diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 14 | ||||
-rw-r--r-- | net/ipv4/esp4_offload.c | 4 | ||||
-rw-r--r-- | net/ipv4/fou.c | 20 | ||||
-rw-r--r-- | net/ipv4/gre_offload.c | 8 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 9 | ||||
-rw-r--r-- | net/ipv4/inet_fragment.c | 1 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_input.c | 147 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 22 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 22 | ||||
-rw-r--r-- | net/ipv4/ipmr_base.c | 1 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_log_ipv4.c | 8 | ||||
-rw-r--r-- | net/ipv4/ping.c | 10 | ||||
-rw-r--r-- | net/ipv4/proc.c | 2 | ||||
-rw-r--r-- | net/ipv4/raw.c | 11 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 20 | ||||
-rw-r--r-- | net/ipv4/tcp_bbr.c | 6 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 48 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 229 | ||||
-rw-r--r-- | net/ipv4/tcp_offload.c | 17 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 14 | ||||
-rw-r--r-- | net/ipv4/tcp_rate.c | 4 | ||||
-rw-r--r-- | net/ipv4/udp.c | 11 | ||||
-rw-r--r-- | net/ipv4/udp_offload.c | 13 |
25 files changed, 389 insertions, 257 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b403499fdabe..f2a0a3bab6b5 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -229,6 +229,7 @@ int inet_listen(struct socket *sock, int backlog) err = inet_csk_listen_start(sk, backlog); if (err) goto out; + tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } sk->sk_max_ack_backlog = backlog; err = 0; @@ -1384,12 +1385,12 @@ out: } EXPORT_SYMBOL(inet_gso_segment); -struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) +struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; - struct sk_buff **pp = NULL; - struct sk_buff *p; + struct sk_buff *pp = NULL; const struct iphdr *iph; + struct sk_buff *p; unsigned int hlen; unsigned int off; unsigned int id; @@ -1425,7 +1426,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); id >>= 16; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { struct iphdr *iph2; u16 flush_id; @@ -1505,8 +1506,8 @@ out: } EXPORT_SYMBOL(inet_gro_receive); -static struct sk_buff **ipip_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *ipip_gro_receive(struct list_head *head, + struct sk_buff *skb) { if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; @@ -1882,6 +1883,7 @@ fs_initcall(ipv4_offload_init); static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, + .list_func = ip_list_rcv, }; static int __init inet_init(void) diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 7cf755ef9efb..bbeecd13e534 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -28,8 +28,8 @@ #include <linux/spinlock.h> #include <net/udp.h> -static struct sk_buff **esp4_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *esp4_gro_receive(struct list_head *head, + struct sk_buff *skb) { int offset = skb_gro_offset(skb); struct xfrm_offload *xo; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index c9ec1603666b..500a59906b87 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -224,14 +224,14 @@ drop: return 0; } -static struct sk_buff **fou_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *fou_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { - const struct net_offload *ops; - struct sk_buff **pp = NULL; u8 proto = fou_from_sock(sk)->protocol; const struct net_offload **offloads; + const struct net_offload *ops; + struct sk_buff *pp = NULL; /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel @@ -305,13 +305,13 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, return guehdr; } -static struct sk_buff **gue_gro_receive(struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *gue_gro_receive(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { const struct net_offload **offloads; const struct net_offload *ops; - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; struct guehdr *guehdr; size_t len, optlen, hdrlen, off; @@ -397,7 +397,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, skb_gro_pull(skb, hdrlen); - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { const struct guehdr *guehdr2; if (!NAPI_GRO_CB(p)->same_flow) diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 6a7d980105f6..6c63524f598a 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -108,10 +108,10 @@ out: return segs; } -static struct sk_buff **gre_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *gre_gro_receive(struct list_head *head, + struct sk_buff *skb) { - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; const struct gre_base_hdr *greh; unsigned int hlen, grehlen; @@ -182,7 +182,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, null_compute_pseudo); } - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { const struct gre_base_hdr *greh2; if (!NAPI_GRO_CB(p)->same_flow) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1617604c9284..695979b7ef6d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -429,14 +429,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) icmp_param->data.icmph.checksum = 0; + ipcm_init(&ipc); inet->tos = ip_hdr(skb)->tos; sk->sk_mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); - ipc.opt = NULL; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; if (icmp_param->replyopts.opt.opt.optlen) { ipc.opt = &icmp_param->replyopts.opt; @@ -710,11 +707,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; sk->sk_mark = mark; + ipcm_init(&ipc); ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 1e4cf3ab560f..d3162baca9f1 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -20,6 +20,7 @@ #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/slab.h> +#include <linux/rhashtable.h> #include <net/sock.h> #include <net/inet_frag.h> diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 2d8efeecf619..c8ca5d8f0f75 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -587,6 +587,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, goto err_free_skb; key = &tun_info->key; + if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + goto err_free_rt; md = ip_tunnel_info_opts(tun_info); if (!md) goto err_free_rt; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 7582713dd18f..3196cf58f418 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -307,7 +307,8 @@ drop: return true; } -static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +static int ip_rcv_finish_core(struct net *net, struct sock *sk, + struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); int (*edemux)(struct sk_buff *skb); @@ -315,13 +316,6 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) struct rtable *rt; int err; - /* if ingress device is enslaved to an L3 master device pass the - * skb to its handler for processing - */ - skb = l3mdev_ip_rcv(skb); - if (!skb) - return NET_RX_SUCCESS; - if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk && @@ -393,7 +387,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) goto drop; } - return dst_input(skb); + return NET_RX_SUCCESS; drop: kfree_skb(skb); @@ -405,13 +399,29 @@ drop_error: goto drop; } +static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + int ret; + + /* if ingress device is enslaved to an L3 master device pass the + * skb to its handler for processing + */ + skb = l3mdev_ip_rcv(skb); + if (!skb) + return NET_RX_SUCCESS; + + ret = ip_rcv_finish_core(net, sk, skb); + if (ret != NET_RX_DROP) + ret = dst_input(skb); + return ret; +} + /* * Main IP Receive routine. */ -int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) +static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) { const struct iphdr *iph; - struct net *net; u32 len; /* When the interface is in promisc. mode, drop all the crap @@ -421,7 +431,6 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, goto drop; - net = dev_net(dev); __IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len); skb = skb_share_check(skb, GFP_ATOMIC); @@ -489,9 +498,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, /* Must drop socket now because of tproxy. */ skb_orphan(skb); - return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, - net, NULL, skb, dev, NULL, - ip_rcv_finish); + return skb; csum_error: __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); @@ -500,5 +507,113 @@ inhdr_error: drop: kfree_skb(skb); out: - return NET_RX_DROP; + return NULL; +} + +/* + * IP receive entry point + */ +int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, + struct net_device *orig_dev) +{ + struct net *net = dev_net(dev); + + skb = ip_rcv_core(skb, net); + if (skb == NULL) + return NET_RX_DROP; + return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, + net, NULL, skb, dev, NULL, + ip_rcv_finish); +} + +static void ip_sublist_rcv_finish(struct list_head *head) +{ + struct sk_buff *skb, *next; + + list_for_each_entry_safe(skb, next, head, list) { + list_del(&skb->list); + /* Handle ip{6}_forward case, as sch_direct_xmit have + * another kind of SKB-list usage (see validate_xmit_skb_list) + */ + skb->next = NULL; + dst_input(skb); + } +} + +static void ip_list_rcv_finish(struct net *net, struct sock *sk, + struct list_head *head) +{ + struct dst_entry *curr_dst = NULL; + struct sk_buff *skb, *next; + struct list_head sublist; + + INIT_LIST_HEAD(&sublist); + list_for_each_entry_safe(skb, next, head, list) { + struct dst_entry *dst; + + list_del(&skb->list); + /* if ingress device is enslaved to an L3 master device pass the + * skb to its handler for processing + */ + skb = l3mdev_ip_rcv(skb); + if (!skb) + continue; + if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP) + continue; + + dst = skb_dst(skb); + if (curr_dst != dst) { + /* dispatch old sublist */ + if (!list_empty(&sublist)) + ip_sublist_rcv_finish(&sublist); + /* start new sublist */ + INIT_LIST_HEAD(&sublist); + curr_dst = dst; + } + list_add_tail(&skb->list, &sublist); + } + /* dispatch final sublist */ + ip_sublist_rcv_finish(&sublist); +} + +static void ip_sublist_rcv(struct list_head *head, struct net_device *dev, + struct net *net) +{ + NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL, + head, dev, NULL, ip_rcv_finish); + ip_list_rcv_finish(net, NULL, head); +} + +/* Receive a list of IP packets */ +void ip_list_rcv(struct list_head *head, struct packet_type *pt, + struct net_device *orig_dev) +{ + struct net_device *curr_dev = NULL; + struct net *curr_net = NULL; + struct sk_buff *skb, *next; + struct list_head sublist; + + INIT_LIST_HEAD(&sublist); + list_for_each_entry_safe(skb, next, head, list) { + struct net_device *dev = skb->dev; + struct net *net = dev_net(dev); + + list_del(&skb->list); + skb = ip_rcv_core(skb, net); + if (skb == NULL) + continue; + + if (curr_dev != dev || curr_net != net) { + /* dispatch old sublist */ + if (!list_empty(&sublist)) + ip_sublist_rcv(&sublist, curr_dev, curr_net); + /* start new sublist */ + INIT_LIST_HEAD(&sublist); + curr_dev = dev; + curr_net = net; + } + list_add_tail(&skb->list, &sublist); + } + /* dispatch final sublist */ + ip_sublist_rcv(&sublist, curr_dev, curr_net); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b3308e9d9762..e2b6bd478afb 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -423,7 +423,8 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) } /* Note: skb->sk can be different from sk, in case of tunnels */ -int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) +int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, + __u8 tos) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); @@ -462,7 +463,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS(sk), + RT_CONN_FLAGS_TOS(sk, tos), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; @@ -478,7 +479,7 @@ packet_routed: skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); - *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff)); + *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff)); if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df) iph->frag_off = htons(IP_DF); else @@ -511,7 +512,7 @@ no_route: kfree_skb(skb); return -EHOSTUNREACH; } -EXPORT_SYMBOL(ip_queue_xmit); +EXPORT_SYMBOL(__ip_queue_xmit); static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { @@ -1145,14 +1146,15 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->fragsize = ip_sk_use_pmtu(sk) ? dst_mtu(&rt->dst) : rt->dst.dev->mtu; - cork->gso_size = sk->sk_type == SOCK_DGRAM && - sk->sk_protocol == IPPROTO_UDP ? ipc->gso_size : 0; + cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->priority = ipc->priority; - cork->tx_flags = ipc->tx_flags; + cork->transmit_time = ipc->sockc.transmit_time; + cork->tx_flags = 0; + sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags); return 0; } @@ -1413,6 +1415,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; skb->mark = sk->sk_mark; + skb->tstamp = cork->transmit_time; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount @@ -1545,11 +1548,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt)) return; + ipcm_init(&ipc); ipc.addr = daddr; - ipc.opt = NULL; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; if (replyopts.opt.opt.optlen) { ipc.opt = &replyopts.opt; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9f79b9803a16..5660adcf7a04 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -60,6 +60,7 @@ #include <linux/netfilter_ipv4.h> #include <linux/compat.h> #include <linux/export.h> +#include <linux/rhashtable.h> #include <net/ip_tunnels.h> #include <net/checksum.h> #include <net/netlink.h> @@ -1051,7 +1052,7 @@ static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *skb; int ret; - if (assert == IGMPMSG_WHOLEPKT) + if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) skb = skb_realloc_headroom(pkt, sizeof(struct iphdr)); else skb = alloc_skb(128, GFP_ATOMIC); @@ -1059,7 +1060,7 @@ static int ipmr_cache_report(struct mr_table *mrt, if (!skb) return -ENOBUFS; - if (assert == IGMPMSG_WHOLEPKT) { + if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) { /* Ugly, but we have no choice with this interface. * Duplicate old header, fix ihl, length etc. * And all this only to mangle msg->im_msgtype and @@ -1070,9 +1071,12 @@ static int ipmr_cache_report(struct mr_table *mrt, skb_reset_transport_header(skb); msg = (struct igmpmsg *)skb_network_header(skb); memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr)); - msg->im_msgtype = IGMPMSG_WHOLEPKT; + msg->im_msgtype = assert; msg->im_mbz = 0; - msg->im_vif = mrt->mroute_reg_vif_num; + if (assert == IGMPMSG_WRVIFWHOLE) + msg->im_vif = vifi; + else + msg->im_vif = mrt->mroute_reg_vif_num; ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); @@ -1371,6 +1375,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, struct mr_table *mrt; struct vifctl vif; struct mfcctl mfc; + bool do_wrvifwhole; u32 uval; /* There's one exception to the lock - MRT_DONE which needs to unlock */ @@ -1501,10 +1506,12 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, break; } + do_wrvifwhole = (val == IGMPMSG_WRVIFWHOLE); val = !!val; if (val != mrt->mroute_do_pim) { mrt->mroute_do_pim = val; mrt->mroute_do_assert = val; + mrt->mroute_do_wrvifwhole = do_wrvifwhole; } break; case MRT_TABLE: @@ -1982,6 +1989,9 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, MFC_ASSERT_THRESH)) { c->_c.mfc_un.res.last_assert = jiffies; ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF); + if (mrt->mroute_do_wrvifwhole) + ipmr_cache_report(mrt, skb, true_vifi, + IGMPMSG_WRVIFWHOLE); } goto dont_forward; } @@ -2658,7 +2668,9 @@ static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb) mrt->mroute_reg_vif_num) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT, mrt->mroute_do_assert) || - nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim)) + nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim) || + nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE, + mrt->mroute_do_wrvifwhole)) return false; return true; diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index cafb0506c8c9..1ad9aa62a97b 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -2,6 +2,7 @@ * Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation */ +#include <linux/rhashtable.h> #include <linux/mroute_base.h> /* Sets everything common except 'dev', since that is done under locking */ diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 4388de0e5380..1e6f28c97d3a 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -35,7 +35,7 @@ static const struct nf_loginfo default_loginfo = { }; /* One level of recursion won't kill us */ -static void dump_ipv4_packet(struct nf_log_buf *m, +static void dump_ipv4_packet(struct net *net, struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int iphoff) { @@ -183,7 +183,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m, /* Max length: 3+maxlen */ if (!iphoff) { /* Only recurse once. */ nf_log_buf_add(m, "["); - dump_ipv4_packet(m, info, skb, + dump_ipv4_packet(net, m, info, skb, iphoff + ih->ihl*4+sizeof(_icmph)); nf_log_buf_add(m, "] "); } @@ -251,7 +251,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m, /* Max length: 15 "UID=4294967295 " */ if ((logflags & NF_LOG_UID) && !iphoff) - nf_log_dump_sk_uid_gid(m, skb->sk); + nf_log_dump_sk_uid_gid(net, m, skb->sk); /* Max length: 16 "MARK=0xFFFFFFFF " */ if (!iphoff && skb->mark) @@ -333,7 +333,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, if (in != NULL) dump_ipv4_mac_header(m, loginfo, skb); - dump_ipv4_packet(m, loginfo, skb, 0); + dump_ipv4_packet(net, m, loginfo, skb, 0); nf_log_buf_close(m); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2ed64bca54e3..b54c964ad925 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -739,13 +739,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* no remote port */ } - ipc.sockc.tsflags = sk->sk_tsflags; - ipc.addr = inet->inet_saddr; - ipc.opt = NULL; - ipc.oif = sk->sk_bound_dev_if; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; + ipcm_init_sk(&ipc, inet); if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -769,8 +763,6 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } - sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); - saddr = ipc.addr; ipc.addr = faddr = daddr; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 77350c1256ce..b46e4cf9a55a 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -287,6 +287,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED), SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE), SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED), + SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP), + SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index abb3c9490c55..33df4d76db2d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -381,6 +381,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; + skb->tstamp = sockc->transmit_time; skb_dst_set(skb, &rt->dst); *rtp = NULL; @@ -561,13 +562,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) daddr = inet->inet_daddr; } - ipc.sockc.tsflags = sk->sk_tsflags; - ipc.addr = inet->inet_saddr; - ipc.opt = NULL; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; - ipc.oif = sk->sk_bound_dev_if; + ipcm_init_sk(&ipc, inet); if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -670,8 +665,6 @@ back_from_confirm: &rt, msg->msg_flags, &ipc.sockc); else { - sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); - if (!ipc.addr) ipc.addr = fl4.daddr; lock_sock(sk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4491faf83f4f..bce53b1728a6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -817,8 +817,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, * This occurs when user tries to