summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_rules.c5
-rw-r--r--net/ipv4/gre_offload.c11
-rw-r--r--net/ipv4/inet_diag.c21
-rw-r--r--net/ipv4/ip_gre.c1
-rw-r--r--net/ipv4/ip_output.c5
-rw-r--r--net/ipv4/ip_sockglue.c3
-rw-r--r--net/ipv4/ipmr.c7
-rw-r--r--net/ipv4/netfilter/ipt_SYNPROXY.c1
-rw-r--r--net/ipv4/netfilter/nft_reject_ipv4.c2
-rw-r--r--net/ipv4/ping.c7
-rw-r--r--net/ipv4/protocol.c8
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/tcp.c4
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_memcontrol.c9
-rw-r--r--net/ipv4/tcp_metrics.c51
-rw-r--r--net/ipv4/tcp_offload.c31
-rw-r--r--net/ipv4/udp.c53
-rw-r--r--net/ipv4/udp_offload.c37
19 files changed, 150 insertions, 110 deletions
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 523be38e37de..f2e15738534d 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -104,7 +104,10 @@ errout:
static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
{
struct fib_result *result = (struct fib_result *) arg->result;
- struct net_device *dev = result->fi->fib_dev;
+ struct net_device *dev = NULL;
+
+ if (result->fi)
+ dev = result->fi->fib_dev;
/* do not accept result if the route does
* not meet the required prefix length
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index e5d436188464..2cd02f32f99f 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -28,6 +28,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
netdev_features_t enc_features;
int ghl = GRE_HEADER_SECTION;
struct gre_base_hdr *greh;
+ u16 mac_offset = skb->mac_header;
int mac_len = skb->mac_len;
__be16 protocol = skb->protocol;
int tnl_hlen;
@@ -58,13 +59,13 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
} else
csum = false;
+ if (unlikely(!pskb_may_pull(skb, ghl)))
+ goto out;
+
/* setup inner skb. */
skb->protocol = greh->protocol;
skb->encapsulation = 0;
- if (unlikely(!pskb_may_pull(skb, ghl)))
- goto out;
-
__skb_pull(skb, ghl);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
@@ -73,8 +74,10 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
/* segment inner packet. */
enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
segs = skb_mac_gso_segment(skb, enc_features);
- if (!segs || IS_ERR(segs))
+ if (!segs || IS_ERR(segs)) {
+ skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len);
goto out;
+ }
skb = segs;
tnl_hlen = skb_tnl_header_len(skb);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 56a964a553d2..e34dccbc4d70 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -106,6 +106,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
r->id.idiag_sport = inet->inet_sport;
r->id.idiag_dport = inet->inet_dport;
+
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
r->id.idiag_src[0] = inet->inet_rcv_saddr;
r->id.idiag_dst[0] = inet->inet_daddr;
@@ -240,12 +244,19 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
r->idiag_family = tw->tw_family;
r->idiag_retrans = 0;
+
r->id.idiag_if = tw->tw_bound_dev_if;
sock_diag_save_cookie(tw, r->id.idiag_cookie);
+
r->id.idiag_sport = tw->tw_sport;
r->id.idiag_dport = tw->tw_dport;
+
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
r->id.idiag_src[0] = tw->tw_rcv_saddr;
r->id.idiag_dst[0] = tw->tw_daddr;
+
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = jiffies_to_msecs(tmo);
@@ -726,8 +737,13 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
r->id.idiag_sport = inet->inet_sport;
r->id.idiag_dport = ireq->ir_rmt_port;
+
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
r->id.idiag_src[0] = ireq->ir_loc_addr;
r->id.idiag_dst[0] = ireq->ir_rmt_addr;
+
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
@@ -914,12 +930,15 @@ skip_listen_ht:
spin_lock_bh(lock);
sk_nulls_for_each(sk, node, &head->chain) {
int res;
+ int state;
if (!net_eq(sock_net(sk), net))
continue;
if (num < s_num)
goto next_normal;
- if (!(r->idiag_states & (1 << sk->sk_state)))
+ state = (sk->sk_state == TCP_TIME_WAIT) ?
