summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig10
-rw-r--r--net/ipv4/Makefile1
-rw-r--r--net/ipv4/af_inet.c36
-rw-r--r--net/ipv4/fib_rules.c4
-rw-r--r--net/ipv4/fib_trie.c2
-rw-r--r--net/ipv4/inetpeer.c2
-rw-r--r--net/ipv4/ip_input.c3
-rw-r--r--net/ipv4/ip_output.c4
-rw-r--r--net/ipv4/ipcomp.c3
-rw-r--r--net/ipv4/tcp_compound.c448
-rw-r--r--net/ipv4/tcp_highspeed.c13
-rw-r--r--net/ipv4/tcp_ipv4.c18
-rw-r--r--net/ipv4/xfrm4_output.c2
13 files changed, 75 insertions, 471 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index da33393be45..8514106761b 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -572,16 +572,6 @@ config TCP_CONG_VENO
loss packets.
See http://www.ntu.edu.sg/home5/ZHOU0022/papers/CPFu03a.pdf
-config TCP_CONG_COMPOUND
- tristate "TCP Compound"
- depends on EXPERIMENTAL
- default n
- ---help---
- TCP Compound is a sender-side only change to TCP that uses
- a mixed Reno/Vegas approach to calculate the cwnd.
- For further details look here:
- ftp://ftp.research.microsoft.com/pub/tr/TR-2005-86.pdf
-
endmenu
config TCP_CONG_BIC
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 38b8039bdd5..4878fc5be85 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -47,7 +47,6 @@ obj-$(CONFIG_TCP_CONG_VEGAS) += tcp_vegas.o
obj-$(CONFIG_TCP_CONG_VENO) += tcp_veno.o
obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
-obj-$(CONFIG_TCP_CONG_COMPOUND) += tcp_compound.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
xfrm4_output.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 318d4674faa..c84a32070f8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1097,6 +1097,40 @@ int inet_sk_rebuild_header(struct sock *sk)
EXPORT_SYMBOL(inet_sk_rebuild_header);
+static int inet_gso_send_check(struct sk_buff *skb)
+{
+ struct iphdr *iph;
+ struct net_protocol *ops;
+ int proto;
+ int ihl;
+ int err = -EINVAL;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
+ goto out;
+
+ iph = skb->nh.iph;
+ ihl = iph->ihl * 4;
+ if (ihl < sizeof(*iph))
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, ihl)))
+ goto out;
+
+ skb->h.raw = __skb_pull(skb, ihl);
+ iph = skb->nh.iph;
+ proto = iph->protocol & (MAX_INET_PROTOS - 1);
+ err = -EPROTONOSUPPORT;
+
+ rcu_read_lock();
+ ops = rcu_dereference(inet_protos[proto]);
+ if (likely(ops && ops->gso_send_check))
+ err = ops->gso_send_check(skb);
+ rcu_read_unlock();
+
+out:
+ return err;
+}
+
static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
@@ -1162,6 +1196,7 @@ static struct net_protocol igmp_protocol = {
static struct net_protocol tcp_protocol = {
.handler = tcp_v4_rcv,
.err_handler = tcp_v4_err,
+ .gso_send_check = tcp_v4_gso_send_check,
.gso_segment = tcp_tso_segment,
.no_policy = 1,
};
@@ -1208,6 +1243,7 @@ static int ipv4_proc_init(void);
static struct packet_type ip_packet_type = {
.type = __constant_htons(ETH_P_IP),
.func = ip_rcv,
+ .gso_send_check = inet_gso_send_check,
.gso_segment = inet_gso_segment,
};
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 6c642d11d4c..773b12ba4e3 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -457,13 +457,13 @@ int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_lock();
hlist_for_each_entry(r, node, &fib_rules, hlist) {
-
if (idx < s_idx)
- continue;
+ goto next;
if (inet_fill_rule(skb, r, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq,
RTM_NEWRULE, NLM_F_MULTI) < 0)
break;
+next:
idx++;
}
rcu_read_unlock();
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1cb65305e10..23fb9d9768e 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1252,8 +1252,8 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta,
*/
if (!fa_head) {
- fa_head = fib_insert_node(t, &err, key, plen);
err = 0;
+ fa_head = fib_insert_node(t, &err, key, plen);
if (err)
goto out_free_new_fa;
}
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 2160874ce7a..03ff62ebcfe 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -86,7 +86,7 @@ static struct inet_peer *peer_root = peer_avl_empty;
