summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c12
-rw-r--r--net/ipv4/devinet.c2
-rw-r--r--net/ipv4/igmp.c64
-rw-r--r--net/ipv4/inet_timewait_sock.c6
-rw-r--r--net/ipv4/ip_tunnel.c4
-rw-r--r--net/ipv4/ipmr.c9
-rw-r--r--net/ipv4/raw.c15
-rw-r--r--net/ipv4/tcp.c1
-rw-r--r--net/ipv4/tcp_bbr.c12
-rw-r--r--net/ipv4/tcp_input.c12
-rw-r--r--net/ipv4/tcp_ipv4.c61
-rw-r--r--net/ipv4/tcp_minisocks.c6
-rw-r--r--net/ipv4/tcp_rate.c10
-rw-r--r--net/ipv4/tcp_recovery.c28
-rw-r--r--net/ipv4/udp_offload.c49
15 files changed, 206 insertions, 85 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ce4aa827be05..f00499a46927 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1223,9 +1223,10 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
struct sk_buff *inet_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
- bool fixedid = false, gso_partial, encap;
+ bool udpfrag = false, fixedid = false, gso_partial, encap;
struct sk_buff *segs = ERR_PTR(-EINVAL);
const struct net_offload *ops;
+ unsigned int offset = 0;
struct iphdr *iph;
int proto, tot_len;
int nhoff;
@@ -1260,6 +1261,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
segs = ERR_PTR(-EPROTONOSUPPORT);
if (!skb->encapsulation || encap) {
+ udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
/* fixed ID is invalid if DF bit is not set */
@@ -1279,7 +1281,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
skb = segs;
do {
iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
- if (skb_is_gso(skb)) {
+ if (udpfrag) {
+ iph->frag_off = htons(offset >> 3);
+ if (skb->next)
+ iph->frag_off |= htons(IP_MF);
+ offset += skb->len - nhoff - ihl;
+ tot_len = skb->len - nhoff;
+ } else if (skb_is_gso(skb)) {
if (!fixedid) {
iph->id = htons(id);
id += skb_shinfo(skb)->gso_segs;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index a4573bccd6da..7a93359fbc72 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1428,7 +1428,7 @@ skip:
static bool inetdev_valid_mtu(unsigned int mtu)
{
- return mtu >= 68;
+ return mtu >= IPV4_MIN_MTU;
}
static void inetdev_send_gratuitous_arp(struct net_device *dev,
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index ab183af0b5b6..726f6b608274 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -89,6 +89,7 @@
#include <linux/rtnetlink.h>
#include <linux/times.h>
#include <linux/pkt_sched.h>
+#include <linux/byteorder/generic.h>
#include <net/net_namespace.h>
#include <net/arp.h>
@@ -321,6 +322,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
return scount;
}
+/* source address selection per RFC 3376 section 4.2.13 */
+static __be32 igmpv3_get_srcaddr(struct net_device *dev,
+ const struct flowi4 *fl4)
+{
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+ if (!in_dev)
+ return htonl(INADDR_ANY);
+
+ for_ifa(in_dev) {
+ if (inet_ifa_match(fl4->saddr, ifa))
+ return fl4->saddr;
+ } endfor_ifa(in_dev);
+
+ return htonl(INADDR_ANY);
+}
+
static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
{
struct sk_buff *skb;
@@ -368,7 +386,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
pip->frag_off = htons(IP_DF);
pip->ttl = 1;
pip->daddr = fl4.daddr;
- pip->saddr = fl4.saddr;
+ pip->saddr = igmpv3_get_srcaddr(dev, &fl4);
pip->protocol = IPPROTO_IGMP;
pip->tot_len = 0; /* filled in later */
ip_select_ident(net, skb, NULL);
@@ -404,16 +422,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)
}
static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
- int type, struct igmpv3_grec **ppgr)
+ int type, struct igmpv3_grec **ppgr, unsigned int mtu)
{
struct net_device *dev = pmc->interface->dev;
struct igmpv3_report *pih;
struct igmpv3_grec *pgr;
- if (!skb)
- skb = igmpv3_newpack(dev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = igmpv3_newpack(dev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = skb_put(skb, sizeof(struct igmpv3_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -436,12 +455,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
struct igmpv3_grec *pgr = NULL;
struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;
if (pmc->multiaddr == IGMP_ALL_HOSTS)
return skb;
if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
return skb;
+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV4_MIN_MTU)
+ return skb;
+
isquery = type == IGMPV3_MODE_IS_INCLUDE ||
type == IGMPV3_MODE_IS_EXCLUDE;
truncate = type == IGMPV3_MODE_IS_EXCLUDE ||
@@ -462,7 +486,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
}
}
first = 1;
@@ -498,12 +522,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -538,7 +562,7 @@ empty_source:
igmpv3_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
@@ -752,18 +776,18 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
return ip_local_out(net, skb->sk, skb);
}
-static void igmp_gq_timer_expire(unsigned long data)
+static void igmp_gq_timer_expire(struct timer_list *t)
{