+ inet_twsk(sk)->tw_substate : sk->sk_state;
+ if (!(r->idiag_states & (1 << state)))
goto next_normal;
if (r->sdiag_family != AF_UNSPEC &&
sk->sk_family != r->sdiag_family)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index d7aea4c5b940..e560ef34cf4b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -217,6 +217,7 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
iph->saddr, iph->daddr, tpi->key);
if (tunnel) {
+ skb_pop_mac_header(skb);
ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error);
return PACKET_RCVD;
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 912402752f2f..df184616493f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -828,7 +828,7 @@ static int __ip_append_data(struct sock *sk,
if (cork->length + length > maxnonfragsize - fragheaderlen) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
- mtu-exthdrlen);
+ mtu - (opt ? opt->optlen : 0));
return -EMSGSIZE;
}
@@ -1151,7 +1151,8 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
mtu : 0xFFFF;
if (cork->length + size > maxnonfragsize - fragheaderlen) {
- ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
+ ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
+ mtu - (opt ? opt->optlen : 0));
return -EMSGSIZE;
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 3f858266fa7e..ddf32a6bc415 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -386,7 +386,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
/*
* Handle MSG_ERRQUEUE
*/
-int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct sock_exterr_skb *serr;
struct sk_buff *skb, *skb2;
@@ -423,6 +423,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
serr->addr_offset);
sin->sin_port = serr->port;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 62212c772a4b..1672409f5ba5 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -157,9 +157,12 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id)
static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
struct mr_table **mrt)
{
- struct ipmr_result res;
- struct fib_lookup_arg arg = { .result = &res, };
int err;
+ struct ipmr_result res;
+ struct fib_lookup_arg arg = {
+ .result = &res,
+ .flags = FIB_LOOKUP_NOREF,
+ };
err = fib_rules_lookup(net->ipv4.mr_rules_ops,
flowi4_to_flowi(flp4), 0, &arg);
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index f13bd91d9a56..a313c3fbeb46 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -423,6 +423,7 @@ static void synproxy_tg4_destroy(const struct xt_tgdtor_param *par)
static struct xt_target synproxy_tg4_reg __read_mostly = {
.name = "SYNPROXY",
.family = NFPROTO_IPV4,
+ .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD),
.target = synproxy_tg4,
.targetsize = sizeof(struct xt_synproxy_info),
.checkentry = synproxy_tg4_check,
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index fff5ba1a33b7..4a5e94ac314a 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -72,7 +72,7 @@ static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
const struct nft_reject *priv = nft_expr_priv(expr);
- if (nla_put_be32(skb, NFTA_REJECT_TYPE, priv->type))
+ if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
goto nla_put_failure;
switch (priv->type) {
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 876c6ca2d8f9..242e7f4ed6f4 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -772,7 +772,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
err = PTR_ERR(rt);
rt = NULL;
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
}
@@ -841,10 +841,11 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (flags & MSG_ERRQUEUE) {
if (family == AF_INET) {
- return ip_recv_error(sk, msg, len);
+ return ip_recv_error(sk, msg, len, addr_len);
#if IS_ENABLED(CONFIG_IPV6)
} else if (family == AF_INET6) {
- return pingv6_ops.ipv6_recv_error(sk, msg, len);
+ return pingv6_ops.ipv6_recv_error(sk, msg, len,
+ addr_len);
#endif
}
}
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index ce848461acbb..46d6a1c923a8 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -31,10 +31,6 @@
const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
-/*
- * Add a protocol handler to the hash tables
- */
-
int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
{
if (!prot->netns_ok) {
@@ -55,10 +51,6 @@ int inet_add_offload(const struct net_offload *prot, unsigned char protocol)
}
EXPORT_SYMBOL(inet_add_offload);
-/*
- * Remove a protocol from the hash tables.