static DEFINE_RWLOCK(peer_pool_lock);
#define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */
-static volatile int peer_total;
+static int peer_total;
/* Exported for sysctl_net_ipv4. */
int inet_peer_threshold = 65536 + 128; /* start to throw entries more
* aggressively at this stage */
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index e1a7dba2fa8..184c78ca79e 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -428,6 +428,9 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
goto drop;
}
+ /* Remove any debris in the socket control block */
+ memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
+
return NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, dev, NULL,
ip_rcv_finish);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ca0e714613f..7c9f9a6421b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -209,7 +209,7 @@ static inline int ip_finish_output(struct sk_buff *skb)
return dst_output(skb);
}
#endif
- if (skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size)
+ if (skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb))
return ip_fragment(skb, ip_finish_output2);
else
return ip_finish_output2(skb);
@@ -1095,7 +1095,7 @@ ssize_t ip_append_page(struct sock *sk, struct page *page,
while (size > 0) {
int i;
- if (skb_shinfo(skb)->gso_size)
+ if (skb_is_gso(skb))
len = size;
else {
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 8e037484753..8a8b5cf2f7f 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -70,7 +70,8 @@ static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb)
if (err)
goto out;
- skb_put(skb, dlen - plen);
+ skb->truesize += dlen - plen;
+ __skb_put(skb, dlen - plen);
memcpy(skb->data, scratch, dlen);
out:
put_cpu();
diff --git a/net/ipv4/tcp_compound.c b/net/ipv4/tcp_compound.c
deleted file mode 100644
index bc54f7e9aea..00000000000
--- a/net/ipv4/tcp_compound.c
+++ /dev/null
@@ -1,448 +0,0 @@
-/*
- * TCP Vegas congestion control
- *
- * This is based on the congestion detection/avoidance scheme described in
- * Lawrence S. Brakmo and Larry L. Peterson.
- * "TCP Vegas: End to end congestion avoidance on a global internet."
- * IEEE Journal on Selected Areas in Communication, 13(8):1465--1480,
- * October 1995. Available from:
- * ftp://ftp.cs.arizona.edu/xkernel/Papers/jsac.ps
- *
- * See http://www.cs.arizona.edu/xkernel/ for their implementation.
- * The main aspects that distinguish this implementation from the
- * Arizona Vegas implementation are:
- * o We do not change the loss detection or recovery mechanisms of
- * Linux in any way. Linux already recovers from losses quite well,
- * using fine-grained timers, NewReno, and FACK.
- * o To avoid the performance penalty imposed by increasing cwnd
- * only every-other RTT during slow start, we increase during
- * every RTT during slow start, just like Reno.
- * o Largely to allow continuous cwnd growth during slow start,
- * we use the rate at which ACKs come back as the "actual"
- * rate, rather than the rate at which data is sent.
- * o To speed convergence to the right rate, we set the cwnd
- * to achieve the right ("actual") rate when we exit slow start.
- * o To filter out the noise caused by delayed ACKs, we use the
- * minimum RTT sample observed during the last RTT to calculate
- * the actual rate.
- * o When the sender re-starts from idle, it waits until it has
- * received ACKs for an entire flight of new data before making
- * a cwnd adjustment decision. The original Vegas implementation
- * assumed senders never went idle.
- *
- *
- * TCP Compound based on TCP Vegas
- *
- * further details can be found here:
- * ftp://ftp.research.microsoft.com/pub/tr/TR-2005-86.pdf
- */
-
-#include <linux/config.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/inet_diag.h>
-
-#include <net/tcp.h>
-
-/* Default values of the Vegas variables, in fixed-point representation
- * with V_PARAM_SHIFT bits to the right of the binary point.
