summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/esp4.c53
-rw-r--r--net/ipv4/fib_frontend.c18
-rw-r--r--net/ipv4/fib_rules.c4
-rw-r--r--net/ipv4/fib_trie.c22
-rw-r--r--net/ipv4/inet_hashtables.c37
-rw-r--r--net/ipv4/ip_gre.c16
-rw-r--r--net/ipv4/netfilter/nft_fib_ipv4.c20
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_fastopen.c3
-rw-r--r--net/ipv4/tcp_input.c135
-rw-r--r--net/ipv4/tcp_offload.c3
-rw-r--r--net/ipv4/udp_offload.c67
-rw-r--r--net/ipv4/xfrm4_input.c21
14 files changed, 239 insertions, 166 deletions
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index f3281312eb5e..cbe4c6fc8b8e 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -120,47 +120,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
}
#ifdef CONFIG_INET_ESPINTCP
-struct esp_tcp_sk {
- struct sock *sk;
- struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
- struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
- sock_put(esk->sk);
- kfree(esk);
-}
-
static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
{
struct xfrm_encap_tmpl *encap = x->encap;
struct net *net = xs_net(x);
- struct esp_tcp_sk *esk;
__be16 sport, dport;
- struct sock *nsk;
struct sock *sk;
- sk = rcu_dereference(x->encap_sk);
- if (sk && sk->sk_state == TCP_ESTABLISHED)
- return sk;
-
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
dport = encap->encap_dport;
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (sk && sk == nsk) {
- esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
- if (!esk) {
- spin_unlock_bh(&x->lock);
- return ERR_PTR(-ENOMEM);
- }
- RCU_INIT_POINTER(x->encap_sk, NULL);
- esk->sk = sk;
- call_rcu(&esk->rcu, esp_free_tcp_sk);
- }
spin_unlock_bh(&x->lock);
sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4,
@@ -173,20 +142,6 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
return ERR_PTR(-EINVAL);
}
- spin_lock_bh(&x->lock);
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (encap->encap_sport != sport ||
- encap->encap_dport != dport) {
- sock_put(sk);
- sk = nsk ?: ERR_PTR(-EREMCHG);
- } else if (sk == nsk) {
- sock_put(sk);
- } else {
- rcu_assign_pointer(x->encap_sk, sk);
- }
- spin_unlock_bh(&x->lock);
-
return sk;
}
@@ -199,8 +154,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
sk = esp_find_tcp_sk(x);
err = PTR_ERR_OR_ZERO(sk);
- if (err)
+ if (err) {
+ kfree_skb(skb);
goto out;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
@@ -209,6 +166,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
err = espintcp_push_skb(sk, skb);
bh_unlock_sock(sk);
+ sock_put(sk);
+
out:
rcu_read_unlock();
return err;
@@ -392,6 +351,8 @@ static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
if (IS_ERR(sk))
return ERR_CAST(sk);
+ sock_put(sk);
+
*lenp = htons(len);
esph = (struct ip_esp_hdr *)(lenp + 1);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 793e6781399a..5b7c41333d6f 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -829,19 +829,33 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
}
}
+ if (cfg->fc_dst_len > 32) {
+ NL_SET_ERR_MSG(extack, "Invalid prefix length");
+ err = -EINVAL;
+ goto errout;
+ }
+
+ if (cfg->fc_dst_len < 32 && (ntohl(cfg->fc_dst) << cfg->fc_dst_len)) {
+ NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length");
+ err = -EINVAL;
+ goto errout;
+ }
+
if (cfg->fc_nh_id) {
if (cfg->fc_oif || cfg->fc_gw_family ||
