summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/arp.c2
-rw-r--r--net/ipv4/tcp.c55
-rw-r--r--net/ipv4/tcp_bpf.c36
-rw-r--r--net/ipv4/tcp_fastopen.c4
-rw-r--r--net/ipv4/tcp_input.c20
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_minisocks.c10
-rw-r--r--net/ipv4/tcp_offload.c11
-rw-r--r--net/ipv4/udp_offload.c8
9 files changed, 104 insertions, 44 deletions
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index f23a1ec6694c..814300eee39d 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1077,7 +1077,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r,
__be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr;
if (!dev && (r->arp_flags & ATF_COM)) {
- dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family,
+ dev = dev_getbyhwaddr(net, r->arp_ha.sa_family,
r->arp_ha.sa_data);
if (!dev)
return -ENODEV;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0d704bda6c41..57df7c1d2faa 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1565,12 +1565,13 @@ EXPORT_SYMBOL(tcp_recv_skb);
* or for 'peeking' the socket using this routine
* (although both would be easy to implement).
*/
-int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
- sk_read_actor_t recv_actor)
+static int __tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor, bool noack,
+ u32 *copied_seq)
{
struct sk_buff *skb;
struct tcp_sock *tp = tcp_sk(sk);
- u32 seq = tp->copied_seq;
+ u32 seq = *copied_seq;
u32 offset;
int copied = 0;
@@ -1624,9 +1625,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
tcp_eat_recv_skb(sk, skb);
if (!desc->count)
break;
- WRITE_ONCE(tp->copied_seq, seq);
+ WRITE_ONCE(*copied_seq, seq);
}
- WRITE_ONCE(tp->copied_seq, seq);
+ WRITE_ONCE(*copied_seq, seq);
+
+ if (noack)
+ goto out;
tcp_rcv_space_adjust(sk);
@@ -1635,10 +1639,25 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
tcp_recv_skb(sk, seq, &offset);
tcp_cleanup_rbuf(sk, copied);
}
+out:
return copied;
}
+
+int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor)
+{
+ return __tcp_read_sock(sk, desc, recv_actor, false,
+ &tcp_sk(sk)->copied_seq);
+}
EXPORT_SYMBOL(tcp_read_sock);
+int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor, bool noack,
+ u32 *copied_seq)
+{
+ return __tcp_read_sock(sk, desc, recv_actor, noack, copied_seq);
+}
+
int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
{
struct sk_buff *skb;
@@ -2438,14 +2457,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
*/
memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg));
dmabuf_cmsg.frag_size = copy;
- err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR,
- sizeof(dmabuf_cmsg), &dmabuf_cmsg);
- if (err || msg->msg_flags & MSG_CTRUNC) {
- msg->msg_flags &= ~MSG_CTRUNC;
- if (!err)
- err = -ETOOSMALL;
+ err = put_cmsg_notrunc(msg, SOL_SOCKET,
+ SO_DEVMEM_LINEAR,
+ sizeof(dmabuf_cmsg),
+ &dmabuf_cmsg);
+ if (err)
goto out;
- }
sent += copy;
@@ -2499,16 +2516,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
offset += copy;
remaining_len -= copy;
- err = put_cmsg(msg, SOL_SOCKET,
- SO_DEVMEM_DMABUF,
- sizeof(dmabuf_cmsg),
- &dmabuf_cmsg);
- if (err || msg->msg_flags & MSG_CTRUNC) {
- msg->msg_flags &= ~MSG_CTRUNC;
- if (!err)
- err = -ETOOSMALL;
+ err = put_cmsg_notrunc(msg, SOL_SOCKET,
+ SO_DEVMEM_DMABUF,
+ sizeof(dmabuf_cmsg),
+ &dmabuf_cmsg);
+ if (err)
goto out;
- }
atomic_long_inc(&niov->pp_ref_count);
tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 47f65b1b70ca..ba581785adb4 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -646,6 +646,42 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops)
ops->sendmsg == tcp_sendmsg ? 0 : -ENOTSUPP;
}
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor)
+{
+ struct sock *sk = strp->sk;
+ struct sk_psock *psock;
+ struct tcp_sock *tp;
+ int copied = 0;
+
+ tp = tcp_sk(sk);
+ rcu_read_lock();
+ psock = sk_psock(sk);
+ if (WARN_ON_ONCE(!psock)) {
+ desc->error = -EINVAL;
+ goto out;
+ }
+
+ psock->ingress_bytes = 0;
+ copied = tcp_read_sock_noack(sk, desc, recv_actor, true,
+ &psock->copied_seq);
+ if (copied < 0)
+ goto out;
+ /* recv_actor may redirect skb to another socket (SK_REDIRECT) or
+ * just put skb into ingress queue of current socket (SK_PASS).
+ * For SK_REDIRECT, we need to ack the frame immediately but for
+ * SK_PASS, we want to delay the ack until tcp_bpf_recvmsg_parser().
+ */
+ tp->copied_seq = psock->copied_seq - psock->ingress_bytes;
+ tcp_rcv_space_adjust(sk);
+ __tcp_cleanup_rbuf(sk, copied - psock->ingress_bytes);
+out:
+ rcu_read_unlock();
+ return copied;
+}
+#endif /* CONFIG_BPF_STREAM_PARSER */
+
int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 0f523cbfe329..32b28fc21b63 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -178,7 +178,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
if (!skb)
return;
- skb_dst_drop(skb);
+ tcp_cleanup_skb(skb);
/* segs_in has been initialized to 1 in tcp_create_openreq_child().
