aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c14
-rw-r--r--net/ipv4/esp4.c36
-rw-r--r--net/ipv4/esp4_offload.c73
-rw-r--r--net/ipv4/fib_frontend.c9
-rw-r--r--net/ipv4/fib_semantics.c8
-rw-r--r--net/ipv4/inet_connection_sock.c8
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/ip_gre.c6
-rw-r--r--net/ipv4/tcp.c34
-rw-r--r--net/ipv4/tcp_diag.c2
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/xfrm4_mode_tunnel.c5
12 files changed, 101 insertions, 100 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f00499a46927..bab98a4fedad 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -121,6 +121,7 @@
#endif
#include <net/l3mdev.h>
+#include <trace/events/sock.h>
/* The inetsw table contains everything that inet_create needs to
* build a new socket.
@@ -1220,6 +1221,19 @@ int inet_sk_rebuild_header(struct sock *sk)
}
EXPORT_SYMBOL(inet_sk_rebuild_header);
+void inet_sk_set_state(struct sock *sk, int state)
+{
+ trace_inet_sock_set_state(sk, sk->sk_state, state);
+ sk->sk_state = state;
+}
+EXPORT_SYMBOL(inet_sk_set_state);
+
+void inet_sk_state_store(struct sock *sk, int newstate)
+{
+ trace_inet_sock_set_state(sk, sk->sk_state, newstate);
+ smp_store_release(&sk->sk_state, newstate);
+}
+
struct sk_buff *inet_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index d57aa64fa7c7..6f00e43120a8 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -121,14 +121,32 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
static void esp_output_done(struct crypto_async_request *base, int err)
{
struct sk_buff *skb = base->data;
+ struct xfrm_offload *xo = xfrm_offload(skb);
void *tmp;
- struct dst_entry *dst = skb_dst(skb);
- struct xfrm_state *x = dst->xfrm;
+ struct xfrm_state *x;
+
+ if (xo && (xo->flags & XFRM_DEV_RESUME))
+ x = skb->sp->xvec[skb->sp->len - 1];
+ else
+ x = skb_dst(skb)->xfrm;
tmp = ESP_SKB_CB(skb)->tmp;
esp_ssg_unref(x, tmp);
kfree(tmp);
- xfrm_output_resume(skb, err);
+
+ if (xo && (xo->flags & XFRM_DEV_RESUME)) {
+ if (err) {
+ XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR);
+ kfree_skb(skb);
+ return;
+ }
+
+ skb_push(skb, skb->data - skb_mac_header(skb));
+ secpath_reset(skb);
+ xfrm_dev_resume(skb);
+ } else {
+ xfrm_output_resume(skb, err);
+ }
}
/* Move ESP header back into place. */
@@ -825,17 +843,13 @@ static int esp_init_aead(struct xfrm_state *x)
char aead_name[CRYPTO_MAX_ALG_NAME];
struct crypto_aead *aead;
int err;
- u32 mask = 0;
err = -ENAMETOOLONG;
if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
goto error;
- if (x->xso.offload_handle)
- mask |= CRYPTO_ALG_ASYNC;
-
- aead = crypto_alloc_aead(aead_name, 0, mask);
+ aead = crypto_alloc_aead(aead_name, 0, 0);
err = PTR_ERR(aead);
if (IS_ERR(aead))
goto error;
@@ -865,7 +879,6 @@ static int esp_init_authenc(struct xfrm_state *x)
char authenc_name[CRYPTO_MAX_ALG_NAME];
unsigned int keylen;
int err;
- u32 mask = 0;
err = -EINVAL;
if (!x->ealg)
@@ -891,10 +904,7 @@ static int esp_init_authenc(struct xfrm_state *x)
goto error;
}
- if (x->xso.offload_handle)
- mask |= CRYPTO_ALG_ASYNC;
-
- aead = crypto_alloc_aead(authenc_name, 0, mask);
+ aead = crypto_alloc_aead(authenc_name, 0, 0);
err = PTR_ERR(aead);
if (IS_ERR(aead))
goto error;
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index f8b918c766b0..c359f3cfeec3 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -108,75 +108,36 @@ static void esp4_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
