* [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-26 21:13 Rao Shoaib
0 siblings, 0 replies; 14+ messages in thread
From: Rao Shoaib @ 2017-06-26 21:13 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 49898 bytes --]
This patch returns tcp_skb_cb to it's original size. It also refactors MPTCP code so that there are no MPTCP checks in the main Rx pathi, no performance overheads such as cpu prodiction issues. tcp_v4_rcv() and tcp_v4_do_rcv() do not have any MPTCP specific checks any more, niether does tcp_ack(). On the Rx path MPTCP options are not parsed till the data is being pushed up to the meta socket (mptcp_data_ready). on the Tx side there is one check to add MPTCP specific options but that's it, that should not be that bad as for regular TCP it is a simple check, but it would be good to remove it..
I have tested the changes with ndiffports set to 2, so join works. I have also tested accessing multipath-tcp.org and downloading files from there and also ran the speed test.
The Bad:
The error cases still have MPTCP checks but that should be OK as they are error cases. I had to use a special marker 0xFEE1DEAD for indicate a special case. I had to introdue a new socket specfic function. IPv6 has not been changed yet. I am sure I have missed some corner cases and more testing will reveal more issues but we just have to fix them.
I would like to hear comments from the list and if this direction seems reasonable we can take this as the starting point, port it to latest Linux and share the design with the mainstream folks.
Signed-off-by: Rao Shoaib <rao.shoaib(a)oracle.com>
---
include/linux/skbuff.h | 8 ++-
include/net/mptcp.h | 21 +++---
include/net/mptcp_v4.h | 1 +
include/net/sock.h | 12 +++-
include/net/tcp.h | 23 +++----
net/ipv4/af_inet.c | 4 ++
net/ipv4/tcp_input.c | 37 ++--------
net/ipv4/tcp_ipv4.c | 135 +++++++++++++++++++++++--------------
net/ipv4/tcp_output.c | 1 +
net/ipv6/af_inet6.c | 4 ++
net/ipv6/tcp_ipv6.c | 4 --
net/mptcp/mptcp_ctrl.c | 21 ++++++
net/mptcp/mptcp_input.c | 131 ++++++++++++++++++++++++++++--------
net/mptcp/mptcp_ipv4.c | 35 +---------
net/mptcp/mptcp_ipv6.c | 4 +-
net/mptcp/mptcp_output.c | 160 +++++++++++++++++---------------------------
net/mptcp/mptcp_redundant.c | 6 +-
net/mptcp/mptcp_rr.c | 4 +-
net/mptcp/mptcp_sched.c | 10 +--
19 files changed, 335 insertions(+), 286 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f66cd5e..348cbc1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -532,7 +532,13 @@ struct sk_buff {
struct rb_node rbnode; /* used in netem & tcp stack */
};
struct sock *sk;
- struct net_device *dev;
+ union {
+ struct net_device *dev;
+ struct {
+ __u8 mptcp_flags;
+ __u8 mptcp_dss_off;
+ };
+ };
/*
* This is the control buffer. It is free to use for every
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 876f1e6..d087cb4 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -807,7 +807,7 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
struct mptcp_options_received *mopt);
void mptcp_parse_options(const uint8_t *ptr, int opsize,
struct mptcp_options_received *mopt,
- const struct sk_buff *skb,
+ struct sk_buff *skb,
struct tcp_sock *tp);
void mptcp_syn_options(const struct sock *sk, struct tcp_out_options *opts,
unsigned *remaining);
@@ -998,14 +998,15 @@ static inline void mptcp_sub_force_close_all(struct mptcp_cb *mpcb,
}
}
+/* currently tp is being used for Rx packets */
static inline bool mptcp_is_data_seq(const struct sk_buff *skb)
{
- return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ;
+ return skb->mptcp_flags & MPTCPHDR_SEQ;
}
static inline bool mptcp_is_data_fin(const struct sk_buff *skb)
{
- return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_FIN;
+ return skb->mptcp_flags & MPTCPHDR_FIN;
}
/* Is it a data-fin while in infinite mapping mode?
@@ -1034,17 +1035,17 @@ static inline u8 mptcp_get_64_bit(u64 data_seq, struct mptcp_cb *mpcb)
/* Sets the data_seq and returns pointer to the in-skb field of the data_seq.
* If the packet has a 64-bit dseq, the pointer points to the last 32 bits.
*/
-static inline __u32 *mptcp_skb_set_data_seq(const struct sk_buff *skb,
+static inline __u32 *mptcp_skb_set_data_seq(struct sk_buff *skb,
u32 *data_seq,
struct mptcp_cb *mpcb)
{
- __u32 *ptr = (__u32 *)(skb_transport_header(skb) + TCP_SKB_CB(skb)->dss_off);
+ __u32 *ptr = (__u32 *)(skb_transport_header(skb) + skb->mptcp_dss_off);
- if (TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ64_SET) {
+ if (skb->mptcp_flags & MPTCPHDR_SEQ64_SET) {
u64 data_seq64 = get_unaligned_be64(ptr);
if (mpcb)
- TCP_SKB_CB(skb)->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
+ skb->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
*data_seq = (u32)data_seq64;
ptr++;
@@ -1142,7 +1143,7 @@ static inline void mptcp_reset_mopt(struct tcp_sock *tp)
static inline __be32 mptcp_get_highorder_sndbits(const struct sk_buff *skb,
const struct mptcp_cb *mpcb)
{
- return htonl(mpcb->snd_high_order[(TCP_SKB_CB(skb)->mptcp_flags &
+ return htonl(mpcb->snd_high_order[(skb->mptcp_flags &
MPTCPHDR_SEQ64_INDEX) ? 1 : 0]);
}
@@ -1404,8 +1405,8 @@ static inline void mptcp_set_rto(const struct sock *sk) {}
static inline void mptcp_send_fin(const struct sock *meta_sk) {}
static inline void mptcp_parse_options(const uint8_t *ptr, const int opsize,
struct mptcp_options_received *mopt,
- const struct sk_buff *skb,
- const struct tcp_sock *tp) {}
+ struct sk_buff *skb,
+ struct tcp_sock *tp) {}
static inline void mptcp_syn_options(const struct sock *sk,
struct tcp_out_options *opts,
unsigned *remaining) {}
diff --git a/include/net/mptcp_v4.h b/include/net/mptcp_v4.h
index c83dca0..46394a4 100644
--- a/include/net/mptcp_v4.h
+++ b/include/net/mptcp_v4.h
@@ -45,6 +45,7 @@ extern struct tcp_request_sock_ops mptcp_join_request_sock_ipv4_ops;
#ifdef CONFIG_MPTCP
int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb);
+int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb);
struct sock *mptcp_v4_search_req(const __be16 rport, const __be32 raddr,
const __be32 laddr, const struct net *net);
int mptcp_init4_subsockets(struct sock *meta_sk, const struct mptcp_loc4 *loc,
diff --git a/include/net/sock.h b/include/net/sock.h
index 0f12593..0d1bda5 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -296,6 +296,7 @@ struct cg_proto;
* @sk_write_space: callback to indicate there is bf sending space available
* @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
* @sk_backlog_rcv: callback to process the backlog
+ * @sk_prequeue: callback to prequeue
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
*/
struct sock {
@@ -437,7 +438,9 @@ struct sock {
void (*sk_write_space)(struct sock *sk);
void (*sk_error_report)(struct sock *sk);
int (*sk_backlog_rcv)(struct sock *sk,
- struct sk_buff *skb);
+ struct sk_buff *skb);
+ bool (*sk_prequeue)(struct sock *sk,
+ struct sk_buff *skb);
void (*sk_destruct)(struct sock *sk);
};
@@ -853,6 +856,11 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
return sk->sk_backlog_rcv(sk, skb);
}
+static inline bool sk_prequeue(struct sock *sk, struct sk_buff *skb)
+{
+ return (false);
+}
+
static inline void sk_incoming_cpu_update(struct sock *sk)
{
sk->sk_incoming_cpu = raw_smp_processor_id();
@@ -993,6 +1001,8 @@ struct proto {
int (*backlog_rcv) (struct sock *sk,
struct sk_buff *skb);
+ bool (*prequeue) (struct sock *sk,
+ struct sk_buff *skb);
void (*release_cb)(struct sock *sk);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 655ecd4..cbe8ef2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -47,6 +47,9 @@
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
+typedef int (* process_unclaimed)(struct sock *sk, struct sk_buff *skb);
+extern process_unclaimed tcp_process_unclaimed;
+
extern struct inet_hashinfo tcp_hashinfo;
extern struct percpu_counter tcp_orphan_count;
@@ -581,6 +584,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst);
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
+
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
int tcp_connect(struct sock *sk);
struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
@@ -842,11 +846,6 @@ struct tcp_skb_cb {
__u32 tcp_gso_segs;
};
-#ifdef CONFIG_MPTCP
- __u8 mptcp_flags; /* flags for the MPTCP layer */
- __u8 dss_off; /* Number of 4-byte words until
- * seq-number */
-#endif
__u8 tcp_flags; /* TCP header flags. (tcp[13]) */
__u8 sacked; /* State flags for SACK/FACK. */
@@ -859,9 +858,13 @@ struct tcp_skb_cb {
#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
TCPCB_REPAIRED)
- __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
+ __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
/* 1 byte hole */
- __u32 ack_seq; /* Sequence number ACK'd */
+ union {
+ __u32 ack_seq; /* Sequence number ACK'd */
+ __u32 mptcp_data_seq;
+ __u32 mptcp_path_mask;
+ };
union {
union {
struct inet_skb_parm h4;
@@ -869,12 +872,6 @@ struct tcp_skb_cb {
struct inet6_skb_parm h6;
#endif
} header; /* For incoming frames */
-#ifdef CONFIG_MPTCP
- union { /* For MPTCP outgoing frames */
- __u32 path_mask; /* paths that tried to send this skb */
- __u32 dss[6]; /* DSS options */
- };
-#endif
};
};
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 73480b9..1e7827f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -356,6 +356,10 @@ lookup_protocol:
sk->sk_destruct = inet_sock_destruct;
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
+ sk->sk_prequeue = sk->sk_prot->prequeue;
+ if (sk->sk_prequeue == NULL) {
+ sk->sk_prequeue = sk_prequeue;
+ }
inet->uc_ttl = -1;
inet->mc_loop = 1;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 16a7256..cb6bbf9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3133,8 +3133,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
*/
if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
flag |= FLAG_DATA_ACKED;
- if (mptcp(tp) && mptcp_is_data_seq(skb))
- flag |= MPTCP_FLAG_DATA_ACKED;
} else {
flag |= FLAG_SYN_ACKED;
tp->retrans_stamp = 0;
@@ -3582,16 +3580,6 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
sack_rtt_us);
acked -= tp->packets_out;
- if (mptcp(tp)) {
- if (mptcp_fallback_infinite(sk, flag)) {
- pr_err("%s resetting flow\n", __func__);
- mptcp_send_reset(sk);
- goto invalid_ack;
- }
-
- mptcp_clean_rtx_infinite(skb, sk);
- }
-
/* Advance cwnd if state allows */
if (tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, acked);
@@ -3824,8 +3812,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
if (tcp_parse_aligned_timestamp(tp, th))
return true;
}
- tcp_parse_options(skb, &tp->rx_opt,
- mptcp(tp) ? &tp->mptcp->rx_opt : NULL, 1, NULL, tp);
+ tcp_parse_options(skb, &tp->rx_opt, NULL, 1, NULL, tp);
if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
@@ -4550,11 +4537,12 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
int eaten = -1;
bool fragstolen = false;
- /* If no data is present, but a data_fin is in the options, we still
- * have to call mptcp_queue_skb later on. */
- if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq &&
- !(mptcp(tp) && mptcp_is_data_fin(skb)))
+ /*
+ * send every packet to MPTCP
+ */
+ if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)) {
goto drop;
+ }
skb_dst_drop(skb);
__skb_pull(skb, tcp_hdr(skb)->doff * 4);
@@ -5242,15 +5230,9 @@ syn_challenge:
goto discard;
}
- /* If valid: post process the received MPTCP options. */
- if (mptcp(tp) && mptcp_handle_options(sk, th, skb))
- goto discard;
-
return true;
discard:
- if (mptcp(tp))
- mptcp_reset_mopt(tp);
__kfree_skb(skb);
return false;
}
@@ -5302,10 +5284,6 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
tp->rx_opt.saw_tstamp = 0;
- /* MPTCP: force slowpath. */
- if (mptcp(tp))
- goto slow_path;
-
/* pred_flags is 0xS?10 << 16 + snd_wnd
* if header_prediction is to be made
* 'S' will always be tp->tcp_header_len >> 2
@@ -5585,8 +5563,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct mptcp_options_received mopt;
mptcp_init_mp_opt(&mopt);
- tcp_parse_options(skb, &tp->rx_opt,
- mptcp(tp) ? &tp->mptcp->rx_opt : &mopt, 0, &foc, tp);
+ tcp_parse_options(skb, &tp->rx_opt, &mopt, 0, &foc, tp);
if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6967a86..3329679 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1420,6 +1420,71 @@ struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
return sk;
}
+int mptcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ struct net *net = dev_net(skb->dev);
+ const struct tcphdr *th = tcp_hdr(skb);
+ int ret;
+ struct sock *meta_sk;
+
+ if (sk == NULL) {
+ if (th->syn && !th->ack) {
+ int ret = mptcp_lookup_join(skb, NULL);
+
+ if (ret < 0) {
+ tcp_v4_send_reset(NULL, skb);
+ kfree_skb(skb);
+ return (1);
+ } else if (ret > 0) {
+ return (1);
+ }
+ }
+ /* Is there a pending request sock for this segment ? */
+ if (mptcp_check_req(skb, net)) {
+ return(1);
+ }
+ return (0);
+ }
+
+ /* The socket passed in should never be the meta socket */
+
+ BUG_ON(is_meta_sk(sk));
+
+ /* Is there a pending request sock for this segment ? */
+ if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
+ return 0;
+ }
+
+ skb->dev = NULL;
+ meta_sk = mptcp_meta_sk(sk);
+
+ ret = 0;
+ skb->sk = sk;
+ bh_lock_sock_nested(meta_sk);
+ if (sock_owned_by_user(meta_sk)) {
+ if (unlikely(sk_add_backlog(meta_sk, skb,
+ meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
+
+ NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
+ kfree_skb(skb);
+ }
+ } else {
+
+ if (is_meta_sk(sk)) {
+ ret = mptcp_v4_process_join_req(sk, skb);
+ goto done;
+ }
+ if (!meta_sk->sk_prequeue(meta_sk, skb)) {
+ skb->sk = NULL;
+ ret = tcp_v4_do_rcv(sk, skb);
+ }
+
+ }
+done:
+ bh_unlock_sock(meta_sk);
+ return (ret);
+}
+
/* The socket must have it's spinlock held when we get
* here.
*
@@ -1432,8 +1497,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
struct sock *rsk;
- if (is_meta_sk(sk))
- return mptcp_v4_do_rcv(sk, skb);
+ BUG_ON(is_meta_sk(sk));
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
struct dst_entry *dst = sk->sk_rx_dst;
@@ -1587,6 +1651,8 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_prequeue);
+process_unclaimed tcp_process_unclaimed = NULL;
+
/*
* From tcp_input.c
*/
@@ -1595,7 +1661,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
{
const struct iphdr *iph;
const struct tcphdr *th;
- struct sock *sk, *meta_sk = NULL;
+ struct sock *sk = NULL;
int ret;
struct net *net = dev_net(skb->dev);
@@ -1636,10 +1702,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff * 4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-#ifdef CONFIG_MPTCP
- TCP_SKB_CB(skb)->mptcp_flags = 0;
- TCP_SKB_CB(skb)->dss_off = 0;
-#endif
+
TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
TCP_SKB_CB(skb)->tcp_tw_isn = 0;
TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
@@ -1662,15 +1725,6 @@ process:
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
-#ifdef CONFIG_MPTCP
- /* Is there a pending request sock for this segment ? */
- if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
- if (sk)
- sock_put(sk);
- return 0;
- }
-#endif
-
#ifdef CONFIG_TCP_MD5SIG
/*
* We really want to reject the packet as early as possible
@@ -1688,30 +1742,21 @@ process:
goto discard_and_relse;
sk_incoming_cpu_update(sk);
- skb->dev = NULL;
- if (mptcp(tcp_sk(sk))) {
- meta_sk = mptcp_meta_sk(sk);
-
- bh_lock_sock_nested(meta_sk);
- if (sock_owned_by_user(meta_sk))
- skb->sk = sk;
- } else {
- meta_sk = sk;
- bh_lock_sock_nested(sk);
- }
+ /* Do I have to set skb->dev to null ? */
+ bh_lock_sock_nested(sk);
ret = 0;
- if (!sock_owned_by_user(meta_sk)) {
- if (!tcp_prequeue(meta_sk, skb))
- ret = tcp_v4_do_rcv(sk, skb);
- } else if (unlikely(sk_add_backlog(meta_sk, skb,
- meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
- bh_unlock_sock(meta_sk);
+ if (!sock_owned_by_user(sk)) {
+ if (!sk->sk_prequeue(sk, skb))
+ ret = sk->sk_backlog_rcv(sk, skb);
+ } else if (unlikely(sk_add_backlog(sk, skb,
+ sk->sk_rcvbuf + sk->sk_sndbuf))) {
+ bh_unlock_sock(sk);
NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
goto discard_and_relse;
}
- bh_unlock_sock(meta_sk);
+ bh_unlock_sock(sk);
sock_put(sk);
@@ -1721,26 +1766,11 @@ no_tcp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
-#ifdef CONFIG_MPTCP
- if (!sk && th->syn && !th->ack) {
- int ret = mptcp_lookup_join(skb, NULL);
-
- if (ret < 0) {
- tcp_v4_send_reset(NULL, skb);
- goto discard_it;
- } else if (ret > 0) {
- return 0;
- }
+ if (unlikely (tcp_process_unclaimed != NULL)) {
+ if ((tcp_process_unclaimed)(NULL, skb))
+ return (0);
}
- /* Is there a pending request sock for this segment ? */
- if (!sk && mptcp_check_req(skb, net)) {
- if (sk)
- sock_put(sk);
- return 0;
- }
-#endif
-
if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
csum_error:
TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
@@ -2506,6 +2536,7 @@ struct proto tcp_prot = {
.sendmsg = tcp_sendmsg,
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v4_do_rcv,
+ .prequeue = tcp_prequeue,
.release_cb = tcp_release_cb,
.hash = inet_hash,
.unhash = inet_unhash,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a635483..41b8be8 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3413,6 +3413,7 @@ void tcp_send_delayed_ack(struct sock *sk)
void tcp_send_ack(struct sock *sk)
{
struct sk_buff *buff;
+ struct tcp_sock *tp = tcp_sk(sk);
/* If we have been reset, we may not send again. */
if (sk->sk_state == TCP_CLOSE)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8c4dd4a..1554217 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -193,6 +193,10 @@ lookup_protocol:
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = answer->prot->backlog_rcv;
+ sk->sk_prequeue = answer->prot->prequeue;
+ if (sk->sk_prequeue == NULL) {
+ sk->sk_prequeue = sk_prequeue;
+ }
inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
np->hop_limit = -1;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index eba2436..d360128 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1412,10 +1412,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff*4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-#ifdef CONFIG_MPTCP
- TCP_SKB_CB(skb)->mptcp_flags = 0;
- TCP_SKB_CB(skb)->dss_off = 0;
-#endif
TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
TCP_SKB_CB(skb)->tcp_tw_isn = 0;
TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
diff --git a/net/mptcp/mptcp_ctrl.c b/net/mptcp/mptcp_ctrl.c
index 28f348f..b1e780a 100644
--- a/net/mptcp/mptcp_ctrl.c
+++ b/net/mptcp/mptcp_ctrl.c
@@ -976,6 +976,20 @@ int mptcp_backlog_rcv(struct sock *meta_sk, struct sk_buff *skb)
struct sock *sk = skb->sk ? skb->sk : meta_sk;
int ret = 0;
+ /* socket was owned by the user in mptcp_check_req()
+ */
+ if (sk == (struct sock *)0xFEE1DEAD) {
+ bh_lock_sock_nested(meta_sk);
+ if (skb->protocol == htons(ETH_P_IP))
+ mptcp_v4_process_join_req(meta_sk, skb);
+#if IS_ENABLED(CONFIG_IPV6)
+ else
+ //mptcp_v6_process_join_req(meta_sk, skb);
+#endif /* CONFIG_IPV6 */
+ bh_unlock_sock(meta_sk);
+ return(0);
+ }
+
skb->sk = NULL;
if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
@@ -1297,6 +1311,10 @@ int mptcp_add_sock(struct sock *meta_sk, struct sock *sk, u8 loc_id, u8 rem_id,
sk->sk_write_space = mptcp_write_space;
sk->sk_state_change = mptcp_set_state;
sk->sk_destruct = mptcp_sock_destruct;
+ /* MPTCP takes a different path in tcp_v4_rcv
+ * thus not impacting main tcp code */
+ sk->sk_backlog_rcv = mptcp_v4_do_rcv;
+ sk->sk_prequeue = sk_prequeue;
if (sk->sk_family == AF_INET)
mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d dst_addr:%pI4:%d, cnt_subflows now %d\n",
@@ -2658,6 +2676,9 @@ void __init mptcp_init(void)
if (mptcp_pm_v4_init())
goto mptcp_pm_v4_failed;
+ if ((cmpxchg(&tcp_process_unclaimed, NULL, mptcp_v4_do_rcv)) != NULL)
+ printk("tcp_process_unclaimed not NULL \n");
+
mptcp_sysctl = register_net_sysctl(&init_net, "net/mptcp", mptcp_table);
if (!mptcp_sysctl)
goto register_sysctl_failed;
diff --git a/net/mptcp/mptcp_input.c b/net/mptcp/mptcp_input.c
index 51cbb06..0e09ddf 100644
--- a/net/mptcp/mptcp_input.c
+++ b/net/mptcp/mptcp_input.c
@@ -323,9 +323,8 @@ static int mptcp_verif_dss_csum(struct sock *sk)
* by 4 bytes, as the high-order 64-bits will be added
* in the final csum_partial-call.
*/
- u32 offset = skb_transport_offset(tmp) +
- TCP_SKB_CB(tmp)->dss_off;
- if (TCP_SKB_CB(tmp)->mptcp_flags & MPTCPHDR_SEQ64_SET)
+ u32 offset = skb_transport_offset(tmp) + tmp->mptcp_dss_off;
+ if (tmp->mptcp_flags & MPTCPHDR_SEQ64_SET)
offset += 4;
csum_tcp = skb_checksum(tmp, offset,
@@ -758,7 +757,7 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
}
/* Does the DSS had 64-bit seqnum's ? */
- if (!(tcb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
+ if (!(skb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
/* Wrapped around? */
if (unlikely(after(data_seq, meta_tp->rcv_nxt) && data_seq < meta_tp->rcv_nxt)) {
tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, !mpcb->rcv_hiseq_index, data_seq);
@@ -767,9 +766,9 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, mpcb->rcv_hiseq_index, data_seq);
}
} else {
- tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (tcb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
+ tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (skb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
- if (unlikely(tcb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
+ if (unlikely(skb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
/* We make sure that the data_seq is invalid.
* It will be dropped later.
*/
@@ -1020,6 +1019,67 @@ next:
return data_queued ? -1 : -2;
}
+static struct sk_buff *
+mptcp_process_ack(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int flag = 0;
+
+ /*
+ * TCP takes care of invalid ack's
+ * they will never show up here.