- */
-#define V_PARAM_SHIFT 1
-
-#define TCP_COMPOUND_ALPHA 3U
-#define TCP_COMPOUND_BETA 1U
-#define TCP_COMPOUND_GAMMA 30
-#define TCP_COMPOUND_ZETA 1
-
-/* TCP compound variables */
-struct compound {
- u32 beg_snd_nxt; /* right edge during last RTT */
- u32 beg_snd_una; /* left edge during last RTT */
- u32 beg_snd_cwnd; /* saves the size of the cwnd */
- u8 doing_vegas_now; /* if true, do vegas for this RTT */
- u16 cntRTT; /* # of RTTs measured within last RTT */
- u32 minRTT; /* min of RTTs measured within last RTT (in usec) */
- u32 baseRTT; /* the min of all Vegas RTT measurements seen (in usec) */
-
- u32 cwnd;
- u32 dwnd;
-};
-
-/* There are several situations when we must "re-start" Vegas:
- *
- * o when a connection is established
- * o after an RTO
- * o after fast recovery
- * o when we send a packet and there is no outstanding
- * unacknowledged data (restarting an idle connection)
- *
- * In these circumstances we cannot do a Vegas calculation at the
- * end of the first RTT, because any calculation we do is using
- * stale info -- both the saved cwnd and congestion feedback are
- * stale.
- *
- * Instead we must wait until the completion of an RTT during
- * which we actually receive ACKs.
- */
-static inline void vegas_enable(struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- struct compound *vegas = inet_csk_ca(sk);
-
- /* Begin taking Vegas samples next time we send something. */
- vegas->doing_vegas_now = 1;
-
- /* Set the beginning of the next send window. */
- vegas->beg_snd_nxt = tp->snd_nxt;
-
- vegas->cntRTT = 0;
- vegas->minRTT = 0x7fffffff;
-}
-
-/* Stop taking Vegas samples for now. */
-static inline void vegas_disable(struct sock *sk)
-{
- struct compound *vegas = inet_csk_ca(sk);
-
- vegas->doing_vegas_now = 0;
-}
-
-static void tcp_compound_init(struct sock *sk)
-{
- struct compound *vegas = inet_csk_ca(sk);
- const struct tcp_sock *tp = tcp_sk(sk);
-
- vegas->baseRTT = 0x7fffffff;
- vegas_enable(sk);
-
- vegas->dwnd = 0;
- vegas->cwnd = tp->snd_cwnd;
-}
-
-/* Do RTT sampling needed for Vegas.
- * Basically we:
- * o min-filter RTT samples from within an RTT to get the current
- * propagation delay + queuing delay (we are min-filtering to try to
- * avoid the effects of delayed ACKs)
- * o min-filter RTT samples from a much longer window (forever for now)
- * to find the propagation delay (baseRTT)
- */
-static void tcp_compound_rtt_calc(struct sock *sk, u32 usrtt)
-{
- struct compound *vegas = inet_csk_ca(sk);
- u32 vrtt = usrtt + 1; /* Never allow zero rtt or baseRTT */
-
- /* Filter to find propagation delay: */
- if (vrtt < vegas->baseRTT)
- vegas->baseRTT = vrtt;
-
- /* Find the min RTT during the last RTT to find
- * the current prop. delay + queuing delay:
- */
-
- vegas->minRTT = min(vegas->minRTT, vrtt);
- vegas->cntRTT++;
-}
-
-static void tcp_compound_state(struct sock *sk, u8 ca_state)
-{
-
- if (ca_state == TCP_CA_Open)
- vegas_enable(sk);
- else
- vegas_disable(sk);
-}
-
-
-/* 64bit divisor, dividend and result. dynamic precision */
-static inline u64 div64_64(u64 dividend, u64 divisor)
-{
- u32 d = divisor;
-
- if (divisor > 0xffffffffULL) {
- unsigned int shift = fls(divisor >> 32);
-
- d = divisor >> shift;
- dividend >>= shift;
- }
-