- struct in_device *in_dev = (struct in_device *)data;
+ struct in_device *in_dev = from_timer(in_dev, t, mr_gq_timer);
in_dev->mr_gq_running = 0;
igmpv3_send_report(in_dev, NULL);
in_dev_put(in_dev);
}
-static void igmp_ifc_timer_expire(unsigned long data)
+static void igmp_ifc_timer_expire(struct timer_list *t)
{
- struct in_device *in_dev = (struct in_device *)data;
+ struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer);
igmpv3_send_cr(in_dev);
if (in_dev->mr_ifc_count) {
@@ -784,9 +808,9 @@ static void igmp_ifc_event(struct in_device *in_dev)
}
-static void igmp_timer_expire(unsigned long data)
+static void igmp_timer_expire(struct timer_list *t)
{
- struct ip_mc_list *im = (struct ip_mc_list *)data;
+ struct ip_mc_list *im = from_timer(im, t, timer);
struct in_device *in_dev = im->interface;
spin_lock(&im->lock);
@@ -1385,7 +1409,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
refcount_set(&im->refcnt, 1);
spin_lock_init(&im->lock);
#ifdef CONFIG_IP_MULTICAST
- setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im);
+ timer_setup(&im->timer, igmp_timer_expire, 0);
im->unsolicit_count = net->ipv4.sysctl_igmp_qrv;
#endif
@@ -1695,10 +1719,8 @@ void ip_mc_init_dev(struct in_device *in_dev)
ASSERT_RTNL();
#ifdef CONFIG_IP_MULTICAST
- setup_timer(&in_dev->mr_gq_timer, igmp_gq_timer_expire,
- (unsigned long)in_dev);
- setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire,
- (unsigned long)in_dev);
+ timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0);
+ timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0);
in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
#endif
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index c690cd0d9b3f..b563e0c46bac 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -93,7 +93,7 @@ static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
}
/*
- * Enter the time wait state.
+ * Enter the time wait state. This is called with locally disabled BH.
* Essentially we whip up a timewait bucket, copy the relevant info into it
* from the SK, and mess with hash chains and list linkage.
*/
@@ -111,7 +111,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
*/
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
hashinfo->bhash_size)];
- spin_lock_bh(&bhead->lock);
+ spin_lock(&bhead->lock);
tw->tw_tb = icsk->icsk_bind_hash;
WARN_ON(!icsk->icsk_bind_hash);
inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
@@ -137,7 +137,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
if (__sk_nulls_del_node_init_rcu(sk))
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
- spin_unlock_bh(lock);
+ spin_unlock(lock);
}
EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index fe6fee728ce4..5ddb1cb52bd4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -349,8 +349,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
dev->needed_headroom = t_hlen + hlen;
mtu -= (dev->hard_header_len + t_hlen);
- if (mtu < 68)
- mtu = 68;
+ if (mtu < IPV4_MIN_MTU)
+ mtu = IPV4_MIN_MTU;
return mtu;
}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 40a43ad294cb..fd5f19c988e4 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -112,7 +112,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
int cmd);
static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt);
static void mroute_clean_tables(struct mr_table *mrt, bool all);
-static void ipmr_expire_process(unsigned long arg);
+static void ipmr_expire_process(struct timer_list *t);
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
#define ipmr_for_each_table(mrt, net) \
@@ -375,8 +375,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
INIT_LIST_HEAD(&mrt->mfc_cache_list);
INIT_LIST_HEAD(&mrt->mfc_unres_queue);
- setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process,
- (unsigned long)mrt);
+ timer_setup(&mrt->ipmr_expire_timer, ipmr_expire_process, 0);
mrt->mroute_reg_vif_num = -1;
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -804,9 +803,9 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c)
}
/* Timer process for the unresolved queue. */
-static void ipmr_expire_process(unsigned long arg)
+static void ipmr_expire_process(struct timer_list *t)
{
- struct mr_table *mrt = (struct mr_table *)arg;
+ struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer);
unsigned long now;
unsigned long expires;
struct mfc_cache *c, *next;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 33b70bfd1122..125c1eab3eaa 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -513,11 +513,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int err;
struct ip_options_data opt_copy;
struct raw_frag_vec rfv;
+ int hdrincl;
err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;
+ /* hdrincl should be READ_ONCE(inet->hdrincl)
+ * but READ_ONCE() doesn't work with bit fields
+ */
+ hdrincl = inet->hdrincl;
/*
* Check the flags.