+ */
+
+ /* Is this skb acknowleding anything data */
+
+ if (tp->mptcp->snt_isn + 1 != TCP_SKB_CB(skb)->ack_seq) {
+ flag = MPTCP_FLAG_DATA_ACKED;
+ }
+
+ if (mptcp_fallback_infinite(sk, flag)) {
+ pr_err("%s resetting flow\n", __func__);
+ mptcp_send_reset(sk);
+ goto invalid_ack;
+ }
+
+ mptcp_clean_rtx_infinite(skb, sk);
+
+ return (skb);
+invalid_ack:
+ __skb_unlink(skb, &sk->sk_receive_queue);
+ __kfree_skb(skb);
+ return (NULL);
+
+}
+
+static struct sk_buff *
+mptcp_process_options_ack(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ const struct tcphdr *th = tcp_hdr(skb);
+
+ skb->mptcp_flags = 0;
+ skb->mptcp_dss_off = 0;
+
+ tcp_parse_mptcp_options(skb, &tp->mptcp->rx_opt);
+ if (mptcp_handle_options(sk, th, skb)) {
+ mptcp_reset_mopt(tp);
+ __skb_unlink(skb, &sk->sk_receive_queue);
+ __kfree_skb(skb);
+ skb = NULL;
+ }
+ if ((skb != NULL) && skb->len == 0) {
+ skb = mptcp_process_ack(sk, skb);
+ if (skb != NULL && skb->len == 0) {
+ /* Pure ack */
+ __skb_unlink(skb, &sk->sk_receive_queue);
+ __kfree_skb(skb);
+ skb = NULL;
+ }
+ }
+ return (skb);
+}
+
void mptcp_data_ready(struct sock *sk)
{
struct sock *meta_sk = mptcp_meta_sk(sk);
@@ -1045,6 +1105,10 @@ restart:
*/
skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
int ret;
+
+ skb = mptcp_process_options_ack(sk, skb);
+ if (skb == NULL)
+ continue;
/* Pre-validation - e.g., early fallback */
ret = mptcp_prevalidate_skb(sk, skb);
if (ret < 0)
@@ -1108,13 +1172,11 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
if (!meta_sk)
return 0;
- TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
-
bh_lock_sock_nested(meta_sk);
if (sock_owned_by_user(meta_sk)) {
- skb->sk = meta_sk;
+ skb->sk = (struct sock *)0xFEE1DEAD;
if (unlikely(sk_add_backlog(meta_sk, skb,
- meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
+ meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
bh_unlock_sock(meta_sk);
NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
sock_put(meta_sk); /* Taken by mptcp_search_req */
@@ -1122,10 +1184,14 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
return 1;
}
} else if (skb->protocol == htons(ETH_P_IP)) {
- tcp_v4_do_rcv(meta_sk, skb);
+ /*
+ * call old mptcp_v4_do_rcv
+ */
+ mptcp_v4_process_join_req(meta_sk, skb);
#if IS_ENABLED(CONFIG_IPV6)
} else { /* IPv6 */
- tcp_v6_do_rcv(meta_sk, skb);
+ WARN_ON(1);
+ //mptcp_v6_handle_join_req(meta_sk, skb);
#endif /* CONFIG_IPV6 */
}
bh_unlock_sock(meta_sk);
@@ -1222,7 +1288,7 @@ int mptcp_lookup_join(struct sk_buff *skb, struct inet_timewait_sock *tw)
inet_twsk_put(tw);
}
- TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
+ skb->mptcp_flags |= MPTCPHDR_JOIN;
/* OK, this is a new syn/join, let's create a new open request and
* send syn+ack
*/
@@ -1279,7 +1345,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
return -1;
}
- TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
+ //TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
/* OK, this is a new syn/join, let's create a new open request and
* send syn+ack
@@ -1303,7 +1369,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
}
if (sock_owned_by_user(meta_sk)) {
- skb->sk = meta_sk;
+ skb->sk = (struct sock *)0xFEE1DEAD; //skb->sk = meta_sk;
if (unlikely(sk_add_backlog(meta_sk, skb,
meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf)))
NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
@@ -1319,10 +1385,12 @@ int mptcp_do_join_short(struct sk_buff *skb,
*/
skb_get(skb);
if (skb->protocol == htons(ETH_P_IP)) {
- tcp_v4_do_rcv(meta_sk, skb);
+ //tcp_v4_do_rcv(meta_sk, skb);
+ mptcp_v4_process_join_req(meta_sk, skb);
#if IS_ENABLED(CONFIG_IPV6)
} else { /* IPv6 */
- tcp_v6_do_rcv(meta_sk, skb);
+ //mptcp_v6_process_join_req(meta_sk, skb);
+ //tcp_v6_do_rcv(meta_sk, skb);
#endif /* CONFIG_IPV6 */
}
}
@@ -1461,7 +1529,6 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
{
struct sock *meta_sk = mptcp_meta_sk(sk);
struct tcp_sock *meta_tp = tcp_sk(meta_sk), *tp = tcp_sk(sk);
- struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
u32 prior_snd_una = meta_tp->snd_una;
int prior_packets;
u32 nwin, data_ack, data_seq;
@@ -1481,7 +1548,7 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
/* If we are in infinite mapping mode, rx_opt.data_ack has been
* set by mptcp_clean_rtx_infinite.
*/
- if (!(tcb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
+ if (!(skb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
goto exit;
data_ack = tp->mptcp->rx_opt.data_ack;
@@ -1647,10 +1714,11 @@ static inline bool is_valid_addropt_opsize(u8 mptcp_ver,
void mptcp_parse_options(const uint8_t *ptr, int opsize,
struct mptcp_options_received *mopt,
- const struct sk_buff *skb,
+ struct sk_buff *skb,
struct tcp_sock *tp)
{
const struct mptcp_option *mp_opt = (struct mptcp_option *)ptr;
+ struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
/* If the socket is mp-capable we would have a mopt. */
if (!mopt)
@@ -1757,7 +1825,7 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
ptr += 4;
if (mdss->A) {
- tcb->mptcp_flags |= MPTCPHDR_ACK;
+ skb->mptcp_flags |= MPTCPHDR_ACK;
if (mdss->a) {
mopt->data_ack = (u32) get_unaligned_be64(ptr);
@@ -1768,13 +1836,13 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
}
}
- tcb->dss_off = (ptr - skb_transport_header(skb));
+ skb->mptcp_dss_off = (ptr - skb_transport_header(skb));
if (mdss->M) {
if (mdss->m) {
u64 data_seq64 = get_unaligned_be64(ptr);
- tcb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
+ skb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
mopt->data_seq = (u32) data_seq64;
ptr += 12; /* 64-bit dseq + subseq */
@@ -1784,15 +1852,16 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
}
mopt->data_len = get_unaligned_be16(ptr);
- tcb->mptcp_flags |= MPTCPHDR_SEQ;
+ skb->mptcp_flags |= MPTCPHDR_SEQ;
/* Is a check-sum present? */
- if (opsize == mptcp_sub_len_dss(mdss, 1))
- tcb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
+ if (opsize == mptcp_sub_len_dss(mdss, 1)) {
+ skb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
+ }
/* DATA_FIN only possible with DSS-mapping */
if (mdss->F)
- tcb->mptcp_flags |= MPTCPHDR_FIN;
+ skb->mptcp_flags |= MPTCPHDR_FIN;
}
break;
@@ -1907,8 +1976,9 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
return;
if (opsize > length)
return; /* don't parse partial options */
- if (opcode == TCPOPT_MPTCP)
+ if (opcode == TCPOPT_MPTCP) {
mptcp_parse_options(ptr - 2, opsize, mopt, skb, NULL);
+ }
}
ptr += opsize - 2;
length -= opsize;
@@ -2168,6 +2238,8 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
struct tcp_sock *tp = tcp_sk(sk);
struct mptcp_options_received *mopt = &tp->mptcp->rx_opt;
+ BUG_ON(sk == mptcp_meta_sk(sk));
+
if (tp->mpcb->infinite_mapping_rcv || tp->mpcb->infinite_mapping_snd)
return false;
@@ -2185,7 +2257,7 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
* receiver MUST close the subflow with a RST as it is considered broken.
*/
if (mptcp_is_data_seq(skb) && tp->mpcb->dss_csum &&
- !(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
+ !(skb->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
mptcp_send_reset(sk);
return true;
}
@@ -2330,6 +2402,7 @@ int mptcp_rcv_synsent_state_process(struct sock *sk, struct sock **skptr,
/* Set this flag in order to postpone data sending
* until the 4th ack arrives.
*/
+printk("mptcp_rcv_synsent_state_process pre_established set \n");
tp->mptcp->pre_established = 1;
tp->mptcp->rcv_low_prio = tp->mptcp->rx_opt.low_prio;
diff --git a/net/mptcp/mptcp_ipv4.c b/net/mptcp/mptcp_ipv4.c
index a147b20..3e60ab5 100644
--- a/net/mptcp/mptcp_ipv4.c
+++ b/net/mptcp/mptcp_ipv4.c
@@ -180,45 +180,12 @@ static int mptcp_v4_join_request(struct sock *meta_sk, struct sk_buff *skb)
}
/* We only process join requests here. (either the SYN or the final ACK) */
-int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
+int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb)
{
const struct mptcp_cb *mpcb = tcp_sk(meta_sk)->mpcb;
struct sock *child, *rsk = NULL;
int ret;
- if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
- struct tcphdr *th = tcp_hdr(skb);
- const struct iphdr *iph = ip_hdr(skb);
- struct sock *sk;
-
- sk = inet_lookup_established(sock_net(meta_sk), &tcp_hashinfo,
- iph->saddr, th->source, iph->daddr,
- th->dest, inet_iif(skb));
-
- if (!sk) {
- kfree_skb(skb);
- return 0;
- }
- if (is_meta_sk(sk)) {
- WARN("%s Did not find a sub-sk - did found the meta!\n", __func__);
- kfree_skb(skb);
- sock_put(sk);
- return 0;
- }
-
- if (sk->sk_state == TCP_TIME_WAIT) {
- inet_twsk_put(inet_twsk(sk));
- kfree_skb(skb);
- return 0;
- }
-
- ret = tcp_v4_do_rcv(sk, skb);
- sock_put(sk);
-
- return ret;
- }
- TCP_SKB_CB(skb)->mptcp_flags = 0;
-
/* Has been removed from the tk-table. Thus, no new subflows.
*
* Check for close-state is necessary, because we may have been closed
diff --git a/net/mptcp/mptcp_ipv6.c b/net/mptcp/mptcp_ipv6.c
index 0de953d..1959d01 100644
--- a/net/mptcp/mptcp_ipv6.c
+++ b/net/mptcp/mptcp_ipv6.c
@@ -199,7 +199,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
struct sock *child, *rsk = NULL;
int ret;
- if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
+ if (!(skb->mptcp_flags & MPTCPHDR_JOIN)) {
struct tcphdr *th = tcp_hdr(skb);
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct sock *sk;
@@ -232,7 +232,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
return ret;
}
- TCP_SKB_CB(skb)->mptcp_flags = 0;
+ skb->mptcp_flags = 0;
/* Has been removed from the tk-table. Thus, no new subflows.
*
diff --git a/net/mptcp/mptcp_output.c b/net/mptcp/mptcp_output.c
index 691ef6f..e7d340d 100644
--- a/net/mptcp/mptcp_output.c
+++ b/net/mptcp/mptcp_output.c
@@ -59,39 +59,17 @@ EXPORT_SYMBOL(mptcp_sub_len_remove_addr_align);
*/
static bool mptcp_reconstruct_mapping(struct sk_buff *skb)
{
- const struct mp_dss *mpdss = (struct mp_dss *)TCP_SKB_CB(skb)->dss;
- u32 *p32;
- u16 *p16;
-
if (!mptcp_is_data_seq(skb))
return false;
- if (!mpdss->M)
- return false;
-
- /* Move the pointer to the data-seq */
- p32 = (u32 *)mpdss;
- p32++;
- if (mpdss->A) {
- p32++;
- if (mpdss->a)
- p32++;
- }
-
- TCP_SKB_CB(skb)->seq = ntohl(*p32);
-
- /* Get the data_len to calculate the end_data_seq */
- p32++;
- p32++;
- p16 = (u16 *)p32;
- TCP_SKB_CB(skb)->end_seq = ntohs(*p16) + TCP_SKB_CB(skb)->seq;
+ TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->mptcp_data_seq;
return true;
}
static bool mptcp_is_reinjected(const struct sk_buff *skb)
{
- return TCP_SKB_CB(skb)->mptcp_flags & MPTCP_REINJECT;
+ return skb->mptcp_flags & MPTCP_REINJECT;
}
static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_buff *skb)
@@ -105,7 +83,7 @@ static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_bu
break;
if (TCP_SKB_CB(skb_it)->seq == TCP_SKB_CB(skb)->seq) {
- TCP_SKB_CB(skb)->path_mask = TCP_SKB_CB(skb_it)->path_mask;
+ TCP_SKB_CB(skb)->mptcp_path_mask = TCP_SKB_CB(skb_it)->mptcp_path_mask;
break;
}
}
@@ -180,9 +158,9 @@ static void __mptcp_reinject_data(struct sk_buff *orig_skb, struct sock *meta_sk
}
/* Segment goes back to the MPTCP-layer. So, we need to zero the
- * path_mask/dss.
+ * path_mask.
*/
- memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
+ TCP_SKB_CB(skb)->mptcp_path_mask = 0;
/* We need to find out the path-mask from the meta-write-queue
* to properly select a subflow.
@@ -272,14 +250,14 @@ void mptcp_reinject_data(struct sock *sk, int clone_it)
if (mptcp_is_reinjected(skb_it))
continue;
- tcb->mptcp_flags |= MPTCP_REINJECT;
+ skb_it->mptcp_flags |= MPTCP_REINJECT;
__mptcp_reinject_data(skb_it, meta_sk, sk, clone_it);
}
skb_it = tcp_write_queue_tail(meta_sk);
/* If sk has sent the empty data-fin, we have to reinject it too. */
if (skb_it && mptcp_is_data_fin(skb_it) && skb_it->len == 0 &&
- TCP_SKB_CB(skb_it)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
+ TCP_SKB_CB(skb_it)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
__mptcp_reinject_data(skb_it, meta_sk, NULL, 1);
}
@@ -319,25 +297,43 @@ combine:
}
}
-static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_buff *skb,
- __be32 *ptr)
+/*
+ * RFC6824 states that once a particular subflow mapping has been sent
+ * out it must never be changed. However, packets may be split while
+ * they are in the retransmission queue (due to SACK or ACKs) and that
+ * arguably means that we would change the mapping (e.g. it splits it,
+ * our sends out a subset of the initial mapping).
+ *
+ * Furthermore, the skb checksum is not always preserved across splits
+ * (e.g. mptcp_fragment) which would mean that we need to recompute
+ * the DSS checksum in this case.
+ *
+ * To avoid this we save the initial DSS mapping which allows us to
+ * send the same DSS mapping even for fragmented retransmits.
+ */
+
+static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
+ const struct sk_buff *skb, __be32 *ptr)
{
const struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
- __be32 *start = ptr;
__u16 data_len;
- *ptr++ = htonl(tcb->seq); /* data_seq */
+ *ptr++ = htonl(tcb->mptcp_data_seq); /* data_seq */
/* If it's a non-data DATA_FIN, we set subseq to 0 (draft v7) */
if (mptcp_is_data_fin(skb) && skb->len == 0)
*ptr++ = 0; /* subseq */
else
- *ptr++ = htonl(tp->write_seq - tp->mptcp->snt_isn); /* subseq */
+ *ptr++ = htonl(tcb->seq - tp->mptcp->snt_isn); /* subseq */
- if (tcb->mptcp_flags & MPTCPHDR_INF)
+ if (skb->mptcp_flags & MPTCPHDR_INF)
data_len = 0;
- else
+ else {
data_len = tcb->end_seq - tcb->seq;
+ /* mptcp_entail_skb adds one for FIN */
+ if (tcb->tcp_flags & TCPHDR_FIN)
+ data_len -= 1;
+ }
if (tp->mpcb->dss_csum && data_len) {
__be16 *p16 = (__be16 *)ptr;
@@ -356,11 +352,11 @@ static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_bu
(TCPOPT_NOP));
}
- return ptr - start;
+ return mptcp_dss_len/sizeof(*ptr);
}
-static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_buff *skb,
- __be32 *ptr)
+static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
+ const struct sk_buff *skb, __be32 *ptr)
{
struct mp_dss *mdss = (struct mp_dss *)ptr;
__be32 *start = ptr;
@@ -377,54 +373,12 @@ static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_b
mdss->len = mptcp_sub_len_dss(mdss, tp->mpcb->dss_csum);
ptr++;
+ /* data_ack */
*ptr++ = htonl(mptcp_meta_tp(tp)->rcv_nxt);
return ptr - start;
}
-/* RFC6824 states that once a particular subflow mapping has been sent
- * out it must never be changed. However, packets may be split while
- * they are in the retransmission queue (due to SACK or ACKs) and that
- * arguably means that we would change the mapping (e.g. it splits it,
- * our sends out a subset of the initial mapping).
- *
- * Furthermore, the skb checksum is not always preserved across splits
- * (e.g. mptcp_fragment) which would mean that we need to recompute
- * the DSS checksum in this case.
- *
- * To avoid this we save the initial DSS mapping which allows us to
- * send the same DSS mapping even for fragmented retransmits.
- */
-static void mptcp_save_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb)
-{
- struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
- __be32 *ptr = (__be32 *)tcb->dss;
-
- tcb->mptcp_flags |= MPTCPHDR_SEQ;
-
- ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
- ptr += mptcp_write_dss_mapping(tp, skb, ptr);
-}
-
-/* Write the saved DSS mapping to the header */
-static int mptcp_write_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb,
- __be32 *ptr)
-{
- __be32 *start = ptr;
-
- memcpy(ptr, TCP_SKB_CB(skb)->dss, mptcp_dss_len);
-
- /* update the data_ack */
- start[1] = htonl(mptcp_meta_tp(tp)->rcv_nxt);
-
- /* dss is in a union with inet_skb_parm and
- * the IP layer expects zeroed IPCB fields.
- */
- memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
-
- return mptcp_dss_len/sizeof(*ptr);
-}
-
static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -434,7 +388,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
struct sk_buff *subskb = NULL;
if (!reinject)
- TCP_SKB_CB(skb)->mptcp_flags |= (mpcb->snd_hiseq_index ?
+ skb->mptcp_flags |= (mpcb->snd_hiseq_index ?
MPTCPHDR_SEQ64_INDEX : 0);
subskb = pskb_copy_for_clone(skb, GFP_ATOMIC);
@@ -447,7 +401,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
*/
tcp_skb_pcount_set(subskb, 0);
- TCP_SKB_CB(skb)->path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
+ TCP_SKB_CB(skb)->mptcp_path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
if (!(sk->sk_route_caps & NETIF_F_ALL_CSUM) &&
skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -463,13 +417,14 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
tp->mptcp->fully_established = 1;
tp->mpcb->infinite_mapping_snd = 1;
tp->mptcp->infinite_cutoff_seq = tp->write_seq;
- tcb->mptcp_flags |= MPTCPHDR_INF;
+ skb->mptcp_flags |= MPTCPHDR_INF;
}
if (mptcp_is_data_fin(subskb))
mptcp_combine_dfin(subskb, meta_sk, sk);
- mptcp_save_dss_data_seq(tp, subskb);
+ subskb->mptcp_flags |= MPTCPHDR_SEQ;
+ tcb->mptcp_data_seq = tcb->seq;
tcb->seq = tp->write_seq;
@@ -536,10 +491,10 @@ static int mptcp_fragment(struct sock *meta_sk, struct sk_buff *skb, u32 len,
buff = skb->next;
- flags = TCP_SKB_CB(skb)->mptcp_flags;
- TCP_SKB_CB(skb)->mptcp_flags = flags & ~(MPTCPHDR_FIN);
- TCP_SKB_CB(buff)->mptcp_flags = flags;
- TCP_SKB_CB(buff)->path_mask = TCP_SKB_CB(skb)->path_mask;
+ flags = skb->mptcp_flags;
+ skb->mptcp_flags = flags & ~(MPTCPHDR_FIN);
+ buff->mptcp_flags = flags;
+ TCP_SKB_CB(buff)->mptcp_path_mask = TCP_SKB_CB(skb)->mptcp_path_mask;
/* If reinject == 1, the buff will be added to the reinject
* queue, which is currently not part of memory accounting. So
@@ -927,8 +882,9 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
* It does not make sense to check for the options, because when the
* segment gets sent, another subflow will be chosen.
*/
- if (!skb && is_meta_sk(sk))
+ if (!skb && is_meta_sk(sk)) {
return;
+ }
/* In fallback mp_fail-mode, we have to repeat it until the fallback
* has been done by the sender
@@ -967,10 +923,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
if (unlikely(mpcb->infinite_mapping_snd) &&
((mpcb->send_infinite_mapping && tcb &&
mptcp_is_data_seq(skb) &&
- !(tcb->mptcp_flags & MPTCPHDR_INF) &&
+ !(skb->mptcp_flags & MPTCPHDR_INF) &&
!before(tcb->seq, tp->mptcp->infinite_cutoff_seq)) ||
- !mpcb->send_infinite_mapping))
+ !mpcb->send_infinite_mapping)) {
return;
+ }
if (unlikely(tp->mptcp->include_mpc)) {
opts->options |= OPTION_MPTCP;
@@ -995,9 +952,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
mpcb->mptcp_ver >= MPTCP_VERSION_1 && skb && !mptcp_is_data_seq(skb)) {
mpcb->pm_ops->addr_signal(sk, size, opts, skb);
- if (opts->add_addr_v6)
+ if (opts->add_addr_v6) {
+
/* Skip subsequent options */
return;
+ }
}
if (!tp->mptcp->include_mpc && !tp->mptcp->pre_established) {
@@ -1197,10 +1156,11 @@ void mptcp_options_write(__be32 *ptr, struct tcp_sock *tp,
}
if (OPTION_DATA_ACK & opts->mptcp_options) {
- if (!mptcp_is_data_seq(skb))
- ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
- else
- ptr += mptcp_write_dss_data_seq(tp, skb, ptr);
+ ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
+ if (mptcp_is_data_seq(skb)) {
+ ptr += mptcp_write_dss_mapping(tp, skb, ptr);
+ }
+ skb->dev = NULL;
}
if (unlikely(OPTION_MP_PRIO & opts->mptcp_options)) {
struct mp_prio *mpprio = (struct mp_prio *)ptr;
@@ -1233,7 +1193,7 @@ void mptcp_send_fin(struct sock *meta_sk)
mss_now = mptcp_current_mss(meta_sk);
if (tcp_send_head(meta_sk) != NULL) {
- TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
+ skb->mptcp_flags |= MPTCPHDR_FIN;
TCP_SKB_CB(skb)->end_seq++;
meta_tp->write_seq++;
} else {
@@ -1250,7 +1210,7 @@ void mptcp_send_fin(struct sock *meta_sk)
tcp_init_nondata_skb(skb, meta_tp->write_seq, TCPHDR_ACK);
TCP_SKB_CB(skb)->end_seq++;
- TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
+ skb->mptcp_flags |= MPTCPHDR_FIN;
tcp_queue_skb(meta_sk, skb);
}
__tcp_push_pending_frames(meta_sk, mss_now, TCP_NAGLE_OFF);
diff --git a/net/mptcp/mptcp_redundant.c b/net/mptcp/mptcp_redundant.c
index 8fa2dba..37a13f4 100644
--- a/net/mptcp/mptcp_redundant.c
+++ b/net/mptcp/mptcp_redundant.c
@@ -72,10 +72,10 @@ static bool redsched_use_subflow(struct sock *meta_sk,
if (!skb || !mptcp_is_available((struct sock *)tp, skb, false))
return false;
- if (TCP_SKB_CB(skb)->path_mask != 0)
+ if (TCP_SKB_CB(skb)->mptcp_path_mask != 0)
return subflow_is_active(tp);
- if (TCP_SKB_CB(skb)->path_mask == 0) {
+ if (TCP_SKB_CB(skb)->mptcp_path_mask == 0) {
if (active_valid_sks == -1)
active_valid_sks = redsched_get_active_valid_sks(meta_sk);
@@ -209,7 +209,7 @@ static struct sk_buff *redundant_next_segment(struct sock *meta_sk,
cb_data->next_subflow = tp->mptcp->next;
*subsk = (struct sock *)tp;
- if (TCP_SKB_CB(skb)->path_mask)
+ if (TCP_SKB_CB(skb)->mptcp_path_mask)
*reinject = -1;
return skb;
}
diff --git a/net/mptcp/mptcp_rr.c b/net/mptcp/mptcp_rr.c
index 8910ba9..83837f2 100644
--- a/net/mptcp/mptcp_rr.c
+++ b/net/mptcp/mptcp_rr.c
@@ -93,7 +93,7 @@ static int mptcp_rr_dont_reinject_skb(const struct tcp_sock *tp, const struct sk
*/
return skb &&
/* Has the skb already been enqueued into this subsocket? */
- mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
+ mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
}
/* We just look for any subflow that is available */
@@ -136,7 +136,7 @@ static struct sock *rr_get_available_subflow(struct sock *meta_sk,
* chance again by restarting its pathmask.
