda997..143d2b31a316 100644 --- a/include/uapi/linux/tc_act/tc_pedit.h +++ b/include/uapi/linux/tc_act/tc_pedit.h @@ -20,6 +20,7 @@ enum { enum { TCA_PEDIT_KEY_EX_HTYPE = 1, + TCA_PEDIT_KEY_EX_CMD = 2, __TCA_PEDIT_KEY_EX_MAX }; #define TCA_PEDIT_KEY_EX_MAX (__TCA_PEDIT_KEY_EX_MAX - 1) @@ -38,6 +39,13 @@ enum pedit_header_type { }; #define TCA_PEDIT_HDR_TYPE_MAX (__PEDIT_HDR_TYPE_MAX - 1) +enum pedit_cmd { + TCA_PEDIT_KEY_EX_CMD_SET = 0, + TCA_PEDIT_KEY_EX_CMD_ADD = 1, + __PEDIT_CMD_MAX, +}; +#define TCA_PEDIT_CMD_MAX (__PEDIT_CMD_MAX - 1) + struct tc_pedit_key { __u32 mask; /* AND */ __u32 val; /*XOR */ diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index fdd012bd3602..c1310472f620 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -36,6 +36,7 @@ static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { static const struct nla_policy pedit_key_ex_policy[TCA_PEDIT_KEY_EX_MAX + 1] = { [TCA_PEDIT_KEY_EX_HTYPE] = { .type = NLA_U16 }, + [TCA_PEDIT_KEY_EX_CMD] = { .type = NLA_U16 }, }; static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, @@ -75,14 +76,17 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, if (err) goto err_out; - if (!tb[TCA_PEDIT_KEY_EX_HTYPE]) { + if (!tb[TCA_PEDIT_KEY_EX_HTYPE] || + !tb[TCA_PEDIT_KEY_EX_CMD]) { err = -EINVAL; goto err_out; } k->htype = nla_get_u16(tb[TCA_PEDIT_KEY_EX_HTYPE]); + k->cmd = nla_get_u16(tb[TCA_PEDIT_KEY_EX_CMD]); - if (k->htype > TCA_PEDIT_HDR_TYPE_MAX) { + if (k->htype > TCA_PEDIT_HDR_TYPE_MAX || + k->cmd > TCA_PEDIT_CMD_MAX) { err = -EINVAL; goto err_out; } @@ -110,7 +114,8 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX); - if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype)) { + if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype) || + nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) { nlmsg_trim(skb, keys_start); return -EINVAL; } @@ -280,15 +285,19 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, struct tc_pedit_key *tkey = p->tcfp_keys; struct tcf_pedit_key_ex *tkey_ex = p->tcfp_keys_ex; enum pedit_header_type htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK; + enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET; for (i = p->tcfp_nkeys; i > 0; i--, tkey++) { u32 *ptr, _data; int offset = tkey->off; int hoffset; + u32 val; int rc; if (tkey_ex) { htype = tkey_ex->htype; + cmd = tkey_ex->cmd; + tkey_ex++; } @@ -330,7 +339,20 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, if (!ptr) goto bad; /* just do it, baby */ - *ptr = ((*ptr & tkey->mask) ^ tkey->val); + switch (cmd) { + case TCA_PEDIT_KEY_EX_CMD_SET: + val = tkey->val; + break; + case TCA_PEDIT_KEY_EX_CMD_ADD: + val = (*ptr + tkey->val) & ~tkey->mask; + break; + default: + pr_info("tc filter pedit bad command (%d)\n", + cmd); + goto bad; + } + + *ptr = ((*ptr & tkey->mask) ^ val); if (ptr == &_data) skb_store_bits(skb, hoffset + offset, ptr, 4); } -- cgit v1.3-14-g43fede From adf200f31c000d707e4afe238ed1d1199e0cce7c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 9 Feb 2017 15:54:33 +0100 Subject: devlink: fix the name of eswitch commands The eswitch_[gs]et command is supposed to be similar to port_[gs]et command - for multiple eswitch attributes. However, when it was introduced by 08f4b5918b2d ("net/devlink: Add E-Switch mode control") it was wrongly named with the word "mode" in it. So fix this now, make the oririnal enum value existing but obsolete. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 10 ++++++++-- net/core/devlink.c | 18 +++++++++--------- 2 files changed, 17 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 9014c33d4e77..0f1f3a12e23c 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -57,8 +57,14 @@ enum devlink_command { DEVLINK_CMD_SB_OCC_SNAPSHOT, DEVLINK_CMD_SB_OCC_MAX_CLEAR, - DEVLINK_CMD_ESWITCH_MODE_GET, - DEVLINK_CMD_ESWITCH_MODE_SET, + DEVLINK_CMD_ESWITCH_GET, +#define DEVLINK_CMD_ESWITCH_MODE_GET /* obsolete, never use this! */ \ + DEVLINK_CMD_ESWITCH_GET + + DEVLINK_CMD_ESWITCH_SET, +#define DEVLINK_CMD_ESWITCH_MODE_SET /* obsolete, never use this! */ \ + DEVLINK_CMD_ESWITCH_SET + /* add new commands above here */ __DEVLINK_CMD_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 2b5bf9efa720..7aa8e5369dc5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1435,8 +1435,8 @@ out: return err; } -static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb, - struct genl_info *info) +static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; @@ -1450,7 +1450,7 @@ static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb, if (!msg) return -ENOMEM; - err = devlink_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_MODE_GET, + err = devlink_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, info->snd_portid, info->snd_seq, 0); if (err) { @@ -1461,8 +1461,8 @@ static int devlink_nl_cmd_eswitch_mode_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_eswitch_mode_set_doit(struct sk_buff *skb, - struct genl_info *info) +static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; @@ -1629,15 +1629,15 @@ static const struct genl_ops devlink_nl_ops[] = { DEVLINK_NL_FLAG_LOCK_PORTS, }, { - .cmd = DEVLINK_CMD_ESWITCH_MODE_GET, - .doit = devlink_nl_cmd_eswitch_mode_get_doit, + .cmd = DEVLINK_CMD_ESWITCH_GET, + .doit = devlink_nl_cmd_eswitch_get_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { - .cmd = DEVLINK_CMD_ESWITCH_MODE_SET, - .doit = devlink_nl_cmd_eswitch_mode_set_doit, + .cmd = DEVLINK_CMD_ESWITCH_SET, + .doit = devlink_nl_cmd_eswitch_set_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, -- cgit v1.3-14-g43fede From 8c4d4e8b5626fec965fd5034e5bd5e57790f243f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 10 Feb 2017 12:08:17 +0100 Subject: netfilter: nfnetlink: allow to check for generation ID This patch allows userspace to specify the generation ID that has been used to build an incremental batch update. If userspace specifies the generation ID in the batch message as attribute, then nfnetlink compares it to the current generation ID so you make sure that you work against the right baseline. Otherwise, bail out with ERESTART so userspace knows that its changeset is stale and needs to respin. Userspace can do this transparently at the cost of taking slightly more time to refresh caches and rework the changeset. This check is optional, if there is no NFNL_BATCH_GENID attribute in the batch begin message, then no check is performed. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 1 + include/uapi/linux/netfilter/nfnetlink.h | 12 ++++++++++++ net/netfilter/nfnetlink.c | 31 +++++++++++++++++++++++++++---- 3 files changed, 40 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 1d82dd5e9a08..1b49209dd5c7 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -28,6 +28,7 @@ struct nfnetlink_subsystem { const struct nfnl_callback *cb; /* callback for individual types */ int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb); + bool (*valid_genid)(struct net *net, u32 genid); }; int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n); diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h index 4bb8cb7730e7..a09906a30d77 100644 --- a/include/uapi/linux/netfilter/nfnetlink.h +++ b/include/uapi/linux/netfilter/nfnetlink.h @@ -65,4 +65,16 @@ struct nfgenmsg { #define NFNL_MSG_BATCH_BEGIN NLMSG_MIN_TYPE #define NFNL_MSG_BATCH_END NLMSG_MIN_TYPE+1 +/** + * enum nfnl_batch_attributes - nfnetlink batch netlink attributes + * + * @NFNL_BATCH_GENID: generation ID for this changeset (NLA_U32) + */ +enum nfnl_batch_attributes { + NFNL_BATCH_UNSPEC, + NFNL_BATCH_GENID, + __NFNL_BATCH_MAX +}; +#define NFNL_BATCH_MAX (__NFNL_BATCH_MAX - 1) + #endif /* _UAPI_NFNETLINK_H */ diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index ca645a3b1375..a2148d0bc50e 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -3,7 +3,7 @@ * * (C) 2001 by Jay Schulist , * (C) 2002-2005 by Harald Welte - * (C) 2005,2007 by Pablo Neira Ayuso + * (C) 2005-2017 by Pablo Neira Ayuso * * Initial netfilter messages via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) @@ -273,7 +273,7 @@ enum { }; static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, - u16 subsys_id) + u16 subsys_id, u32 genid) { struct sk_buff *oskb = skb; struct net *net = sock_net(skb->sk); @@ -315,6 +315,12 @@ replay: return kfree_skb(skb); } + if (genid && ss->valid_genid && !ss->valid_genid(net, genid)) { + nfnl_unlock(subsys_id); + netlink_ack(oskb, nlh, -ERESTART); + return kfree_skb(skb); + } + while (skb->len >= nlmsg_total_size(0)) { int msglen, type; @@ -436,11 +442,20 @@ done: kfree_skb(skb); } +static const struct nla_policy nfnl_batch_policy[NFNL_BATCH_MAX + 1] = { + [NFNL_BATCH_GENID] = { .type = NLA_U32 }, +}; + static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) { + int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); + struct nlattr *attr = (void *)nlh + min_len; + struct nlattr *cda[NFNL_BATCH_MAX + 1]; + int attrlen = nlh->nlmsg_len - min_len; struct nfgenmsg *nfgenmsg; + int msglen, err; + u32 gen_id = 0; u16 res_id; - int msglen; msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) @@ -450,6 +465,14 @@ static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) return; + err = nla_parse(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy); + if (err < 0) { + netlink_ack(skb, nlh, err); + return; + } + if (cda[NFNL_BATCH_GENID]) + gen_id = ntohl(nla_get_be32(cda[NFNL_BATCH_GENID])); + nfgenmsg = nlmsg_data(nlh); skb_pull(skb, msglen); /* Work around old nft using host byte order */ @@ -458,7 +481,7 @@ static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) else res_id = ntohs(nfgenmsg->res_id); - nfnetlink_rcv_batch(skb, nlh, res_id); + nfnetlink_rcv_batch(skb, nlh, res_id, gen_id); } static void nfnetlink_rcv(struct sk_buff *skb) -- cgit v1.3-14-g43fede From 1a94e38d254b3622d5d53f74b3b716b0fcab0ba8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 10 Feb 2017 12:08:23 +0100 Subject: netfilter: nf_tables: add NFTA_RULE_ID attribute This new attribute allows us to uniquely identify a rule in transaction. Robots may trigger an insertion followed by deletion in a batch, in that scenario we still don't have a public rule handle that we can use to delete the rule. This is similar to the NFTA_SET_ID attribute that allows us to refer to an anonymous set from a batch. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 +++ include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nf_tables_api.c | 26 ++++++++++++++++++++++++++ 3 files changed, 31 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 21ce50e6d0c5..ac84686aaafb 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1202,10 +1202,13 @@ struct nft_trans { struct nft_trans_rule { struct nft_rule *rule; + u32 rule_id; }; #define nft_trans_rule(trans) \ (((struct nft_trans_rule *)trans->data)->rule) +#define nft_trans_rule_id(trans) \ + (((struct nft_trans_rule *)trans->data)->rule_id) struct nft_trans_set { struct nft_set *set; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 207951516ede..05215d30fe5c 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -207,6 +207,7 @@ enum nft_chain_attributes { * @NFTA_RULE_COMPAT: compatibility specifications of the rule (NLA_NESTED: nft_rule_compat_attributes) * @NFTA_RULE_POSITION: numeric handle of the previous rule (NLA_U64) * @NFTA_RULE_USERDATA: user data (NLA_BINARY, NFT_USERDATA_MAXLEN) + * @NFTA_RULE_ID: uniquely identifies a rule in a transaction (NLA_U32) */ enum nft_rule_attributes { NFTA_RULE_UNSPEC, @@ -218,6 +219,7 @@ enum nft_rule_attributes { NFTA_RULE_POSITION, NFTA_RULE_USERDATA, NFTA_RULE_PAD, + NFTA_RULE_ID, __NFTA_RULE_MAX }; #define NFTA_RULE_MAX (__NFTA_RULE_MAX - 1) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 71c60a04b66b..6c782532615f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -240,6 +240,10 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, if (trans == NULL) return NULL; + if (msg_type == NFT_MSG_NEWRULE && ctx->nla[NFTA_RULE_ID] != NULL) { + nft_trans_rule_id(trans) = + ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); + } nft_trans_rule(trans) = rule; list_add_tail(&trans->list, &ctx->net->nft.commit_list); @@ -2293,6 +2297,22 @@ err1: return err; } +static struct nft_rule *nft_rule_lookup_byid(const struct net *net, + const struct nlattr *nla) +{ + u32 id = ntohl(nla_get_be32(nla)); + struct nft_trans *trans; + + list_for_each_entry(trans, &net->nft.commit_list, list) { + struct nft_rule *rule = nft_trans_rule(trans); + + if (trans->msg_type == NFT_MSG_NEWRULE && + id == nft_trans_rule_id(trans)) + return rule; + } + return ERR_PTR(-ENOENT); +} + static int nf_tables_delrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -2330,6 +2350,12 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, if (IS_ERR(rule)) return PTR_ERR(rule); + err = nft_delrule(&ctx, rule); + } else if (nla[NFTA_RULE_ID]) { + rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]); + if (IS_ERR(rule)) + return PTR_ERR(rule); + err = nft_delrule(&ctx, rule); } else { err = nft_delrule_by_chain(&ctx); -- cgit v1.3-14-g43fede From e696028acc458aa3d43ad899371a963eb28336d8 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 16 Feb 2017 10:31:12 +0200 Subject: net/sched: Reflect HW offload status Currently there is no way of querying whether a filter is offloaded to HW or not when using "both" policy (where none of skip_sw or skip_hw flags are set by user-space). Add two new flags, "in hw" and "not in hw" such that user space can determine if a filter is actually offloaded to hw or not. The "in hw" UAPI semantics was chosen so it's similar to the "skip hw" flag logic. If none of these two flags are set, this signals running over older kernel. Signed-off-by: Or Gerlitz Reviewed-by: Amir Vadai Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 5 +++++ include/uapi/linux/pkt_cls.h | 6 ++++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index be5c12a5c375..269fd78bb0ae 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -481,6 +481,11 @@ static inline bool tc_flags_valid(u32 flags) return true; } +static inline bool tc_in_hw(u32 flags) +{ + return (flags & TCA_CLS_FLAGS_IN_HW) ? true : false; +} + enum tc_fl_command { TC_CLSFLOWER_REPLACE, TC_CLSFLOWER_DESTROY, diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 345551e71410..7a69f2a4ca0c 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -103,8 +103,10 @@ enum { #define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1) /* tca flags definitions */ -#define TCA_CLS_FLAGS_SKIP_HW (1 << 0) -#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) +#define TCA_CLS_FLAGS_SKIP_HW (1 << 0) /* don't offload filter to HW */ +#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) /* don't use filter in SW */ +#define TCA_CLS_FLAGS_IN_HW (1 << 2) /* filter is offloaded to HW */ +#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */ /* U32 filters */ -- cgit v1.3-14-g43fede From 6c07ec0fa5712b01d0967cf74129fa9b4d234af8 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Thu, 16 Feb 2017 18:04:14 +0300 Subject: uapi: fix linux/ipv6_route.h userspace compilation errors Include to fix the following linux/ipv6_route.h userspace compilation errors: /usr/include/linux/ipv6_route.h:42:19: error: field 'rtmsg_dst' has incomplete type struct in6_addr rtmsg_dst; /usr/include/linux/ipv6_route.h:43:19: error: field 'rtmsg_src' has incomplete type struct in6_addr rtmsg_src; /ust/include/linux/ipv6_route.h:44:19: error: field 'rtmsg_gateway' has incomplete type struct in6_addr rtmsg_gateway; Signed-off-by: Dmitry V. Levin Signed-off-by: David S. Miller --- include/uapi/linux/ipv6_route.