- */
-
int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol)
{
int ret;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 5cb8ddb505ee..23c3e5b5bb53 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -697,7 +697,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
goto out;
if (flags & MSG_ERRQUEUE) {
- err = ip_recv_error(sk, msg, len);
+ err = ip_recv_error(sk, msg, len, addr_len);
goto out;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c4638e6f0238..82de78603686 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1623,11 +1623,11 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
(len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
!sysctl_tcp_low_latency &&
net_dma_find_channel()) {
- preempt_enable_no_resched();
+ preempt_enable();
tp->ucopy.pinned_list =
dma_pin_iovec_pages(msg->msg_iov, len);
} else {
- preempt_enable_no_resched();
+ preempt_enable();
}
}
#endif
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 59a6f8b90cd9..067213924751 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -177,7 +177,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
return err;
}
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 03e9154f7e68..f7e522c558ba 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -6,13 +6,6 @@
#include <linux/memcontrol.h>
#include <linux/module.h>
-static void memcg_tcp_enter_memory_pressure(struct sock *sk)
-{
- if (sk->sk_cgrp->memory_pressure)
- sk->sk_cgrp->memory_pressure = 1;
-}
-EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
-
int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
/*
@@ -60,7 +53,6 @@ EXPORT_SYMBOL(tcp_destroy_cgroup);
static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
{
struct cg_proto *cg_proto;
- u64 old_lim;
int i;
int ret;
@@ -71,7 +63,6 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
if (val > RES_COUNTER_MAX)
val = RES_COUNTER_MAX;
- old_lim = res_counter_read_u64(&cg_proto->memory_allocated, RES_LIMIT);
ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
if (ret)
return ret;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 06493736fbc8..098b3a29f6f3 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -22,6 +22,9 @@
int sysctl_tcp_nometrics_save __read_mostly;
+static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr,
+ struct net *net, unsigned int hash);
+
struct tcp_fastopen_metrics {
u16 mss;
u16 syn_loss:10; /* Recurring Fast Open SYN losses */
@@ -130,16 +133,41 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
}
}
+#define TCP_METRICS_TIMEOUT (60 * 60 * HZ)
+
+static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+{
+ if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+ tcpm_suck_dst(tm, dst, false);
+}
+
+#define TCP_METRICS_RECLAIM_DEPTH 5
+#define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL
+
static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
struct inetpeer_addr *addr,
- unsigned int hash,
- bool reclaim)
+ unsigned int hash)
{
struct tcp_metrics_block *tm;
struct net *net;
+ bool reclaim = false;
spin_lock_bh(&tcp_metrics_lock);
net = dev_net(dst->dev);
+
+ /* While waiting for the spin-lock the cache might have been populated
+ * with this entry and so we have to check again.
+ */
+ tm = __tcp_get_metrics(addr, net, hash);
+ if (tm == TCP_METRICS_RECLAIM_PTR) {
+ reclaim = true;
+ tm = NULL;
+ }
+ if (tm) {
+ tcpm_check_stamp(tm, dst);
+ goto out_unlock;
+ }
+
if (unlikely(reclaim)) {
struct tcp_metrics_block *oldest;
@@ -169,17 +197,6 @@ out_unlock:
return tm;
}
-#define TCP_METRICS_TIMEOUT (60 * 60 * HZ)
-
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
-{
- if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
- tcpm_suck_dst(tm, dst, false);
-}
-
-#define TCP_METRICS_RECLAIM_DEPTH 5
-#define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL
-
static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth)
{
if (tm)
@@ -282,7 +299,6 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
struct inetpeer_addr addr;
unsigned int hash;
struct net *net;
- bool reclaim;
addr.family = sk->sk_family;
switch (addr.family) {
@@ -304,13 +320,10 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
tm = __tcp_get_metrics(&addr, net, hash);
- reclaim = false;
- if (tm == TCP_METRICS_RECLAIM_PTR) {
- reclaim = true;
+ if (tm == TCP_METRICS_RECLAIM_PTR)
tm = NULL;
- }
if (!tm && create)
- tm = tcpm_new(dst, &addr, hash, reclaim);
+ tm = tcpm_new(dst, &addr, hash);
else
tcpm_check_stamp(tm, dst);
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index a2b68a108eae..05606353c7e7 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -274,33 +274,32 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *
{
const struct iphdr *iph = skb_gro_network_header(skb);
__wsum wsum;
- __sum16 sum;
+
+ /* Don't bother verifying checksum if we're going to flush anyway. */
+ if (NAPI_GRO_CB(skb)->flush)
+ goto skip_csum;
+
+ wsum = skb->csum;
switch (skb->ip_summed) {
+ case CHECKSUM_NONE:
+ wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb),
+ 0);
+
+ /* fall through */
+
case CHECKSUM_COMPLETE:
if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
- skb->csum)) {
+ wsum)) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
-flush:
+
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
-
- case CHECKSUM_NONE:
- wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
- skb_gro_len(skb), IPPROTO_TCP, 0);
- sum = csum_fold(skb_checksum(skb,
- skb_gro_offset(skb),
- skb_gro_len(skb),
- wsum));
- if (sum)
- goto flush;
-
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- break;
}
+skip_csum:
return tcp_gro_receive(head, skb);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5944d7d668dd..a7e4729e974b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -560,15 +560,11 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport,
struct udp_table *udptable)
{
- struct sock *sk;
const struct iphdr *iph = ip_hdr(skb);
- if (unlikely(sk = skb_steal_sock(skb)))
- return sk;
- else
- return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
- iph->daddr, dport, inet_iif(skb),
- udptable);
+ return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
+ iph->daddr, dport, inet_iif(skb),
+ udptable);
}
struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
@@ -999,7 +995,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
err = PTR_ERR(rt);
rt = NULL;
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
}
@@ -1098,6 +1094,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
struct udp_sock *up = udp_sk(sk);
int ret;
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ flags |= MSG_MORE;
+
if (!up->pending) {
struct msghdr msg = { .msg_flags = flags|MSG_MORE };
@@ -1236,7 +1235,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
bool slow;
if (flags & MSG_ERRQUEUE)
- return ip_recv_error(sk, msg, len);
+ return ip_recv_error(sk, msg, len, addr_len);
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -1600,12 +1599,16 @@ static void flush_stack(struct sock **stack, unsigned int count,
kfree_skb(skb1);
}
-static void udp_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+/* For TCP sockets, sk_rx_dst is protected by socket lock
+ * For UDP, we use xchg() to guard against concurrent changes.