*/
if (skb)
- TCP_SKB_CB(skb)->path_mask = 0;
+ TCP_SKB_CB(skb)->mptcp_path_mask = 0;
sk = backupsk;
}
diff --git a/net/mptcp/mptcp_sched.c b/net/mptcp/mptcp_sched.c
index 54408ff..5cbbf91 100644
--- a/net/mptcp/mptcp_sched.c
+++ b/net/mptcp/mptcp_sched.c
@@ -118,7 +118,7 @@ static int mptcp_dont_reinject_skb(const struct tcp_sock *tp, const struct sk_bu
*/
return skb &&
/* Has the skb already been enqueued into this subsocket? */
- mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
+ mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
}
bool subflow_is_backup(const struct tcp_sock *tp)
@@ -261,7 +261,7 @@ struct sock *get_available_subflow(struct sock *meta_sk, struct sk_buff *skb,
* the skb passed through all the available active and backups
* sks, so clean the path mask
*/
- TCP_SKB_CB(skb)->path_mask = 0;
+ TCP_SKB_CB(skb)->mptcp_path_mask = 0;
return sk;
}
EXPORT_SYMBOL_GPL(get_available_subflow);
@@ -298,7 +298,7 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
/* Half the cwnd of the slow flow */
mptcp_for_each_tp(tp->mpcb, tp_it) {
if (tp_it != tp &&
- TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
+ TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
if (tp->srtt_us < tp_it->srtt_us && inet_csk((struct sock *)tp_it)->icsk_ca_state == TCP_CA_Open) {
u32 prior_cwnd = tp_it->snd_cwnd;
@@ -317,11 +317,11 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
retrans:
/* Segment not yet injected into this path? Take it!!! */
- if (!(TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
+ if (!(TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
bool do_retrans = false;
mptcp_for_each_tp(tp->mpcb, tp_it) {
if (tp_it != tp &&
- TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
+ TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
if (tp_it->snd_cwnd <= 4) {
do_retrans = true;
break;
--
2.7.4
^ permalink raw reply related [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-28 20:13 Rao Shoaib
0 siblings, 0 replies; 14+ messages in thread
From: Rao Shoaib @ 2017-06-28 20:13 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 6160 bytes --]
Hi Mat,
Please see my response inline
On 06/27/2017 04:22 PM, Mat Martineau wrote:
>
> Hi Rao,
>
> On Mon, 26 Jun 2017, Rao Shoaib wrote:
>
>> This patch returns tcp_skb_cb to it's original size. It also
>> refactors MPTCP code so that there are no MPTCP checks in the main Rx
>> pathi, no performance overheads such as cpu prodiction issues.
>> tcp_v4_rcv() and tcp_v4_do_rcv() do not have any MPTCP specific
>> checks any more, niether does tcp_ack(). On the Rx path MPTCP options
>> are not parsed till the data is being pushed up to the meta socket
>> (mptcp_data_ready). on the Tx side there is one check to add MPTCP
>> specific options but that's it, that should not be that bad as for
>> regular TCP it is a simple check, but it would be good to remove it..
>>
>> I have tested the changes with ndiffports set to 2, so join works. I
>> have also tested accessing multipath-tcp.org and downloading files
>> from there and also ran the speed test.
>>
>> The Bad:
>>
>> The error cases still have MPTCP checks but that should be OK as they
>> are error cases. I had to use a special marker 0xFEE1DEAD for
>> indicate a special case. I had to introdue a new socket specfic
>> function. IPv6 has not been changed yet. I am sure I have missed some
>> corner cases and more testing will reveal more issues but we just
>> have to fix them.
>>
>> I would like to hear comments from the list and if this direction
>> seems reasonable we can take this as the starting point, port it to
>> latest Linux and share the design with the mainstream folks.
>
> I've read the earlier messages in this thread, so I've seen
> Christoph's concern about zero-length packets and your comment that
> more work is needed.
>
> The TCP option handling patch I posted earlier (I'm testing an updated
> version of that before sending it out again) might help us avoid
> passing unexpected zero-length packets up the stack.
Christoph has elaborated his concerns. His concern is not about zero
length packets going up the stack (there is no issue with that), instead
he is concerned about some packets not making up the stack and onto
MPTCP, for that there are solutions.
>
> My coworkers and I have some ideas for other upstream-friendly
> architecture changes, but I still need to type those up for mailing
> list discussion. We've done some work building up from the current
> net-next kernel and will get some patches in shape for this list.
>
> I have some comments below:
>
>
>>
>>
>
> I think the maintainers will oppose placement of protocol-specific
> fields in struct sk_buff.
I don't see this as an issue at all. As you point out below, UDP is
already using it. There is a reason why they named it dev_scratch.
union {
struct net_device *dev;
/* Some protocols might use this space to store
information,
* while device pointer would be NULL.
* UDP receive path is one user.
*/
unsigned long dev_scratch;
};
In the patch the field is being used when dev is null. It would have
been legal to overload this field even if the change had not been made
upstream, we missed the chance to be the first one :-(.
> Recent kernels have changed this to a union between the dev pointer
> and a dev_scratch integer. So far dev_scratch is only used by UDP.
>
>
>> diff --git a/include/net/tcp.h b/include/net/tcp.h
>> index 655ecd4..cbe8ef2 100644
>> --- a/include/net/tcp.h
>> +++ b/include/net/tcp.h
>> @@ -47,6 +47,9 @@
>> #include <linux/seq_file.h>
>> #include <linux/memcontrol.h>
>>
>> +typedef int (* process_unclaimed)(struct sock *sk, struct sk_buff
>> *skb);
>> +extern process_unclaimed tcp_process_unclaimed;
>> +
>> extern struct inet_hashinfo tcp_hashinfo;
>>
>> extern struct percpu_counter tcp_orphan_count;
>> @@ -581,6 +584,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock
>> *sk, struct sk_buff *skb,
>> struct request_sock *req,
>> struct dst_entry *dst);
>> int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
>> +
>> int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int
>> addr_len);
>> int tcp_connect(struct sock *sk);
>> struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
>> @@ -842,11 +846,6 @@ struct tcp_skb_cb {
>> __u32 tcp_gso_segs;
>> };
>>
>> -#ifdef CONFIG_MPTCP
>> - __u8 mptcp_flags; /* flags for the MPTCP layer */
>> - __u8 dss_off; /* Number of 4-byte words until
>> - * seq-number */
>> -#endif
>> __u8 tcp_flags; /* TCP header flags. (tcp[13]) */
>>
>> __u8 sacked; /* State flags for SACK/FACK. */
>> @@ -859,9 +858,13 @@ struct tcp_skb_cb {
>> #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
>> TCPCB_REPAIRED)
>>
>> - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
>> + __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
>> /* 1 byte hole */
>> - __u32 ack_seq; /* Sequence number ACK'd */
>> + union {
>> + __u32 ack_seq; /* Sequence number ACK'd */
>> + __u32 mptcp_data_seq;
>
> ack_seq is only used on incoming packets, and mptcp_data_seq only on
> outgoing?
Yup, there are three members of this union and none of them are used at
the same time.
>
>> + __u32 mptcp_path_mask;
>> + };
>
> One architectural change we're considering is not sharing sk_buffs
> between subflows, which would make mptcp_path_mask unnecessary. It
> would still be necessary to track that information, just not as part
> of sk_buff.
Any change that reduces the usage of sk_buff is very good. However this
is not a big issue any more. I prefer we rather look at reducing mptcp
checks in the main tcp code.
The patch that I have sent should apply cleanly to the net-next as well.
I am looking forward to your patch.
Rao
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-28 20:10 Rao Shoaib
0 siblings, 0 replies; 14+ messages in thread
From: Rao Shoaib @ 2017-06-28 20:10 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 3185 bytes --]
On 06/28/2017 12:41 PM, Christoph Paasch wrote:
> On 28/06/17 - 12:13:27, Rao Shoaib wrote:
>> Hi Christoph,
>>
>>
>> On 06/27/2017 09:53 PM, Christoph Paasch wrote:
>>> There are several reasons why such a packet might not make it up to the
>>> receive-queue. For example:
>>>
>>> * tcp_receive_window() returns 0
>>> * the sequence-number of the ack-packet is not the rcv_nxt. Then it goes
>>> into the ofo-queue. Which is why we had to add tests for mptcp() in
>>> tcp_data_queue_ofo() to handle DATA_FINs.
>>> * tcp_try_rmem_schedule() returns false
>>>
>>> Such kind of conditions will make that the signal from the peer (DATA_ACK,
>>> ADD_ADDR,...) does not reach the MPTCP-stack. But these signals should be
>>> delivered to the stack as reliably as possible.
>>>
>>>
>>> What if we rather use the error-queue for these signalling skbs? The
>>> error-queue has already been "abused" for tx-timestamps,... so this might be
>>> a good place to put this information. I think that would be cleaner.
>>>
>>>
>>> Christoph
>>>
>> Thanks for elaborating. Now I understand. Your concern is not the zero
>> length but the general constraints with queuing. Yes, the current
>> implementation does not bypass those constraints. It treats pure ack as a
>> zero length data packet. If this is an issue with MPTCP the fix is very
>> straight forward, in fact I want to make that change, In tcp_data_queue()
>> where we check if the packet is a pure ack and make decision to deliver it
>> if the socket is an MPTCP we can just call sk_data_ready . An
>> architecturally correct solution would be to have a another socket specific
>> function to deal with non data packets and remove checks for mptcp.
> I think the more and more that the error-queue is the right approach for
> such kind of signalling-information.
>
> Because, these signals can even be redundant (aka, if we get twice the same
> DATA_ACK). Having it in the error-queue would allow us to check for that and
> avoid adding another redundant skb into it.
>
> Would you want to explore the error-queue route?
I will definitely look into using the error-queue and any other
optimizations, I do not want to add any mptcp specific checks though. My
current focus is mostly just cleaning up TCP code and keep current MPTCP
working. I am hoping that we can cleanup the TCP code and can present
the design at the next netdev and get approval from the main stream
folks. Then we will look into how MPTCP implementation can be improved.
So right now I rather spend time looking at other main TCP areas and let
MPTCP do whatever it does today. This does not mean I will not look
into using error-queue, just that it might not be my top priority. I
hope that is OK with you :-).
Rao
>
>> The goal is to (When possible) not do any MPTCP parsing/processing till TCP
>> processing is done and the packet is handed off to MPTCP. This makes the
>> code look cleaner and less intrusive. Which is the biggest complain that the
>> upstream folks have. They are not concerned what we do in the MPTCP code.
> Yes, we all agree on that.
>
>
> Christoph
>
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-28 19:41 Christoph Paasch
0 siblings, 0 replies; 14+ messages in thread
From: Christoph Paasch @ 2017-06-28 19:41 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 2419 bytes --]
On 28/06/17 - 12:13:27, Rao Shoaib wrote:
> Hi Christoph,
>
>
> On 06/27/2017 09:53 PM, Christoph Paasch wrote:
> >
> > There are several reasons why such a packet might not make it up to the
> > receive-queue. For example:
> >
> > * tcp_receive_window() returns 0
> > * the sequence-number of the ack-packet is not the rcv_nxt. Then it goes
> > into the ofo-queue. Which is why we had to add tests for mptcp() in
> > tcp_data_queue_ofo() to handle DATA_FINs.
> > * tcp_try_rmem_schedule() returns false
> >
> > Such kind of conditions will make that the signal from the peer (DATA_ACK,
> > ADD_ADDR,...) does not reach the MPTCP-stack. But these signals should be
> > delivered to the stack as reliably as possible.
> >
> >
> > What if we rather use the error-queue for these signalling skbs? The
> > error-queue has already been "abused" for tx-timestamps,... so this might be
> > a good place to put this information. I think that would be cleaner.
> >
> >
> > Christoph
> >
> Thanks for elaborating. Now I understand. Your concern is not the zero
> length but the general constraints with queuing. Yes, the current
> implementation does not bypass those constraints. It treats pure ack as a
> zero length data packet. If this is an issue with MPTCP the fix is very
> straight forward, in fact I want to make that change, In tcp_data_queue()
> where we check if the packet is a pure ack and make decision to deliver it
> if the socket is an MPTCP we can just call sk_data_ready . An
> architecturally correct solution would be to have a another socket specific
> function to deal with non data packets and remove checks for mptcp.
I think the more and more that the error-queue is the right approach for
such kind of signalling-information.
Because, these signals can even be redundant (aka, if we get twice the same
DATA_ACK). Having it in the error-queue would allow us to check for that and
avoid adding another redundant skb into it.
Would you want to explore the error-queue route?
> The goal is to (When possible) not do any MPTCP parsing/processing till TCP
> processing is done and the packet is handed off to MPTCP. This makes the
> code look cleaner and less intrusive. Which is the biggest complain that the
> upstream folks have. They are not concerned what we do in the MPTCP code.
Yes, we all agree on that.
Christoph
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-28 19:13 Rao Shoaib
0 siblings, 0 replies; 14+ messages in thread
From: Rao Shoaib @ 2017-06-28 19:13 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 1897 bytes --]
Hi Christoph,
On 06/27/2017 09:53 PM, Christoph Paasch wrote:
>
> There are several reasons why such a packet might not make it up to the
> receive-queue. For example:
>
> * tcp_receive_window() returns 0
> * the sequence-number of the ack-packet is not the rcv_nxt. Then it goes
> into the ofo-queue. Which is why we had to add tests for mptcp() in
> tcp_data_queue_ofo() to handle DATA_FINs.
> * tcp_try_rmem_schedule() returns false
>
> Such kind of conditions will make that the signal from the peer (DATA_ACK,
> ADD_ADDR,...) does not reach the MPTCP-stack. But these signals should be
> delivered to the stack as reliably as possible.
>
>
> What if we rather use the error-queue for these signalling skbs? The
> error-queue has already been "abused" for tx-timestamps,... so this might be
> a good place to put this information. I think that would be cleaner.
>
>
> Christoph
>
Thanks for elaborating. Now I understand. Your concern is not the zero
length but the general constraints with queuing. Yes, the current
implementation does not bypass those constraints. It treats pure ack as
a zero length data packet. If this is an issue with MPTCP the fix is
very straight forward, in fact I want to make that change, In
tcp_data_queue() where we check if the packet is a pure ack and make
decision to deliver it if the socket is an MPTCP we can just call
sk_data_ready . An architecturally correct solution would be to have a
another socket specific function to deal with non data packets and
remove checks for mptcp.
The goal is to (When possible) not do any MPTCP parsing/processing till
TCP processing is done and the packet is handed off to MPTCP. This makes
the code look cleaner and less intrusive. Which is the biggest complain
that the upstream folks have. They are not concerned what we do in the
MPTCP code.
Rao
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-28 4:53 Christoph Paasch
0 siblings, 0 replies; 14+ messages in thread
From: Christoph Paasch @ 2017-06-28 4:53 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 72532 bytes --]
On 27/06/17 - 11:51:21, Rao Shoaib wrote:
>
>
> On 06/27/2017 10:37 AM, Christoph Paasch wrote:
> > Hello Rao,
> >
> > > On Jun 27, 2017, at 10:22 AM, Rao Shoaib <rao.shoaib(a)oracle.com
> > > <mailto:rao.shoaib(a)oracle.com>> wrote:
> > >
> > > Hi Christoph,
> > >
> > >
> > > On 06/26/2017 11:27 PM, Christoph Paasch wrote:
> > > > Hello Rao,
> > > >
> > > > can you try to give some more details on how the datapath looks
> > > > like with
> > > > this patch?
> > > >
> > > > For example, I wonder how data-acks are being processed.
> > > > Because, I see in
> > > > mptcp_data_ready, that you now expects skbs with len 0, upon
> > > > which you end
> > > > up calling mptcp_process_ack().
> > > >
> > > > I don't see how such zero-length skbs could end up in the
> > > > receive-queue of
> > > > the subflows.
> > > >
> > > >
> > > > Thanks,
> > >
> > > I send every packet that is coming on an MPTCP based socket down and
> > > let MPTCP deal with it. In tcp data_queue(). I also removed the
> > > directive to go to the slow_path in tcp_rcv_established().
> > >
> > > static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
> > > {
> > > struct tcp_sock *tp = tcp_sk(sk);
> > > int eaten = -1;
> > > bool fragstolen = false;
> > >
> > > /*
> > > * send every packet to MPTCP
> > > */
> > > if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq ==
> > > TCP_SKB_CB(skb)->end_seq)) {
> > > goto drop;
> > > }
> > >
> > > There is only one case that I need investigate more is the
> > > following. In that the he only interesting case is (len ==
> > > tcp_header_len) but in my unidirectional bulk data transfer tests I
> > > did not hit that case. So I need to investigate more later. The last
> > > resort would be to just directly go to the slow path.
> > >
> > > if (len <= tcp_header_len) { /* Bulk data transfer: sender */
> > >
> > > if (len == tcp_header_len) {
> >
> > The problem is, how are these zero-len packets being queued in the
> > receive-queue of the socket ? I am pretty sure that TCP won't like
> > having such packets in the receive-queue, which means there will be
> > quite some changes needed to support this.
> I don't understand why there are any changes needed to TCP, these packet
> will be handled in mptcp_data_ready() and discarded, just like TCP does
> with a pure ack. Please note that we only do this for MPTCP sockets not just
> any TCP socket.
> >
> > I might be missing something here. A high-level description with some
> > call-stacks of how the data-path looks like with your patch would be
> > good.
> It's actually very straight forward, normally in tcp_data_queue() a pure ack
> is simply dropped as TCP state has been updated and the packet is of no use.
> In case of MPTCP we force the packet to be delivered to the meta socket
> queue (See the mptcp check in the if statement). When mptcp_data_ready()
> processes the packet it, updates MPTCP state, frees packets that have been
> acked and than throws away the packet.
>
> If you wanted for some reason to do this with regular TCP, you could very
> well as long as the socket Rx function knows how to deal these packets.
>
> Can you be more specific about what TCP queue will have issues because at
> this point the packet is headed to the socket queue.
There are several reasons why such a packet might not make it up to the
receive-queue. For example:
* tcp_receive_window() returns 0
* the sequence-number of the ack-packet is not the rcv_nxt. Then it goes
into the ofo-queue. Which is why we had to add tests for mptcp() in
tcp_data_queue_ofo() to handle DATA_FINs.
* tcp_try_rmem_schedule() returns false
Such kind of conditions will make that the signal from the peer (DATA_ACK,
ADD_ADDR,...) does not reach the MPTCP-stack. But these signals should be
delivered to the stack as reliably as possible.
What if we rather use the error-queue for these signalling skbs? The
error-queue has already been "abused" for tx-timestamps,... so this might be
a good place to put this information. I think that would be cleaner.
Christoph
> If you prefer a stack trace, I can instrument the kernel with WARN_ON
> directive and get you one, that is the only way I know to get one in Linux.
> In Solaris it would be a 2 min operation on a running system. If there is a
> better way than please educate me.
>
> > Or maybe try to split the patch in separate pieces.
> That would be difficult because everything is tied together. If you prefer I
> can provide you with a tar ball of the source, you can look at it, compile
> and run it.
>
> I am actually wondering how folks do code review on Linux based on the patch
> that is submitted. There is no context diff or anything else, I am used to
> very sophisticated tools.
> >
> > >
> > > If there are other issues than let me know and I will work on
> > > resolving them. We obviously need to run extensive tests, that
> > > brings me to the question of, how does the MPTCP development team
> > > test changes. We need the same tests to validate the changes.
> >
> > packetdrill is the best tool to reproduce specific scenarios:
> > https://github.com/cpaasch/packetdrill_mptcp (tests are in there in
> > example/mptcp/).
> >
> > And, a testing-script is at
> > https://github.com/multipath-tcp/mptcp-scripts/tree/master/testing.
> > It does a bunch of stress-testing (iperf, haproxy, apache-benchmark,...)
> > on three machines that need to be inter-connected in a specific way.
> > It's a bit tricky to setup. I have KVMs that I boot that have two links
> > between each other. One is the client, one the router (sometimes acting
> > as a haproxy), one is the server. They need tools like ab, apache,
> > haproxy, iperf,...
> Well I do not have 3 machines and my system will die if I started 3 KVM's.
> Let me see what I can get.
>
> Thanks,
>
> Rao.
> >
> >
> > Christoph
> >
> > >
> > > Rao.
> > >
> > > > Christoph
> > > >
> > > >
> > > > On 26/06/17 - 15:34:09, Rao Shoaib wrote:
> > > > > I forgot to mention two things
> > > > >
> > > > > 1) Connection setup still has checks for MPTCP, Ideally these should be
> > > > > removed but at least we need to run some benchmarks and fix
> > > > > any issues. The
> > > > > mainstream folks will not accept any performance degradation
> > > > > in TCP. I can
> > > > > look into this next.
> > > > >
> > > > > 2) The code overloads dev field of skb, when it is not being used. IIRC
> > > > > there is precedence for this already. I will try to find it.
> > > > >
> > > > > Rao
> > > > >
> > > > >
> > > > > On 06/26/2017 02:13 PM, Rao Shoaib wrote:
> > > > > > This patch returns tcp_skb_cb to it's original size. It
> > > > > > also refactors MPTCP code so that there are no MPTCP
> > > > > > checks in the main Rx pathi, no performance overheads
> > > > > > such as cpu prodiction issues. tcp_v4_rcv() and
> > > > > > tcp_v4_do_rcv() do not have any MPTCP specific checks
> > > > > > any more, niether does tcp_ack(). On the Rx path MPTCP
> > > > > > options are not parsed till the data is being pushed up
> > > > > > to the meta socket (mptcp_data_ready). on the Tx side
> > > > > > there is one check to add MPTCP specific options but
> > > > > > that's it, that should not be that bad as for regular
> > > > > > TCP it is a simple check, but it would be good to remove
> > > > > > it..
> > > > > >
> > > > > > I have tested the changes with ndiffports set to 2, so
> > > > > > join works. I have also tested accessing
> > > > > > multipath-tcp.org <http://multipath-tcp.org> and
> > > > > > downloading files from there and also ran the speed
> > > > > > test.
> > > > > >
> > > > > > The Bad:
> > > > > >
> > > > > > The error cases still have MPTCP checks but that should
> > > > > > be OK as they are error cases. I had to use a special
> > > > > > marker 0xFEE1DEAD for indicate a special case. I had to
> > > > > > introdue a new socket specfic function. IPv6 has not
> > > > > > been changed yet. I am sure I have missed some corner
> > > > > > cases and more testing will reveal more issues but we
> > > > > > just have to fix them.
> > > > > >
> > > > > > I would like to hear comments from the list and if this
> > > > > > direction seems reasonable we can take this as the
> > > > > > starting point, port it to latest Linux and share the
> > > > > > design with the mainstream folks.
> > > > > >
> > > > > > Signed-off-by: Rao Shoaib <rao.shoaib(a)oracle.com
> > > > > > <mailto:rao.shoaib(a)oracle.com>>
> > > > > > ---
> > > > > > include/linux/skbuff.h | 8 ++-
> > > > > > include/net/mptcp.h | 21 +++---
> > > > > > include/net/mptcp_v4.h | 1 +
> > > > > > include/net/sock.h | 12 +++-
> > > > > > include/net/tcp.h | 23 +++----
> > > > > > net/ipv4/af_inet.c | 4 ++
> > > > > > net/ipv4/tcp_input.c | 37 ++--------
> > > > > > net/ipv4/tcp_ipv4.c | 135
> > > > > > +++++++++++++++++++++++--------------
> > > > > > net/ipv4/tcp_output.c | 1 +
> > > > > > net/ipv6/af_inet6.c | 4 ++
> > > > > > net/ipv6/tcp_ipv6.c | 4 --
> > > > > > net/mptcp/mptcp_ctrl.c | 21 ++++++
> > > > > > net/mptcp/mptcp_input.c | 131
> > > > > > ++++++++++++++++++++++++++++--------
> > > > > > net/mptcp/mptcp_ipv4.c | 35 +---------
> > > > > > net/mptcp/mptcp_ipv6.c | 4 +-
> > > > > > net/mptcp/mptcp_output.c | 160
> > > > > > +++++++++++++++++---------------------------
> > > > > > net/mptcp/mptcp_redundant.c | 6 +-
> > > > > > net/mptcp/mptcp_rr.c | 4 +-
> > > > > > net/mptcp/mptcp_sched.c | 10 +--
> > > > > > 19 files changed, 335 insertions(+), 286 deletions(-)
> > > > > >
> > > > > > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> > > > > > index f66cd5e..348cbc1 100644
> > > > > > --- a/include/linux/skbuff.h
> > > > > > +++ b/include/linux/skbuff.h
> > > > > > @@ -532,7 +532,13 @@ struct sk_buff {
> > > > > > struct rb_noderbnode; /* used in netem & tcp stack */
> > > > > > };
> > > > > > struct sock*sk;
> > > > > > -struct net_device*dev;
> > > > > > +union {
> > > > > > +struct net_device*dev;
> > > > > > +struct {
> > > > > > +__u8 mptcp_flags;
> > > > > > +__u8 mptcp_dss_off;
> > > > > > +};
> > > > > > +};
> > > > > > /*
> > > > > > * This is the control buffer. It is free to use for every
> > > > > > diff --git a/include/net/mptcp.h b/include/net/mptcp.h
> > > > > > index 876f1e6..d087cb4 100644
> > > > > > --- a/include/net/mptcp.h
> > > > > > +++ b/include/net/mptcp.h
> > > > > > @@ -807,7 +807,7 @@ void tcp_parse_mptcp_options(const
> > > > > > struct sk_buff *skb,
> > > > > > struct mptcp_options_received *mopt);
> > > > > > void mptcp_parse_options(const uint8_t *ptr, int opsize,
> > > > > > struct mptcp_options_received *mopt,
> > > > > > -const struct sk_buff *skb,
> > > > > > +struct sk_buff *skb,
> > > > > > struct tcp_sock *tp);
> > > > > > void mptcp_syn_options(const struct sock *sk, struct
> > > > > > tcp_out_options *opts,
> > > > > > unsigned *remaining);
> > > > > > @@ -998,14 +998,15 @@ static inline void
> > > > > > mptcp_sub_force_close_all(struct mptcp_cb *mpcb,
> > > > > > }
> > > > > > }
> > > > > > +/* currently tp is being used for Rx packets */
> > > > > > static inline bool mptcp_is_data_seq(const struct sk_buff *skb)
> > > > > > {
> > > > > > -return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ;
> > > > > > +return skb->mptcp_flags & MPTCPHDR_SEQ;
> > > > > > }
> > > > > > static inline bool mptcp_is_data_fin(const struct sk_buff *skb)
> > > > > > {
> > > > > > -return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_FIN;
> > > > > > +return skb->mptcp_flags & MPTCPHDR_FIN;
> > > > > > }
> > > > > > /* Is it a data-fin while in infinite mapping mode?