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h index f6598d1c886e..85bbb1799df3 100644 --- a/include/uapi/linux/ipv6_route.h +++ b/include/uapi/linux/ipv6_route.h @@ -14,6 +14,7 @@ #define _UAPI_LINUX_IPV6_ROUTE_H #include +#include /* For struct in6_addr. */ #define RTF_DEFAULT 0x00010000 /* default - learned via ND */ #define RTF_ALLONLINK 0x00020000 /* (deprecated and will be removed) -- cgit v1.3-14-g43fede From 72aa107df6a275cf03359934ca5799a2be7a1bf7 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Thu, 16 Feb 2017 18:04:29 +0300 Subject: uapi: fix linux/mroute6.h userspace compilation errors Include to fix the following linux/mroute6.h userspace compilation errors: /usr/include/linux/mroute6.h:80:22: error: field 'mf6cc_origin' has incomplete type struct sockaddr_in6 mf6cc_origin; /* Origin of mcast */ /usr/include/linux/mroute6.h:81:22: error: field 'mf6cc_mcastgrp' has incomplete type struct sockaddr_in6 mf6cc_mcastgrp; /* Group in question */ /usr/include/linux/mroute6.h:91:22: error: field 'src' has incomplete type struct sockaddr_in6 src; /usr/include/linux/mroute6.h:92:22: error: field 'grp' has incomplete type struct sockaddr_in6 grp; /usr/include/linux/mroute6.h:132:18: error: field 'im6_src' has incomplete type struct in6_addr im6_src, im6_dst; /usr/include/linux/mroute6.h:132:27: error: field 'im6_dst' has incomplete type struct in6_addr im6_src, im6_dst; Signed-off-by: Dmitry V. Levin Signed-off-by: David S. Miller --- include/uapi/linux/mroute6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h index 5062fb5751e1..ed5721148768 100644 --- a/include/uapi/linux/mroute6.h +++ b/include/uapi/linux/mroute6.h @@ -4,6 +4,7 @@ #include #include #include +#include /* For struct sockaddr_in6. */ /* * Based on the MROUTING 3.5 defines primarily to keep -- cgit v1.3-14-g43fede From bcb41c6bced1ee778d23c53a6b4807fb08cf5540 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Thu, 16 Feb 2017 18:04:46 +0300 Subject: uapi: fix linux/mroute.h userspace compilation errors Include to fix the following linux/mroute.h userspace compilation errors: /usr/include/linux/mroute.h:58:18: error: field 'vifc_lcl_addr' has incomplete type struct in_addr vifc_lcl_addr; /* Local interface address */ /usr/include/linux/mroute.h:61:17: error: field 'vifc_rmt_addr' has incomplete type struct in_addr vifc_rmt_addr; /* IPIP tunnel addr */ /usr/include/linux/mroute.h:72:17: error: field 'mfcc_origin' has incomplete type struct in_addr mfcc_origin; /* Origin of mcast */ /usr/include/linux/mroute.h:73:17: error: field 'mfcc_mcastgrp' has incomplete type struct in_addr mfcc_mcastgrp; /* Group in question */ /usr/include/linux/mroute.h:84:17: error: field 'src' has incomplete type struct in_addr src; /usr/include/linux/mroute.h:85:17: error: field 'grp' has incomplete type struct in_addr grp; /usr/include/linux/mroute.h:109:17: error: field 'im_src' has incomplete type struct in_addr im_src,im_dst; /usr/include/linux/mroute.h:109:24: error: field 'im_dst' has incomplete type struct in_addr im_src,im_dst; Signed-off-by: Dmitry V. Levin Signed-off-by: David S. Miller --- include/uapi/linux/mroute.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h index cf943016930f..1fe4c1e7d66e 100644 --- a/include/uapi/linux/mroute.h +++ b/include/uapi/linux/mroute.h @@ -3,6 +3,7 @@ #include #include +#include /* For struct in_addr. */ /* Based on the MROUTING 3.5 defines primarily to keep * source compatibility with BSD. -- cgit v1.3-14-g43fede From feb0869d90e51ce8b6fd8a46588465b1b5a26d09 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Thu, 16 Feb 2017 18:05:13 +0300 Subject: uapi: fix linux/rds.h userspace compilation errors Consistently use types from linux/types.h to fix the following linux/rds.h userspace compilation errors: /usr/include/linux/rds.h:106:2: error: unknown type name 'uint8_t' uint8_t name[32]; /usr/include/linux/rds.h:107:2: error: unknown type name 'uint64_t' uint64_t value; /usr/include/linux/rds.h:117:2: error: unknown type name 'uint64_t' uint64_t next_tx_seq; /usr/include/linux/rds.h:118:2: error: unknown type name 'uint64_t' uint64_t next_rx_seq; /usr/include/linux/rds.h:121:2: error: unknown type name 'uint8_t' uint8_t transport[TRANSNAMSIZ]; /* null term ascii */ /usr/include/linux/rds.h:122:2: error: unknown type name 'uint8_t' uint8_t flags; /usr/include/linux/rds.h:129:2: error: unknown type name 'uint64_t' uint64_t seq; /usr/include/linux/rds.h:130:2: error: unknown type name 'uint32_t' uint32_t