@@ -222,13 +222,6 @@ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metr
return msecs_to_jiffies(dst_metric(dst, metric));
}
-static inline u32
-dst_allfrag(const struct dst_entry *dst)
-{
- int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG);
- return ret;
-}
-
static inline int
dst_metric_locked(const struct dst_entry *dst, int metric)
{
@@ -44,7 +44,6 @@ struct inet_connection_sock_af_ops {
struct request_sock *req_unhash,
bool *own_req);
u16 net_header_len;
- u16 net_frag_header_len;
u16 sockaddr_len;
int (*setsockopt)(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen);
@@ -244,7 +244,7 @@ struct inet_sock {
};
#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */
-#define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */
+#define IPCORK_ALLFRAG 2 /* (unused) always fragment (for ipv6 for now) */
enum {
INET_FLAGS_PKTINFO = 0,
@@ -505,7 +505,7 @@ enum {
#define RTAX_FEATURE_ECN (1 << 0)
#define RTAX_FEATURE_SACK (1 << 1) /* unused */
#define RTAX_FEATURE_TIMESTAMP (1 << 2) /* unused */
-#define RTAX_FEATURE_ALLFRAG (1 << 3)
+#define RTAX_FEATURE_ALLFRAG (1 << 3) /* unused */
#define RTAX_FEATURE_TCP_USEC_TS (1 << 4)
#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | \
@@ -1698,14 +1698,6 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
*/
mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr);
- /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
- if (icsk->icsk_af_ops->net_frag_header_len) {
- const struct dst_entry *dst = __sk_dst_get(sk);
-
- if (dst && dst_allfrag(dst))
- mss_now -= icsk->icsk_af_ops->net_frag_header_len;
- }
-
/* Clamp it (mss_clamp does not include tcp options) */
if (mss_now > tp->rx_opt.mss_clamp)
mss_now = tp->rx_opt.mss_clamp;
@@ -1733,21 +1725,11 @@ int tcp_mss_to_mtu(struct sock *sk, int mss)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
- int mtu;
- mtu = mss +
+ return mss +
tp->tcp_header_len +
icsk->icsk_ext_hdr_len +
icsk->icsk_af_ops->net_header_len;
-
- /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */
- if (icsk->icsk_af_ops->net_frag_header_len) {
- const struct dst_entry *dst = __sk_dst_get(sk);
-
- if (dst && dst_allfrag(dst))
- mtu += icsk->icsk_af_ops->net_frag_header_len;
- }
- return mtu;
}
EXPORT_SYMBOL(tcp_mss_to_mtu);
@@ -191,7 +191,6 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
if ((skb->len > mtu && !skb_is_gso(skb)) ||
- dst_allfrag(skb_dst(skb)) ||
(IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
return ip6_fragment(net, sk, skb, ip6_finish_output2);
else
@@ -1017,9 +1016,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
return err;
fail_toobig:
- if (skb->sk && dst_allfrag(skb_dst(skb)))
- sk_gso_disable(skb->sk);
-
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
err = -EMSGSIZE;
@@ -1384,10 +1380,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
cork->base.mark = ipc6->sockc.mark;
sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
- if (dst_allfrag(xfrm_dst_path(&rt->dst)))
- cork->base.flags |= IPCORK_ALLFRAG;
cork->base.length = 0;
-
cork->base.transmit_time = ipc6->sockc.transmit_time;
return 0;
@@ -1444,8 +1437,6 @@ static int __ip6_append_data(struct sock *sk,
headersize = sizeof(struct ipv6hdr) +
(opt ? opt->opt_flen + opt->opt_nflen : 0) +
- (dst_allfrag(&rt->dst) ?
- sizeof(struct frag_hdr) : 0) +
rt->rt6i_nfheader_len;
if (mtu <= fragheaderlen ||
@@ -1555,7 +1546,7 @@ static int __ip6_append_data(struct sock *sk,
while (length > 0) {
/* Check if the remaining data fits into current packet. */
- copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
+ copy = (cork->length <= mtu ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
@@ -1586,7 +1577,7 @@ static int __ip6_append_data(struct sock *sk,
*/
datalen = length + fraggap;
- if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
+ if (datalen > (cork->length <= mtu ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
fraglen = datalen + fragheaderlen;
pagedlen = 0;
@@ -1835,7 +1826,6 @@ static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork)
struct dst_entry *dst = cork->base.dst;
cork->base.dst = NULL;
- cork->base.flags &= ~IPCORK_ALLFRAG;
skb_dst_set(skb, dst);
}
@@ -1856,7 +1846,6 @@ static void ip6_cork_release(struct inet_cork_full *cork,
if (cork->base.dst) {
dst_release(cork->base.dst);
cork->base.dst = NULL;
- cork->base.flags &= ~IPCORK_ALLFRAG;
}
}
@@ -1895,7 +1895,6 @@ const struct inet_connection_sock_af_ops ipv6_specific = {
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.net_header_len = sizeof(struct ipv6hdr),
- .net_frag_header_len = sizeof(struct frag_hdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
@@ -95,7 +95,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
return -EMSGSIZE;
}
- if (toobig || dst_allfrag(skb_dst(skb)))
+ if (toobig)
return ip6_fragment(net, sk, skb,
__xfrm6_output_finish);
@@ -2044,7 +2044,6 @@ void __init mptcp_subflow_init(void)
subflow_v6m_specific.send_check = ipv4_specific.send_check;
subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len;
subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced;
- subflow_v6m_specific.net_frag_header_len = 0;
subflow_v6m_specific.rebuild_header = subflow_rebuild_header;
tcpv6_prot_override = tcpv6_prot;
RTAX_FEATURE_ALLFRAG was added before the first git commit: https://www.mail-archive.com/bk-commits-head@vger.kernel.org/msg03399.html The feature would send packets to the fragmentation path if a box receives a PMTU value with less than 1280 byte. However, since commit 9d289715eb5c ("ipv6: stop sending PTB packets for MTU < 1280"), such message would be simply discarded. The feature flag is neither supported in iproute2 utility. In theory one can still manipulate it with direct netlink message, but it is not ideal because it was based on obsoleted guidance of RFC-2460 (replaced by RFC-8200). The feature would always test false at the moment, so remove related code or mark them as unused. Signed-off-by: Yan Zhai <yan@cloudflare.com> --- V3 -> V4: cleaned up all RTAX_FEATURE_ALLFRAG code, rather than just drop the check at IPv6 output. --- include/net/dst.h | 7 ------- include/net/inet_connection_sock.h | 1 - include/net/inet_sock.h | 2 +- include/uapi/linux/rtnetlink.h | 2 +- net/ipv4/tcp_output.c | 20 +------------------- net/ipv6/ip6_output.c | 15 ++------------- net/ipv6/tcp_ipv6.c | 1 - net/ipv6/xfrm6_output.c | 2 +- net/mptcp/subflow.c | 1 - 9 files changed, 6 insertions(+), 45 deletions(-)