> > > > > > @@ -1034,17 +1035,17 @@ static inline u8
> > > > > > mptcp_get_64_bit(u64 data_seq, struct mptcp_cb *mpcb)
> > > > > > /* Sets the data_seq and returns pointer to the in-skb
> > > > > > field of the data_seq.
> > > > > > * If the packet has a 64-bit dseq, the pointer points
> > > > > > to the last 32 bits.
> > > > > > */
> > > > > > -static inline __u32 *mptcp_skb_set_data_seq(const
> > > > > > struct sk_buff *skb,
> > > > > > +static inline __u32 *mptcp_skb_set_data_seq(struct sk_buff *skb,
> > > > > > u32 *data_seq,
> > > > > > struct mptcp_cb *mpcb)
> > > > > > {
> > > > > > -__u32 *ptr = (__u32 *)(skb_transport_header(skb) +
> > > > > > TCP_SKB_CB(skb)->dss_off);
> > > > > > +__u32 *ptr = (__u32 *)(skb_transport_header(skb) +
> > > > > > skb->mptcp_dss_off);
> > > > > > -if (TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ64_SET) {
> > > > > > +if (skb->mptcp_flags & MPTCPHDR_SEQ64_SET) {
> > > > > > u64 data_seq64 = get_unaligned_be64(ptr);
> > > > > > if (mpcb)
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
> > > > > > +skb->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
> > > > > > *data_seq = (u32)data_seq64;
> > > > > > ptr++;
> > > > > > @@ -1142,7 +1143,7 @@ static inline void
> > > > > > mptcp_reset_mopt(struct tcp_sock *tp)
> > > > > > static inline __be32 mptcp_get_highorder_sndbits(const
> > > > > > struct sk_buff *skb,
> > > > > > const struct mptcp_cb *mpcb)
> > > > > > {
> > > > > > -return htonl(mpcb->snd_high_order[(TCP_SKB_CB(skb)->mptcp_flags &
> > > > > > +return htonl(mpcb->snd_high_order[(skb->mptcp_flags &
> > > > > > MPTCPHDR_SEQ64_INDEX) ? 1 : 0]);
> > > > > > }
> > > > > > @@ -1404,8 +1405,8 @@ static inline void
> > > > > > mptcp_set_rto(const struct sock *sk) {}
> > > > > > static inline void mptcp_send_fin(const struct sock *meta_sk) {}
> > > > > > static inline void mptcp_parse_options(const uint8_t
> > > > > > *ptr, const int opsize,
> > > > > > struct mptcp_options_received *mopt,
> > > > > > - const struct sk_buff *skb,
> > > > > > - const struct tcp_sock *tp) {}
> > > > > > + struct sk_buff *skb,
> > > > > > + struct tcp_sock *tp) {}
> > > > > > static inline void mptcp_syn_options(const struct sock *sk,
> > > > > > struct tcp_out_options *opts,
> > > > > > unsigned *remaining) {}
> > > > > > diff --git a/include/net/mptcp_v4.h b/include/net/mptcp_v4.h
> > > > > > index c83dca0..46394a4 100644
> > > > > > --- a/include/net/mptcp_v4.h
> > > > > > +++ b/include/net/mptcp_v4.h
> > > > > > @@ -45,6 +45,7 @@ extern struct tcp_request_sock_ops
> > > > > > mptcp_join_request_sock_ipv4_ops;
> > > > > > #ifdef CONFIG_MPTCP
> > > > > > int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb);
> > > > > > +int mptcp_v4_process_join_req(struct sock *meta_sk,
> > > > > > struct sk_buff *skb);
> > > > > > struct sock *mptcp_v4_search_req(const __be16 rport,
> > > > > > const __be32 raddr,
> > > > > > const __be32 laddr, const struct net *net);
> > > > > > int mptcp_init4_subsockets(struct sock *meta_sk, const
> > > > > > struct mptcp_loc4 *loc,
> > > > > > diff --git a/include/net/sock.h b/include/net/sock.h
> > > > > > index 0f12593..0d1bda5 100644
> > > > > > --- a/include/net/sock.h
> > > > > > +++ b/include/net/sock.h
> > > > > > @@ -296,6 +296,7 @@ struct cg_proto;
> > > > > > *@sk_write_space: callback to indicate there is bf
> > > > > > sending space available
> > > > > > *@sk_error_report: callback to indicate errors (e.g.
> > > > > > %MSG_ERRQUEUE)
> > > > > > *@sk_backlog_rcv: callback to process the backlog
> > > > > > + *@sk_prequeue: callback to prequeue
> > > > > > *@sk_destruct: called at sock freeing time, i.e.
> > > > > > when all refcnt == 0
> > > > > > */
> > > > > > struct sock {
> > > > > > @@ -437,7 +438,9 @@ struct sock {
> > > > > > void(*sk_write_space)(struct sock *sk);
> > > > > > void(*sk_error_report)(struct sock *sk);
> > > > > > int(*sk_backlog_rcv)(struct sock *sk,
> > > > > > - struct sk_buff *skb);
> > > > > > +struct sk_buff *skb);
> > > > > > +bool(*sk_prequeue)(struct sock *sk,
> > > > > > +struct sk_buff *skb);
> > > > > > void (*sk_destruct)(struct sock *sk);
> > > > > > };
> > > > > > @@ -853,6 +856,11 @@ static inline int
> > > > > > sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
> > > > > > return sk->sk_backlog_rcv(sk, skb);
> > > > > > }
> > > > > > +static inline bool sk_prequeue(struct sock *sk, struct sk_buff *skb)
> > > > > > +{
> > > > > > +return (false);
> > > > > > +}
> > > > > > +
> > > > > > static inline void sk_incoming_cpu_update(struct sock *sk)
> > > > > > {
> > > > > > sk->sk_incoming_cpu = raw_smp_processor_id();
> > > > > > @@ -993,6 +1001,8 @@ struct proto {
> > > > > > int(*backlog_rcv) (struct sock *sk,
> > > > > > struct sk_buff *skb);
> > > > > > +bool(*prequeue) (struct sock *sk,
> > > > > > +struct sk_buff *skb);
> > > > > > void(*release_cb)(struct sock *sk);
> > > > > > diff --git a/include/net/tcp.h b/include/net/tcp.h
> > > > > > index 655ecd4..cbe8ef2 100644
> > > > > > --- a/include/net/tcp.h
> > > > > > +++ b/include/net/tcp.h
> > > > > > @@ -47,6 +47,9 @@
> > > > > > #include <linux/seq_file.h>
> > > > > > #include <linux/memcontrol.h>
> > > > > > +typedef int (* process_unclaimed)(struct sock *sk,
> > > > > > struct sk_buff *skb);
> > > > > > +extern process_unclaimed tcp_process_unclaimed;
> > > > > > +
> > > > > > extern struct inet_hashinfo tcp_hashinfo;
> > > > > > extern struct percpu_counter tcp_orphan_count;
> > > > > > @@ -581,6 +584,7 @@ struct sock
> > > > > > *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff
> > > > > > *skb,
> > > > > > struct request_sock *req,
> > > > > > struct dst_entry *dst);
> > > > > > int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
> > > > > > +
> > > > > > int tcp_v4_connect(struct sock *sk, struct sockaddr
> > > > > > *uaddr, int addr_len);
> > > > > > int tcp_connect(struct sock *sk);
> > > > > > struct sk_buff *tcp_make_synack(struct sock *sk,
> > > > > > struct dst_entry *dst,
> > > > > > @@ -842,11 +846,6 @@ struct tcp_skb_cb {
> > > > > > __u32tcp_gso_segs;
> > > > > > };
> > > > > > -#ifdef CONFIG_MPTCP
> > > > > > -__u8mptcp_flags;/* flags for the MPTCP layer */
> > > > > > -__u8dss_off;/* Number of 4-byte words until
> > > > > > -* seq-number */
> > > > > > -#endif
> > > > > > __u8tcp_flags;/* TCP header flags. (tcp[13])*/
> > > > > > __u8sacked;/* State flags for SACK/FACK.*/
> > > > > > @@ -859,9 +858,13 @@ struct tcp_skb_cb {
> > > > > > #define TCPCB_RETRANS(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
> > > > > > TCPCB_REPAIRED)
> > > > > > -__u8ip_dsfield;/* IPv4 tos or IPv6 dsfield*/
> > > > > > +__u8ip_dsfield;/* IPv4 tos or IPv6 dsfield */
> > > > > > /* 1 byte hole */
> > > > > > -__u32ack_seq;/* Sequence number ACK'd*/
> > > > > > +union {
> > > > > > +__u32ack_seq;/* Sequence number ACK'd */
> > > > > > +__u32 mptcp_data_seq;
> > > > > > +__u32mptcp_path_mask;
> > > > > > +};
> > > > > > union {
> > > > > > union {
> > > > > > struct inet_skb_parmh4;
> > > > > > @@ -869,12 +872,6 @@ struct tcp_skb_cb {
> > > > > > struct inet6_skb_parmh6;
> > > > > > #endif
> > > > > > } header;/* For incoming frames*/
> > > > > > -#ifdef CONFIG_MPTCP
> > > > > > -union {/* For MPTCP outgoing frames */
> > > > > > -__u32 path_mask; /* paths that tried to send this skb */
> > > > > > -__u32 dss[6];/* DSS options */
> > > > > > -};
> > > > > > -#endif
> > > > > > };
> > > > > > };
> > > > > > diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
> > > > > > index 73480b9..1e7827f 100644
> > > > > > --- a/net/ipv4/af_inet.c
> > > > > > +++ b/net/ipv4/af_inet.c
> > > > > > @@ -356,6 +356,10 @@ lookup_protocol:
> > > > > > sk->sk_destruct = inet_sock_destruct;
> > > > > > sk->sk_protocol = protocol;
> > > > > > sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
> > > > > > +sk->sk_prequeue = sk->sk_prot->prequeue;
> > > > > > +if (sk->sk_prequeue == NULL) {
> > > > > > +sk->sk_prequeue = sk_prequeue;
> > > > > > +}
> > > > > > inet->uc_ttl= -1;
> > > > > > inet->mc_loop= 1;
> > > > > > diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> > > > > > index 16a7256..cb6bbf9 100644
> > > > > > --- a/net/ipv4/tcp_input.c
> > > > > > +++ b/net/ipv4/tcp_input.c
> > > > > > @@ -3133,8 +3133,6 @@ static int
> > > > > > tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
> > > > > > */
> > > > > > if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
> > > > > > flag |= FLAG_DATA_ACKED;
> > > > > > -if (mptcp(tp) && mptcp_is_data_seq(skb))
> > > > > > -flag |= MPTCP_FLAG_DATA_ACKED;
> > > > > > } else {
> > > > > > flag |= FLAG_SYN_ACKED;
> > > > > > tp->retrans_stamp = 0;
> > > > > > @@ -3582,16 +3580,6 @@ static int tcp_ack(struct sock
> > > > > > *sk, struct sk_buff *skb, int flag)
> > > > > > sack_rtt_us);
> > > > > > acked -= tp->packets_out;
> > > > > > -if (mptcp(tp)) {
> > > > > > -if (mptcp_fallback_infinite(sk, flag)) {
> > > > > > -pr_err("%s resetting flow\n", __func__);
> > > > > > -mptcp_send_reset(sk);
> > > > > > -goto invalid_ack;
> > > > > > -}
> > > > > > -
> > > > > > -mptcp_clean_rtx_infinite(skb, sk);
> > > > > > -}
> > > > > > -
> > > > > > /* Advance cwnd if state allows */
> > > > > > if (tcp_may_raise_cwnd(sk, flag))
> > > > > > tcp_cong_avoid(sk, ack, acked);
> > > > > > @@ -3824,8 +3812,7 @@ static bool
> > > > > > tcp_fast_parse_options(const struct sk_buff *skb,
> > > > > > if (tcp_parse_aligned_timestamp(tp, th))
> > > > > > return true;
> > > > > > }
> > > > > > -tcp_parse_options(skb, &tp->rx_opt,
> > > > > > - mptcp(tp) ? &tp->mptcp->rx_opt : NULL, 1, NULL, tp);
> > > > > > +tcp_parse_options(skb, &tp->rx_opt, NULL, 1, NULL, tp);
> > > > > > if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
> > > > > > tp->rx_opt.rcv_tsecr -= tp->tsoffset;
> > > > > > @@ -4550,11 +4537,12 @@ static void
> > > > > > tcp_data_queue(struct sock *sk, struct sk_buff *skb)
> > > > > > int eaten = -1;
> > > > > > bool fragstolen = false;
> > > > > > -/* If no data is present, but a data_fin is in the options, we still
> > > > > > -* have to call mptcp_queue_skb later on. */
> > > > > > -if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq &&
> > > > > > - !(mptcp(tp) && mptcp_is_data_fin(skb)))
> > > > > > +/*
> > > > > > +* send every packet to MPTCP
> > > > > > +*/
> > > > > > +if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq ==
> > > > > > TCP_SKB_CB(skb)->end_seq)) {
> > > > > > goto drop;
> > > > > > +}
> > > > > > skb_dst_drop(skb);
> > > > > > __skb_pull(skb, tcp_hdr(skb)->doff * 4);
> > > > > > @@ -5242,15 +5230,9 @@ syn_challenge:
> > > > > > goto discard;
> > > > > > }
> > > > > > -/* If valid: post process the received MPTCP options. */
> > > > > > -if (mptcp(tp) && mptcp_handle_options(sk, th, skb))
> > > > > > -goto discard;
> > > > > > -
> > > > > > return true;
> > > > > > discard:
> > > > > > -if (mptcp(tp))
> > > > > > -mptcp_reset_mopt(tp);
> > > > > > __kfree_skb(skb);
> > > > > > return false;
> > > > > > }
> > > > > > @@ -5302,10 +5284,6 @@ void tcp_rcv_established(struct
> > > > > > sock *sk, struct sk_buff *skb,
> > > > > > tp->rx_opt.saw_tstamp = 0;
> > > > > > -/* MPTCP: force slowpath. */
> > > > > > -if (mptcp(tp))
> > > > > > -goto slow_path;
> > > > > > -
> > > > > > /*pred_flags is 0xS?10 << 16 + snd_wnd
> > > > > > *if header_prediction is to be made
> > > > > > *'S' will always be tp->tcp_header_len >> 2
> > > > > > @@ -5585,8 +5563,7 @@ static int
> > > > > > tcp_rcv_synsent_state_process(struct sock *sk, struct
> > > > > > sk_buff *skb,
> > > > > > struct mptcp_options_received mopt;
> > > > > > mptcp_init_mp_opt(&mopt);
> > > > > > -tcp_parse_options(skb, &tp->rx_opt,
> > > > > > - mptcp(tp) ? &tp->mptcp->rx_opt : &mopt, 0, &foc, tp);
> > > > > > +tcp_parse_options(skb, &tp->rx_opt, &mopt, 0, &foc, tp);
> > > > > > if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
> > > > > > tp->rx_opt.rcv_tsecr -= tp->tsoffset;
> > > > > > diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> > > > > > index 6967a86..3329679 100644
> > > > > > --- a/net/ipv4/tcp_ipv4.c
> > > > > > +++ b/net/ipv4/tcp_ipv4.c
> > > > > > @@ -1420,6 +1420,71 @@ struct sock
> > > > > > *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
> > > > > > return sk;
> > > > > > }
> > > > > > +int mptcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
> > > > > > +{
> > > > > > +struct net *net = dev_net(skb->dev);
> > > > > > +const struct tcphdr *th = tcp_hdr(skb);
> > > > > > +int ret;
> > > > > > +struct sock *meta_sk;
> > > > > > +
> > > > > > +if (sk == NULL) {
> > > > > > +if (th->syn && !th->ack) {
> > > > > > +int ret = mptcp_lookup_join(skb, NULL);
> > > > > > +
> > > > > > +if (ret < 0) {
> > > > > > +tcp_v4_send_reset(NULL, skb);
> > > > > > +kfree_skb(skb);
> > > > > > +return (1);
> > > > > > +} else if (ret > 0) {
> > > > > > +return (1);
> > > > > > +}
> > > > > > +}
> > > > > > +/* Is there a pending request sock for this segment ? */
> > > > > > +if (mptcp_check_req(skb, net)) {
> > > > > > +return(1);
> > > > > > +}
> > > > > > +return (0);
> > > > > > +}
> > > > > > +
> > > > > > +/* The socket passed in should never be the meta socket */
> > > > > > +
> > > > > > +BUG_ON(is_meta_sk(sk));
> > > > > > +
> > > > > > + /* Is there a pending request sock for this segment ? */
> > > > > > +if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
> > > > > > +return 0;
> > > > > > +}
> > > > > > +
> > > > > > +skb->dev = NULL;
> > > > > > +meta_sk = mptcp_meta_sk(sk);
> > > > > > +
> > > > > > +ret = 0;
> > > > > > +skb->sk = sk;
> > > > > > +bh_lock_sock_nested(meta_sk);
> > > > > > +if (sock_owned_by_user(meta_sk)) {
> > > > > > +if (unlikely(sk_add_backlog(meta_sk, skb,
> > > > > > + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> > > > > > +
> > > > > > +NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> > > > > > +kfree_skb(skb);
> > > > > > +}
> > > > > > +} else {
> > > > > > +
> > > > > > +if (is_meta_sk(sk)) {
> > > > > > +ret = mptcp_v4_process_join_req(sk, skb);
> > > > > > +goto done;
> > > > > > +}
> > > > > > +if (!meta_sk->sk_prequeue(meta_sk, skb)) {
> > > > > > +skb->sk = NULL;
> > > > > > +ret = tcp_v4_do_rcv(sk, skb);
> > > > > > +}
> > > > > > +
> > > > > > +}
> > > > > > +done:
> > > > > > +bh_unlock_sock(meta_sk);
> > > > > > +return (ret);
> > > > > > +}
> > > > > > +
> > > > > > /* The socket must have it's spinlock held when we get
> > > > > > * here.