- __u32 seq;
- int err = 0;
- struct sk_buff *skb2;
struct xfrm_state *x;
struct ip_esp_hdr *esph;
struct crypto_aead *aead;
- struct sk_buff *segs = ERR_PTR(-EINVAL);
netdev_features_t esp_features = features;
struct xfrm_offload *xo = xfrm_offload(skb);
if (!xo)
- goto out;
-
- seq = xo->seq.low;
+ return ERR_PTR(-EINVAL);
x = skb->sp->xvec[skb->sp->len - 1];
aead = x->data;
esph = ip_esp_hdr(skb);
if (esph->spi != x->id.spi)
- goto out;
+ return ERR_PTR(-EINVAL);
if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
- goto out;
+ return ERR_PTR(-EINVAL);
__skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead));
skb->encap_hdr_csum = 1;
- if (!(features & NETIF_F_HW_ESP))
+ if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
+ (x->xso.dev != skb->dev))
esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
- segs = x->outer_mode->gso_segment(x, skb, esp_features);
- if (IS_ERR_OR_NULL(segs))
- goto out;
-
- __skb_pull(skb, skb->data - skb_mac_header(skb));
-
- skb2 = segs;
- do {
- struct sk_buff *nskb = skb2->next;
-
- xo = xfrm_offload(skb2);
- xo->flags |= XFRM_GSO_SEGMENT;
- xo->seq.low = seq;
- xo->seq.hi = xfrm_replay_seqhi(x, seq);
+ xo->flags |= XFRM_GSO_SEGMENT;
- if(!(features & NETIF_F_HW_ESP))
- xo->flags |= CRYPTO_FALLBACK;
-
- x->outer_mode->xmit(x, skb2);
-
- err = x->type_offload->xmit(x, skb2, esp_features);
- if (err) {
- kfree_skb_list(segs);
- return ERR_PTR(err);
- }
-
- if (!skb_is_gso(skb2))
- seq++;
- else
- seq += skb_shinfo(skb2)->gso_segs;
-
- skb_push(skb2, skb2->mac_len);
- skb2 = nskb;
- } while (skb2);
-
-out:
- return segs;
+ return x->outer_mode->gso_segment(x, skb, esp_features);
}
static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb)
@@ -203,6 +164,7 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_
struct crypto_aead *aead;
struct esp_info esp;
bool hw_offload = true;
+ __u32 seq;
esp.inplace = true;
@@ -241,23 +203,30 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_
return esp.nfrags;
}
+ seq = xo->seq.low;
+
esph = esp.esph;
esph->spi = x->id.spi;
skb_push(skb, -skb_network_offset(skb));
if (xo->flags & XFRM_GSO_SEGMENT) {
- esph->seq_no = htonl(xo->seq.low);
- } else {
- ip_hdr(skb)->tot_len = htons(skb->len);
- ip_send_check(ip_hdr(skb));
+ esph->seq_no = htonl(seq);
+
+ if (!skb_is_gso(skb))
+ xo->seq.low++;
+ else
+ xo->seq.low += skb_shinfo(skb)->gso_segs;
}
+ esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32));
+
+ ip_hdr(skb)->tot_len = htons(skb->len);
+ ip_send_check(ip_hdr(skb));
+
if (hw_offload)
return 0;
- esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
-
err = esp_output_tail(x, skb, &esp);
if (err)
return err;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index f52d27a422c3..08259d078b1c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1298,14 +1298,19 @@ err_table_hash_alloc:
static void ip_fib_net_exit(struct net *net)
{
- unsigned int i;
+ int i;
rtnl_lock();
#ifdef CONFIG_IP_MULTIPLE_TABLES
RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
#endif
- for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+ /* Destroy the tables in reverse order to guarantee that the
+ * local table, ID 255, is destroyed before the main table, ID
+ * 254. This is necessary as the local table may contain
+ * references to data contained in the main table.