read * from never connected socket. */ - if (!sock_flag(sk, SOCK_DONE)) - ret = -ENOTCONN; + ret = -ENOTCONN; break; } if (!timeo) { @@ -1241,7 +1240,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) /* 'common' sending to sendq */ } - sockc.tsflags = sk->sk_tsflags; + sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) { @@ -1275,9 +1274,6 @@ restart: int linear; new_segment: - /* Allocate new segment. If the interface is SG, - * allocate skb fitting to single page. - */ if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; @@ -2042,13 +2038,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, break; if (sk->sk_state == TCP_CLOSE) { - if (!sock_flag(sk, SOCK_DONE)) { - /* This occurs when user tries to read - * from never connected socket. - */ - copied = -ENOTCONN; - break; - } + /* This occurs when user tries to read + * from never connected socket. + */ + copied = -ENOTCONN; break; } @@ -2576,6 +2569,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; + tp->rcv_rtt_last_tsecr = 0; tp->write_seq += tp->max_window + 2; if (tp->write_seq == 0) tp->write_seq = 1; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 58e2f479ffb4..3b5f45b9e81e 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -205,7 +205,11 @@ static u32 bbr_bw(const struct sock *sk) */ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) { - rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache); + unsigned int mss = tcp_sk(sk)->mss_cache; + + if (!tcp_needs_internal_pacing(sk)) + mss = tcp_mss_to_mtu(sk, mss); + rate *= mss; rate *= gain; rate >>= BBR_SCALE; rate *= USEC_PER_SEC; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8e5522c6833a..91dbb9afb950 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -78,6 +78,7 @@ #include <linux/errqueue.h> #include <trace/events/tcp.h> #include <linux/static_key.h> +#include <net/busy_poll.h> int sysctl_tcp_max_orphans __read_mostly = NR_FILE; @@ -582,9 +583,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, { struct tcp_sock *tp = tcp_sk(sk); - if (tp->rx_opt.rcv_tsecr && - (TCP_SKB_CB(skb)->end_seq - - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) { + if (tp->rx_opt.rcv_tsecr == tp->rcv_rtt_last_tsecr) + return; + tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr; + + if (TCP_SKB_CB(skb)->end_seq - + TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) { u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; u32 delta_us; @@ -3458,7 +3462,7 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static void tcp_store_ts_recent(struct tcp_sock *tp) { tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; - tp->rx_opt.ts_recent_stamp = get_seconds(); + tp->rx_opt.ts_recent_stamp = ktime_get_seconds(); } static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) @@ -4339,6 +4343,11 @@ static bool tcp_try_coalesce(struct sock *sk, if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq) return false; +#ifdef CONFIG_TLS_DEVICE + if (from->decrypted != to->decrypted) + return false; +#endif + if (!skb_try_coalesce(to, from, fragstolen, &delta)) return false; @@ -4617,8 +4626,10 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) skb->data_len = data_len; skb->len = size; - if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) + if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); goto err_free; + } err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); if (err) @@ -4674,18 +4685,21 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) * Out of sequence packets to the out_of_order_queue. */ if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) { - if (tcp_receive_window(tp) == 0) + if (tcp_receive_window(tp) == 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; + } /* Ok. In sequence. In window. */ queue_and_out: if (skb_queue_len(&sk->sk_receive_queue) == 0) sk_forced_mem_schedule(sk, skb->truesize); - else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) + else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); goto drop; + } eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); - tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); if (skb->len) tcp_event_data_recv(sk, skb); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) @@ -4741,8 +4755,10 @@ drop: /* If window is closed, drop tail of packet. But after * remembering D-SACK for its head made in previous line. */ - if (!tcp_receive_window(tp)) + if (!tcp_receive_window(tp)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; + } goto queue_and_out; } @@ -4860,6 +4876,9 @@ restart: break; memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); +#ifdef CONFIG_TLS_DEVICE + nskb->decrypted = skb->decrypted; +#endif TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start; if (list) __skb_queue_before(list, skb, nskb); @@ -4887,6 +4906,10 @@ restart: skb == tail || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) goto end; +#ifdef CONFIG_TLS_DEVICE + if (skb->decrypted != nskb->decrypted) + goto end; +#endif } } } @@ -5484,6 +5507,11 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) tcp_ack(sk, skb, 0); __kfree_skb(skb); tcp_data_snd_check(sk); + /* When receiving pure ack in fast path, update + * last ts ecr directly instead of calling + * tcp_rcv_rtt_measure_ts() + */ + tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr; return; } else { /* Header too small */ TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); @@ -5585,6 +5613,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); + sk_mark_napi_id(sk, skb); } tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); @@ -6413,6 +6442,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->txhash = net_tx_rndhash(); tcp_openreq_init_rwin(req, sk, dst); + sk_rx_queue_set(req_to_sk(req), skb); if (!want_cookie) { tcp_reqsk_record_syn(sk, req, skb); fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3b2711e33e4c..9e041fa5c545 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -155,7 +155,8 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) and use initial timestamp retrieved from peer table. */ if (tcptw->tw_ts_recent_stamp && - (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) { + (!twp || (reuse && time_after32(ktime_get_seconds(), + tcptw->tw_ts_recent_stamp)))) { /* In case of repair and re-using TIME-WAIT sockets we still * want to be sure that it is safe as above but honor the * sequence numbers and time stamps set as part of the repair diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 1dda1341a223..75ef332a7caf 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -144,7 +144,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tw->tw_substate = TCP_TIME_WAIT; tcptw->tw_rcv_nxt = TCP_SKB_CB(skb)->end_seq; if (tmp_opt.saw_tstamp) { - tcptw->tw_ts_recent_stamp = get_seconds(); + tcptw->tw_ts_recent_stamp = ktime_get_seconds(); tcptw->tw_ts_recent = tmp_opt.rcv_tsval; } @@ -189,7 +189,7 @@ kill: if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; - tcptw->tw_ts_recent_stamp = get_seconds(); + tcptw->tw_ts_recent_stamp = ktime_get_seconds(); } inet_twsk_put(tw); @@ -449,119 +449,122 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct sk_buff *skb) { struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); + const struct inet_request_sock *ireq = inet_rsk(req); + struct tcp_request_sock *treq = tcp_rsk(req); + struct inet_connection_sock *newicsk; + struct tcp_sock *oldtp, *newtp; - if (newsk) { - const struct inet_request_sock *ireq = inet_rsk(req); - struct tcp_request_sock *treq = tcp_rsk(req); - struct inet_connection_sock *newicsk = inet_csk(newsk); - struct tcp_sock *newtp = tcp_sk(newsk); - struct tcp_sock *oldtp = tcp_sk(sk); - - smc_check_reset_syn_req(oldtp, req, newtp); - - /* Now setup tcp_sock */ - newtp->pred_flags = 0; - - newtp->rcv_wup = newtp->copied_seq = - newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->segs_in = 1; - - newtp->snd_sml = newtp->snd_una = - newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; - - INIT_LIST_HEAD(&newtp->tsq_node); - INIT_LIST_HEAD(&newtp->tsorted_sent_queue); - - tcp_init_wl(newtp, treq->rcv_isn); - - newtp->srtt_us = 0; - newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U); - newicsk->icsk_rto = TCP_TIMEOUT_INIT; - newicsk->icsk_ack.lrcvtime = tcp_jiffies32; - - newtp->packets_out = 0; - newtp->retrans_out = 0; - newtp->sacked_out = 0; - newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; - newtp->tlp_high_seq = 0; - newtp->lsndtime = tcp_jiffies32; - newsk->sk_txhash = treq->txhash; - newtp->last_oow_ack_time = 0; - newtp->total_retrans = req->num_retrans; - - /* So many TCP implementations out there (incorrectly) count the - * initial SYN frame in their delayed-ACK and congestion control - * algorithms that we must have the following bandaid to talk - * efficiently to them. -DaveM - */ - newtp->snd_cwnd = TCP_INIT_CWND; - newtp->snd_cwnd_cnt = 0; - - /* There's a bubble in the pipe until at least the first ACK. */ - newtp->app_limited = ~0U; - - tcp_init_xmit_timers(newsk); - newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; - - newtp->rx_opt.saw_tstamp = 0; - - newtp->rx_opt.dsack = 0; - newtp->rx_opt.num_sacks = 0; - - newtp->urg_data = 0; - - if (sock_flag(newsk, SOCK_KEEPOPEN)) - inet_csk_reset_keepalive_timer(newsk, - keepalive_time_when(newtp)); - - newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; - newtp->rx_opt.sack_ok = ireq->sack_ok; - newtp->window_clamp = req->rsk_window_clamp; - newtp->rcv_ssthresh = req->rsk_rcv_wnd; - newtp->rcv_wnd = req->rsk_rcv_wnd; - newtp->rx_opt.wscale_ok = ireq->wscale_ok; - if (newtp->rx_opt.wscale_ok) { - newtp->rx_opt.snd_wscale = ireq->snd_wscale; - newtp->rx_opt.rcv_wscale = ireq->rcv_wscale; - } else { - newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0; - newtp->window_clamp = min(newtp->window_clamp, 65535U); - } - newtp->snd_wnd = (ntohs(tcp_hdr(skb)->window) << - newtp->rx_opt.snd_wscale); - newtp->max_window = newtp->snd_wnd; - - if (newtp->rx_opt.tstamp_ok) { - newtp->rx_opt.ts_recent = req->ts_recent; - newtp->rx_opt.ts_recent_stamp = get_seconds(); - newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; - } else { - newtp->rx_opt.ts_recent_stamp = 0; - newtp->tcp_header_len = sizeof(struct tcphdr); - } - newtp->tsoffset = treq->ts_off; + if (!newsk) + return NULL; + + newicsk = inet_csk(newsk); + newtp = tcp_sk(newsk); + oldtp = tcp_sk(sk); + + smc_check_reset_syn_req(oldtp, req, newtp); + + /* Now setup tcp_sock */ + newtp->pred_flags = 0; + + newtp->rcv_wup = newtp->copied_seq = + newtp->rcv_nxt = treq->rcv_isn + 1; + newtp->segs_in = 1; + + newtp->snd_sml = newtp->snd_una = + newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; + + INIT_LIST_HEAD(&newtp->tsq_node); + INIT_LIST_HEAD(&newtp->tsorted_sent_queue); + + tcp_init_wl(newtp, treq->rcv_isn); + + newtp->srtt_us = 0; + newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); + minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U); + newicsk->icsk_rto = TCP_TIMEOUT_INIT; + newicsk->icsk_ack.lrcvtime = tcp_jiffies32; + + newtp->packets_out = 0; + newtp->retrans_out = 0; + newtp->sacked_out = 0; + newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + newtp->tlp_high_seq = 0; + newtp->lsndtime = tcp_jiffies32; + newsk->sk_txhash = treq->txhash; + newtp->last_oow_ack_time = 0; + newtp->total_retrans = req->num_retrans; + + /* So many TCP implementations out there (incorrectly) count the + * initial SYN frame in their delayed-ACK and congestion control + * algorithms that we must have the following bandaid to talk + * efficiently to them. -DaveM + */ + newtp->snd_cwnd = TCP_INIT_CWND; + newtp->snd_cwnd_cnt = 0; + + /* There's a bubble in the pipe until at least the first ACK. */ + newtp->app_limited = ~0U; + + tcp_init_xmit_timers(newsk); + newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; + + newtp->rx_opt.saw_tstamp = 0; + + newtp->rx_opt.dsack = 0; + newtp->rx_opt.num_sacks = 0; + + newtp->urg_data = 0; + + if (sock_flag(newsk, SOCK_KEEPOPEN)) + inet_csk_reset_keepalive_timer(newsk, + keepalive_time_when(newtp)); + + newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; + newtp->rx_opt.sack_ok = ireq->sack_ok; + newtp->window_clamp = req->rsk_window_clamp; + newtp->rcv_ssthresh = req->rsk_rcv_wnd; + newtp->rcv_wnd = req->rsk_rcv_wnd; + newtp->rx_opt.wscale_ok = ireq->wscale_ok; + if (newtp->rx_opt.wscale_ok) { + newtp->rx_opt.snd_wscale = ireq->snd_wscale; + newtp->rx_opt.rcv_wscale = ireq->rcv_wscale; + } else { + newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0; + newtp->window_clamp = min(newtp->window_clamp, 65535U); + } + newtp->snd_wnd = ntohs(tcp_hdr(skb)->window) << newtp->rx_opt.snd_wscale; + newtp->max_window = newtp->snd_wnd; + + if (newtp->rx_opt.tstamp_ok) { + newtp->rx_opt.ts_recent = req->ts_recent; + newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); + newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; + } else { + newtp->rx_opt.ts_recent_stamp = 0; + newtp->tcp_header_len = sizeof(struct tcphdr); + } + newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG - newtp->md5sig_info = NULL; /*XXX*/ - if (newtp->af_specific->md5_lookup(sk, newsk)) - newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; + newtp->md5sig_info = NULL; /*XXX*/ + if (newtp->af_specific->md5_lookup(sk, newsk)) + newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif - if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) - newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; - newtp->rx_opt.mss_clamp = req->mss; - tcp_ecn_openreq_child(newtp, req); - newtp->fastopen_req = NULL; - newtp->fastopen_rsk = NULL; - newtp->syn_data_acked = 0; - newtp->rack.mstamp = 0; - newtp->rack.advanced = 0; - newtp->rack.reo_wnd_steps = 1; - newtp->rack.last_delivered = 0; - newtp->rack.reo_wnd_persist = 0; - newtp->rack.dsack_seen = 0; - - __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); - } + if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) + newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; + newtp->rx_opt.mss_clamp = req->mss; + tcp_ecn_openreq_child(newtp, req); + newtp->fastopen_req = NULL; + newtp->fastopen_rsk = NULL; + newtp->syn_data_acked = 0; + newtp->rack.mstamp = 0; + newtp->rack.advanced = 0; + newtp->rack.reo_wnd_steps = 1; + newtp->rack.last_delivered = 0; + newtp->rack.reo_wnd_persist = 0; + newtp->rack.dsack_seen = 0; + + __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); + return newsk; } EXPORT_SYMBOL(tcp_create_openreq_child); @@ -600,7 +603,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * it can be estimated (approximately) * from another data. */ - tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout); + tmp_opt.ts_recent_stamp = ktime_get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout); paws_reject = tcp_paws_reject(&tmp_opt, th->rst); } } diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 8cc7c3487330..870b0a335061 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -180,9 +180,9 @@ out: return segs; } -struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) { - struct sk_buff **pp = NULL; + struct sk_buff *pp = NULL; struct sk_buff *p; struct tcphdr *th; struct tcphdr *th2; @@ -220,7 +220,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) len = skb_gro_len(skb); flags = tcp_flag_word(th); - for (; (p = *head); head = &p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -233,7 +233,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) goto found; } - + p = NULL; goto out_check_final; found: @@ -262,8 +262,11 @@ found: flush |= (len - 1) >= mss; flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); +#ifdef CONFIG_TLS_DEVICE + flush |= p->decrypted ^ skb->decrypted; +#endif - if (flush || skb_gro_receive(head, skb)) { + if (flush || skb_gro_receive(p, skb)) { mss = 1; goto out_check_final; } @@ -277,7 +280,7 @@ out_check_final: TCP_FLAG_FIN)); if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) - pp = head; + pp = p; out: NAPI_GRO_CB(skb)->flush |= (flush != 0); @@ -302,7 +305,7 @@ int tcp_gro_complete(struct sk_buff *skb) } EXPORT_SYMBOL(tcp_gro_complete); -static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) +static struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 00e5a300ddb9..6cbab56e7407 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -973,17 +973,6 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) return HRTIMER_NORESTART; } -/* BBR congestion control needs pacing. - * Same remark for SO_MAX_PACING_RATE. - * sch_fq packet scheduler is efficiently handling pacing, - * but is not always installed/used. - * Return true if TCP stack should pace packets itself. - */ -static bool tcp_needs_internal_pacing(const struct sock *sk) -{ - return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; -} - static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) { u64 len_ns; @@ -995,9 +984,6 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) if (!rate || rate == ~0U) return; - /* Should account for header sizes as sch_fq does, - * but lets make things simple. - */ len_ns = (u64)skb->len * NSEC_PER_SEC; do_div(len_ns, rate); hrtimer_start(&tcp_sk(sk)->pacing_timer, diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index c61240e43923..4dff40dad4dc 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -146,6 +146,10 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, rs->prior_mstamp); /* ack phase */ rs->interval_us = max(snd_us, ack_us); + /* Record both segment send and ack receive intervals */ + rs->snd_interval_us = snd_us; + rs->rcv_interval_us = ack_us; + /* Normally we expect interval_us >= min-rtt. * Note that rate may still be over-estimated when a spuriously * retransmistted skb was first (s)acked because "interval_us" diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 24e116ddae79..060e841dde40 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -926,11 +926,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */ return -EOPNOTSUPP; - ipc.opt = NULL; - ipc.tx_flags = 0; - ipc.ttl = 0; - ipc.tos = -1; - getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; fl4 = &inet->cork.fl.u.ip4; @@ -977,9 +972,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) connected = 1; } - ipc.sockc.tsflags = sk->sk_tsflags; - ipc.addr = inet->inet_saddr; - ipc.oif = sk->sk_bound_dev_if; + ipcm_init_sk(&ipc, inet); ipc.gso_size = up->gso_size; if (msg->msg_controllen) { @@ -1027,8 +1020,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) saddr = ipc.addr; ipc.addr = faddr = daddr; - sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); - if (ipc.opt && ipc.opt->opt.srr) { if (!daddr) { err = -EINVAL; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 69c54540d5b4..0c0522b79b43 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -343,10 +343,11 @@ out: return segs; } -struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, - struct udphdr *uh, udp_lookup_t lookup) +struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct udphdr *uh, udp_lookup_t lookup) { - struct sk_buff *p, **pp = NULL; + struct sk_buff *pp = NULL; + struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; @@ -371,7 +372,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, unflush: flush = 0; - for (p = *head; p; p = p->next) { + list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -399,8 +400,8 @@ out: } EXPORT_SYMBOL(udp_gro_receive); -static struct sk_buff **udp4_gro_receive(struct sk_buff **head, - struct sk_buff *skb) +static struct sk_buff *udp4_gro_receive(struct list_head *head, + struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); |