> > > > > > *
> > > > > > @@ -1432,8 +1497,7 @@ int tcp_v4_do_rcv(struct sock *sk,
> > > > > > struct sk_buff *skb)
> > > > > > {
> > > > > > struct sock *rsk;
> > > > > > -if (is_meta_sk(sk))
> > > > > > -return mptcp_v4_do_rcv(sk, skb);
> > > > > > +BUG_ON(is_meta_sk(sk));
> > > > > > if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
> > > > > > struct dst_entry *dst = sk->sk_rx_dst;
> > > > > > @@ -1587,6 +1651,8 @@ bool tcp_prequeue(struct sock *sk,
> > > > > > struct sk_buff *skb)
> > > > > > }
> > > > > > EXPORT_SYMBOL(tcp_prequeue);
> > > > > > +process_unclaimed tcp_process_unclaimed = NULL;
> > > > > > +
> > > > > > /*
> > > > > > *From tcp_input.c
> > > > > > */
> > > > > > @@ -1595,7 +1661,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
> > > > > > {
> > > > > > const struct iphdr *iph;
> > > > > > const struct tcphdr *th;
> > > > > > -struct sock *sk, *meta_sk = NULL;
> > > > > > +struct sock *sk = NULL;
> > > > > > int ret;
> > > > > > struct net *net = dev_net(skb->dev);
> > > > > > @@ -1636,10 +1702,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
> > > > > > TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
> > > > > > skb->len - th->doff * 4);
> > > > > > TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
> > > > > > -#ifdef CONFIG_MPTCP
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags = 0;
> > > > > > -TCP_SKB_CB(skb)->dss_off = 0;
> > > > > > -#endif
> > > > > > +
> > > > > > TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
> > > > > > TCP_SKB_CB(skb)->tcp_tw_isn = 0;
> > > > > > TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
> > > > > > @@ -1662,15 +1725,6 @@ process:
> > > > > > if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
> > > > > > goto discard_and_relse;
> > > > > > -#ifdef CONFIG_MPTCP
> > > > > > -/* Is there a pending request sock for this segment ? */
> > > > > > -if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
> > > > > > -if (sk)
> > > > > > -sock_put(sk);
> > > > > > -return 0;
> > > > > > -}
> > > > > > -#endif
> > > > > > -
> > > > > > #ifdef CONFIG_TCP_MD5SIG
> > > > > > /*
> > > > > > * We really want to reject the packet as early as possible
> > > > > > @@ -1688,30 +1742,21 @@ process:
> > > > > > goto discard_and_relse;
> > > > > > sk_incoming_cpu_update(sk);
> > > > > > -skb->dev = NULL;
> > > > > > -if (mptcp(tcp_sk(sk))) {
> > > > > > -meta_sk = mptcp_meta_sk(sk);
> > > > > > -
> > > > > > -bh_lock_sock_nested(meta_sk);
> > > > > > -if (sock_owned_by_user(meta_sk))
> > > > > > -skb->sk = sk;
> > > > > > -} else {
> > > > > > -meta_sk = sk;
> > > > > > -bh_lock_sock_nested(sk);
> > > > > > -}
> > > > > > +/* Do I have to set skb->dev to null ? */
> > > > > > +bh_lock_sock_nested(sk);
> > > > > > ret = 0;
> > > > > > -if (!sock_owned_by_user(meta_sk)) {
> > > > > > -if (!tcp_prequeue(meta_sk, skb))
> > > > > > -ret = tcp_v4_do_rcv(sk, skb);
> > > > > > -} else if (unlikely(sk_add_backlog(meta_sk, skb,
> > > > > > - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> > > > > > -bh_unlock_sock(meta_sk);
> > > > > > +if (!sock_owned_by_user(sk)) {
> > > > > > +if (!sk->sk_prequeue(sk, skb))
> > > > > > +ret = sk->sk_backlog_rcv(sk, skb);
> > > > > > +} else if (unlikely(sk_add_backlog(sk, skb,
> > > > > > + sk->sk_rcvbuf + sk->sk_sndbuf))) {
> > > > > > +bh_unlock_sock(sk);
> > > > > > NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> > > > > > goto discard_and_relse;
> > > > > > }
> > > > > > -bh_unlock_sock(meta_sk);
> > > > > > +bh_unlock_sock(sk);
> > > > > > sock_put(sk);
> > > > > > @@ -1721,26 +1766,11 @@ no_tcp_socket:
> > > > > > if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
> > > > > > goto discard_it;
> > > > > > -#ifdef CONFIG_MPTCP
> > > > > > -if (!sk && th->syn && !th->ack) {
> > > > > > -int ret = mptcp_lookup_join(skb, NULL);
> > > > > > -
> > > > > > -if (ret < 0) {
> > > > > > -tcp_v4_send_reset(NULL, skb);
> > > > > > -goto discard_it;
> > > > > > -} else if (ret > 0) {
> > > > > > -return 0;
> > > > > > -}
> > > > > > +if (unlikely (tcp_process_unclaimed != NULL)) {
> > > > > > +if ((tcp_process_unclaimed)(NULL, skb))
> > > > > > +return (0);
> > > > > > }
> > > > > > -/* Is there a pending request sock for this segment ? */
> > > > > > -if (!sk && mptcp_check_req(skb, net)) {
> > > > > > -if (sk)
> > > > > > -sock_put(sk);
> > > > > > -return 0;
> > > > > > -}
> > > > > > -#endif
> > > > > > -
> > > > > > if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
> > > > > > csum_error:
> > > > > > TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
> > > > > > @@ -2506,6 +2536,7 @@ struct proto tcp_prot = {
> > > > > > .sendmsg= tcp_sendmsg,
> > > > > > .sendpage= tcp_sendpage,
> > > > > > .backlog_rcv= tcp_v4_do_rcv,
> > > > > > +.prequeue= tcp_prequeue,
> > > > > > .release_cb= tcp_release_cb,
> > > > > > .hash= inet_hash,
> > > > > > .unhash= inet_unhash,
> > > > > > diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> > > > > > index a635483..41b8be8 100644
> > > > > > --- a/net/ipv4/tcp_output.c
> > > > > > +++ b/net/ipv4/tcp_output.c
> > > > > > @@ -3413,6 +3413,7 @@ void tcp_send_delayed_ack(struct sock *sk)
> > > > > > void tcp_send_ack(struct sock *sk)
> > > > > > {
> > > > > > struct sk_buff *buff;
> > > > > > +struct tcp_sock *tp = tcp_sk(sk);
> > > > > > /* If we have been reset, we may not send again. */
> > > > > > if (sk->sk_state == TCP_CLOSE)
> > > > > > diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
> > > > > > index 8c4dd4a..1554217 100644
> > > > > > --- a/net/ipv6/af_inet6.c
> > > > > > +++ b/net/ipv6/af_inet6.c
> > > > > > @@ -193,6 +193,10 @@ lookup_protocol:
> > > > > > sk->sk_protocol= protocol;
> > > > > > sk->sk_backlog_rcv= answer->prot->backlog_rcv;
> > > > > > +sk->sk_prequeue= answer->prot->prequeue;
> > > > > > +if (sk->sk_prequeue == NULL) {
> > > > > > +sk->sk_prequeue = sk_prequeue;
> > > > > > +}
> > > > > > inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
> > > > > > np->hop_limit= -1;
> > > > > > diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> > > > > > index eba2436..d360128 100644
> > > > > > --- a/net/ipv6/tcp_ipv6.c
> > > > > > +++ b/net/ipv6/tcp_ipv6.c
> > > > > > @@ -1412,10 +1412,6 @@ static void tcp_v6_fill_cb(struct
> > > > > > sk_buff *skb, const struct ipv6hdr *hdr,
> > > > > > TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
> > > > > > skb->len - th->doff*4);
> > > > > > TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
> > > > > > -#ifdef CONFIG_MPTCP
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags = 0;
> > > > > > -TCP_SKB_CB(skb)->dss_off = 0;
> > > > > > -#endif
> > > > > > TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
> > > > > > TCP_SKB_CB(skb)->tcp_tw_isn = 0;
> > > > > > TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
> > > > > > diff --git a/net/mptcp/mptcp_ctrl.c b/net/mptcp/mptcp_ctrl.c
> > > > > > index 28f348f..b1e780a 100644
> > > > > > --- a/net/mptcp/mptcp_ctrl.c
> > > > > > +++ b/net/mptcp/mptcp_ctrl.c
> > > > > > @@ -976,6 +976,20 @@ int mptcp_backlog_rcv(struct sock
> > > > > > *meta_sk, struct sk_buff *skb)
> > > > > > struct sock *sk = skb->sk ? skb->sk : meta_sk;
> > > > > > int ret = 0;
> > > > > > +/* socket was owned by the user in mptcp_check_req()
> > > > > > + */
> > > > > > +if (sk == (struct sock *)0xFEE1DEAD) {
> > > > > > +bh_lock_sock_nested(meta_sk);
> > > > > > +if (skb->protocol == htons(ETH_P_IP))
> > > > > > +mptcp_v4_process_join_req(meta_sk, skb);
> > > > > > +#if IS_ENABLED(CONFIG_IPV6)
> > > > > > +else
> > > > > > +//mptcp_v6_process_join_req(meta_sk, skb);
> > > > > > +#endif /* CONFIG_IPV6 */
> > > > > > +bh_unlock_sock(meta_sk);
> > > > > > +return(0);
> > > > > > +}
> > > > > > +
> > > > > > skb->sk = NULL;
> > > > > > if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
> > > > > > @@ -1297,6 +1311,10 @@ int mptcp_add_sock(struct sock
> > > > > > *meta_sk, struct sock *sk, u8 loc_id, u8 rem_id,
> > > > > > sk->sk_write_space = mptcp_write_space;
> > > > > > sk->sk_state_change = mptcp_set_state;
> > > > > > sk->sk_destruct = mptcp_sock_destruct;
> > > > > > +/* MPTCP takes a different path in tcp_v4_rcv
> > > > > > + * thus not impacting main tcp code */
> > > > > > +sk->sk_backlog_rcv = mptcp_v4_do_rcv;
> > > > > > +sk->sk_prequeue = sk_prequeue;
> > > > > > if (sk->sk_family == AF_INET)
> > > > > > mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d
> > > > > > dst_addr:%pI4:%d, cnt_subflows now %d\n",
> > > > > > @@ -2658,6 +2676,9 @@ void __init mptcp_init(void)
> > > > > > if (mptcp_pm_v4_init())
> > > > > > goto mptcp_pm_v4_failed;
> > > > > > +if ((cmpxchg(&tcp_process_unclaimed, NULL, mptcp_v4_do_rcv)) != NULL)
> > > > > > +printk("tcp_process_unclaimed not NULL \n");
> > > > > > +
> > > > > > mptcp_sysctl = register_net_sysctl(&init_net,
> > > > > > "net/mptcp", mptcp_table);
> > > > > > if (!mptcp_sysctl)
> > > > > > goto register_sysctl_failed;
> > > > > > diff --git a/net/mptcp/mptcp_input.c b/net/mptcp/mptcp_input.c
> > > > > > index 51cbb06..0e09ddf 100644
> > > > > > --- a/net/mptcp/mptcp_input.c
> > > > > > +++ b/net/mptcp/mptcp_input.c
> > > > > > @@ -323,9 +323,8 @@ static int mptcp_verif_dss_csum(struct sock *sk)
> > > > > > * by 4 bytes, as the high-order 64-bits will be added
> > > > > > * in the final csum_partial-call.
> > > > > > */
> > > > > > -u32 offset = skb_transport_offset(tmp) +
> > > > > > - TCP_SKB_CB(tmp)->dss_off;
> > > > > > -if (TCP_SKB_CB(tmp)->mptcp_flags & MPTCPHDR_SEQ64_SET)
> > > > > > +u32 offset = skb_transport_offset(tmp) + tmp->mptcp_dss_off;
> > > > > > +if (tmp->mptcp_flags & MPTCPHDR_SEQ64_SET)
> > > > > > offset += 4;
> > > > > > csum_tcp = skb_checksum(tmp, offset,
> > > > > > @@ -758,7 +757,7 @@ static int
> > > > > > mptcp_detect_mapping(struct sock *sk, struct sk_buff
> > > > > > *skb)
> > > > > > }
> > > > > > /* Does the DSS had 64-bit seqnum's ? */
> > > > > > -if (!(tcb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
> > > > > > +if (!(skb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
> > > > > > /* Wrapped around? */
> > > > > > if (unlikely(after(data_seq, meta_tp->rcv_nxt) &&
> > > > > > data_seq < meta_tp->rcv_nxt)) {
> > > > > > tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
> > > > > > !mpcb->rcv_hiseq_index, data_seq);
> > > > > > @@ -767,9 +766,9 @@ static int
> > > > > > mptcp_detect_mapping(struct sock *sk, struct sk_buff
> > > > > > *skb)
> > > > > > tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
> > > > > > mpcb->rcv_hiseq_index, data_seq);
> > > > > > }
> > > > > > } else {
> > > > > > -tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
> > > > > > (tcb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0,
> > > > > > data_seq);
> > > > > > +tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
> > > > > > (skb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0,
> > > > > > data_seq);
> > > > > > -if (unlikely(tcb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
> > > > > > +if (unlikely(skb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
> > > > > > /* We make sure that the data_seq is invalid.
> > > > > > * It will be dropped later.
> > > > > > */
> > > > > > @@ -1020,6 +1019,67 @@ next:
> > > > > > return data_queued ? -1 : -2;
> > > > > > }
> > > > > > +static struct sk_buff *
> > > > > > +mptcp_process_ack(struct sock *sk, struct sk_buff *skb)
> > > > > > +{
> > > > > > +struct tcp_sock *tp = tcp_sk(sk);
> > > > > > +int flag = 0;
> > > > > > +
> > > > > > +/*
> > > > > > +* TCP takes care of invalid ack's
> > > > > > +* they will never show up here.
> > > > > > +*/
> > > > > > +
> > > > > > +/* Is this skb acknowleding anything data */
> > > > > > +
> > > > > > +if (tp->mptcp->snt_isn + 1 != TCP_SKB_CB(skb)->ack_seq) {
> > > > > > +flag = MPTCP_FLAG_DATA_ACKED;
> > > > > > +}
> > > > > > +
> > > > > > +if (mptcp_fallback_infinite(sk, flag)) {
> > > > > > +pr_err("%s resetting flow\n", __func__);
> > > > > > +mptcp_send_reset(sk);
> > > > > > +goto invalid_ack;
> > > > > > +}
> > > > > > +
> > > > > > +mptcp_clean_rtx_infinite(skb, sk);
> > > > > > +
> > > > > > +return (skb);
> > > > > > +invalid_ack:
> > > > > > +__skb_unlink(skb, &sk->sk_receive_queue);
> > > > > > +__kfree_skb(skb);
> > > > > > +return (NULL);
> > > > > > +
> > > > > > +}
> > > > > > +
> > > > > > +static struct sk_buff *
> > > > > > +mptcp_process_options_ack(struct sock *sk, struct sk_buff *skb)
> > > > > > +{
> > > > > > +struct tcp_sock *tp = tcp_sk(sk);
> > > > > > +const struct tcphdr *th = tcp_hdr(skb);
> > > > > > +
> > > > > > +skb->mptcp_flags = 0;
> > > > > > +skb->mptcp_dss_off = 0;
> > > > > > +
> > > > > > +tcp_parse_mptcp_options(skb, &tp->mptcp->rx_opt);
> > > > > > +if (mptcp_handle_options(sk, th, skb)) {
> > > > > > +mptcp_reset_mopt(tp);
> > > > > > +__skb_unlink(skb, &sk->sk_receive_queue);
> > > > > > +__kfree_skb(skb);
> > > > > > +skb = NULL;
> > > > > > +}
> > > > > > +if ((skb != NULL) && skb->len == 0) {
> > > > > > +skb = mptcp_process_ack(sk, skb);
> > > > > > +if (skb != NULL && skb->len == 0) {
> > > > > > +/* Pure ack */
> > > > > > +__skb_unlink(skb, &sk->sk_receive_queue);
> > > > > > +__kfree_skb(skb);
> > > > > > +skb = NULL;
> > > > > > +}
> > > > > > +}
> > > > > > +return (skb);
> > > > > > +}
> > > > > > +
> > > > > > void mptcp_data_ready(struct sock *sk)
> > > > > > {
> > > > > > struct sock *meta_sk = mptcp_meta_sk(sk);
> > > > > > @@ -1045,6 +1105,10 @@ restart:
> > > > > > */
> > > > > > skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
> > > > > > int ret;
> > > > > > +
> > > > > > +skb = mptcp_process_options_ack(sk, skb);
> > > > > > +if (skb == NULL)
> > > > > > +continue;
> > > > > > /* Pre-validation - e.g., early fallback */
> > > > > > ret = mptcp_prevalidate_skb(sk, skb);
> > > > > > if (ret < 0)
> > > > > > @@ -1108,13 +1172,11 @@ int mptcp_check_req(struct
> > > > > > sk_buff *skb, struct net *net)
> > > > > > if (!meta_sk)
> > > > > > return 0;
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> > > > > > -
> > > > > > bh_lock_sock_nested(meta_sk);
> > > > > > if (sock_owned_by_user(meta_sk)) {
> > > > > > -skb->sk = meta_sk;
> > > > > > +skb->sk = (struct sock *)0xFEE1DEAD;
> > > > > > if (unlikely(sk_add_backlog(meta_sk, skb,
> > > > > > - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> > > > > > +meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> > > > > > bh_unlock_sock(meta_sk);
> > > > > > NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> > > > > > sock_put(meta_sk); /* Taken by mptcp_search_req */
> > > > > > @@ -1122,10 +1184,14 @@ int mptcp_check_req(struct
> > > > > > sk_buff *skb, struct net *net)
> > > > > > return 1;
> > > > > > }
> > > > > > } else if (skb->protocol == htons(ETH_P_IP)) {
> > > > > > -tcp_v4_do_rcv(meta_sk, skb);
> > > > > > +/*
> > > > > > +* call old mptcp_v4_do_rcv
> > > > > > +*/
> > > > > > +mptcp_v4_process_join_req(meta_sk, skb);
> > > > > > #if IS_ENABLED(CONFIG_IPV6)
> > > > > > } else { /* IPv6 */
> > > > > > -tcp_v6_do_rcv(meta_sk, skb);
> > > > > > +WARN_ON(1);
> > > > > > +//mptcp_v6_handle_join_req(meta_sk, skb);
> > > > > > #endif /* CONFIG_IPV6 */
> > > > > > }
> > > > > > bh_unlock_sock(meta_sk);
> > > > > > @@ -1222,7 +1288,7 @@ int mptcp_lookup_join(struct
> > > > > > sk_buff *skb, struct inet_timewait_sock *tw)
> > > > > > inet_twsk_put(tw);
> > > > > > }
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> > > > > > +skb->mptcp_flags |= MPTCPHDR_JOIN;
> > > > > > /* OK, this is a new syn/join, let's create a new open request and
> > > > > > * send syn+ack
> > > > > > */
> > > > > > @@ -1279,7 +1345,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
> > > > > > return -1;
> > > > > > }
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> > > > > > +//TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> > > > > > /* OK, this is a new syn/join, let's create a new open request and
> > > > > > * send syn+ack
> > > > > > @@ -1303,7 +1369,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
> > > > > > }
> > > > > > if (sock_owned_by_user(meta_sk)) {
> > > > > > -skb->sk = meta_sk;
> > > > > > +skb->sk = (struct sock *)0xFEE1DEAD; //skb->sk = meta_sk;
> > > > > > if (unlikely(sk_add_backlog(meta_sk, skb,
> > > > > > meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf)))
> > > > > > NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> > > > > > @@ -1319,10 +1385,12 @@ int mptcp_do_join_short(struct sk_buff *skb,
> > > > > > */
> > > > > > skb_get(skb);
> > > > > > if (skb->protocol == htons(ETH_P_IP)) {
> > > > > > -tcp_v4_do_rcv(meta_sk, skb);
> > > > > > +//tcp_v4_do_rcv(meta_sk, skb);
> > > > > > +mptcp_v4_process_join_req(meta_sk, skb);
> > > > > > #if IS_ENABLED(CONFIG_IPV6)
> > > > > > } else { /* IPv6 */
> > > > > > -tcp_v6_do_rcv(meta_sk, skb);
> > > > > > +//mptcp_v6_process_join_req(meta_sk, skb);
> > > > > > +//tcp_v6_do_rcv(meta_sk, skb);
> > > > > > #endif /* CONFIG_IPV6 */
> > > > > > }
> > > > > > }
> > > > > > @@ -1461,7 +1529,6 @@ static void mptcp_data_ack(struct
> > > > > > sock *sk, const struct sk_buff *skb)
> > > > > > {
> > > > > > struct sock *meta_sk = mptcp_meta_sk(sk);
> > > > > > struct tcp_sock *meta_tp = tcp_sk(meta_sk), *tp = tcp_sk(sk);
> > > > > > -struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> > > > > > u32 prior_snd_una = meta_tp->snd_una;
> > > > > > int prior_packets;
> > > > > > u32 nwin, data_ack, data_seq;
> > > > > > @@ -1481,7 +1548,7 @@ static void mptcp_data_ack(struct
> > > > > > sock *sk, const struct sk_buff *skb)
> > > > > > /* If we are in infinite mapping mode, rx_opt.data_ack has been
> > > > > > * set by mptcp_clean_rtx_infinite.
> > > > > > */
> > > > > > -if (!(tcb->mptcp_flags & MPTCPHDR_ACK) &&
> > > > > > !tp->mpcb->infinite_mapping_snd)
> > > > > > +if (!(skb->mptcp_flags & MPTCPHDR_ACK) &&
> > > > > > !tp->mpcb->infinite_mapping_snd)
> > > > > > goto exit;
> > > > > > data_ack = tp->mptcp->rx_opt.data_ack;
> > > > > > @@ -1647,10 +1714,11 @@ static inline bool
> > > > > > is_valid_addropt_opsize(u8 mptcp_ver,
> > > > > > void mptcp_parse_options(const uint8_t *ptr, int opsize,
> > > > > > struct mptcp_options_received *mopt,
> > > > > > -const struct sk_buff *skb,
> > > > > > +struct sk_buff *skb,
> > > > > > struct tcp_sock *tp)
> > > > > > {
> > > > > > const struct mptcp_option *mp_opt = (struct mptcp_option *)ptr;
> > > > > > +struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> > > > > > /* If the socket is mp-capable we would have a mopt. */
> > > > > > if (!mopt)
> > > > > > @@ -1757,7 +1825,7 @@ void mptcp_parse_options(const
> > > > > > uint8_t *ptr, int opsize,
> > > > > > ptr += 4;
> > > > > > if (mdss->A) {
> > > > > > -tcb->mptcp_flags |= MPTCPHDR_ACK;
> > > > > > +skb->mptcp_flags |= MPTCPHDR_ACK;
> > > > > > if (mdss->a) {
> > > > > > mopt->data_ack = (u32) get_unaligned_be64(ptr);
> > > > > > @@ -1768,13 +1836,13 @@ void mptcp_parse_options(const
> > > > > > uint8_t *ptr, int opsize,
> > > > > > }
> > > > > > }
> > > > > > -tcb->dss_off = (ptr - skb_transport_header(skb));
> > > > > > +skb->mptcp_dss_off = (ptr - skb_transport_header(skb));
> > > > > > if (mdss->M) {
> > > > > > if (mdss->m) {
> > > > > > u64 data_seq64 = get_unaligned_be64(ptr);
> > > > > > -tcb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
> > > > > > +skb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
> > > > > > mopt->data_seq = (u32) data_seq64;
> > > > > > ptr += 12; /* 64-bit dseq + subseq */
> > > > > > @@ -1784,15 +1852,16 @@ void mptcp_parse_options(const
> > > > > > uint8_t *ptr, int opsize,
> > > > > > }
> > > > > > mopt->data_len = get_unaligned_be16(ptr);
> > > > > > -tcb->mptcp_flags |= MPTCPHDR_SEQ;
> > > > > > +skb->mptcp_flags |= MPTCPHDR_SEQ;
> > > > > > /* Is a check-sum present? */
> > > > > > -if (opsize == mptcp_sub_len_dss(mdss, 1))
> > > > > > -tcb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
> > > > > > +if (opsize == mptcp_sub_len_dss(mdss, 1)) {
> > > > > > +skb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
> > > > > > +}
> > > > > > /* DATA_FIN only possible with DSS-mapping */
> > > > > > if (mdss->F)
> > > > > > -tcb->mptcp_flags |= MPTCPHDR_FIN;
> > > > > > +skb->mptcp_flags |= MPTCPHDR_FIN;
> > > > > > }
> > > > > > break;
> > > > > > @@ -1907,8 +1976,9 @@ void tcp_parse_mptcp_options(const
> > > > > > struct sk_buff *skb,
> > > > > > return;
> > > > > > if (opsize > length)
> > > > > > return;/* don't parse partial options */
> > > > > > -if (opcode == TCPOPT_MPTCP)
> > > > > > +if (opcode == TCPOPT_MPTCP) {
> > > > > > mptcp_parse_options(ptr - 2, opsize, mopt, skb, NULL);
> > > > > > +}
> > > > > > }
> > > > > > ptr += opsize - 2;
> > > > > > length -= opsize;
> > > > > > @@ -2168,6 +2238,8 @@ bool mptcp_handle_options(struct
> > > > > > sock *sk, const struct tcphdr *th,
> > > > > > struct tcp_sock *tp = tcp_sk(sk);
> > > > > > struct mptcp_options_received *mopt = &tp->mptcp->rx_opt;
> > > > > > +BUG_ON(sk == mptcp_meta_sk(sk));
> > > > > > +
> > > > > > if (tp->mpcb->infinite_mapping_rcv || tp->mpcb->infinite_mapping_snd)
> > > > > > return false;
> > > > > > @@ -2185,7 +2257,7 @@ bool mptcp_handle_options(struct
> > > > > > sock *sk, const struct tcphdr *th,
> > > > > > * receiver MUST close the subflow with a RST as it is
> > > > > > considered broken.
> > > > > > */
> > > > > > if (mptcp_is_data_seq(skb) && tp->mpcb->dss_csum &&
> > > > > > - !(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
> > > > > > + !(skb->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
> > > > > > mptcp_send_reset(sk);
> > > > > > return true;
> > > > > > }
> > > > > > @@ -2330,6 +2402,7 @@ int
> > > > > > mptcp_rcv_synsent_state_process(struct sock *sk, struct
> > > > > > sock **skptr,
> > > > > > /* Set this flag in order to postpone data sending
> > > > > > * until the 4th ack arrives.
> > > > > > */
> > > > > > +printk("mptcp_rcv_synsent_state_process pre_established set \n");
> > > > > > tp->mptcp->pre_established = 1;
> > > > > > tp->mptcp->rcv_low_prio = tp->mptcp->rx_opt.low_prio;
> > > > > > diff --git a/net/mptcp/mptcp_ipv4.c b/net/mptcp/mptcp_ipv4.c
> > > > > > index a147b20..3e60ab5 100644
> > > > > > --- a/net/mptcp/mptcp_ipv4.c
> > > > > > +++ b/net/mptcp/mptcp_ipv4.c
> > > > > > @@ -180,45 +180,12 @@ static int
> > > > > > mptcp_v4_join_request(struct sock *meta_sk, struct
> > > > > > sk_buff *skb)
> > > > > > }
> > > > > > /* We only process join requests here. (either the SYN
> > > > > > or the final ACK) */
> > > > > > -int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
> > > > > > +int mptcp_v4_process_join_req(struct sock *meta_sk,
> > > > > > struct sk_buff *skb)
> > > > > > {
> > > > > > const struct mptcp_cb *mpcb = tcp_sk(meta_sk)->mpcb;
> > > > > > struct sock *child, *rsk = NULL;
> > > > > > int ret;
> > > > > > -if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
> > > > > > -struct tcphdr *th = tcp_hdr(skb);
> > > > > > -const struct iphdr *iph = ip_hdr(skb);
> > > > > > -struct sock *sk;
> > > > > > -
> > > > > > -sk = inet_lookup_established(sock_net(meta_sk), &tcp_hashinfo,
> > > > > > - iph->saddr, th->source, iph->daddr,
> > > > > > - th->dest, inet_iif(skb));
> > > > > > -
> > > > > > -if (!sk) {
> > > > > > -kfree_skb(skb);
> > > > > > -return 0;
> > > > > > -}
> > > > > > -if (is_meta_sk(sk)) {
> > > > > > -WARN("%s Did not find a sub-sk - did found the meta!\n", __func__);
> > > > > > -kfree_skb(skb);
> > > > > > -sock_put(sk);
> > > > > > -return 0;
> > > > > > -}
> > > > > > -
> > > > > > -if (sk->sk_state == TCP_TIME_WAIT) {
> > > > > > -inet_twsk_put(inet_twsk(sk));
> > > > > > -kfree_skb(skb);
> > > > > > -return 0;
> > > > > > -}
> > > > > > -
> > > > > > -ret = tcp_v4_do_rcv(sk, skb);
> > > > > > -sock_put(sk);
> > > > > > -
> > > > > > -return ret;
> > > > > > -}
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags = 0;
> > > > > > -
> > > > > > /* Has been removed from the tk-table. Thus, no new subflows.