- /* avoid 64 bit division if possible */
- if (dividend >> 32)
- do_div(dividend, d);
- else
- dividend = (u32) dividend / d;
-
- return dividend;
-}
-
-/* calculate the quartic root of "a" using Newton-Raphson */
-static u32 qroot(u64 a)
-{
- u32 x, x1;
-
- /* Initial estimate is based on:
- * qrt(x) = exp(log(x) / 4)
- */
- x = 1u << (fls64(a) >> 2);
-
- /*
- * Iteration based on:
- * 3
- * x = ( 3 * x + a / x ) / 4
- * k+1 k k
- */
- do {
- u64 x3 = x;
-
- x1 = x;
- x3 *= x;
- x3 *= x;
-
- x = (3 * x + (u32) div64_64(a, x3)) / 4;
- } while (abs(x1 - x) > 1);
-
- return x;
-}
-
-
-/*
- * If the connection is idle and we are restarting,
- * then we don't want to do any Vegas calculations
- * until we get fresh RTT samples. So when we
- * restart, we reset our Vegas state to a clean
- * slate. After we get acks for this flight of
- * packets, _then_ we can make Vegas calculations
- * again.
- */
-static void tcp_compound_cwnd_event(struct sock *sk, enum tcp_ca_event event)
-{
- if (event == CA_EVENT_CWND_RESTART || event == CA_EVENT_TX_START)
- tcp_compound_init(sk);
-}
-
-static void tcp_compound_cong_avoid(struct sock *sk, u32 ack,
- u32 seq_rtt, u32 in_flight, int flag)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- struct compound *vegas = inet_csk_ca(sk);
- u8 inc = 0;
-
- if (vegas->cwnd + vegas->dwnd > tp->snd_cwnd) {
- if (vegas->cwnd > tp->snd_cwnd || vegas->dwnd > tp->snd_cwnd) {
- vegas->cwnd = tp->snd_cwnd;
- vegas->dwnd = 0;
- } else
- vegas->cwnd = tp->snd_cwnd - vegas->dwnd;
-
- }
-
- if (!tcp_is_cwnd_limited(sk, in_flight))
- return;
-
- if (vegas->cwnd <= tp->snd_ssthresh)
- inc = 1;
- else if (tp->snd_cwnd_cnt < tp->snd_cwnd)
- tp->snd_cwnd_cnt++;
-
- if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
- inc = 1;
- tp->snd_cwnd_cnt = 0;
- }
-
- if (inc && tp->snd_cwnd < tp->snd_cwnd_clamp)
- vegas->cwnd++;
-
- /* The key players are v_beg_snd_una and v_beg_snd_nxt.
- *
- * These are so named because they represent the approximate values
- * of snd_una and snd_nxt at the beginning of the current RTT. More
- * precisely, they represent the amount of data sent during the RTT.
- * At the end of the RTT, when we receive an ACK for v_beg_snd_nxt,
- * we will calculate that (v_beg_snd_nxt - v_beg_snd_una) outstanding
- * bytes of data have been ACKed during the course of the RTT, giving
- * an "actual" rate of:
- *
- * (v_beg_snd_nxt - v_beg_snd_una) / (rtt duration)
- *
- * Unfortunately, v_beg_snd_una is not exactly equal to snd_una,
- * because delayed ACKs can cover more than one segment, so they
- * don't line up nicely with the boundaries of RTTs.
- *
- * Another unfortunate fact of life is that delayed ACKs delay the
- * advance of the left edge of our send window, so that the number
- * of bytes we send in an RTT is often less than our cwnd will allow.
- * So we keep track of our cwnd separately, in v_beg_snd_cwnd.
- */
-
- if (after(ack, vegas->beg_snd_nxt)) {
- /* Do the Vegas once-per-RTT cwnd adjustment. */
- u32 old_wnd, old_snd_cwnd;
-
- /* Here old_wnd is essentially the window of data that was
- * sent during the previous RTT, and has all
- * been acknowledged in the course of the RTT that ended
- * with the ACK we just received. Likewise, old_snd_cwnd
- * is the cwnd during the previous RTT.