cfg->fc_encap || cfg->fc_mp) {
NL_SET_ERR_MSG(extack,
"Nexthop specification and nexthop id are mutually exclusive");
- return -EINVAL;
+ err = -EINVAL;
+ goto errout;
}
}
if (has_gw && has_via) {
NL_SET_ERR_MSG(extack,
"Nexthop configuration can not contain both GATEWAY and VIA");
- return -EINVAL;
+ err = -EINVAL;
+ goto errout;
}
if (!cfg->fc_table)
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index b07292d50ee7..4563e5303c1a 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -245,9 +245,9 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
- struct net *net = sock_net(skb->sk);
+ struct fib4_rule *rule4 = (struct fib4_rule *)rule;
+ struct net *net = rule->fr_net;
int err = -EINVAL;
- struct fib4_rule *rule4 = (struct fib4_rule *) rule;
if (!inet_validate_dscp(frh->tos)) {
NL_SET_ERR_MSG(extack,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 09e31757e96c..cc86031d2050 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1193,22 +1193,6 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp,
return 0;
}
-static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack)
-{
- if (plen > KEYLENGTH) {
- NL_SET_ERR_MSG(extack, "Invalid prefix length");
- return false;
- }
-
- if ((plen < KEYLENGTH) && (key << plen)) {
- NL_SET_ERR_MSG(extack,
- "Invalid prefix for given prefix length");
- return false;
- }
-
- return true;
-}
-
static void fib_remove_alias(struct trie *t, struct key_vector *tp,
struct key_vector *l, struct fib_alias *old);
@@ -1229,9 +1213,6 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
key = ntohl(cfg->fc_dst);
- if (!fib_valid_key_len(key, plen, extack))
- return -EINVAL;
-
pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen);
fi = fib_create_info(cfg, extack);
@@ -1723,9 +1704,6 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
key = ntohl(cfg->fc_dst);
- if (!fib_valid_key_len(key, plen, extack))
- return -EINVAL;
-
l = fib_find_node(t, &tp, key);
if (!l)
return -ESRCH;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 9bfcfd016e18..2b4a58824763 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -1230,22 +1230,37 @@ int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
{
unsigned int locksz = sizeof(spinlock_t);
unsigned int i, nblocks = 1;
+ spinlock_t *ptr = NULL;
- if (locksz != 0) {
- /* allocate 2 cache lines or at least one spinlock per cpu */
- nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U);
- nblocks = roundup_pow_of_two(nblocks * num_possible_cpus());
+ if (locksz == 0)
+ goto set_mask;
- /* no more locks than number of hash buckets */
- nblocks = min(nblocks, hashinfo->ehash_mask + 1);
+ /* Allocate 2 cache lines or at least one spinlock per cpu. */
+ nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U) * num_possible_cpus();
- hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL);
- if (!hashinfo->ehash_locks)
- return -ENOMEM;
+ /* At least one page per NUMA node. */
+ nblocks = max(nblocks, num_online_nodes() * PAGE_SIZE / locksz);
+
+ nblocks = roundup_pow_of_two(nblocks);
+
+ /* No more locks than number of hash buckets. */
+ nblocks = min(nblocks, hashinfo->ehash_mask + 1);
- for (i = 0; i < nblocks; i++)
- spin_lock_init(&hashinfo->ehash_locks[i]);
+ if (num_online_nodes() > 1) {
+ /* Use vmalloc() to allow NUMA policy to spread pages
+ * on all available nodes if desired.