> > > > > > *
> > > > > > * Check for close-state is necessary, because we may have been closed
> > > > > > diff --git a/net/mptcp/mptcp_ipv6.c b/net/mptcp/mptcp_ipv6.c
> > > > > > index 0de953d..1959d01 100644
> > > > > > --- a/net/mptcp/mptcp_ipv6.c
> > > > > > +++ b/net/mptcp/mptcp_ipv6.c
> > > > > > @@ -199,7 +199,7 @@ int mptcp_v6_do_rcv(struct sock
> > > > > > *meta_sk, struct sk_buff *skb)
> > > > > > struct sock *child, *rsk = NULL;
> > > > > > int ret;
> > > > > > -if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
> > > > > > +if (!(skb->mptcp_flags & MPTCPHDR_JOIN)) {
> > > > > > struct tcphdr *th = tcp_hdr(skb);
> > > > > > const struct ipv6hdr *ip6h = ipv6_hdr(skb);
> > > > > > struct sock *sk;
> > > > > > @@ -232,7 +232,7 @@ int mptcp_v6_do_rcv(struct sock
> > > > > > *meta_sk, struct sk_buff *skb)
> > > > > > return ret;
> > > > > > }
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags = 0;
> > > > > > +skb->mptcp_flags = 0;
> > > > > > /* Has been removed from the tk-table. Thus, no new subflows.
> > > > > > *
> > > > > > diff --git a/net/mptcp/mptcp_output.c b/net/mptcp/mptcp_output.c
> > > > > > index 691ef6f..e7d340d 100644
> > > > > > --- a/net/mptcp/mptcp_output.c
> > > > > > +++ b/net/mptcp/mptcp_output.c
> > > > > > @@ -59,39 +59,17 @@ EXPORT_SYMBOL(mptcp_sub_len_remove_addr_align);
> > > > > > */
> > > > > > static bool mptcp_reconstruct_mapping(struct sk_buff *skb)
> > > > > > {
> > > > > > -const struct mp_dss *mpdss = (struct mp_dss *)TCP_SKB_CB(skb)->dss;
> > > > > > -u32 *p32;
> > > > > > -u16 *p16;
> > > > > > -
> > > > > > if (!mptcp_is_data_seq(skb))
> > > > > > return false;
> > > > > > -if (!mpdss->M)
> > > > > > -return false;
> > > > > > -
> > > > > > -/* Move the pointer to the data-seq */
> > > > > > -p32 = (u32 *)mpdss;
> > > > > > -p32++;
> > > > > > -if (mpdss->A) {
> > > > > > -p32++;
> > > > > > -if (mpdss->a)
> > > > > > -p32++;
> > > > > > -}
> > > > > > -
> > > > > > -TCP_SKB_CB(skb)->seq = ntohl(*p32);
> > > > > > -
> > > > > > -/* Get the data_len to calculate the end_data_seq */
> > > > > > -p32++;
> > > > > > -p32++;
> > > > > > -p16 = (u16 *)p32;
> > > > > > -TCP_SKB_CB(skb)->end_seq = ntohs(*p16) + TCP_SKB_CB(skb)->seq;
> > > > > > +TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->mptcp_data_seq;
> > > > > > return true;
> > > > > > }
> > > > > > static bool mptcp_is_reinjected(const struct sk_buff *skb)
> > > > > > {
> > > > > > -return TCP_SKB_CB(skb)->mptcp_flags & MPTCP_REINJECT;
> > > > > > +return skb->mptcp_flags & MPTCP_REINJECT;
> > > > > > }
> > > > > > static void mptcp_find_and_set_pathmask(const struct
> > > > > > sock *meta_sk, struct sk_buff *skb)
> > > > > > @@ -105,7 +83,7 @@ static void
> > > > > > mptcp_find_and_set_pathmask(const struct sock *meta_sk,
> > > > > > struct sk_bu
> > > > > > break;
> > > > > > if (TCP_SKB_CB(skb_it)->seq == TCP_SKB_CB(skb)->seq) {
> > > > > > -TCP_SKB_CB(skb)->path_mask = TCP_SKB_CB(skb_it)->path_mask;
> > > > > > +TCP_SKB_CB(skb)->mptcp_path_mask =
> > > > > > TCP_SKB_CB(skb_it)->mptcp_path_mask;
> > > > > > break;
> > > > > > }
> > > > > > }
> > > > > > @@ -180,9 +158,9 @@ static void
> > > > > > __mptcp_reinject_data(struct sk_buff *orig_skb, struct
> > > > > > sock *meta_sk
> > > > > > }
> > > > > > /* Segment goes back to the MPTCP-layer. So, we need to zero the
> > > > > > -* path_mask/dss.
> > > > > > +* path_mask.
> > > > > > */
> > > > > > -memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
> > > > > > +TCP_SKB_CB(skb)->mptcp_path_mask = 0;
> > > > > > /* We need to find out the path-mask from the meta-write-queue
> > > > > > * to properly select a subflow.
> > > > > > @@ -272,14 +250,14 @@ void mptcp_reinject_data(struct
> > > > > > sock *sk, int clone_it)
> > > > > > if (mptcp_is_reinjected(skb_it))
> > > > > > continue;
> > > > > > -tcb->mptcp_flags |= MPTCP_REINJECT;
> > > > > > +skb_it->mptcp_flags |= MPTCP_REINJECT;
> > > > > > __mptcp_reinject_data(skb_it, meta_sk, sk, clone_it);
> > > > > > }
> > > > > > skb_it = tcp_write_queue_tail(meta_sk);
> > > > > > /* If sk has sent the empty data-fin, we have to reinject it too. */
> > > > > > if (skb_it && mptcp_is_data_fin(skb_it) && skb_it->len == 0 &&
> > > > > > - TCP_SKB_CB(skb_it)->path_mask &
> > > > > > mptcp_pi_to_flag(tp->mptcp->path_index)) {
> > > > > > + TCP_SKB_CB(skb_it)->mptcp_path_mask &
> > > > > > mptcp_pi_to_flag(tp->mptcp->path_index)) {
> > > > > > __mptcp_reinject_data(skb_it, meta_sk, NULL, 1);
> > > > > > }
> > > > > > @@ -319,25 +297,43 @@ combine:
> > > > > > }
> > > > > > }
> > > > > > -static int mptcp_write_dss_mapping(const struct
> > > > > > tcp_sock *tp, const struct sk_buff *skb,
> > > > > > - __be32 *ptr)
> > > > > > +/*
> > > > > > + * RFC6824 states that once a particular subflow
> > > > > > mapping has been sent
> > > > > > + * out it must never be changed. However, packets may be split while
> > > > > > + * they are in the retransmission queue (due to SACK or
> > > > > > ACKs) and that
> > > > > > + * arguably means that we would change the mapping
> > > > > > (e.g. it splits it,
> > > > > > + * our sends out a subset of the initial mapping).
> > > > > > + *
> > > > > > + * Furthermore, the skb checksum is not always
> > > > > > preserved across splits
> > > > > > + * (e.g. mptcp_fragment) which would mean that we need to recompute
> > > > > > + * the DSS checksum in this case.
> > > > > > + *
> > > > > > + * To avoid this we save the initial DSS mapping which allows us to
> > > > > > + * send the same DSS mapping even for fragmented retransmits.
> > > > > > + */
> > > > > > +
> > > > > > +static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
> > > > > > + const struct sk_buff *skb, __be32 *ptr)
> > > > > > {
> > > > > > const struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> > > > > > -__be32 *start = ptr;
> > > > > > __u16 data_len;
> > > > > > -*ptr++ = htonl(tcb->seq); /* data_seq */
> > > > > > +*ptr++ = htonl(tcb->mptcp_data_seq); /* data_seq */
> > > > > > /* If it's a non-data DATA_FIN, we set subseq to 0 (draft v7) */
> > > > > > if (mptcp_is_data_fin(skb) && skb->len == 0)
> > > > > > *ptr++ = 0; /* subseq */
> > > > > > else
> > > > > > -*ptr++ = htonl(tp->write_seq - tp->mptcp->snt_isn); /* subseq */
> > > > > > +*ptr++ = htonl(tcb->seq - tp->mptcp->snt_isn); /* subseq */
> > > > > > -if (tcb->mptcp_flags & MPTCPHDR_INF)
> > > > > > +if (skb->mptcp_flags & MPTCPHDR_INF)
> > > > > > data_len = 0;
> > > > > > -else
> > > > > > +else {
> > > > > > data_len = tcb->end_seq - tcb->seq;
> > > > > > +/* mptcp_entail_skb adds one for FIN */
> > > > > > +if (tcb->tcp_flags & TCPHDR_FIN)
> > > > > > +data_len -= 1;
> > > > > > +}
> > > > > > if (tp->mpcb->dss_csum && data_len) {
> > > > > > __be16 *p16 = (__be16 *)ptr;
> > > > > > @@ -356,11 +352,11 @@ static int
> > > > > > mptcp_write_dss_mapping(const struct tcp_sock *tp, const
> > > > > > struct sk_bu
> > > > > > (TCPOPT_NOP));
> > > > > > }
> > > > > > -return ptr - start;
> > > > > > +return mptcp_dss_len/sizeof(*ptr);
> > > > > > }
> > > > > > -static int mptcp_write_dss_data_ack(const struct
> > > > > > tcp_sock *tp, const struct sk_buff *skb,
> > > > > > - __be32 *ptr)
> > > > > > +static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
> > > > > > + const struct sk_buff *skb, __be32 *ptr)
> > > > > > {
> > > > > > struct mp_dss *mdss = (struct mp_dss *)ptr;
> > > > > > __be32 *start = ptr;
> > > > > > @@ -377,54 +373,12 @@ static int
> > > > > > mptcp_write_dss_data_ack(const struct tcp_sock *tp,
> > > > > > const struct sk_b
> > > > > > mdss->len = mptcp_sub_len_dss(mdss, tp->mpcb->dss_csum);
> > > > > > ptr++;
> > > > > > +/* data_ack */
> > > > > > *ptr++ = htonl(mptcp_meta_tp(tp)->rcv_nxt);
> > > > > > return ptr - start;
> > > > > > }
> > > > > > -/* RFC6824 states that once a particular subflow
> > > > > > mapping has been sent
> > > > > > - * out it must never be changed. However, packets may be split while
> > > > > > - * they are in the retransmission queue (due to SACK or
> > > > > > ACKs) and that
> > > > > > - * arguably means that we would change the mapping
> > > > > > (e.g. it splits it,
> > > > > > - * our sends out a subset of the initial mapping).
> > > > > > - *
> > > > > > - * Furthermore, the skb checksum is not always
> > > > > > preserved across splits
> > > > > > - * (e.g. mptcp_fragment) which would mean that we need to recompute
> > > > > > - * the DSS checksum in this case.
> > > > > > - *
> > > > > > - * To avoid this we save the initial DSS mapping which allows us to
> > > > > > - * send the same DSS mapping even for fragmented retransmits.
> > > > > > - */
> > > > > > -static void mptcp_save_dss_data_seq(const struct
> > > > > > tcp_sock *tp, struct sk_buff *skb)
> > > > > > -{
> > > > > > -struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> > > > > > -__be32 *ptr = (__be32 *)tcb->dss;
> > > > > > -
> > > > > > -tcb->mptcp_flags |= MPTCPHDR_SEQ;
> > > > > > -
> > > > > > -ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
> > > > > > -ptr += mptcp_write_dss_mapping(tp, skb, ptr);
> > > > > > -}
> > > > > > -
> > > > > > -/* Write the saved DSS mapping to the header */
> > > > > > -static int mptcp_write_dss_data_seq(const struct
> > > > > > tcp_sock *tp, struct sk_buff *skb,
> > > > > > - __be32 *ptr)
> > > > > > -{
> > > > > > -__be32 *start = ptr;
> > > > > > -
> > > > > > -memcpy(ptr, TCP_SKB_CB(skb)->dss, mptcp_dss_len);
> > > > > > -
> > > > > > -/* update the data_ack */
> > > > > > -start[1] = htonl(mptcp_meta_tp(tp)->rcv_nxt);
> > > > > > -
> > > > > > -/* dss is in a union with inet_skb_parm and
> > > > > > -* the IP layer expects zeroed IPCB fields.
> > > > > > -*/
> > > > > > -memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
> > > > > > -
> > > > > > -return mptcp_dss_len/sizeof(*ptr);
> > > > > > -}
> > > > > > -
> > > > > > static bool mptcp_skb_entail(struct sock *sk, struct
> > > > > > sk_buff *skb, int reinject)
> > > > > > {
> > > > > > struct tcp_sock *tp = tcp_sk(sk);
> > > > > > @@ -434,7 +388,7 @@ static bool mptcp_skb_entail(struct
> > > > > > sock *sk, struct sk_buff *skb, int reinject)
> > > > > > struct sk_buff *subskb = NULL;
> > > > > > if (!reinject)
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags |= (mpcb->snd_hiseq_index ?
> > > > > > +skb->mptcp_flags |= (mpcb->snd_hiseq_index ?
> > > > > > MPTCPHDR_SEQ64_INDEX : 0);
> > > > > > subskb = pskb_copy_for_clone(skb, GFP_ATOMIC);
> > > > > > @@ -447,7 +401,7 @@ static bool mptcp_skb_entail(struct
> > > > > > sock *sk, struct sk_buff *skb, int reinject)
> > > > > > */
> > > > > > tcp_skb_pcount_set(subskb, 0);
> > > > > > -TCP_SKB_CB(skb)->path_mask |=
> > > > > > mptcp_pi_to_flag(tp->mptcp->path_index);
> > > > > > +TCP_SKB_CB(skb)->mptcp_path_mask |=
> > > > > > mptcp_pi_to_flag(tp->mptcp->path_index);
> > > > > > if (!(sk->sk_route_caps & NETIF_F_ALL_CSUM) &&
> > > > > > skb->ip_summed == CHECKSUM_PARTIAL) {
> > > > > > @@ -463,13 +417,14 @@ static bool
> > > > > > mptcp_skb_entail(struct sock *sk, struct sk_buff *skb,
> > > > > > int reinject)
> > > > > > tp->mptcp->fully_established = 1;
> > > > > > tp->mpcb->infinite_mapping_snd = 1;
> > > > > > tp->mptcp->infinite_cutoff_seq = tp->write_seq;
> > > > > > -tcb->mptcp_flags |= MPTCPHDR_INF;
> > > > > > +skb->mptcp_flags |= MPTCPHDR_INF;
> > > > > > }
> > > > > > if (mptcp_is_data_fin(subskb))
> > > > > > mptcp_combine_dfin(subskb, meta_sk, sk);
> > > > > > -mptcp_save_dss_data_seq(tp, subskb);
> > > > > > +subskb->mptcp_flags |= MPTCPHDR_SEQ;
> > > > > > +tcb->mptcp_data_seq = tcb->seq;
> > > > > > tcb->seq = tp->write_seq;
> > > > > > @@ -536,10 +491,10 @@ static int mptcp_fragment(struct
> > > > > > sock *meta_sk, struct sk_buff *skb, u32 len,
> > > > > > buff = skb->next;
> > > > > > -flags = TCP_SKB_CB(skb)->mptcp_flags;
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags = flags & ~(MPTCPHDR_FIN);
> > > > > > -TCP_SKB_CB(buff)->mptcp_flags = flags;
> > > > > > -TCP_SKB_CB(buff)->path_mask = TCP_SKB_CB(skb)->path_mask;
> > > > > > +flags = skb->mptcp_flags;
> > > > > > +skb->mptcp_flags = flags & ~(MPTCPHDR_FIN);
> > > > > > +buff->mptcp_flags = flags;
> > > > > > +TCP_SKB_CB(buff)->mptcp_path_mask = TCP_SKB_CB(skb)->mptcp_path_mask;
> > > > > > /* If reinject == 1, the buff will be added to the reinject
> > > > > > * queue, which is currently not part of memory accounting. So
> > > > > > @@ -927,8 +882,9 @@ void
> > > > > > mptcp_established_options(struct sock *sk, struct
> > > > > > sk_buff *skb,
> > > > > > * It does not make sense to check for the options, because when the
> > > > > > * segment gets sent, another subflow will be chosen.
> > > > > > */
> > > > > > -if (!skb && is_meta_sk(sk))
> > > > > > +if (!skb && is_meta_sk(sk)) {
> > > > > > return;
> > > > > > +}
> > > > > > /* In fallback mp_fail-mode, we have to repeat it until the fallback
> > > > > > * has been done by the sender
> > > > > > @@ -967,10 +923,11 @@ void
> > > > > > mptcp_established_options(struct sock *sk, struct
> > > > > > sk_buff *skb,
> > > > > > if (unlikely(mpcb->infinite_mapping_snd) &&
> > > > > > ((mpcb->send_infinite_mapping && tcb &&
> > > > > > mptcp_is_data_seq(skb) &&
> > > > > > - !(tcb->mptcp_flags & MPTCPHDR_INF) &&
> > > > > > + !(skb->mptcp_flags & MPTCPHDR_INF) &&
> > > > > > !before(tcb->seq, tp->mptcp->infinite_cutoff_seq)) ||
> > > > > > - !mpcb->send_infinite_mapping))
> > > > > > + !mpcb->send_infinite_mapping)) {
> > > > > > return;
> > > > > > +}
> > > > > > if (unlikely(tp->mptcp->include_mpc)) {
> > > > > > opts->options |= OPTION_MPTCP;
> > > > > > @@ -995,9 +952,11 @@ void
> > > > > > mptcp_established_options(struct sock *sk, struct
> > > > > > sk_buff *skb,
> > > > > > mpcb->mptcp_ver >= MPTCP_VERSION_1 && skb &&
> > > > > > !mptcp_is_data_seq(skb)) {
> > > > > > mpcb->pm_ops->addr_signal(sk, size, opts, skb);
> > > > > > -if (opts->add_addr_v6)
> > > > > > +if (opts->add_addr_v6) {
> > > > > > +
> > > > > > /* Skip subsequent options */
> > > > > > return;
> > > > > > +}
> > > > > > }
> > > > > > if (!tp->mptcp->include_mpc && !tp->mptcp->pre_established) {
> > > > > > @@ -1197,10 +1156,11 @@ void mptcp_options_write(__be32
> > > > > > *ptr, struct tcp_sock *tp,
> > > > > > }
> > > > > > if (OPTION_DATA_ACK & opts->mptcp_options) {
> > > > > > -if (!mptcp_is_data_seq(skb))
> > > > > > -ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
> > > > > > -else
> > > > > > -ptr += mptcp_write_dss_data_seq(tp, skb, ptr);
> > > > > > +ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
> > > > > > +if (mptcp_is_data_seq(skb)) {
> > > > > > +ptr += mptcp_write_dss_mapping(tp, skb, ptr);
> > > > > > +}
> > > > > > +skb->dev = NULL;
> > > > > > }
> > > > > > if (unlikely(OPTION_MP_PRIO & opts->mptcp_options)) {
> > > > > > struct mp_prio *mpprio = (struct mp_prio *)ptr;
> > > > > > @@ -1233,7 +1193,7 @@ void mptcp_send_fin(struct sock *meta_sk)
> > > > > > mss_now = mptcp_current_mss(meta_sk);
> > > > > > if (tcp_send_head(meta_sk) != NULL) {
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
> > > > > > +skb->mptcp_flags |= MPTCPHDR_FIN;
> > > > > > TCP_SKB_CB(skb)->end_seq++;
> > > > > > meta_tp->write_seq++;
> > > > > > } else {
> > > > > > @@ -1250,7 +1210,7 @@ void mptcp_send_fin(struct sock *meta_sk)
> > > > > > tcp_init_nondata_skb(skb, meta_tp->write_seq, TCPHDR_ACK);
> > > > > > TCP_SKB_CB(skb)->end_seq++;
> > > > > > -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
> > > > > > +skb->mptcp_flags |= MPTCPHDR_FIN;
> > > > > > tcp_queue_skb(meta_sk, skb);
> > > > > > }
> > > > > > __tcp_push_pending_frames(meta_sk, mss_now, TCP_NAGLE_OFF);
> > > > > > diff --git a/net/mptcp/mptcp_redundant.c b/net/mptcp/mptcp_redundant.c
> > > > > > index 8fa2dba..37a13f4 100644
> > > > > > --- a/net/mptcp/mptcp_redundant.c
> > > > > > +++ b/net/mptcp/mptcp_redundant.c
> > > > > > @@ -72,10 +72,10 @@ static bool
> > > > > > redsched_use_subflow(struct sock *meta_sk,
> > > > > > if (!skb || !mptcp_is_available((struct sock *)tp, skb, false))
> > > > > > return false;
> > > > > > -if (TCP_SKB_CB(skb)->path_mask != 0)
> > > > > > +if (TCP_SKB_CB(skb)->mptcp_path_mask != 0)
> > > > > > return subflow_is_active(tp);
> > > > > > -if (TCP_SKB_CB(skb)->path_mask == 0) {
> > > > > > +if (TCP_SKB_CB(skb)->mptcp_path_mask == 0) {
> > > > > > if (active_valid_sks == -1)
> > > > > > active_valid_sks = redsched_get_active_valid_sks(meta_sk);
> > > > > > @@ -209,7 +209,7 @@ static struct sk_buff
> > > > > > *redundant_next_segment(struct sock *meta_sk,
> > > > > > cb_data->next_subflow = tp->mptcp->next;
> > > > > > *subsk = (struct sock *)tp;
> > > > > > -if (TCP_SKB_CB(skb)->path_mask)
> > > > > > +if (TCP_SKB_CB(skb)->mptcp_path_mask)
> > > > > > *reinject = -1;
> > > > > > return skb;
> > > > > > }
> > > > > > diff --git a/net/mptcp/mptcp_rr.c b/net/mptcp/mptcp_rr.c
> > > > > > index 8910ba9..83837f2 100644
> > > > > > --- a/net/mptcp/mptcp_rr.c
> > > > > > +++ b/net/mptcp/mptcp_rr.c
> > > > > > @@ -93,7 +93,7 @@ static int
> > > > > > mptcp_rr_dont_reinject_skb(const struct tcp_sock *tp,
> > > > > > const struct sk
> > > > > > */
> > > > > > return skb &&
> > > > > > /* Has the skb already been enqueued into this subsocket? */
> > > > > > -mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
> > > > > > +mptcp_pi_to_flag(tp->mptcp->path_index) &
> > > > > > TCP_SKB_CB(skb)->mptcp_path_mask;
> > > > > > }
> > > > > > /* We just look for any subflow that is available */
> > > > > > @@ -136,7 +136,7 @@ static struct sock
> > > > > > *rr_get_available_subflow(struct sock *meta_sk,
> > > > > > * chance again by restarting its pathmask.
> > > > > > */
> > > > > > if (skb)
> > > > > > -TCP_SKB_CB(skb)->path_mask = 0;
> > > > > > +TCP_SKB_CB(skb)->mptcp_path_mask = 0;
> > > > > > sk = backupsk;
> > > > > > }
> > > > > > diff --git a/net/mptcp/mptcp_sched.c b/net/mptcp/mptcp_sched.c
> > > > > > index 54408ff..5cbbf91 100644
> > > > > > --- a/net/mptcp/mptcp_sched.c
> > > > > > +++ b/net/mptcp/mptcp_sched.c
> > > > > > @@ -118,7 +118,7 @@ static int
> > > > > > mptcp_dont_reinject_skb(const struct tcp_sock *tp, const
> > > > > > struct sk_bu
> > > > > > */
> > > > > > return skb &&
> > > > > > /* Has the skb already been enqueued into this subsocket? */
> > > > > > -mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
> > > > > > +mptcp_pi_to_flag(tp->mptcp->path_index) &
> > > > > > TCP_SKB_CB(skb)->mptcp_path_mask;
> > > > > > }
> > > > > > bool subflow_is_backup(const struct tcp_sock *tp)
> > > > > > @@ -261,7 +261,7 @@ struct sock
> > > > > > *get_available_subflow(struct sock *meta_sk, struct
> > > > > > sk_buff *skb,
> > > > > > * the skb passed through all the available active and backups
> > > > > > * sks, so clean the path mask
> > > > > > */
> > > > > > -TCP_SKB_CB(skb)->path_mask = 0;
> > > > > > +TCP_SKB_CB(skb)->mptcp_path_mask = 0;
> > > > > > return sk;
> > > > > > }
> > > > > > EXPORT_SYMBOL_GPL(get_available_subflow);
> > > > > > @@ -298,7 +298,7 @@ static struct sk_buff
> > > > > > *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
> > > > > > /* Half the cwnd of the slow flow */
> > > > > > mptcp_for_each_tp(tp->mpcb, tp_it) {
> > > > > > if (tp_it != tp &&
> > > > > > - TCP_SKB_CB(skb_head)->path_mask &
> > > > > > mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> > > > > > + TCP_SKB_CB(skb_head)->mptcp_path_mask &
> > > > > > mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> > > > > > if (tp->srtt_us < tp_it->srtt_us && inet_csk((struct
> > > > > > sock *)tp_it)->icsk_ca_state == TCP_CA_Open) {
> > > > > > u32 prior_cwnd = tp_it->snd_cwnd;
> > > > > > @@ -317,11 +317,11 @@ static struct sk_buff
> > > > > > *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
> > > > > > retrans:
> > > > > > /* Segment not yet injected into this path? Take it!!! */
> > > > > > -if (!(TCP_SKB_CB(skb_head)->path_mask &
> > > > > > mptcp_pi_to_flag(tp->mptcp->path_index))) {
> > > > > > +if (!(TCP_SKB_CB(skb_head)->mptcp_path_mask &
> > > > > > mptcp_pi_to_flag(tp->mptcp->path_index))) {
> > > > > > bool do_retrans = false;
> > > > > > mptcp_for_each_tp(tp->mpcb, tp_it) {
> > > > > > if (tp_it != tp &&
> > > > > > - TCP_SKB_CB(skb_head)->path_mask &
> > > > > > mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> > > > > > + TCP_SKB_CB(skb_head)->mptcp_path_mask &
> > > > > > mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> > > > > > if (tp_it->snd_cwnd <= 4) {
> > > > > > do_retrans = true;
> > > > > > break;
> > > > > _______________________________________________
> > > > > mptcp mailing list
> > > > > mptcp(a)lists.01.org <mailto:mptcp(a)lists.01.org>
> > > > > https://lists.01.org/mailman/listinfo/mptcp
> > >
> >
>
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-27 23:35 Mat Martineau
0 siblings, 0 replies; 14+ messages in thread
From: Mat Martineau @ 2017-06-27 23:35 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 695 bytes --]
Rao,
On Tue, 27 Jun 2017, Rao Shoaib wrote:
> I am actually wondering how folks do code review on Linux based on the
> patch that is submitted. There is no context diff or anything else, I am
> used to very sophisticated tools.