- */
- if (!tp->mss_cache)
- return;
-
- old_wnd = (vegas->beg_snd_nxt - vegas->beg_snd_una) /
- tp->mss_cache;
- old_snd_cwnd = vegas->beg_snd_cwnd;
-
- /* Save the extent of the current window so we can use this
- * at the end of the next RTT.
- */
- vegas->beg_snd_una = vegas->beg_snd_nxt;
- vegas->beg_snd_nxt = tp->snd_nxt;
- vegas->beg_snd_cwnd = tp->snd_cwnd;
-
- /* We do the Vegas calculations only if we got enough RTT
- * samples that we can be reasonably sure that we got
- * at least one RTT sample that wasn't from a delayed ACK.
- * If we only had 2 samples total,
- * then that means we're getting only 1 ACK per RTT, which
- * means they're almost certainly delayed ACKs.
- * If we have 3 samples, we should be OK.
- */
-
- if (vegas->cntRTT > 2) {
- u32 rtt, target_cwnd, diff;
- u32 brtt, dwnd;
-
- /* We have enough RTT samples, so, using the Vegas
- * algorithm, we determine if we should increase or
- * decrease cwnd, and by how much.
- */
-
- /* Pluck out the RTT we are using for the Vegas
- * calculations. This is the min RTT seen during the
- * last RTT. Taking the min filters out the effects
- * of delayed ACKs, at the cost of noticing congestion
- * a bit later.
- */
- rtt = vegas->minRTT;
-
- /* Calculate the cwnd we should have, if we weren't
- * going too fast.
- *
- * This is:
- * (actual rate in segments) * baseRTT
- * We keep it as a fixed point number with
- * V_PARAM_SHIFT bits to the right of the binary point.
- */
- if (!rtt)
- return;
-
- brtt = vegas->baseRTT;
- target_cwnd = ((old_wnd * brtt)
- << V_PARAM_SHIFT) / rtt;
-
- /* Calculate the difference between the window we had,
- * and the window we would like to have. This quantity
- * is the "Diff" from the Arizona Vegas papers.
- *
- * Again, this is a fixed point number with
- * V_PARAM_SHIFT bits to the right of the binary
- * point.
- */
-
- diff = (old_wnd << V_PARAM_SHIFT) - target_cwnd;
-
- dwnd = vegas->dwnd;
-
- if (diff < (TCP_COMPOUND_GAMMA << V_PARAM_SHIFT)) {
- u64 v;
- u32 x;
-
- /*
- * The TCP Compound paper describes the choice
- * of "k" determines the agressiveness,
- * ie. slope of the response function.
- *
- * For same value as HSTCP would be 0.8
- * but for computaional reasons, both the
- * original authors and this implementation
- * use 0.75.