+ */
+static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
{
- struct dst_entry *dst = skb_dst(skb);
+ struct dst_entry *old;
dst_hold(dst);
- sk->sk_rx_dst = dst;
+ old = xchg(&sk->sk_rx_dst, dst);
+ dst_release(old);
}
/*
@@ -1736,15 +1739,16 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (udp4_csum_init(skb, uh, proto))
goto csum_error;
- if (skb->sk) {
+ sk = skb_steal_sock(skb);
+ if (sk) {
+ struct dst_entry *dst = skb_dst(skb);
int ret;
- sk = skb->sk;
- if (unlikely(sk->sk_rx_dst == NULL))
- udp_sk_rx_dst_set(sk, skb);
+ if (unlikely(sk->sk_rx_dst != dst))
+ udp_sk_rx_dst_set(sk, dst);
ret = udp_queue_rcv_skb(sk, skb);
-
+ sock_put(sk);
/* a return value > 0 means to resubmit the input, but
* it wants the return to be -protocol, or 0
*/
@@ -1910,17 +1914,20 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
void udp_v4_early_demux(struct sk_buff *skb)
{
- const struct iphdr *iph = ip_hdr(skb);
- const struct udphdr *uh = udp_hdr(skb);
+ struct net *net = dev_net(skb->dev);
+ const struct iphdr *iph;
+ const struct udphdr *uh;
struct sock *sk;
struct dst_entry *dst;
- struct net *net = dev_net(skb->dev);
int dif = skb->dev->ifindex;
/* validate the packet */
if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
return;
+ iph = ip_hdr(skb);
+ uh = udp_hdr(skb);
+
if (skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST)
sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
@@ -2471,6 +2478,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
+ u16 mac_offset = skb->mac_header;
int mac_len = skb->mac_len;
int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
__be16 protocol = skb->protocol;
@@ -2490,8 +2498,11 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
/* segment inner packet. */
enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
segs = skb_mac_gso_segment(skb, enc_features);
- if (!segs || IS_ERR(segs))
+ if (!segs || IS_ERR(segs)) {
+ skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
+ mac_len);
goto out;
+ }
outer_hlen = skb_tnl_header_len(skb);
skb = segs;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 83206de2bc76..79c62bdcd3c5 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -41,6 +41,14 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
unsigned int mss;
+ int offset;
+ __wsum csum;
+
+ if (skb->encapsulation &&
+ skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) {
+ segs = skb_udp_tunnel_segment(skb, features);
+ goto out;
+ }
mss = skb_shinfo(skb)->gso_size;
if (unlikely(skb->len <= mss))
@@ -63,27 +71,20 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
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.
+ */
+ offset = skb_checksum_start_offset(skb);
+ csum = skb_checksum(skb, offset, skb->len - offset, 0);
+ offset += skb->csum_offset;
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+ skb->ip_summed = CHECKSUM_NONE;
+
/* Fragment the skb. IP headers of the fragments are updated in
* inet_gso_segment()
*/
- if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
- segs = skb_udp_tunnel_segment(skb, features);
- else {
- int offset;
- __wsum csum;
-
- /* Do software UFO. Complete and fill in the UDP checksum as
- * HW cannot do checksum of UDP packets sent as multiple
- * IP fragments.
- */
- offset = skb_checksum_start_offset(skb);
- csum = skb_checksum(skb, offset, skb->len - offset, 0);
- offset += skb->csum_offset;
- *(__sum16 *)(skb->data + offset) = csum_fold(csum);
- skb->ip_summed = CHECKSUM_NONE;
-
- segs = skb_segment(skb, features);
- }
+ segs = skb_segment(skb, features);
out:
return segs;
}
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-01 08:16:01 +0300