*/
@@ -593,7 +598,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
- if (inet->hdrincl)
+ if (hdrincl)
goto done;
if (ipc.opt->opt.srr) {
if (!daddr)
@@ -615,12 +620,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
- inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
- (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
+ (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
- if (!inet->hdrincl) {
+ if (!hdrincl) {
rfv.msg = msg;
rfv.hlen = 0;
@@ -645,7 +650,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
goto do_confirm;
back_from_confirm:
- if (inet->hdrincl)
+ if (hdrincl)
err = raw_send_hdrinc(sk, &fl4, msg, len,
&rt, msg->msg_flags, &ipc.sockc);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bf97317e6c97..f08eebe60446 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2412,6 +2412,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
tcp_clear_retrans(tp);
inet_csk_delack_init(sk);
/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 69ee877574d0..8322f26e770e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -110,7 +110,8 @@ struct bbr {
u32 lt_last_lost; /* LT intvl start: tp->lost */
u32 pacing_gain:10, /* current gain for setting pacing rate */
cwnd_gain:10, /* current gain for setting cwnd */
- full_bw_cnt:3, /* number of rounds without large bw gains */
+ full_bw_reached:1, /* reached full bw in Startup? */
+ full_bw_cnt:2, /* number of rounds without large bw gains */
cycle_idx:3, /* current index in pacing_gain cycle array */
has_seen_rtt:1, /* have we seen an RTT sample yet? */
unused_b:5;
@@ -180,7 +181,7 @@ static bool bbr_full_bw_reached(const struct sock *sk)
{
const struct bbr *bbr = inet_csk_ca(sk);
- return bbr->full_bw_cnt >= bbr_full_bw_cnt;
+ return bbr->full_bw_reached;
}
/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
@@ -717,6 +718,7 @@ static void bbr_check_full_bw_reached(struct sock *sk,
return;
}
++bbr->full_bw_cnt;
+ bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt;
}
/* If pipe is probably full, drain the queue and then enter steady-state. */
@@ -850,6 +852,7 @@ static void bbr_init(struct sock *sk)
bbr->restore_cwnd = 0;
bbr->round_start = 0;
bbr->idle_restart = 0;
+ bbr->full_bw_reached = 0;
bbr->full_bw = 0;
bbr->full_bw_cnt = 0;
bbr->cycle_mstamp = 0;
@@ -871,6 +874,11 @@ static u32 bbr_sndbuf_expand(struct sock *sk)
*/
static u32 bbr_undo_cwnd(struct sock *sk)
{
+ struct bbr *bbr = inet_csk_ca(sk);
+
+ bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */
+ bbr->full_bw_cnt = 0;
+ bbr_reset_lt_bw_sampling(sk);
return tcp_sk(sk)->snd_cwnd;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 734cfc8ff76e..9550cc42de2d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -579,6 +579,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
int time;
int copied;
+ tcp_mstamp_refresh(tp);
time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0)
return;
@@ -1941,6 +1942,8 @@ void tcp_enter_loss(struct sock *sk)
if (is_reneg) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
tp->sacked_out = 0;
+ /* Mark SACK reneging until we recover from this loss event. */
+ tp->is_sack_reneg = 1;
}
tcp_clear_all_retrans_hints(tp);
@@ -2326,6 +2329,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
}
tp->snd_cwnd_stamp = tcp_jiffies32;
tp->undo_marker = 0;
+ tp->rack.advanced = 1; /* Force RACK to re-exam losses */
}
static inline bool tcp_may_undo(const struct tcp_sock *tp)
@@ -2364,6 +2368,7 @@ static bool tcp_try_undo_recovery(struct sock *sk)
return true;
}
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
return false;
}
@@ -2397,8 +2402,10 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
- if (frto_undo || tcp_is_sack(tp))
+ if (frto_undo || tcp_is_sack(tp)) {
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
+ }
return true;
}
return false;
@@ -3495,6 +3502,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
struct tcp_sacktag_state sack_state;
struct rate_sample rs = { .prior_delivered = 0 };
u32 prior_snd_una = tp->snd_una;
+ bool is_sack_reneg = tp->is_sack_reneg;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
@@ -3611,7 +3619,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */
lost = tp->lost - lost; /* freshly marked lost */
- tcp_rate_gen(sk, delivered, lost, sack_state.rate);
+ tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
tcp_xmit_recovery(sk, rexmit);
return 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c6bc0c4d19c6..94e28350f420 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -848,7 +848,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
req->ts_recent,
0,
- tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+ tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
AF_INET),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
ip_hdr(skb)->tos);
@@ -1591,6 +1591,34 @@ int tcp_filter(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_filter);
+static void tcp_v4_restore_cb(struct sk_buff *skb)
+{
+ memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4,
+ sizeof(struct inet_skb_parm));
+}
+
+static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
+ const struct tcphdr *th)
+{
+ /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+ * barrier() makes sure compiler wont play fool^Waliasing games.