+ */
+ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) {
struct hlist_head *head = &net->ipv4.fib_table_hash[i];
struct hlist_node *tmp;
struct fib_table *tb;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f04d944f8abe..c586597da20d 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -698,7 +698,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
int type = nla_type(nla);
- u32 val;
+ u32 fi_val, val;
if (!type)
continue;
@@ -715,7 +715,11 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
val = nla_get_u32(nla);
}
- if (fi->fib_metrics->metrics[type - 1] != val)
+ fi_val = fi->fib_metrics->metrics[type - 1];
+ if (type == RTAX_FEATURES)
+ fi_val &= ~DST_FEATURE_ECN_CA;
+
+ if (fi_val != val)
return false;
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4ca46dc08e63..12410ec6f7f7 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -685,7 +685,7 @@ static void reqsk_timer_handler(struct timer_list *t)
int max_retries, thresh;
u8 defer_accept;
- if (sk_state_load(sk_listener) != TCP_LISTEN)
+ if (inet_sk_state_load(sk_listener) != TCP_LISTEN)
goto drop;
max_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
@@ -783,7 +783,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
if (newsk) {
struct inet_connection_sock *newicsk = inet_csk(newsk);
- newsk->sk_state = TCP_SYN_RECV;
+ inet_sk_set_state(newsk, TCP_SYN_RECV);
newicsk->icsk_bind_hash = NULL;
inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
@@ -877,7 +877,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
* It is OK, because this socket enters to hash table only
* after validation is complete.
*/
- sk_state_store(sk, TCP_LISTEN);
+ inet_sk_state_store(sk, TCP_LISTEN);
if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
inet->inet_sport = htons(inet->inet_num);
@@ -888,7 +888,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
return 0;
}
- sk->sk_state = TCP_CLOSE;
+ inet_sk_set_state(sk, TCP_CLOSE);
return err;
}
EXPORT_SYMBOL_GPL(inet_csk_listen_start);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index f6f58108b4c5..37b7da0b975d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -544,7 +544,7 @@ bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
} else {
percpu_counter_inc(sk->sk_prot->orphan_count);
- sk->sk_state = TCP_CLOSE;
+ inet_sk_set_state(sk, TCP_CLOSE);
sock_set_flag(sk, SOCK_DEAD);
inet_csk_destroy_sock(sk);
}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index fd4d6e96da7e..b61f2285816d 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -313,9 +313,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
return PACKET_REJECT;
md = ip_tunnel_info_opts(&tun_dst->u.tun_info);
- if (!md)
- return PACKET_REJECT;
-
memcpy(md, pkt_md, sizeof(*md));
md->version = ver;
@@ -434,11 +431,13 @@ static int gre_rcv(struct sk_buff *skb)
tpi.proto == htons(ETH_P_ERSPAN2))) {
if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
return 0;
+ goto out;
}
if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
return 0;
+out:
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
kfree_skb(skb);
@@ -1332,6 +1331,7 @@ static const struct net_device_ops erspan_netdev_ops = {
static void ipgre_tap_setup(struct net_device *dev)
{
ether_setup(dev);
+ dev->max_mtu = 0;
dev->netdev_ops = &gre_tap_netdev_ops;
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c470fec9062f..7ac583a2b9fe 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -283,8 +283,6 @@
#include <asm/ioctls.h>
#include <net/busy_poll.h>
-#include <trace/events/tcp.h>
-
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
@@ -504,7 +502,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
sock_poll_wait(file, sk_sleep(sk), wait);
- state = sk_state_load(sk);
+ state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
@@ -1106,12 +1104,15 @@ static int linear_payload_sz(bool first_skb)
return 0;
}
-static int select_size(const struct sock *sk, bool sg, bool first_skb)
+static int select_size(const struct sock *sk, bool sg, bool first_skb, bool zc)
{
const struct tcp_sock *tp = tcp_sk(sk);
int tmp = tp->mss_cache;
if (sg) {
+ if (zc)
+ return 0;
+
if (sk_can_gso(sk)) {
tmp = linear_payload_sz(first_skb);
} else {
@@ -1188,7 +1189,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
int flags, err, copied = 0;
int mss_now = 0, size_goal, copied_syn = 0;
bool process_backlog = false;