- */
- v = old_wnd;
- x = qroot(v * v * v) >> TCP_COMPOUND_ALPHA;
- if (x > 1)
- dwnd = x - 1;
- else
- dwnd = 0;
-
- dwnd += vegas->dwnd;
-
- } else if ((dwnd << V_PARAM_SHIFT) <
- (diff * TCP_COMPOUND_BETA))
- dwnd = 0;
- else
- dwnd =
- ((dwnd << V_PARAM_SHIFT) -
- (diff *
- TCP_COMPOUND_BETA)) >> V_PARAM_SHIFT;
-
- vegas->dwnd = dwnd;
-
- }
-
- /* Wipe the slate clean for the next RTT. */
- vegas->cntRTT = 0;
- vegas->minRTT = 0x7fffffff;
- }
-
- tp->snd_cwnd = vegas->cwnd + vegas->dwnd;
-}
-
-/* Extract info for Tcp socket info provided via netlink. */
-static void tcp_compound_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
-{
- const struct compound *ca = inet_csk_ca(sk);
- if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
- struct tcpvegas_info *info;
-
- info = RTA_DATA(__RTA_PUT(skb, INET_DIAG_VEGASINFO,
- sizeof(*info)));
-
- info->tcpv_enabled = ca->doing_vegas_now;
- info->tcpv_rttcnt = ca->cntRTT;
- info->tcpv_rtt = ca->baseRTT;
- info->tcpv_minrtt = ca->minRTT;
- rtattr_failure:;
- }
-}
-
-static struct tcp_congestion_ops tcp_compound = {
- .init = tcp_compound_init,
- .ssthresh = tcp_reno_ssthresh,
- .cong_avoid = tcp_compound_cong_avoid,
- .rtt_sample = tcp_compound_rtt_calc,
- .set_state = tcp_compound_state,
- .cwnd_event = tcp_compound_cwnd_event,
- .get_info = tcp_compound_get_info,
-
- .owner = THIS_MODULE,
- .name = "compound",
-};
-
-static int __init tcp_compound_register(void)
-{
- BUG_ON(sizeof(struct compound) > ICSK_CA_PRIV_SIZE);
- tcp_register_congestion_control(&tcp_compound);
- return 0;
-}
-
-static void __exit tcp_compound_unregister(void)
-{
- tcp_unregister_congestion_control(&tcp_compound);
-}
-
-module_init(tcp_compound_register);
-module_exit(tcp_compound_unregister);
-
-MODULE_AUTHOR("Angelo P. Castellani, Stephen Hemminger");
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("TCP Compound");
diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c
index aaa1538c069..fa3e1aad660 100644
--- a/net/ipv4/tcp_highspeed.c
+++ b/net/ipv4/tcp_highspeed.c
@@ -139,14 +139,19 @@ static void hstcp_cong_avoid(struct sock *sk, u32 adk, u32 rtt,
tp->snd_cwnd++;
}
} else {
- /* Update AIMD parameters */
+ /* Update AIMD parameters.
+ *
+ * We want to guarantee that:
+ * hstcp_aimd_vals[ca->ai-1].cwnd <
+ * snd_cwnd <=
+ * hstcp_aimd_vals[ca->ai].cwnd
+ */
if (tp->snd_cwnd > hstcp_aimd_vals[ca->ai].cwnd) {
while (tp->snd_cwnd > hstcp_aimd_vals[ca->ai].cwnd &&
ca->ai < HSTCP_AIMD_MAX - 1)
ca->ai++;
- } else if (tp->snd_cwnd < hstcp_aimd_vals[ca->ai].cwnd) {
- while (tp->snd_cwnd > hstcp_aimd_vals[ca->ai].cwnd &&
- ca->ai > 0)
+ } else if (ca->ai && tp->snd_cwnd <= hstcp_aimd_vals[ca->ai-1].cwnd) {
+ while (ca->ai && tp->snd_cwnd <= hstcp_aimd_vals[ca->ai-1].cwnd)
ca->ai--;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5a886e6efbb..a891133f00e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -496,6 +496,24 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb)
}
}
+int tcp_v4_gso_send_check(struct sk_buff *skb)
+{
+ struct iphdr *iph;
+ struct tcphdr *th;
+
+ if (!pskb_may_pull(skb, sizeof(*th)))
+ return -EINVAL;
+
+ iph = skb->nh.iph;
+ th = skb->h.th;
+
+ th->check = 0;
+ th->check = ~tcp_v4_check(th, skb->len, iph->saddr, iph->daddr, 0);
+ skb->csum = offsetof(struct tcphdr, check);
+ skb->ip_summed = CHECKSUM_HW;
+ return 0;
+}
+
/*
* This routine will send an RST to the other tcp.
*
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 193363e2293..d16f863cf68 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -134,7 +134,7 @@ static int xfrm4_output_finish(struct sk_buff *skb)
}
#endif
- if (!skb_shinfo(skb)->gso_size)
+ if (!skb_is_gso(skb))
return xfrm4_output_finish2(skb);
skb->protocol = htons(ETH_P_IP);
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-09 10:02:30 +0000