When I'm dealing with a large patch or a lot of unfamiliar context, I
usually apply the patches to a branch in a git workspace and work from
there. I export the email (or patch set email thread) to an mbox file and
use 'git am' to apply them as regular git commits. This does still require
typing and reading reviews in an email client, but it's helpful to have my
usual set of tools for diffs and searching.
--
Mat Martineau
Intel OTC
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-27 23:22 Mat Martineau
0 siblings, 0 replies; 14+ messages in thread
From: Mat Martineau @ 2017-06-27 23:22 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 6618 bytes --]
Hi Rao,
On Mon, 26 Jun 2017, Rao Shoaib wrote:
> This patch returns tcp_skb_cb to it's original size. It also refactors
> MPTCP code so that there are no MPTCP checks in the main Rx pathi, no
> performance overheads such as cpu prodiction issues. tcp_v4_rcv() and
> tcp_v4_do_rcv() do not have any MPTCP specific checks any more, niether
> does tcp_ack(). On the Rx path MPTCP options are not parsed till the
> data is being pushed up to the meta socket (mptcp_data_ready). on the Tx
> side there is one check to add MPTCP specific options but that's it,
> that should not be that bad as for regular TCP it is a simple check, but
> it would be good to remove it..
>
> I have tested the changes with ndiffports set to 2, so join works. I
> have also tested accessing multipath-tcp.org and downloading files from
> there and also ran the speed test.
>
> The Bad:
>
> The error cases still have MPTCP checks but that should be OK as they
> are error cases. I had to use a special marker 0xFEE1DEAD for indicate a
> special case. I had to introdue a new socket specfic function. IPv6 has
> not been changed yet. I am sure I have missed some corner cases and more
> testing will reveal more issues but we just have to fix them.
>
> I would like to hear comments from the list and if this direction seems
> reasonable we can take this as the starting point, port it to latest
> Linux and share the design with the mainstream folks.
I've read the earlier messages in this thread, so I've seen Christoph's
concern about zero-length packets and your comment that more work is
needed.
The TCP option handling patch I posted earlier (I'm testing an updated
version of that before sending it out again) might help us avoid passing
unexpected zero-length packets up the stack.
My coworkers and I have some ideas for other upstream-friendly
architecture changes, but I still need to type those up for mailing list
discussion. We've done some work building up from the current net-next
kernel and will get some patches in shape for this list.
I have some comments below:
>
> Signed-off-by: Rao Shoaib <rao.shoaib(a)oracle.com>
> ---
> include/linux/skbuff.h | 8 ++-
> include/net/mptcp.h | 21 +++---
> include/net/mptcp_v4.h | 1 +
> include/net/sock.h | 12 +++-
> include/net/tcp.h | 23 +++----
> net/ipv4/af_inet.c | 4 ++
> net/ipv4/tcp_input.c | 37 ++--------
> net/ipv4/tcp_ipv4.c | 135 +++++++++++++++++++++++--------------
> net/ipv4/tcp_output.c | 1 +
> net/ipv6/af_inet6.c | 4 ++
> net/ipv6/tcp_ipv6.c | 4 --
> net/mptcp/mptcp_ctrl.c | 21 ++++++
> net/mptcp/mptcp_input.c | 131 ++++++++++++++++++++++++++++--------
> net/mptcp/mptcp_ipv4.c | 35 +---------
> net/mptcp/mptcp_ipv6.c | 4 +-
> net/mptcp/mptcp_output.c | 160 +++++++++++++++++---------------------------
> net/mptcp/mptcp_redundant.c | 6 +-
> net/mptcp/mptcp_rr.c | 4 +-
> net/mptcp/mptcp_sched.c | 10 +--
> 19 files changed, 335 insertions(+), 286 deletions(-)
>
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index f66cd5e..348cbc1 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -532,7 +532,13 @@ struct sk_buff {
> struct rb_node rbnode; /* used in netem & tcp stack */
> };
> struct sock *sk;
> - struct net_device *dev;
> + union {
> + struct net_device *dev;
> + struct {
> + __u8 mptcp_flags;
> + __u8 mptcp_dss_off;
> + };
> + };
I think the maintainers will oppose placement of protocol-specific fields
in struct sk_buff.
Recent kernels have changed this to a union between the dev pointer and a
dev_scratch integer. So far dev_scratch is only used by UDP.
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 655ecd4..cbe8ef2 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -47,6 +47,9 @@
> #include <linux/seq_file.h>
> #include <linux/memcontrol.h>
>
> +typedef int (* process_unclaimed)(struct sock *sk, struct sk_buff *skb);
> +extern process_unclaimed tcp_process_unclaimed;
> +
> extern struct inet_hashinfo tcp_hashinfo;
>
> extern struct percpu_counter tcp_orphan_count;
> @@ -581,6 +584,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
> struct request_sock *req,
> struct dst_entry *dst);
> int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
> +
> int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
> int tcp_connect(struct sock *sk);
> struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
> @@ -842,11 +846,6 @@ struct tcp_skb_cb {
> __u32 tcp_gso_segs;
> };
>
> -#ifdef CONFIG_MPTCP
> - __u8 mptcp_flags; /* flags for the MPTCP layer */
> - __u8 dss_off; /* Number of 4-byte words until
> - * seq-number */
> -#endif
> __u8 tcp_flags; /* TCP header flags. (tcp[13]) */
>
> __u8 sacked; /* State flags for SACK/FACK. */
> @@ -859,9 +858,13 @@ struct tcp_skb_cb {
> #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
> TCPCB_REPAIRED)
>
> - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
> + __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
> /* 1 byte hole */
> - __u32 ack_seq; /* Sequence number ACK'd */
> + union {
> + __u32 ack_seq; /* Sequence number ACK'd */
> + __u32 mptcp_data_seq;
ack_seq is only used on incoming packets, and mptcp_data_seq only on
outgoing?
> + __u32 mptcp_path_mask;
> + };
One architectural change we're considering is not sharing sk_buffs between
subflows, which would make mptcp_path_mask unnecessary. It would still be
necessary to track that information, just not as part of sk_buff.
>
> diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
> index 73480b9..1e7827f 100644
> --- a/net/ipv4/af_inet.c
> +++ b/net/ipv4/af_inet.c
> @@ -356,6 +356,10 @@ lookup_protocol:
> sk->sk_destruct = inet_sock_destruct;
> sk->sk_protocol = protocol;
> sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
> + sk->sk_prequeue = sk->sk_prot->prequeue;
> + if (sk->sk_prequeue == NULL) {
> + sk->sk_prequeue = sk_prequeue;
> + }
Although it differs from my personal preference, kernel coding style calls
for no braces when there's a single statement after an 'if':
https://www.kernel.org/doc/html/latest/process/coding-style.html#placing-braces-and-spaces
I noticed this several places in the patch.
--
Mat Martineau
Intel OTC
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-27 18:51 Rao Shoaib
0 siblings, 0 replies; 14+ messages in thread
From: Rao Shoaib @ 2017-06-27 18:51 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 62282 bytes --]
On 06/27/2017 10:37 AM, Christoph Paasch wrote:
> Hello Rao,
>
>> On Jun 27, 2017, at 10:22 AM, Rao Shoaib <rao.shoaib(a)oracle.com
>> <mailto:rao.shoaib(a)oracle.com>> wrote:
>>
>> Hi Christoph,
>>
>>
>> On 06/26/2017 11:27 PM, Christoph Paasch wrote:
>>> Hello Rao,
>>>
>>> can you try to give some more details on how the datapath looks like
>>> with
>>> this patch?
>>>
>>> For example, I wonder how data-acks are being processed. Because, I
>>> see in
>>> mptcp_data_ready, that you now expects skbs with len 0, upon which
>>> you end
>>> up calling mptcp_process_ack().
>>>
>>> I don't see how such zero-length skbs could end up in the
>>> receive-queue of
>>> the subflows.
>>>
>>>
>>> Thanks,
>>
>> I send every packet that is coming on an MPTCP based socket down and
>> let MPTCP deal with it. In tcp data_queue(). I also removed the
>> directive to go to the slow_path in tcp_rcv_established().
>>
>> static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
>> {
>> struct tcp_sock *tp = tcp_sk(sk);
>> int eaten = -1;
>> bool fragstolen = false;
>>
>> /*
>> * send every packet to MPTCP
>> */
>> if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq ==
>> TCP_SKB_CB(skb)->end_seq)) {
>> goto drop;
>> }
>>
>> There is only one case that I need investigate more is the following.
>> In that the he only interesting case is (len == tcp_header_len) but
>> in my unidirectional bulk data transfer tests I did not hit that
>> case. So I need to investigate more later. The last resort would be
>> to just directly go to the slow path.
>>
>> if (len <= tcp_header_len) { /* Bulk data transfer: sender */
>>
>> if (len == tcp_header_len) {
>
> The problem is, how are these zero-len packets being queued in the
> receive-queue of the socket ? I am pretty sure that TCP won't like
> having such packets in the receive-queue, which means there will be
> quite some changes needed to support this.
I don't understand why there are any changes needed to TCP, these packet
will be handled in mptcp_data_ready() and discarded, just like TCP does
with a pure ack. Please note that we only do this for MPTCP sockets not
just any TCP socket.
>
> I might be missing something here. A high-level description with some
> call-stacks of how the data-path looks like with your patch would be good.
It's actually very straight forward, normally in tcp_data_queue() a pure
ack is simply dropped as TCP state has been updated and the packet is of
no use. In case of MPTCP we force the packet to be delivered to the meta
socket queue (See the mptcp check in the if statement). When
mptcp_data_ready() processes the packet it, updates MPTCP state, frees
packets that have been acked and than throws away the packet.
If you wanted for some reason to do this with regular TCP, you could
very well as long as the socket Rx function knows how to deal these
packets.
Can you be more specific about what TCP queue will have issues because
at this point the packet is headed to the socket queue.
If you prefer a stack trace, I can instrument the kernel with WARN_ON
directive and get you one, that is the only way I know to get one in
Linux. In Solaris it would be a 2 min operation on a running system. If
there is a better way than please educate me.
> Or maybe try to split the patch in separate pieces.
That would be difficult because everything is tied together. If you
prefer I can provide you with a tar ball of the source, you can look at
it, compile and run it.
I am actually wondering how folks do code review on Linux based on the
patch that is submitted. There is no context diff or anything else, I am
used to very sophisticated tools.
>
>>
>> If there are other issues than let me know and I will work on
>> resolving them. We obviously need to run extensive tests, that brings
>> me to the question of, how does the MPTCP development team test
>> changes. We need the same tests to validate the changes.
>
> packetdrill is the best tool to reproduce specific scenarios:
> https://github.com/cpaasch/packetdrill_mptcp (tests are in there in
> example/mptcp/).
>
> And, a testing-script is at
> https://github.com/multipath-tcp/mptcp-scripts/tree/master/testing.
> It does a bunch of stress-testing (iperf, haproxy,
> apache-benchmark,...) on three machines that need to be
> inter-connected in a specific way. It's a bit tricky to setup. I have
> KVMs that I boot that have two links between each other. One is the
> client, one the router (sometimes acting as a haproxy), one is the
> server. They need tools like ab, apache, haproxy, iperf,...
Well I do not have 3 machines and my system will die if I started 3
KVM's. Let me see what I can get.
Thanks,
Rao.
>
>
> Christoph
>
>>
>> Rao.
>>
>>> Christoph
>>>
>>>
>>> On 26/06/17 - 15:34:09, Rao Shoaib wrote:
>>>> I forgot to mention two things
>>>>
>>>> 1) Connection setup still has checks for MPTCP, Ideally these should be
>>>> removed but at least we need to run some benchmarks and fix any
>>>> issues. The
>>>> mainstream folks will not accept any performance degradation in
>>>> TCP. I can
>>>> look into this next.
>>>>
>>>> 2) The code overloads dev field of skb, when it is not being used. IIRC
>>>> there is precedence for this already. I will try to find it.
>>>>
>>>> Rao
>>>>
>>>>
>>>> On 06/26/2017 02:13 PM, Rao Shoaib wrote:
>>>>> This patch returns tcp_skb_cb to it's original size. It also
>>>>> refactors MPTCP code so that there are no MPTCP checks in the main
>>>>> Rx pathi, no performance overheads such as cpu prodiction issues.
>>>>> tcp_v4_rcv() and tcp_v4_do_rcv() do not have any MPTCP specific
>>>>> checks any more, niether does tcp_ack(). On the Rx path MPTCP
>>>>> options are not parsed till the data is being pushed up to the
>>>>> meta socket (mptcp_data_ready). on the Tx side there is one check
>>>>> to add MPTCP specific options but that's it, that should not be
>>>>> that bad as for regular TCP it is a simple check, but it would be
>>>>> good to remove it..
>>>>>
>>>>> I have tested the changes with ndiffports set to 2, so join works.
>>>>> I have also tested accessing multipath-tcp.org
>>>>> <http://multipath-tcp.org> and downloading files from there and
>>>>> also ran the speed test.
>>>>>
>>>>> The Bad:
>>>>>
>>>>> The error cases still have MPTCP checks but that should be OK as
>>>>> they are error cases. I had to use a special marker 0xFEE1DEAD for
>>>>> indicate a special case. I had to introdue a new socket specfic
>>>>> function. IPv6 has not been changed yet. I am sure I have missed
>>>>> some corner cases and more testing will reveal more issues but we
>>>>> just have to fix them.
>>>>>
>>>>> I would like to hear comments from the list and if this direction
>>>>> seems reasonable we can take this as the starting point, port it
>>>>> to latest Linux and share the design with the mainstream folks.
>>>>>
>>>>> Signed-off-by: Rao Shoaib <rao.shoaib(a)oracle.com
>>>>> <mailto:rao.shoaib(a)oracle.com>>
>>>>> ---
>>>>> include/linux/skbuff.h | 8 ++-
>>>>> include/net/mptcp.h | 21 +++---
>>>>> include/net/mptcp_v4.h | 1 +
>>>>> include/net/sock.h | 12 +++-
>>>>> include/net/tcp.h | 23 +++----
>>>>> net/ipv4/af_inet.c | 4 ++
>>>>> net/ipv4/tcp_input.c | 37 ++--------
>>>>> net/ipv4/tcp_ipv4.c | 135
>>>>> +++++++++++++++++++++++--------------
>>>>> net/ipv4/tcp_output.c | 1 +
>>>>> net/ipv6/af_inet6.c | 4 ++
>>>>> net/ipv6/tcp_ipv6.c | 4 --
>>>>> net/mptcp/mptcp_ctrl.c | 21 ++++++
>>>>> net/mptcp/mptcp_input.c | 131
>>>>> ++++++++++++++++++++++++++++--------
>>>>> net/mptcp/mptcp_ipv4.c | 35 +---------
>>>>> net/mptcp/mptcp_ipv6.c | 4 +-
>>>>> net/mptcp/mptcp_output.c | 160
>>>>> +++++++++++++++++---------------------------
>>>>> net/mptcp/mptcp_redundant.c | 6 +-
>>>>> net/mptcp/mptcp_rr.c | 4 +-
>>>>> net/mptcp/mptcp_sched.c | 10 +--
>>>>> 19 files changed, 335 insertions(+), 286 deletions(-)
>>>>>
>>>>> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
>>>>> index f66cd5e..348cbc1 100644
>>>>> --- a/include/linux/skbuff.h
>>>>> +++ b/include/linux/skbuff.h
>>>>> @@ -532,7 +532,13 @@ struct sk_buff {
>>>>> struct rb_noderbnode; /* used in netem & tcp stack */
>>>>> };
>>>>> struct sock*sk;
>>>>> -struct net_device*dev;
>>>>> +union {
>>>>> +struct net_device*dev;
>>>>> +struct {
>>>>> +__u8 mptcp_flags;
>>>>> +__u8 mptcp_dss_off;
>>>>> +};
>>>>> +};
>>>>> /*
>>>>> * This is the control buffer. It is free to use for every
>>>>> diff --git a/include/net/mptcp.h b/include/net/mptcp.h
>>>>> index 876f1e6..d087cb4 100644
>>>>> --- a/include/net/mptcp.h
>>>>> +++ b/include/net/mptcp.h
>>>>> @@ -807,7 +807,7 @@ void tcp_parse_mptcp_options(const struct
>>>>> sk_buff *skb,
>>>>> struct mptcp_options_received *mopt);
>>>>> void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>>>> struct mptcp_options_received *mopt,
>>>>> -const struct sk_buff *skb,
>>>>> +struct sk_buff *skb,
>>>>> struct tcp_sock *tp);
>>>>> void mptcp_syn_options(const struct sock *sk, struct
>>>>> tcp_out_options *opts,
>>>>> unsigned *remaining);
>>>>> @@ -998,14 +998,15 @@ static inline void
>>>>> mptcp_sub_force_close_all(struct mptcp_cb *mpcb,
>>>>> }
>>>>> }
>>>>> +/* currently tp is being used for Rx packets */
>>>>> static inline bool mptcp_is_data_seq(const struct sk_buff *skb)
>>>>> {
>>>>> -return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ;
>>>>> +return skb->mptcp_flags & MPTCPHDR_SEQ;
>>>>> }
>>>>> static inline bool mptcp_is_data_fin(const struct sk_buff *skb)
>>>>> {
>>>>> -return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_FIN;
>>>>> +return skb->mptcp_flags & MPTCPHDR_FIN;
>>>>> }
>>>>> /* Is it a data-fin while in infinite mapping mode?
>>>>> @@ -1034,17 +1035,17 @@ static inline u8 mptcp_get_64_bit(u64
>>>>> data_seq, struct mptcp_cb *mpcb)
>>>>> /* Sets the data_seq and returns pointer to the in-skb field of
>>>>> the data_seq.
>>>>> * If the packet has a 64-bit dseq, the pointer points to the
>>>>> last 32 bits.
>>>>> */
>>>>> -static inline __u32 *mptcp_skb_set_data_seq(const struct sk_buff
>>>>> *skb,
>>>>> +static inline __u32 *mptcp_skb_set_data_seq(struct sk_buff *skb,
>>>>> u32 *data_seq,
>>>>> struct mptcp_cb *mpcb)
>>>>> {
>>>>> -__u32 *ptr = (__u32 *)(skb_transport_header(skb) +
>>>>> TCP_SKB_CB(skb)->dss_off);
>>>>> +__u32 *ptr = (__u32 *)(skb_transport_header(skb) +
>>>>> skb->mptcp_dss_off);
>>>>> -if (TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ64_SET) {
>>>>> +if (skb->mptcp_flags & MPTCPHDR_SEQ64_SET) {
>>>>> u64 data_seq64 = get_unaligned_be64(ptr);
>>>>> if (mpcb)
>>>>> -TCP_SKB_CB(skb)->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
>>>>> +skb->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
>>>>> *data_seq = (u32)data_seq64;
>>>>> ptr++;
>>>>> @@ -1142,7 +1143,7 @@ static inline void mptcp_reset_mopt(struct
>>>>> tcp_sock *tp)
>>>>> static inline __be32 mptcp_get_highorder_sndbits(const struct
>>>>> sk_buff *skb,
>>>>> const struct mptcp_cb *mpcb)
>>>>> {
>>>>> -return htonl(mpcb->snd_high_order[(TCP_SKB_CB(skb)->mptcp_flags &
>>>>> +return htonl(mpcb->snd_high_order[(skb->mptcp_flags &
>>>>> MPTCPHDR_SEQ64_INDEX) ? 1 : 0]);
>>>>> }
>>>>> @@ -1404,8 +1405,8 @@ static inline void mptcp_set_rto(const
>>>>> struct sock *sk) {}
>>>>> static inline void mptcp_send_fin(const struct sock *meta_sk) {}
>>>>> static inline void mptcp_parse_options(const uint8_t *ptr, const
>>>>> int opsize,
>>>>> struct mptcp_options_received *mopt,
>>>>> - const struct sk_buff *skb,
>>>>> - const struct tcp_sock *tp) {}
>>>>> + struct sk_buff *skb,
>>>>> + struct tcp_sock *tp) {}
>>>>> static inline void mptcp_syn_options(const struct sock *sk,
>>>>> struct tcp_out_options *opts,
>>>>> unsigned *remaining) {}
>>>>> diff --git a/include/net/mptcp_v4.h b/include/net/mptcp_v4.h
>>>>> index c83dca0..46394a4 100644
>>>>> --- a/include/net/mptcp_v4.h
>>>>> +++ b/include/net/mptcp_v4.h
>>>>> @@ -45,6 +45,7 @@ extern struct tcp_request_sock_ops
>>>>> mptcp_join_request_sock_ipv4_ops;
>>>>> #ifdef CONFIG_MPTCP
>>>>> int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb);
>>>>> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct
>>>>> sk_buff *skb);
>>>>> struct sock *mptcp_v4_search_req(const __be16 rport, const
>>>>> __be32 raddr,
>>>>> const __be32 laddr, const struct net *net);
>>>>> int mptcp_init4_subsockets(struct sock *meta_sk, const struct
>>>>> mptcp_loc4 *loc,
>>>>> diff --git a/include/net/sock.h b/include/net/sock.h
>>>>> index 0f12593..0d1bda5 100644
>>>>> --- a/include/net/sock.h
>>>>> +++ b/include/net/sock.h
>>>>> @@ -296,6 +296,7 @@ struct cg_proto;
>>>>> *@sk_write_space: callback to indicate there is bf sending
>>>>> space available
>>>>> *@sk_error_report: callback to indicate errors (e.g.