+ */
+ ptr = vmalloc_array(nblocks, locksz);
+ }
+ if (!ptr) {
+ ptr = kvmalloc_array(nblocks, locksz, GFP_KERNEL);
+ if (!ptr)
+ return -ENOMEM;
}
+ for (i = 0; i < nblocks; i++)
+ spin_lock_init(&ptr[i]);
+ hashinfo->ehash_locks = ptr;
+set_mask:
hashinfo->ehash_locks_mask = nblocks - 1;
return 0;
}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f1f31ebfc793..9667f2774025 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -141,7 +141,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
const struct iphdr *iph;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
- unsigned int data_len = 0;
struct ip_tunnel *t;
if (tpi->proto == htons(ETH_P_TEB))
@@ -182,7 +181,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return 0;
- data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
break;
case ICMP_REDIRECT:
@@ -190,10 +188,16 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
}
#if IS_ENABLED(CONFIG_IPV6)
- if (tpi->proto == htons(ETH_P_IPV6) &&
- !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
- type, data_len))
- return 0;
+ if (tpi->proto == htons(ETH_P_IPV6)) {
+ unsigned int data_len = 0;
+
+ if (type == ICMP_TIME_EXCEEDED)
+ data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
+
+ if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
+ type, data_len))
+ return 0;
+ }
#endif
if (t->parms.iph.daddr == 0 ||
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 09fff5d424ef..f514eb52b8d4 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -49,7 +49,12 @@ void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
else
addr = iph->saddr;
- *dst = inet_dev_addr_type(nft_net(pkt), dev, addr);
+ if (priv->flags & (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) {
+ *dst = inet_dev_addr_type(nft_net(pkt), dev, addr);
+ return;
+ }
+
+ *dst = inet_addr_type_dev_table(nft_net(pkt), pkt->skb->dev, addr);
}
EXPORT_SYMBOL_GPL(nft_fib4_eval_type);
@@ -64,12 +69,17 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
struct flowi4 fl4 = {
.flowi4_scope = RT_SCOPE_UNIVERSE,
.flowi4_iif = LOOPBACK_IFINDEX,
+ .flowi4_proto = pkt->tprot,
.flowi4_uid = sock_net_uid(nft_net(pkt), NULL),
- .flowi4_l3mdev = l3mdev_master_ifindex_rcu(nft_in(pkt)),
};
const struct net_device *oif;
const struct net_device *found;
+ if (nft_fib_can_skip(pkt)) {
+ nft_fib_store_result(dest, priv, nft_in(pkt));
+ return;
+ }
+
/*
* Do not set flowi4_oif, it restricts results (for example, asking
* for oif 3 will get RTN_UNICAST result even if the daddr exits
@@ -84,11 +94,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
else
oif = NULL;
- if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
- nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
- nft_fib_store_result(dest, priv, nft_in(pkt));
- return;
- }
+ fl4.flowi4_l3mdev = nft_fib_l3mdev_master_ifindex_rcu(pkt, oif);
iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph);
if (!iph) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 41b320f0c20e..88d7c96bfac0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -189,7 +189,11 @@ const __u8 ip_tos2prio[16] = {
EXPORT_SYMBOL(ip_tos2prio);
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
+#ifndef CONFIG_PREEMPT_RT
#define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field)
+#else
+#define RT_CACHE_STAT_INC(field) this_cpu_inc(rt_cache_stat.field)
+#endif
#ifdef CONFIG_PROC_FS
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b731a4a8f2b0..156da81bce06 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1145,7 +1145,7 @@ restart:
goto do_error;
while (msg_data_left(msg)) {
- ssize_t copy = 0;
+ int copy = 0;
skb = tcp_write_queue_tail(sk);
if (skb)
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 32b28fc21b63..408985eb74ee 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -3,6 +3,7 @@
#include <linux/tcp.h>
#include <linux/rcupdate.h>
#include <net/tcp.h>
+#include <net/busy_poll.h>
void tcp_fastopen_init_key_once(struct net *net)
{
@@ -279,6 +280,8 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
refcount_set(&req->rsk_refcnt, 2);
+ sk_mark_napi_id_set(child, skb);
+
/* Now finish processing the fastopen child socket. */
tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d93a5a89c569..d176e7888a20 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -419,6 +419,20 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr
return false;
}
+static void tcp_count_delivered_ce(struct tcp_sock *tp, u32 ecn_count)
+{
+ tp->delivered_ce += ecn_count;
+}
+
+/* Updates the delivered and delivered_ce counts */
+static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
+ bool ece_ack)
+{
+ tp->delivered += delivered;
+ if (ece_ack)
+ tcp_count_delivered_ce(tp, delivered);
+}
+
/* Buffer size and advertised window tuning.
*
* 1. Tuning sk->sk_sndbuf, when connection enters established state.
@@ -651,10 +665,12 @@ EXPORT_SYMBOL(tcp_initialize_rcv_mss);
*/
static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
{
- u32 new_sample = tp->rcv_rtt_est.rtt_us;
- long m = sample;
+ u32 new_sample, old_sample = tp->rcv_rtt_est.rtt_us;
+ long m = sample << 3;
- if (new_sample != 0) {
+ if (old_sample == 0 || m < old_sample) {
+ new_sample = m;
+ } else {
/* If we sample in larger samples in the non-timestamp
* case, we could grossly overestimate the RTT especially
* with chatty applications or bulk transfer apps which
@@ -665,17 +681,9 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
* else with timestamps disabled convergence takes too
* long.