+ */
+ memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
+ sizeof(struct inet_skb_parm));
+ barrier();
+
+ TCP_SKB_CB(skb)->seq = ntohl(th->seq);
+ TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
+ skb->len - th->doff * 4);
+ TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+ TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+ TCP_SKB_CB(skb)->tcp_tw_isn = 0;
+ TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
+ TCP_SKB_CB(skb)->sacked = 0;
+ TCP_SKB_CB(skb)->has_rxtstamp =
+ skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
+}
+
/*
* From tcp_input.c
*/
@@ -1631,24 +1659,6 @@ int tcp_v4_rcv(struct sk_buff *skb)
th = (const struct tcphdr *)skb->data;
iph = ip_hdr(skb);
- /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
- * barrier() makes sure compiler wont play fool^Waliasing games.
- */
- memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
- sizeof(struct inet_skb_parm));
- barrier();
-
- TCP_SKB_CB(skb)->seq = ntohl(th->seq);
- TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
- skb->len - th->doff * 4);
- TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
- TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
- TCP_SKB_CB(skb)->tcp_tw_isn = 0;
- TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
- TCP_SKB_CB(skb)->sacked = 0;
- TCP_SKB_CB(skb)->has_rxtstamp =
- skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
-
lookup:
sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
th->dest, sdif, &refcounted);
@@ -1679,14 +1689,19 @@ process:
sock_hold(sk);
refcounted = true;
nsk = NULL;
- if (!tcp_filter(sk, skb))
+ if (!tcp_filter(sk, skb)) {
+ th = (const struct tcphdr *)skb->data;
+ iph = ip_hdr(skb);
+ tcp_v4_fill_cb(skb, iph, th);
nsk = tcp_check_req(sk, skb, req, false);
+ }
if (!nsk) {
reqsk_put(req);
goto discard_and_relse;
}
if (nsk == sk) {
reqsk_put(req);
+ tcp_v4_restore_cb(skb);
} else if (tcp_child_process(sk, nsk, skb)) {
tcp_v4_send_reset(nsk, skb);
goto discard_and_relse;
@@ -1712,6 +1727,7 @@ process:
goto discard_and_relse;
th = (const struct tcphdr *)skb->data;
iph = ip_hdr(skb);
+ tcp_v4_fill_cb(skb, iph, th);
skb->dev = NULL;
@@ -1742,6 +1758,8 @@ no_tcp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
+ tcp_v4_fill_cb(skb, iph, th);
+
if (tcp_checksum_complete(skb)) {
csum_error:
__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
@@ -1768,6 +1786,8 @@ do_time_wait:
goto discard_it;
}
+ tcp_v4_fill_cb(skb, iph, th);
+
if (tcp_checksum_complete(skb)) {
inet_twsk_put(inet_twsk(sk));
goto csum_error;
@@ -1784,6 +1804,7 @@ do_time_wait:
if (sk2) {
inet_twsk_deschedule_put(inet_twsk(sk));
sk = sk2;
+ tcp_v4_restore_cb(skb);
refcounted = false;
goto process;
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index e36eff0403f4..b079b619b60c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -310,10 +310,16 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
if (state == TCP_TIME_WAIT)
timeo = TCP_TIMEWAIT_LEN;
+ /* tw_timer is pinned, so we need to make sure BH are disabled
+ * in following section, otherwise timer handler could run before
+ * we complete the initialization.
+ */
+ local_bh_disable();
inet_twsk_schedule(tw, timeo);
/* Linkage updates. */
__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
inet_twsk_put(tw);
+ local_bh_enable();
} else {
/* Sorry, if we're out of memory, just CLOSE this
* socket up. We've got bigger problems than
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index 3330a370d306..c61240e43923 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
/* Update the connection delivery information and generate a rate sample. */
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
- struct rate_sample *rs)
+ bool is_sack_reneg, struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 snd_us, ack_us;
@@ -124,8 +124,12 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
rs->acked_sacked = delivered; /* freshly ACKed or SACKed */
rs->losses = lost; /* freshly marked lost */
- /* Return an invalid sample if no timing information is available. */
- if (!rs->prior_mstamp) {
+ /* Return an invalid sample if no timing information is available or
+ * in recovery from loss with SACK reneging. Rate samples taken during
+ * a SACK reneging event may overestimate bw by including packets that
+ * were SACKed before the reneg.