* Hence, reset segs_in to 0 before calling tcp_segs_in()
* to avoid double counting. Also, tcp_segs_in() expects
@@ -195,7 +195,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
- __skb_queue_tail(&sk->sk_receive_queue, skb);
+ tcp_add_receive_queue(sk, skb);
tp->syn_data_acked = 1;
/* u64_stats_update_begin(&tp->syncp) not needed here,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eb82e01da911..0cbf81bf3d45 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -243,9 +243,15 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
do_div(val, skb->truesize);
tcp_sk(sk)->scaling_ratio = val ? val : 1;
- if (old_ratio != tcp_sk(sk)->scaling_ratio)
- WRITE_ONCE(tcp_sk(sk)->window_clamp,
- tcp_win_from_space(sk, sk->sk_rcvbuf));
+ if (old_ratio != tcp_sk(sk)->scaling_ratio) {
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ val = tcp_win_from_space(sk, sk->sk_rcvbuf);
+ tcp_set_window_clamp(sk, val);
+
+ if (tp->window_clamp < tp->rcvq_space.space)
+ tp->rcvq_space.space = tp->window_clamp;
+ }
}
icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
tcp_sk(sk)->advmss);
@@ -4970,7 +4976,7 @@ static void tcp_ofo_queue(struct sock *sk)
tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
if (!eaten)
- __skb_queue_tail(&sk->sk_receive_queue, skb);
+ tcp_add_receive_queue(sk, skb);
else
kfree_skb_partial(skb, fragstolen);
@@ -5162,7 +5168,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
skb, fragstolen)) ? 1 : 0;
tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
if (!eaten) {
- __skb_queue_tail(&sk->sk_receive_queue, skb);
+ tcp_add_receive_queue(sk, skb);
skb_set_owner_r(skb, sk);
}
return eaten;
@@ -5245,7 +5251,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
__kfree_skb(skb);
return;
}
- skb_dst_drop(skb);
+ tcp_cleanup_skb(skb);
__skb_pull(skb, tcp_hdr(skb)->doff * 4);
reason = SKB_DROP_REASON_NOT_SPECIFIED;
@@ -6226,7 +6232,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS);
/* Bulk data transfer: receiver */
- skb_dst_drop(skb);
+ tcp_cleanup_skb(skb);
__skb_pull(skb, tcp_header_len);
eaten = tcp_queue_rcv(sk, skb, &fragstolen);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cc2b5194a18d..2632844d2c35 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2027,7 +2027,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
*/
skb_condense(skb);
- skb_dst_drop(skb);
+ tcp_cleanup_skb(skb);
if (unlikely(tcp_checksum_complete(skb))) {
bh_unlock_sock(sk);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b089b08e9617..dfdb7a4608a8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -815,12 +815,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
/* In sequence, PAWS is OK. */
- /* TODO: We probably should defer ts_recent change once
- * we take ownership of @req.
- */
- if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
- WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval);
-
if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
/* Truncate SYN, it is out of window starting
at tcp_rsk(req)->rcv_isn + 1. */
@@ -869,6 +863,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!child)
goto listen_overflow;
+ if (own_req && tmp_opt.saw_tstamp &&
+ !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
+ tcp_sk(child)->rx_opt.ts_recent = tmp_opt.rcv_tsval;
+
if (own_req && rsk_drop_req(req)) {
reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 2308665b51c5..2dfac79dc78b 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -13,12 +13,15 @@
#include <net/tcp.h>
#include <net/protocol.h>
-static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
+static void tcp_gso_tstamp(struct sk_buff *skb, struct sk_buff *gso_skb,
unsigned int seq, unsigned int mss)
{
+ u32 flags = skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP;
+ u32 ts_seq = skb_shinfo(gso_skb)->tskey;
+
while (skb) {
if (before(ts_seq, seq + mss)) {
- skb_shinfo(skb)->tx_flags |= SKBTX_SW_TSTAMP;
+ skb_shinfo(skb)->tx_flags |= flags;
skb_shinfo(skb)->tskey = ts_seq;
return;
}
@@ -193,8 +196,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
th = tcp_hdr(skb);
seq = ntohl(th->seq);
- if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP))
- tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss);
+ if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP))
+ tcp_gso_tstamp(segs, gso_skb, seq, mss);
newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta));
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index a5be6e4ed326..ecfca59f31f1 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -321,13 +321,17 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
/* clear destructor to avoid skb_segment assigning it to tail */
copy_dtor = gso_skb->destructor == sock_wfree;
- if (copy_dtor)
+ if (copy_dtor) {
gso_skb->destructor = NULL;
+ gso_skb->sk = NULL;
+ }
segs = skb_segment(gso_skb, features);
if (IS_ERR_OR_NULL(segs)) {
- if (copy_dtor)
+ if (copy_dtor) {
gso_skb->destructor = sock_wfree;
+ gso_skb->sk = sk;
+ }
return segs;
}
generated by cgit v1.2.3 (git 2.46.0) at 2025-12-09 15:52:55 +0000