*/
- if (!win_dep) {
- m -= (new_sample >> 3);
- new_sample += m;
- } else {
- m <<= 3;
- if (m < new_sample)
- new_sample = m;
- }
- } else {
- /* No previous measure. */
- new_sample = m << 3;
+ if (win_dep)
+ return;
+ new_sample = old_sample - (old_sample >> 3) + sample;
}
tp->rcv_rtt_est.rtt_us = new_sample;
@@ -699,7 +707,7 @@ new_measure:
tp->rcv_rtt_est.time = tp->tcp_mstamp;
}
-static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp)
+static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp, u32 min_delta)
{
u32 delta, delta_us;
@@ -709,7 +717,7 @@ static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp)
if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
if (!delta)
- delta = 1;
+ delta = min_delta;
delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
return delta_us;
}
@@ -727,9 +735,9 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
if (TCP_SKB_CB(skb)->end_seq -
TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) {
- s32 delta = tcp_rtt_tsopt_us(tp);
+ s32 delta = tcp_rtt_tsopt_us(tp, 0);
- if (delta >= 0)
+ if (delta > 0)
tcp_rcv_rtt_update(tp, delta, 0);
}
}
@@ -741,8 +749,7 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
void tcp_rcv_space_adjust(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
- u32 copied;
- int time;
+ int time, inq, copied;
trace_tcp_rcv_space_adjust(sk);
@@ -753,6 +760,9 @@ void tcp_rcv_space_adjust(struct sock *sk)
/* Number of bytes copied to user in last RTT */
copied = tp->copied_seq - tp->rcvq_space.seq;
+ /* Number of bytes in receive queue. */
+ inq = tp->rcv_nxt - tp->copied_seq;
+ copied -= inq;
if (copied <= tp->rcvq_space.space)
goto new_measure;
@@ -1154,15 +1164,6 @@ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
}
}
-/* Updates the delivered and delivered_ce counts */
-static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
- bool ece_ack)
-{
- tp->delivered += delivered;
- if (ece_ack)
- tp->delivered_ce += delivered;
-}
-
/* This procedure tags the retransmission queue when SACKs arrive.
*
* We have three tag bits: SACKED(S), RETRANS(R) and LOST(L).
@@ -2481,20 +2482,33 @@ static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
{
const struct sock *sk = (const struct sock *)tp;
- if (tp->retrans_stamp &&
- tcp_tsopt_ecr_before(tp, tp->retrans_stamp))
- return true; /* got echoed TS before first retransmission */
+ /* Received an echoed timestamp before the first retransmission? */
+ if (tp->retrans_stamp)
+ return tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
+
+ /* We set tp->retrans_stamp upon the first retransmission of a loss
+ * recovery episode, so normally if tp->retrans_stamp is 0 then no
+ * retransmission has happened yet (likely due to TSQ, which can cause
+ * fast retransmits to be delayed). So if snd_una advanced while
+ * (tp->retrans_stamp is 0 then apparently a packet was merely delayed,
+ * not lost. But there are exceptions where we retransmit but then
+ * clear tp->retrans_stamp, so we check for those exceptions.
+ */
+
+ /* (1) For non-SACK connections, tcp_is_non_sack_preventing_reopen()
+ * clears tp->retrans_stamp when snd_una == high_seq.
+ */
+ if (!tcp_is_sack(tp) && !before(tp->snd_una, tp->high_seq))
+ return false;
- /* Check if nothing was retransmitted (retrans_stamp==0), which may
- * happen in fast recovery due to TSQ. But we ignore zero retrans_stamp
- * in TCP_SYN_SENT, since when we set FLAG_SYN_ACKED we also clear
- * retrans_stamp even if we had retransmitted the SYN.
+ /* (2) In TCP_SYN_SENT tcp_clean_rtx_queue() clears tp->retrans_stamp
+ * when setting FLAG_SYN_ACKED is set, even if the SYN was
+ * retransmitted.