+ */
+ if (!rs->prior_mstamp || is_sack_reneg) {
rs->delivered = -1;
rs->interval_us = -1;
return;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index d3ea89020c69..3a81720ac0c4 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -55,7 +55,8 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
* to queuing or delayed ACKs.
*/
reo_wnd = 1000;
- if ((tp->rack.reord || !tp->lost_out) && min_rtt != ~0U) {
+ if ((tp->rack.reord || inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery) &&
+ min_rtt != ~0U) {
reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd);
reo_wnd = min(reo_wnd, tp->srtt_us >> 3);
}
@@ -79,12 +80,12 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
*/
remaining = tp->rack.rtt_us + reo_wnd -
tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp);
- if (remaining < 0) {
+ if (remaining <= 0) {
tcp_rack_mark_skb_lost(sk, skb);
list_del_init(&skb->tcp_tsorted_anchor);
} else {
- /* Record maximum wait time (+1 to avoid 0) */
- *reo_timeout = max_t(u32, *reo_timeout, 1 + remaining);
+ /* Record maximum wait time */
+ *reo_timeout = max_t(u32, *reo_timeout, remaining);
}
}
}
@@ -116,13 +117,8 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
{
u32 rtt_us;
- if (tp->rack.mstamp &&
- !tcp_rack_sent_after(xmit_time, tp->rack.mstamp,
- end_seq, tp->rack.end_seq))
- return;
-
rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, xmit_time);
- if (sacked & TCPCB_RETRANS) {
+ if (rtt_us < tcp_min_rtt(tp) && (sacked & TCPCB_RETRANS)) {
/* If the sacked packet was retransmitted, it's ambiguous
* whether the retransmission or the original (or the prior
* retransmission) was sacked.
@@ -133,13 +129,15 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
* so it's at least one RTT (i.e., retransmission is at least
* an RTT later).
*/
- if (rtt_us < tcp_min_rtt(tp))
- return;
+ return;
}
- tp->rack.rtt_us = rtt_us;
- tp->rack.mstamp = xmit_time;
- tp->rack.end_seq = end_seq;
tp->rack.advanced = 1;
+ tp->rack.rtt_us = rtt_us;
+ if (tcp_rack_sent_after(xmit_time, tp->rack.mstamp,
+ end_seq, tp->rack.end_seq)) {
+ tp->rack.mstamp = xmit_time;
+ tp->rack.end_seq = end_seq;
+ }
}
/* We have waited long enough to accommodate reordering. Mark the expired
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e360d55be555..01801b77bd0d 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -187,16 +187,57 @@ out_unlock:
}
EXPORT_SYMBOL(skb_udp_tunnel_segment);
-static struct sk_buff *udp4_tunnel_segment(struct sk_buff *skb,
- netdev_features_t features)
+static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+ netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
+ unsigned int mss;
+ __wsum csum;
+ struct udphdr *uh;
+ struct iphdr *iph;
if (skb->encapsulation &&
(skb_shinfo(skb)->gso_type &
- (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)))
+ (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
segs = skb_udp_tunnel_segment(skb, features, false);
+ goto out;
+ }
+
+ if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+ goto out;
+
+ mss = skb_shinfo(skb)->gso_size;
+ if (unlikely(skb->len <= mss))
+ goto out;
+
+ /* Do software UFO. Complete and fill in the UDP checksum as
+ * HW cannot do checksum of UDP packets sent as multiple
+ * IP fragments.
+ */
+ uh = udp_hdr(skb);
+ iph = ip_hdr(skb);
+
+ uh->check = 0;
+ csum = skb_checksum(skb, 0, skb->len, 0);
+ uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ /* If there is no outer header we can fake a checksum offload
+ * due to the fact that we have already done the checksum in
+ * software prior to segmenting the frame.
+ */
+ if (!skb->encap_hdr_csum)
+ features |= NETIF_F_HW_CSUM;
+
+ /* Fragment the skb. IP headers of the fragments are updated in
+ * inet_gso_segment()
+ */
+ segs = skb_segment(skb, features);
+out:
return segs;
}
@@ -330,7 +371,7 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
static const struct net_offload udpv4_offload = {
.callbacks = {
- .gso_segment = udp4_tunnel_segment,
+ .gso_segment = udp4_ufo_fragment,
.gro_receive = udp4_gro_receive,
.gro_complete = udp4_gro_complete,
},
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-20 10:48:01 +0100