len; /usr/include/linux/rds.h:135:2: error: unknown type name 'uint8_t' uint8_t flags; /usr/include/linux/rds.h:139:2: error: unknown type name 'uint32_t' uint32_t sndbuf; /usr/include/linux/rds.h:144:2: error: unknown type name 'uint32_t' uint32_t rcvbuf; /usr/include/linux/rds.h:145:2: error: unknown type name 'uint64_t' uint64_t inum; /usr/include/linux/rds.h:153:2: error: unknown type name 'uint64_t' uint64_t hdr_rem; /usr/include/linux/rds.h:154:2: error: unknown type name 'uint64_t' uint64_t data_rem; /usr/include/linux/rds.h:155:2: error: unknown type name 'uint32_t' uint32_t last_sent_nxt; /usr/include/linux/rds.h:156:2: error: unknown type name 'uint32_t' uint32_t last_expected_una; /usr/include/linux/rds.h:157:2: error: unknown type name 'uint32_t' uint32_t last_seen_una; /usr/include/linux/rds.h:164:2: error: unknown type name 'uint8_t' uint8_t src_gid[RDS_IB_GID_LEN]; /usr/include/linux/rds.h:165:2: error: unknown type name 'uint8_t' uint8_t dst_gid[RDS_IB_GID_LEN]; /usr/include/linux/rds.h:167:2: error: unknown type name 'uint32_t' uint32_t max_send_wr; /usr/include/linux/rds.h:168:2: error: unknown type name 'uint32_t' uint32_t max_recv_wr; /usr/include/linux/rds.h:169:2: error: unknown type name 'uint32_t' uint32_t max_send_sge; /usr/include/linux/rds.h:170:2: error: unknown type name 'uint32_t' uint32_t rdma_mr_max; /usr/include/linux/rds.h:171:2: error: unknown type name 'uint32_t' uint32_t rdma_mr_size; /usr/include/linux/rds.h:212:9: error: unknown type name 'uint64_t' typedef uint64_t rds_rdma_cookie_t; /usr/include/linux/rds.h:215:2: error: unknown type name 'uint64_t' uint64_t addr; /usr/include/linux/rds.h:216:2: error: unknown type name 'uint64_t' uint64_t bytes; /usr/include/linux/rds.h:221:2: error: unknown type name 'uint64_t' uint64_t cookie_addr; /usr/include/linux/rds.h:222:2: error: unknown type name 'uint64_t' uint64_t flags; /usr/include/linux/rds.h:228:2: error: unknown type name 'uint64_t' uint64_t cookie_addr; /usr/include/linux/rds.h:229:2: error: unknown type name 'uint64_t' uint64_t flags; /usr/include/linux/rds.h:234:2: error: unknown type name 'uint64_t' uint64_t flags; /usr/include/linux/rds.h:240:2: error: unknown type name 'uint64_t' uint64_t local_vec_addr; /usr/include/linux/rds.h:241:2: error: unknown type name 'uint64_t' uint64_t nr_local; /usr/include/linux/rds.h:242:2: error: unknown type name 'uint64_t' uint64_t flags; /usr/include/linux/rds.h:243:2: error: unknown type name 'uint64_t' uint64_t user_token; /usr/include/linux/rds.h:248:2: error: unknown type name 'uint64_t' uint64_t local_addr; /usr/include/linux/rds.h:249:2: error: unknown type name 'uint64_t' uint64_t remote_addr; /usr/include/linux/rds.h:252:4: error: unknown type name 'uint64_t' uint64_t compare; /usr/include/linux/rds.h:253:4: error: unknown type name 'uint64_t' uint64_t swap; /usr/include/linux/rds.h:256:4: error: unknown type name 'uint64_t' uint64_t add; /usr/include/linux/rds.h:259:4: error: unknown type name 'uint64_t' uint64_t compare; /usr/include/linux/rds.h:260:4: error: unknown type name 'uint64_t' uint64_t swap; /usr/include/linux/rds.h:261:4: error: unknown type name 'uint64_t' uint64_t compare_mask; /usr/include/linux/rds.h:262:4: error: unknown type name 'uint64_t' uint64_t swap_mask; /usr/include/linux/rds.h:265:4: error: unknown type name 'uint64_t' uint64_t add; /usr/include/linux/rds.h:266:4: error: unknown type name 'uint64_t' uint64_t nocarry_mask; /usr/include/linux/rds.h:269:2: error: unknown type name 'uint64_t' uint64_t flags; /usr/include/linux/rds.h:270:2: error: unknown type name 'uint64_t' uint64_t user_token; /usr/include/linux/rds.h:274:2: error: unknown type name 'uint64_t' uint64_t user_token; /usr/include/linux/rds.h:275:2: error: unknown type name 'int32_t' int32_t status; Signed-off-by: Dmitry V. Levin Signed-off-by: David S. Miller --- include/uapi/linux/rds.h | 104 +++++++++++++++++++++++------------------------ 1 file changed, 52 insertions(+), 52 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index 3833113ab2c0..f42d2112ccee 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -117,8 +117,8 @@ #define RDS_INFO_LAST 10010 struct rds_info_counter { - uint8_t name[32]; - uint64_t value; + __u8 name[32]; + __u64 value; } __attribute__((packed)); #define RDS_INFO_CONNECTION_FLAG_SENDING 0x01 @@ -128,35 +128,35 @@ struct rds_info_counter { #define TRANSNAMSIZ 16 struct rds_info_connection { - uint64_t next_tx_seq; - uint64_t next_rx_seq; + __u64 next_tx_seq; + __u64 next_rx_seq; __be32 laddr; __be32 faddr; - uint8_t transport[TRANSNAMSIZ]; /* null term ascii */ - uint8_t flags; + __u8 transport[TRANSNAMSIZ]; /* null term ascii */ + __u8 flags; } __attribute__((packed)); #define RDS_INFO_MESSAGE_FLAG_ACK 0x01 #define RDS_INFO_MESSAGE_FLAG_FAST_ACK 0x02 struct rds_info_message { - uint64_t seq; - uint32_t len; + __u64 seq; + __u32 len; __be32 laddr; __be32 faddr; __be16 lport; __be16 fport; - uint8_t flags; + __u8 flags; } __attribute__((packed)); struct rds_info_socket { - uint32_t sndbuf; + __u32 sndbuf; __be32 bound_addr; __be32 connected_addr; __be16 bound_port; __be16 connected_port; - uint32_t rcvbuf; - uint64_t inum; + __u32 rcvbuf; + __u64 inum; } __attribute__((packed)); struct rds_info_tcp_socket { @@ -164,25 +164,25 @@ struct rds_info_tcp_socket { __be16 local_port; __be32 peer_addr; __be16 peer_port; - uint64_t hdr_rem; - uint64_t data_rem; - uint32_t last_sent_nxt; - uint32_t last_expected_una; - uint32_t last_seen_una; + __u64 hdr_rem; + __u64 data_rem; + __u32 last_sent_nxt; + __u32 last_expected_una; + __u32 last_seen_una; } __attribute__((packed)); #define RDS_IB_GID_LEN 16 struct rds_info_rdma_connection { __be32 src_addr; __be32 dst_addr; - uint8_t src_gid[RDS_IB_GID_LEN]; - uint8_t dst_gid[RDS_IB_GID_LEN]; - - uint32_t max_send_wr; - uint32_t max_recv_wr; - uint32_t max_send_sge; - uint32_t rdma_mr_max; - uint32_t rdma_mr_size; + __u8 src_gid[RDS_IB_GID_LEN]; + __u8 dst_gid[RDS_IB_GID_LEN]; + + __u32 max_send_wr; + __u32 max_recv_wr; + __u32 max_send_sge; + __u32 rdma_mr_max; + __u32 rdma_mr_size; }; /* RDS message Receive Path Latency points */ @@ -242,70 +242,70 @@ struct rds_cmsg_rx_trace { * (so that the application does not have to worry about * alignment). */ -typedef uint64_t rds_rdma_cookie_t; +typedef __u64 rds_rdma_cookie_t; struct rds_iovec { - uint64_t addr; - uint64_t bytes; + __u64 addr; + __u64 bytes; }; struct rds_get_mr_args { struct rds_iovec vec; - uint64_t cookie_addr; - uint64_t flags; + __u64 cookie_addr; + __u64 flags; }; struct rds_get_mr_for_dest_args { struct sockaddr_storage dest_addr; struct rds_iovec vec; - uint64_t cookie_addr; - uint64_t flags; + __u64 cookie_addr; + __u64 flags; }; struct rds_free_mr_args { rds_rdma_cookie_t cookie; - uint64_t flags; + __u64 flags; }; struct rds_rdma_args { rds_rdma_cookie_t cookie; struct rds_iovec remote_vec; - uint64_t local_vec_addr; - uint64_t nr_local; - uint64_t flags; - uint64_t user_token; + __u64 local_vec_addr; + __u64 nr_local; + __u64 flags; + __u64 user_token; }; struct rds_atomic_args { rds_rdma_cookie_t cookie; - uint64_t local_addr; - uint64_t remote_addr; + __u64 local_addr; + __u64 remote_addr; union { struct { - uint64_t compare; - uint64_t swap; + __u64 compare; + __u64 swap; } cswp; struct { - uint64_t add; + __u64 add; } fadd; struct { - uint64_t compare; - uint64_t swap; - uint64_t compare_mask; - uint64_t swap_mask; + __u64 compare; + __u64 swap; + __u64 compare_mask; + __u64 swap_mask; } m_cswp; struct { - uint64_t add; - uint64_t nocarry_mask; + __u64 add; + __u64 nocarry_mask; } m_fadd; }; - uint64_t flags; - uint64_t user_token; + __u64 flags; + __u64 user_token; }; struct rds_rdma_notify { - uint64_t user_token; - int32_t status; + __u64 user_token; + __s32 status; }; #define RDS_RDMA_SUCCESS 0 -- cgit v1.3-14-g43fede From 1786dbf3702e33ce3afd2d3dbe630bd04b1d2e58 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Thu, 16 Feb 2017 18:05:45 +0300 Subject: uapi: fix linux/rds.h userspace compilation error On the kernel side, sockaddr_storage is #define'd to __kernel_sockaddr_storage. Replacing struct sockaddr_storage with struct __kernel_sockaddr_storage defined by fixes the following linux/rds.h userspace compilation error: /usr/include/linux/rds.h:226:26: error: field 'dest_addr' has incomplete type struct sockaddr_storage dest_addr; Signed-off-by: Dmitry V. Levin Signed-off-by: David S. Miller --- include/uapi/linux/rds.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index f42d2112ccee..47c03ca5c404 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -35,6 +35,7 @@ #define _LINUX_RDS_H #include +#include /* For __kernel_sockaddr_storage. */ #define RDS_IB_ABI_VERSION 0x301 @@ -256,7 +257,7 @@ struct rds_get_mr_args { }; struct rds_get_mr_for_dest_args { - struct sockaddr_storage dest_addr; + struct __kernel_sockaddr_storage dest_addr; struct rds_iovec vec; __u64 cookie_addr; __u64 flags; -- cgit v1.3-14-g43fede From 35ea82d611da59f8bea44a37996b3b11bb1d3fd7 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 17 Feb 2017 12:45:38 +0800 Subject: sctp: add support for generating stream ssn reset event notification This patch is to add Stream Reset Event described in rfc6525 section 6.1.1. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/ulpevent.h | 4 ++++ include/uapi/linux/sctp.h | 16 ++++++++++++++++ net/sctp/ulpevent.c | 29 +++++++++++++++++++++++++++++ 3 files changed, 49 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 2c098cd7e7e2..324b5965fc4d 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -128,6 +128,10 @@ struct sctp_ulpevent *sctp_ulpevent_make_authkey( struct sctp_ulpevent *sctp_ulpevent_make_sender_dry_event( const struct sctp_association *asoc, gfp_t gfp); +struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( + const struct sctp_association *asoc, __u16 flags, + __u16 stream_num, __u16 *stream_list, gfp_t gfp); + void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, struct msghdr *); void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event, diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index a91a9cccbae6..d3ae381fcf33 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -490,6 +490,18 @@ struct sctp_sender_dry_event { sctp_assoc_t sender_dry_assoc_id; }; +#define SCTP_STREAM_RESET_INCOMING_SSN 0x0001 +#define SCTP_STREAM_RESET_OUTGOING_SSN 0x0002 +#define SCTP_STREAM_RESET_DENIED 0x0004 +#define SCTP_STREAM_RESET_FAILED 0x0008 +struct sctp_stream_reset_event { + __u16 strreset_type; + __u16 strreset_flags; + __u32 strreset_length; + sctp_assoc_t strreset_assoc_id; + __u16 strreset_stream_list[]; +}; + /* * Described in Section 7.3 * Ancillary Data and Notification Interest Options @@ -505,6 +517,7 @@ struct sctp_event_subscribe { __u8 sctp_adaptation_layer_event; __u8 sctp_authentication_event; __u8 sctp_sender_dry_event; + __u8 sctp_stream_reset_event; }; /* @@ -529,6 +542,7 @@ union sctp_notification { struct sctp_pdapi_event sn_pdapi_event; struct sctp_authkey_event sn_authkey_event; struct sctp_sender_dry_event sn_sender_dry_event; + struct sctp_stream_reset_event sn_strreset_event; }; /* Section 5.3.1 @@ -556,6 +570,8 @@ enum sctp_sn_type { #define SCTP_AUTHENTICATION_INDICATION SCTP_AUTHENTICATION_EVENT SCTP_SENDER_DRY_EVENT, #define SCTP_SENDER_DRY_EVENT SCTP_SENDER_DRY_EVENT + SCTP_STREAM_RESET_EVENT, +#define SCTP_STREAM_RESET_EVENT SCTP_STREAM_RESET_EVENT }; /* Notification error codes used to fill up the error fields in some diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index bea00058ce35..c8881bc542a0 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -854,6 +854,35 @@ struct sctp_ulpevent *sctp_ulpevent_make_sender_dry_event( return event; } +struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( + const struct sctp_association *asoc, __u16 flags, __u16 stream_num, + __u16 *stream_list, gfp_t gfp) +{ + struct sctp_stream_reset_event *sreset; + struct sctp_ulpevent *event; + struct sk_buff *skb; + int length, i; + + length = sizeof(struct sctp_stream_reset_event) + 2 * stream_num; + event = sctp_ulpevent_new(length, MSG_NOTIFICATION, gfp); + if (!event) + return NULL; + + skb = sctp_event2skb(event); + sreset = (struct sctp_stream_reset_event *)skb_put(skb, length); + + sreset->strreset_type = SCTP_STREAM_RESET_EVENT; + sreset->strreset_flags = flags; + sreset->strreset_length = length; + sctp_ulpevent_set_owner(event, asoc); + sreset->strreset_assoc_id = sctp_assoc2id(asoc); + + for (i = 0; i < stream_num; i++) + sreset->strreset_stream_list[i] = ntohs(stream_list[i]); + + return event; +} + /* Return the notification type, assuming this is a notification * event. */ -- cgit v1.3-14-g43fede From 24045a03b8796e3e1ddb370dfe4bc592a9f5f301 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 20 Feb 2017 08:03:30 -0800 Subject: net: mpls: Add support for netconf Add netconf support to MPLS. Allows userpsace to learn and be notified of changes to 'input' enable setting per interface. Acked-by: Nicolas Dichtel Signed-off-by: David Ahern Acked-by: Robert Shearman Signed-off-by: David S. Miller --- include/uapi/linux/netconf.h | 1 + include/uapi/linux/rtnetlink.h | 2 + net/mpls/af_mpls.c | 212 ++++++++++++++++++++++++++++++++++++++++- net/mpls/internal.h | 2 +- 4 files changed, 214 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h index 45dfad509c4d..7e5f0f3e31bf 100644 --- a/include/uapi/linux/netconf.h +++ b/include/uapi/linux/netconf.h @@ -16,6 +16,7 @@ enum { NETCONFA_MC_FORWARDING, NETCONFA_PROXY_NEIGH, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + NETCONFA_INPUT, __NETCONFA_MAX }; #define NETCONFA_MAX (__NETCONFA_MAX - 1) diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 8c93ad1ef9ab..6546917d605a 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -658,6 +658,8 @@ enum rtnetlink_groups { #define RTNLGRP_MPLS_ROUTE RTNLGRP_MPLS_ROUTE RTNLGRP_NSID, #define RTNLGRP_NSID RTNLGRP_NSID + RTNLGRP_MPLS_NETCONF, +#define RTNLGRP_MPLS_NETCONF RTNLGRP_MPLS_NETCONF __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 64d3bf269a26..3818686182b2 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -960,15 +961,215 @@ static size_t mpls_get_stats_af_size(const struct net_device *dev) return nla_total_size_64bit(sizeof(struct mpls_link_stats)); } +static int mpls_netconf_fill_devconf(struct sk_buff *skb, struct mpls_dev *mdev, + u32 portid, u32 seq, int event, + unsigned int flags, int type) +{ + struct nlmsghdr *nlh; + struct netconfmsg *ncm; + bool all = false; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), + flags); + if (!nlh) + return -EMSGSIZE; + + if (type == NETCONFA_ALL) + all = true; + + ncm = nlmsg_data(nlh); + ncm->ncm_family = AF_MPLS; + + if (nla_put_s32(skb, NETCONFA_IFINDEX, mdev->dev->ifindex) < 0) + goto nla_put_failure; + + if ((all || type == NETCONFA_INPUT) && + nla_put_s32(skb, NETCONFA_INPUT, + mdev->input_enabled) < 0) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return 0; + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int mpls_netconf_msgsize_devconf(int type) +{ + int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + + nla_total_size(4); /* NETCONFA_IFINDEX */ + bool all = false; + + if (type == NETCONFA_ALL) + all = true; + + if (all || type == NETCONFA_INPUT) + size += nla_total_size(4); + + return size; +} + +static void mpls_netconf_notify_devconf(struct net *net, int type, + struct mpls_dev *mdev) +{ + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(mpls_netconf_msgsize_devconf(type), GFP_KERNEL); + if (!skb) + goto errout; + + err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, RTM_NEWNETCONF, + 0, type); + if (err < 0) { + /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_MPLS_NETCONF, NULL, GFP_KERNEL); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); +} + +static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = { + [NETCONFA_IFINDEX] = { .len = sizeof(int) }, +}; + +static int mpls_netconf_get_devconf(struct sk_buff *in_skb, + struct nlmsghdr *nlh) +{ + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[NETCONFA_MAX + 1]; + struct netconfmsg *ncm; + struct net_device *dev; + struct mpls_dev *mdev; + struct sk_buff *skb; + int ifindex; + int err; + + err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, + devconf_mpls_policy); + if (err < 0) + goto errout; + + err = -EINVAL; + if (!tb[NETCONFA_IFINDEX]) + goto errout; + + ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); + dev = __dev_get_by_index(net, ifindex); + if (!dev) + goto errout; + + mdev = mpls_dev_get(dev); + if (!mdev) + goto errout; + + err = -ENOBUFS; + skb = nlmsg_new(mpls_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); + if (!skb) + goto errout; + + err = mpls_netconf_fill_devconf(skb, mdev, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, RTM_NEWNETCONF, 0, + NETCONFA_ALL); + if (err < 0) { + /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +errout: + return err; +} + +static int mpls_netconf_dump_devconf(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct hlist_head *head; + struct net_device *dev; + struct mpls_dev *mdev; + int idx, s_idx; + int h, s_h; + + s_h = cb->args[0]; + s_idx = idx = cb->args[1]; + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + rcu_read_lock(); + cb->seq = net->dev_base_seq; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + mdev = mpls_dev_get(dev); + if (!mdev) + goto cont; + if (mpls_netconf_fill_devconf(skb, mdev, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, + NLM_F_MULTI, + NETCONFA_ALL) < 0) { + rcu_read_unlock(); + goto done; + } + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); +cont: + idx++; + } + rcu_read_unlock(); + } +done: + cb->args[0] = h; + cb->args[1] = idx; + + return skb->len; +} + #define MPLS_PERDEV_SYSCTL_OFFSET(field) \ (&((struct mpls_dev *)0)->field) +static int mpls_conf_proc(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int oval = *(int *)ctl->data; + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + if (write) { + struct mpls_dev *mdev = ctl->extra1; + int i = (int *)ctl->data - (int *)mdev; + struct net *net = ctl->extra2; + int val = *(int *)ctl->data; + + if (i == offsetof(struct mpls_dev, input_enabled) && + val != oval) { + mpls_netconf_notify_devconf(net, + NETCONFA_INPUT, + mdev); + } + } + + return ret; +} + static const struct ctl_table mpls_dev_table[] = { { .procname = "input", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = mpls_conf_proc, .data = MPLS_PERDEV_SYSCTL_OFFSET(input_enabled), }, { } @@ -978,6 +1179,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev, struct mpls_dev *mdev) { char path[sizeof("net/mpls/conf/") + IFNAMSIZ]; + struct net *net = dev_net(dev); struct ctl_table *table; int i; @@ -988,8 +1190,11 @@ static int mpls_dev_sysctl_register(struct net_device *dev, /* Table data contains only offsets relative to the base of * the mdev at this point, so make them absolute. */ - for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++) + for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++) { table[i].data = (char *)mdev + (uintptr_t)table[i].data; + table[i].extra1 = mdev; + table[i].extra2 = net; + } snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name); @@ -1041,6 +1246,7 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev) if (err) goto free; + mdev->dev = dev; rcu_assign_pointer(dev->mpls_ptr, mdev); return mdev; @@ -1861,6 +2067,8 @@ static int __init mpls_init(void) rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, NULL); rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, NULL); rtnl_register(PF_MPLS, RTM_GETROUTE, NULL, mpls_dump_routes, NULL); + rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, + mpls_netconf_dump_devconf, NULL); err = 0; out: return err; diff --git a/net/mpls/internal.h b/net/mpls/internal.h index d97243034605..76360d8b9579 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -16,7 +16,7 @@ struct mpls_pcpu_stats { struct mpls_dev { int input_enabled; - + struct net_device *dev; struct mpls_pcpu_stats __percpu *stats; struct ctl_table_header *sysctl; -- cgit v1.3-14-g43fede