- bool sg;
+ bool sg, zc = false;
long timeo;
flags = msg->msg_flags;
@@ -1206,7 +1207,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
goto out_err;
}
- if (!(sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG))
+ zc = sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG;
+ if (!zc)
uarg->zerocopy = 0;
}
@@ -1283,6 +1285,7 @@ restart:
if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) {
bool first_skb;
+ int linear;
new_segment:
/* Allocate new segment. If the interface is SG,
@@ -1296,9 +1299,8 @@ new_segment:
goto restart;
}
first_skb = tcp_rtx_and_write_queues_empty(sk);
- skb = sk_stream_alloc_skb(sk,
- select_size(sk, sg, first_skb),
- sk->sk_allocation,
+ linear = select_size(sk, sg, first_skb, zc);
+ skb = sk_stream_alloc_skb(sk, linear, sk->sk_allocation,
first_skb);
if (!skb)
goto wait_for_memory;
@@ -1327,13 +1329,13 @@ new_segment:
copy = msg_data_left(msg);
/* Where to copy to? */
- if (skb_availroom(skb) > 0) {
+ if (skb_availroom(skb) > 0 && !zc) {
/* We have some space in skb head. Superb! */
copy = min_t(int, copy, skb_availroom(skb));
err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy);
if (err)
goto do_fault;
- } else if (!uarg || !uarg->zerocopy) {
+ } else if (!zc) {
bool merge = true;
int i = skb_shinfo(skb)->nr_frags;
struct page_frag *pfrag = sk_page_frag(sk);
@@ -1373,8 +1375,10 @@ new_segment:
pfrag->offset += copy;
} else {
err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
- if (err == -EMSGSIZE || err == -EEXIST)
+ if (err == -EMSGSIZE || err == -EEXIST) {
+ tcp_mark_push(tp, skb);
goto new_segment;
+ }
if (err < 0)
goto do_error;
copy = err;
@@ -2040,8 +2044,6 @@ void tcp_set_state(struct sock *sk, int state)
{
int oldstate = sk->sk_state;
- trace_tcp_set_state(sk, oldstate, state);
-
switch (state) {
case TCP_ESTABLISHED:
if (oldstate != TCP_ESTABLISHED)
@@ -2065,7 +2067,7 @@ void tcp_set_state(struct sock *sk, int state)
/* Change state AFTER socket is unhashed to avoid closed
* socket sitting in hash tables.
*/
- sk_state_store(sk, state);
+ inet_sk_state_store(sk, state);
#ifdef STATE_TRACE
SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
@@ -2920,7 +2922,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
if (sk->sk_type != SOCK_STREAM)
return;
- info->tcpi_state = sk_state_load(sk);
+ info->tcpi_state = inet_sk_state_load(sk);
/* Report meaningful fields for all TCP states, including listeners */
rate = READ_ONCE(sk->sk_pacing_rate);
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index abbf0edcf6c2..81148f7a2323 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -24,7 +24,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
{
struct tcp_info *info = _info;
- if (sk_state_load(sk) == TCP_LISTEN) {
+ if (inet_sk_state_load(sk) == TCP_LISTEN) {
r->idiag_rqueue = sk->sk_ack_backlog;
r->idiag_wqueue = sk->sk_max_ack_backlog;
} else if (sk->sk_type == SOCK_STREAM) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 94e28350f420..5d203248123e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1911,7 +1911,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
/* Clean up the MD5 key list, if any */
if (tp->md5sig_info) {
tcp_clear_md5_list(sk);
- kfree_rcu(tp->md5sig_info, rcu);
+ kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu);
tp->md5sig_info = NULL;
}
#endif
@@ -2281,7 +2281,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
timer_expires = jiffies;
}
- state = sk_state_load(sk);
+ state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
rx_queue = sk->sk_ack_backlog;
else
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 7d885a44dc9d..8affc6d83d58 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -105,18 +105,15 @@ static struct sk_buff *xfrm4_mode_tunnel_gso_segment(struct xfrm_state *x,
{
__skb_push(skb, skb->mac_len);
return skb_mac_gso_segment(skb, features);
-
}
static void xfrm4_mode_tunnel_xmit(struct xfrm_state *x, struct sk_buff *skb)
{
struct xfrm_offload *xo = xfrm_offload(skb);
- if (xo->flags & XFRM_GSO_SEGMENT) {
- skb->network_header = skb->network_header - x->props.header_len;
+ if (xo->flags & XFRM_GSO_SEGMENT)
skb->transport_header = skb->network_header +
sizeof(struct iphdr);
- }
skb_reset_mac_len(skb);
pskb_pull(skb, skb->mac_len + x->props.header_len);
generated by cgit (git 2.34.1) at 2025-05-28 12:29:09 +0000