*/
- if (!tp->retrans_stamp && /* no record of a retransmit/SYN? */
- sk->sk_state != TCP_SYN_SENT) /* not the FLAG_SYN_ACKED case? */
- return true; /* nothing was retransmitted */
+ if (sk->sk_state == TCP_SYN_SENT)
+ return false;
- return false;
+ return true; /* tp->retrans_stamp is zero; no retransmit yet */
}
/* Undo procedures. */
@@ -3221,7 +3235,7 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
*/
if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp &&
tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED)
- seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp);
+ seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp, 1);
rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
if (seq_rtt_us < 0)
@@ -3862,12 +3876,23 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
}
}
-static inline void tcp_in_ack_event(struct sock *sk, u32 flags)
+static void tcp_in_ack_event(struct sock *sk, int flag)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
- if (icsk->icsk_ca_ops->in_ack_event)
- icsk->icsk_ca_ops->in_ack_event(sk, flags);
+ if (icsk->icsk_ca_ops->in_ack_event) {
+ u32 ack_ev_flags = 0;
+
+ if (flag & FLAG_WIN_UPDATE)
+ ack_ev_flags |= CA_ACK_WIN_UPDATE;
+ if (flag & FLAG_SLOWPATH) {
+ ack_ev_flags |= CA_ACK_SLOWPATH;
+ if (flag & FLAG_ECE)
+ ack_ev_flags |= CA_ACK_ECE;
+ }
+
+ icsk->icsk_ca_ops->in_ack_event(sk, ack_ev_flags);
+ }
}
/* Congestion control has updated the cwnd already. So if we're in
@@ -3984,12 +4009,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
tcp_snd_una_update(tp, ack);
flag |= FLAG_WIN_UPDATE;
- tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
-
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS);
} else {
- u32 ack_ev_flags = CA_ACK_SLOWPATH;
-
if (ack_seq != TCP_SKB_CB(skb)->end_seq)
flag |= FLAG_DATA;
else
@@ -4001,19 +4022,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
&sack_state);
- if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) {
+ if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb)))
flag |= FLAG_ECE;
- ack_ev_flags |= CA_ACK_ECE;
- }
if (sack_state.sack_delivered)
tcp_count_delivered(tp, sack_state.sack_delivered,
flag & FLAG_ECE);
-
- if (flag & FLAG_WIN_UPDATE)
- ack_ev_flags |= CA_ACK_WIN_UPDATE;
-
- tcp_in_ack_event(sk, ack_ev_flags);
}
/* This is a deviation from RFC3168 since it states that:
@@ -4040,6 +4054,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
tcp_rack_update_reo_wnd(sk, &rs);
+ tcp_in_ack_event(sk, flag);
+
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);
@@ -4071,6 +4087,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
return 1;
no_queue:
+ tcp_in_ack_event(sk, flag);
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK) {
tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,
@@ -6833,6 +6850,9 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
if (!tp->srtt_us)
tcp_synack_rtt_meas(sk, req);
+ if (tp->rx_opt.tstamp_ok)
+ tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
+
if (req) {
tcp_rcv_synrecv_state_fastopen(sk);
} else {
@@ -6858,9 +6878,6 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
- if (tp->rx_opt.tstamp_ok)
- tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
-
if (!inet_csk(sk)->icsk_ca_ops->cong_control)
tcp_update_pacing_rate(sk);
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 2dfac79dc78b..3a9c5c14c310 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -355,6 +355,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
flush |= skb->ip_summed != p->ip_summed;
flush |= skb->csum_level != p->csum_level;
flush |= NAPI_GRO_CB(p)->count >= 64;
+ skb_set_network_header(skb, skb_gro_receive_network_offset(skb));
if (flush || skb_gro_receive_list(p, skb))
mss = 1;
@@ -435,7 +436,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
iif, sdif);
NAPI_GRO_CB(skb)->is_flist = !sk;
if (sk)
- sock_put(sk);
+ sock_gen_put(sk);
}
INDIRECT_CALLABLE_SCOPE
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index ecfca59f31f1..5de47dd5e909 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -247,6 +247,62 @@ static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs)
return segs;
}
+static void __udpv6_gso_segment_csum(struct sk_buff *seg,
+ struct in6_addr *oldip,
+ const struct in6_addr *newip,
+ __be16 *oldport, __be16 newport)
+{
+ struct udphdr *uh = udp_hdr(seg);
+
+ if (ipv6_addr_equal(oldip, newip) && *oldport == newport)
+ return;
+
+ if (uh->check) {
+ inet_proto_csum_replace16(&uh->check, seg, oldip->s6_addr32,
+ newip->s6_addr32, true);
+
+ inet_proto_csum_replace2(&uh->check, seg, *oldport, newport,
+ false);
+ if (!uh->check)
+ uh->check = CSUM_MANGLED_0;
+ }
+
+ *oldip = *newip;
+ *oldport = newport;
+}
+
+static struct sk_buff *__udpv6_gso_segment_list_csum(struct sk_buff *segs)
+{
+ const struct ipv6hdr *iph;
+ const struct udphdr *uh;
+ struct ipv6hdr *iph2;
+ struct sk_buff *seg;
+ struct udphdr *uh2;
+
+ seg = segs;
+ uh = udp_hdr(seg);
+ iph = ipv6_hdr(seg);
+ uh2 = udp_hdr(seg->next);
+ iph2 = ipv6_hdr(seg->next);
+
+ if (!(*(const u32 *)&uh->source ^ *(const u32 *)&uh2->source) &&
+ ipv6_addr_equal(&iph->saddr, &iph2->saddr) &&
+ ipv6_addr_equal(&iph->daddr, &iph2->daddr))
+ return segs;
+
+ while ((seg = seg->next)) {
+ uh2 = udp_hdr(seg);
+ iph2 = ipv6_hdr(seg);
+
+ __udpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr,
+ &uh2->source, uh->source);
+ __udpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr,
+ &uh2->dest, uh->dest);
+ }
+
+ return segs;
+}
+
static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
netdev_features_t features,
bool is_ipv6)
@@ -259,7 +315,10 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss);
- return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb);
+ if (is_ipv6)
+ return __udpv6_gso_segment_list_csum(skb);
+ else
+ return __udpv4_gso_segment_list_csum(skb);
}
struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
@@ -273,6 +332,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
bool copy_dtor;
__sum16 check;
__be16 newlen;
+ int ret = 0;
mss = skb_shinfo(gso_skb)->gso_size;
if (gso_skb->len <= sizeof(*uh) + mss)
@@ -301,6 +361,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size)
return __udp_gso_segment_list(gso_skb, features, is_ipv6);
+ ret = __skb_linearize(gso_skb);
+ if (ret)
+ return ERR_PTR(ret);
+
/* Setup csum, as fraglist skips this in udp4_gro_receive. */
gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head;
gso_skb->csum_offset = offsetof(struct udphdr, check);
@@ -540,6 +604,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
+ skb_set_network_header(skb, skb_gro_receive_network_offset(skb));
ret = skb_gro_receive_list(p, skb);
} else {
skb_gro_postpull_rcsum(skb, uh,
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index a620618cc568..12a1a0f42195 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -182,11 +182,15 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
int offset = skb_gro_offset(skb);
const struct net_offload *ops;
struct sk_buff *pp = NULL;
- int ret;
-
- offset = offset - sizeof(struct udphdr);
+ int len, dlen;
+ __u8 *udpdata;
+ __be32 *udpdata32;
- if (!pskb_pull(skb, offset))
+ len = skb->len - offset;
+ dlen = offset + min(len, 8);
+ udpdata = skb_gro_header(skb, dlen, offset);
+ udpdata32 = (__be32 *)udpdata;
+ if (unlikely(!udpdata))
return NULL;
rcu_read_lock();
@@ -194,11 +198,13 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
if (!ops || !ops->callbacks.gro_receive)
goto out;
- ret = __xfrm4_udp_encap_rcv(sk, skb, false);
- if (ret)
+ /* check if it is a keepalive or IKE packet */
+ if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
goto out;
- skb_push(skb, offset);
+ /* set the transport header to ESP */
+ skb_set_transport_header(skb, offset);
+
NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +214,6 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
out:
rcu_read_unlock();
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 1;
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-12 09:52:15 +0300