>>>>> %MSG_ERRQUEUE)
>>>>> *@sk_backlog_rcv: callback to process the backlog
>>>>> + *@sk_prequeue: callback to prequeue
>>>>> *@sk_destruct: called at sock freeing time, i.e. when all
>>>>> refcnt == 0
>>>>> */
>>>>> struct sock {
>>>>> @@ -437,7 +438,9 @@ struct sock {
>>>>> void(*sk_write_space)(struct sock *sk);
>>>>> void(*sk_error_report)(struct sock *sk);
>>>>> int(*sk_backlog_rcv)(struct sock *sk,
>>>>> - struct sk_buff *skb);
>>>>> +struct sk_buff *skb);
>>>>> +bool(*sk_prequeue)(struct sock *sk,
>>>>> +struct sk_buff *skb);
>>>>> void (*sk_destruct)(struct sock *sk);
>>>>> };
>>>>> @@ -853,6 +856,11 @@ static inline int sk_backlog_rcv(struct sock
>>>>> *sk, struct sk_buff *skb)
>>>>> return sk->sk_backlog_rcv(sk, skb);
>>>>> }
>>>>> +static inline bool sk_prequeue(struct sock *sk, struct sk_buff *skb)
>>>>> +{
>>>>> +return (false);
>>>>> +}
>>>>> +
>>>>> static inline void sk_incoming_cpu_update(struct sock *sk)
>>>>> {
>>>>> sk->sk_incoming_cpu = raw_smp_processor_id();
>>>>> @@ -993,6 +1001,8 @@ struct proto {
>>>>> int(*backlog_rcv) (struct sock *sk,
>>>>> struct sk_buff *skb);
>>>>> +bool(*prequeue) (struct sock *sk,
>>>>> +struct sk_buff *skb);
>>>>> void(*release_cb)(struct sock *sk);
>>>>> diff --git a/include/net/tcp.h b/include/net/tcp.h
>>>>> index 655ecd4..cbe8ef2 100644
>>>>> --- a/include/net/tcp.h
>>>>> +++ b/include/net/tcp.h
>>>>> @@ -47,6 +47,9 @@
>>>>> #include <linux/seq_file.h>
>>>>> #include <linux/memcontrol.h>
>>>>> +typedef int (* process_unclaimed)(struct sock *sk, struct sk_buff
>>>>> *skb);
>>>>> +extern process_unclaimed tcp_process_unclaimed;
>>>>> +
>>>>> extern struct inet_hashinfo tcp_hashinfo;
>>>>> extern struct percpu_counter tcp_orphan_count;
>>>>> @@ -581,6 +584,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock
>>>>> *sk, struct sk_buff *skb,
>>>>> struct request_sock *req,
>>>>> struct dst_entry *dst);
>>>>> int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
>>>>> +
>>>>> int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int
>>>>> addr_len);
>>>>> int tcp_connect(struct sock *sk);
>>>>> struct sk_buff *tcp_make_synack(struct sock *sk, struct
>>>>> dst_entry *dst,
>>>>> @@ -842,11 +846,6 @@ struct tcp_skb_cb {
>>>>> __u32tcp_gso_segs;
>>>>> };
>>>>> -#ifdef CONFIG_MPTCP
>>>>> -__u8mptcp_flags;/* flags for the MPTCP layer */
>>>>> -__u8dss_off;/* Number of 4-byte words until
>>>>> -* seq-number */
>>>>> -#endif
>>>>> __u8tcp_flags;/* TCP header flags. (tcp[13])*/
>>>>> __u8sacked;/* State flags for SACK/FACK.*/
>>>>> @@ -859,9 +858,13 @@ struct tcp_skb_cb {
>>>>> #define TCPCB_RETRANS(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
>>>>> TCPCB_REPAIRED)
>>>>> -__u8ip_dsfield;/* IPv4 tos or IPv6 dsfield*/
>>>>> +__u8ip_dsfield;/* IPv4 tos or IPv6 dsfield */
>>>>> /* 1 byte hole */
>>>>> -__u32ack_seq;/* Sequence number ACK'd*/
>>>>> +union {
>>>>> +__u32ack_seq;/* Sequence number ACK'd */
>>>>> +__u32 mptcp_data_seq;
>>>>> +__u32mptcp_path_mask;
>>>>> +};
>>>>> union {
>>>>> union {
>>>>> struct inet_skb_parmh4;
>>>>> @@ -869,12 +872,6 @@ struct tcp_skb_cb {
>>>>> struct inet6_skb_parmh6;
>>>>> #endif
>>>>> } header;/* For incoming frames*/
>>>>> -#ifdef CONFIG_MPTCP
>>>>> -union {/* For MPTCP outgoing frames */
>>>>> -__u32 path_mask; /* paths that tried to send this skb */
>>>>> -__u32 dss[6];/* DSS options */
>>>>> -};
>>>>> -#endif
>>>>> };
>>>>> };
>>>>> diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
>>>>> index 73480b9..1e7827f 100644
>>>>> --- a/net/ipv4/af_inet.c
>>>>> +++ b/net/ipv4/af_inet.c
>>>>> @@ -356,6 +356,10 @@ lookup_protocol:
>>>>> sk->sk_destruct = inet_sock_destruct;
>>>>> sk->sk_protocol = protocol;
>>>>> sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
>>>>> +sk->sk_prequeue = sk->sk_prot->prequeue;
>>>>> +if (sk->sk_prequeue == NULL) {
>>>>> +sk->sk_prequeue = sk_prequeue;
>>>>> +}
>>>>> inet->uc_ttl= -1;
>>>>> inet->mc_loop= 1;
>>>>> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
>>>>> index 16a7256..cb6bbf9 100644
>>>>> --- a/net/ipv4/tcp_input.c
>>>>> +++ b/net/ipv4/tcp_input.c
>>>>> @@ -3133,8 +3133,6 @@ static int tcp_clean_rtx_queue(struct sock
>>>>> *sk, int prior_fackets,
>>>>> */
>>>>> if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
>>>>> flag |= FLAG_DATA_ACKED;
>>>>> -if (mptcp(tp) && mptcp_is_data_seq(skb))
>>>>> -flag |= MPTCP_FLAG_DATA_ACKED;
>>>>> } else {
>>>>> flag |= FLAG_SYN_ACKED;
>>>>> tp->retrans_stamp = 0;
>>>>> @@ -3582,16 +3580,6 @@ static int tcp_ack(struct sock *sk, struct
>>>>> sk_buff *skb, int flag)
>>>>> sack_rtt_us);
>>>>> acked -= tp->packets_out;
>>>>> -if (mptcp(tp)) {
>>>>> -if (mptcp_fallback_infinite(sk, flag)) {
>>>>> -pr_err("%s resetting flow\n", __func__);
>>>>> -mptcp_send_reset(sk);
>>>>> -goto invalid_ack;
>>>>> -}
>>>>> -
>>>>> -mptcp_clean_rtx_infinite(skb, sk);
>>>>> -}
>>>>> -
>>>>> /* Advance cwnd if state allows */
>>>>> if (tcp_may_raise_cwnd(sk, flag))
>>>>> tcp_cong_avoid(sk, ack, acked);
>>>>> @@ -3824,8 +3812,7 @@ static bool tcp_fast_parse_options(const
>>>>> struct sk_buff *skb,
>>>>> if (tcp_parse_aligned_timestamp(tp, th))
>>>>> return true;
>>>>> }
>>>>> -tcp_parse_options(skb, &tp->rx_opt,
>>>>> - mptcp(tp) ? &tp->mptcp->rx_opt : NULL, 1, NULL, tp);
>>>>> +tcp_parse_options(skb, &tp->rx_opt, NULL, 1, NULL, tp);
>>>>> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
>>>>> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>>>>> @@ -4550,11 +4537,12 @@ static void tcp_data_queue(struct sock
>>>>> *sk, struct sk_buff *skb)
>>>>> int eaten = -1;
>>>>> bool fragstolen = false;
>>>>> -/* If no data is present, but a data_fin is in the options, we still
>>>>> -* have to call mptcp_queue_skb later on. */
>>>>> -if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq &&
>>>>> - !(mptcp(tp) && mptcp_is_data_fin(skb)))
>>>>> +/*
>>>>> +* send every packet to MPTCP
>>>>> +*/
>>>>> +if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq ==
>>>>> TCP_SKB_CB(skb)->end_seq)) {
>>>>> goto drop;
>>>>> +}
>>>>> skb_dst_drop(skb);
>>>>> __skb_pull(skb, tcp_hdr(skb)->doff * 4);
>>>>> @@ -5242,15 +5230,9 @@ syn_challenge:
>>>>> goto discard;
>>>>> }
>>>>> -/* If valid: post process the received MPTCP options. */
>>>>> -if (mptcp(tp) && mptcp_handle_options(sk, th, skb))
>>>>> -goto discard;
>>>>> -
>>>>> return true;
>>>>> discard:
>>>>> -if (mptcp(tp))
>>>>> -mptcp_reset_mopt(tp);
>>>>> __kfree_skb(skb);
>>>>> return false;
>>>>> }
>>>>> @@ -5302,10 +5284,6 @@ void tcp_rcv_established(struct sock *sk,
>>>>> struct sk_buff *skb,
>>>>> tp->rx_opt.saw_tstamp = 0;
>>>>> -/* MPTCP: force slowpath. */
>>>>> -if (mptcp(tp))
>>>>> -goto slow_path;
>>>>> -
>>>>> /*pred_flags is 0xS?10 << 16 + snd_wnd
>>>>> *if header_prediction is to be made
>>>>> *'S' will always be tp->tcp_header_len >> 2
>>>>> @@ -5585,8 +5563,7 @@ static int
>>>>> tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
>>>>> struct mptcp_options_received mopt;
>>>>> mptcp_init_mp_opt(&mopt);
>>>>> -tcp_parse_options(skb, &tp->rx_opt,
>>>>> - mptcp(tp) ? &tp->mptcp->rx_opt : &mopt, 0, &foc, tp);
>>>>> +tcp_parse_options(skb, &tp->rx_opt, &mopt, 0, &foc, tp);
>>>>> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
>>>>> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>>>>> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
>>>>> index 6967a86..3329679 100644
>>>>> --- a/net/ipv4/tcp_ipv4.c
>>>>> +++ b/net/ipv4/tcp_ipv4.c
>>>>> @@ -1420,6 +1420,71 @@ struct sock *tcp_v4_hnd_req(struct sock
>>>>> *sk, struct sk_buff *skb)
>>>>> return sk;
>>>>> }
>>>>> +int mptcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
>>>>> +{
>>>>> +struct net *net = dev_net(skb->dev);
>>>>> +const struct tcphdr *th = tcp_hdr(skb);
>>>>> +int ret;
>>>>> +struct sock *meta_sk;
>>>>> +
>>>>> +if (sk == NULL) {
>>>>> +if (th->syn && !th->ack) {
>>>>> +int ret = mptcp_lookup_join(skb, NULL);
>>>>> +
>>>>> +if (ret < 0) {
>>>>> +tcp_v4_send_reset(NULL, skb);
>>>>> +kfree_skb(skb);
>>>>> +return (1);
>>>>> +} else if (ret > 0) {
>>>>> +return (1);
>>>>> +}
>>>>> +}
>>>>> +/* Is there a pending request sock for this segment ? */
>>>>> +if (mptcp_check_req(skb, net)) {
>>>>> +return(1);
>>>>> +}
>>>>> +return (0);
>>>>> +}
>>>>> +
>>>>> +/* The socket passed in should never be the meta socket */
>>>>> +
>>>>> +BUG_ON(is_meta_sk(sk));
>>>>> +
>>>>> + /* Is there a pending request sock for this segment ? */
>>>>> +if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
>>>>> +return 0;
>>>>> +}
>>>>> +
>>>>> +skb->dev = NULL;
>>>>> +meta_sk = mptcp_meta_sk(sk);
>>>>> +
>>>>> +ret = 0;
>>>>> +skb->sk = sk;
>>>>> +bh_lock_sock_nested(meta_sk);
>>>>> +if (sock_owned_by_user(meta_sk)) {
>>>>> +if (unlikely(sk_add_backlog(meta_sk, skb,
>>>>> + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>>> +
>>>>> +NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>>> +kfree_skb(skb);
>>>>> +}
>>>>> +} else {
>>>>> +
>>>>> +if (is_meta_sk(sk)) {
>>>>> +ret = mptcp_v4_process_join_req(sk, skb);
>>>>> +goto done;
>>>>> +}
>>>>> +if (!meta_sk->sk_prequeue(meta_sk, skb)) {
>>>>> +skb->sk = NULL;
>>>>> +ret = tcp_v4_do_rcv(sk, skb);
>>>>> +}
>>>>> +
>>>>> +}
>>>>> +done:
>>>>> +bh_unlock_sock(meta_sk);
>>>>> +return (ret);
>>>>> +}
>>>>> +
>>>>> /* The socket must have it's spinlock held when we get
>>>>> * here.
>>>>> *
>>>>> @@ -1432,8 +1497,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct
>>>>> sk_buff *skb)
>>>>> {
>>>>> struct sock *rsk;
>>>>> -if (is_meta_sk(sk))
>>>>> -return mptcp_v4_do_rcv(sk, skb);
>>>>> +BUG_ON(is_meta_sk(sk));
>>>>> if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
>>>>> struct dst_entry *dst = sk->sk_rx_dst;
>>>>> @@ -1587,6 +1651,8 @@ bool tcp_prequeue(struct sock *sk, struct
>>>>> sk_buff *skb)
>>>>> }
>>>>> EXPORT_SYMBOL(tcp_prequeue);
>>>>> +process_unclaimed tcp_process_unclaimed = NULL;
>>>>> +
>>>>> /*
>>>>> *From tcp_input.c
>>>>> */
>>>>> @@ -1595,7 +1661,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
>>>>> {
>>>>> const struct iphdr *iph;
>>>>> const struct tcphdr *th;
>>>>> -struct sock *sk, *meta_sk = NULL;
>>>>> +struct sock *sk = NULL;
>>>>> int ret;
>>>>> struct net *net = dev_net(skb->dev);
>>>>> @@ -1636,10 +1702,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
>>>>> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
>>>>> skb->len - th->doff * 4);
>>>>> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
>>>>> -#ifdef CONFIG_MPTCP
>>>>> -TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>>> -TCP_SKB_CB(skb)->dss_off = 0;
>>>>> -#endif
>>>>> +
>>>>> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
>>>>> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
>>>>> TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
>>>>> @@ -1662,15 +1725,6 @@ process:
>>>>> if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
>>>>> goto discard_and_relse;
>>>>> -#ifdef CONFIG_MPTCP
>>>>> -/* Is there a pending request sock for this segment ? */
>>>>> -if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
>>>>> -if (sk)
>>>>> -sock_put(sk);
>>>>> -return 0;
>>>>> -}
>>>>> -#endif
>>>>> -
>>>>> #ifdef CONFIG_TCP_MD5SIG
>>>>> /*
>>>>> * We really want to reject the packet as early as possible
>>>>> @@ -1688,30 +1742,21 @@ process:
>>>>> goto discard_and_relse;
>>>>> sk_incoming_cpu_update(sk);
>>>>> -skb->dev = NULL;
>>>>> -if (mptcp(tcp_sk(sk))) {
>>>>> -meta_sk = mptcp_meta_sk(sk);
>>>>> -
>>>>> -bh_lock_sock_nested(meta_sk);
>>>>> -if (sock_owned_by_user(meta_sk))
>>>>> -skb->sk = sk;
>>>>> -} else {
>>>>> -meta_sk = sk;
>>>>> -bh_lock_sock_nested(sk);
>>>>> -}
>>>>> +/* Do I have to set skb->dev to null ? */
>>>>> +bh_lock_sock_nested(sk);
>>>>> ret = 0;
>>>>> -if (!sock_owned_by_user(meta_sk)) {
>>>>> -if (!tcp_prequeue(meta_sk, skb))
>>>>> -ret = tcp_v4_do_rcv(sk, skb);
>>>>> -} else if (unlikely(sk_add_backlog(meta_sk, skb,
>>>>> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>>> -bh_unlock_sock(meta_sk);
>>>>> +if (!sock_owned_by_user(sk)) {
>>>>> +if (!sk->sk_prequeue(sk, skb))
>>>>> +ret = sk->sk_backlog_rcv(sk, skb);
>>>>> +} else if (unlikely(sk_add_backlog(sk, skb,
>>>>> + sk->sk_rcvbuf + sk->sk_sndbuf))) {
>>>>> +bh_unlock_sock(sk);
>>>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>>> goto discard_and_relse;
>>>>> }
>>>>> -bh_unlock_sock(meta_sk);
>>>>> +bh_unlock_sock(sk);
>>>>> sock_put(sk);
>>>>> @@ -1721,26 +1766,11 @@ no_tcp_socket:
>>>>> if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
>>>>> goto discard_it;
>>>>> -#ifdef CONFIG_MPTCP
>>>>> -if (!sk && th->syn && !th->ack) {
>>>>> -int ret = mptcp_lookup_join(skb, NULL);
>>>>> -
>>>>> -if (ret < 0) {
>>>>> -tcp_v4_send_reset(NULL, skb);
>>>>> -goto discard_it;
>>>>> -} else if (ret > 0) {
>>>>> -return 0;
>>>>> -}
>>>>> +if (unlikely (tcp_process_unclaimed != NULL)) {
>>>>> +if ((tcp_process_unclaimed)(NULL, skb))
>>>>> +return (0);
>>>>> }
>>>>> -/* Is there a pending request sock for this segment ? */
>>>>> -if (!sk && mptcp_check_req(skb, net)) {
>>>>> -if (sk)
>>>>> -sock_put(sk);
>>>>> -return 0;
>>>>> -}
>>>>> -#endif
>>>>> -
>>>>> if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
>>>>> csum_error:
>>>>> TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
>>>>> @@ -2506,6 +2536,7 @@ struct proto tcp_prot = {
>>>>> .sendmsg= tcp_sendmsg,
>>>>> .sendpage= tcp_sendpage,
>>>>> .backlog_rcv= tcp_v4_do_rcv,
>>>>> +.prequeue= tcp_prequeue,
>>>>> .release_cb= tcp_release_cb,
>>>>> .hash= inet_hash,
>>>>> .unhash= inet_unhash,
>>>>> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
>>>>> index a635483..41b8be8 100644
>>>>> --- a/net/ipv4/tcp_output.c
>>>>> +++ b/net/ipv4/tcp_output.c
>>>>> @@ -3413,6 +3413,7 @@ void tcp_send_delayed_ack(struct sock *sk)
>>>>> void tcp_send_ack(struct sock *sk)
>>>>> {
>>>>> struct sk_buff *buff;
>>>>> +struct tcp_sock *tp = tcp_sk(sk);
>>>>> /* If we have been reset, we may not send again. */
>>>>> if (sk->sk_state == TCP_CLOSE)
>>>>> diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
>>>>> index 8c4dd4a..1554217 100644
>>>>> --- a/net/ipv6/af_inet6.c
>>>>> +++ b/net/ipv6/af_inet6.c
>>>>> @@ -193,6 +193,10 @@ lookup_protocol:
>>>>> sk->sk_protocol= protocol;
>>>>> sk->sk_backlog_rcv= answer->prot->backlog_rcv;
>>>>> +sk->sk_prequeue= answer->prot->prequeue;
>>>>> +if (sk->sk_prequeue == NULL) {
>>>>> +sk->sk_prequeue = sk_prequeue;
>>>>> +}
>>>>> inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
>>>>> np->hop_limit= -1;
>>>>> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
>>>>> index eba2436..d360128 100644
>>>>> --- a/net/ipv6/tcp_ipv6.c
>>>>> +++ b/net/ipv6/tcp_ipv6.c
>>>>> @@ -1412,10 +1412,6 @@ static void tcp_v6_fill_cb(struct sk_buff
>>>>> *skb, const struct ipv6hdr *hdr,
>>>>> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
>>>>> skb->len - th->doff*4);
>>>>> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
>>>>> -#ifdef CONFIG_MPTCP
>>>>> -TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>>> -TCP_SKB_CB(skb)->dss_off = 0;
>>>>> -#endif
>>>>> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
>>>>> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
>>>>> TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
>>>>> diff --git a/net/mptcp/mptcp_ctrl.c b/net/mptcp/mptcp_ctrl.c
>>>>> index 28f348f..b1e780a 100644
>>>>> --- a/net/mptcp/mptcp_ctrl.c
>>>>> +++ b/net/mptcp/mptcp_ctrl.c
>>>>> @@ -976,6 +976,20 @@ int mptcp_backlog_rcv(struct sock *meta_sk,
>>>>> struct sk_buff *skb)
>>>>> struct sock *sk = skb->sk ? skb->sk : meta_sk;
>>>>> int ret = 0;
>>>>> +/* socket was owned by the user in mptcp_check_req()
>>>>> + */
>>>>> +if (sk == (struct sock *)0xFEE1DEAD) {
>>>>> +bh_lock_sock_nested(meta_sk);
>>>>> +if (skb->protocol == htons(ETH_P_IP))
>>>>> +mptcp_v4_process_join_req(meta_sk, skb);
>>>>> +#if IS_ENABLED(CONFIG_IPV6)
>>>>> +else
>>>>> +//mptcp_v6_process_join_req(meta_sk, skb);
>>>>> +#endif /* CONFIG_IPV6 */
>>>>> +bh_unlock_sock(meta_sk);
>>>>> +return(0);
>>>>> +}
>>>>> +
>>>>> skb->sk = NULL;
>>>>> if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
>>>>> @@ -1297,6 +1311,10 @@ int mptcp_add_sock(struct sock *meta_sk,
>>>>> struct sock *sk, u8 loc_id, u8 rem_id,
>>>>> sk->sk_write_space = mptcp_write_space;
>>>>> sk->sk_state_change = mptcp_set_state;
>>>>> sk->sk_destruct = mptcp_sock_destruct;
>>>>> +/* MPTCP takes a different path in tcp_v4_rcv
>>>>> + * thus not impacting main tcp code */
>>>>> +sk->sk_backlog_rcv = mptcp_v4_do_rcv;
>>>>> +sk->sk_prequeue = sk_prequeue;
>>>>> if (sk->sk_family == AF_INET)
>>>>> mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d
>>>>> dst_addr:%pI4:%d, cnt_subflows now %d\n",
>>>>> @@ -2658,6 +2676,9 @@ void __init mptcp_init(void)
>>>>> if (mptcp_pm_v4_init())
>>>>> goto mptcp_pm_v4_failed;
>>>>> +if ((cmpxchg(&tcp_process_unclaimed, NULL, mptcp_v4_do_rcv)) != NULL)
>>>>> +printk("tcp_process_unclaimed not NULL \n");
>>>>> +
>>>>> mptcp_sysctl = register_net_sysctl(&init_net, "net/mptcp",
>>>>> mptcp_table);
>>>>> if (!mptcp_sysctl)
>>>>> goto register_sysctl_failed;
>>>>> diff --git a/net/mptcp/mptcp_input.c b/net/mptcp/mptcp_input.c
>>>>> index 51cbb06..0e09ddf 100644
>>>>> --- a/net/mptcp/mptcp_input.c
>>>>> +++ b/net/mptcp/mptcp_input.c
>>>>> @@ -323,9 +323,8 @@ static int mptcp_verif_dss_csum(struct sock *sk)
>>>>> * by 4 bytes, as the high-order 64-bits will be added
>>>>> * in the final csum_partial-call.
>>>>> */
>>>>> -u32 offset = skb_transport_offset(tmp) +
>>>>> - TCP_SKB_CB(tmp)->dss_off;
>>>>> -if (TCP_SKB_CB(tmp)->mptcp_flags & MPTCPHDR_SEQ64_SET)
>>>>> +u32 offset = skb_transport_offset(tmp) + tmp->mptcp_dss_off;
>>>>> +if (tmp->mptcp_flags & MPTCPHDR_SEQ64_SET)
>>>>> offset += 4;
>>>>> csum_tcp = skb_checksum(tmp, offset,
>>>>> @@ -758,7 +757,7 @@ static int mptcp_detect_mapping(struct sock
>>>>> *sk, struct sk_buff *skb)
>>>>> }
>>>>> /* Does the DSS had 64-bit seqnum's ? */
>>>>> -if (!(tcb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
>>>>> +if (!(skb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
>>>>> /* Wrapped around? */
>>>>> if (unlikely(after(data_seq, meta_tp->rcv_nxt) && data_seq <
>>>>> meta_tp->rcv_nxt)) {
>>>>> tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
>>>>> !mpcb->rcv_hiseq_index, data_seq);
>>>>> @@ -767,9 +766,9 @@ static int mptcp_detect_mapping(struct sock
>>>>> *sk, struct sk_buff *skb)
>>>>> tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
>>>>> mpcb->rcv_hiseq_index, data_seq);
>>>>> }
>>>>> } else {
>>>>> -tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
>>>>> (tcb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
>>>>> +tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
>>>>> (skb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
>>>>> -if (unlikely(tcb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
>>>>> +if (unlikely(skb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
>>>>> /* We make sure that the data_seq is invalid.
>>>>> * It will be dropped later.
>>>>> */
>>>>> @@ -1020,6 +1019,67 @@ next:
>>>>> return data_queued ? -1 : -2;
>>>>> }
>>>>> +static struct sk_buff *
>>>>> +mptcp_process_ack(struct sock *sk, struct sk_buff *skb)
>>>>> +{
>>>>> +struct tcp_sock *tp = tcp_sk(sk);
>>>>> +int flag = 0;
>>>>> +
>>>>> +/*
>>>>> +* TCP takes care of invalid ack's
>>>>> +* they will never show up here.
>>>>> +*/
>>>>> +
>>>>> +/* Is this skb acknowleding anything data */
>>>>> +
>>>>> +if (tp->mptcp->snt_isn + 1 != TCP_SKB_CB(skb)->ack_seq) {
>>>>> +flag = MPTCP_FLAG_DATA_ACKED;
>>>>> +}
>>>>> +
>>>>> +if (mptcp_fallback_infinite(sk, flag)) {
>>>>> +pr_err("%s resetting flow\n", __func__);
>>>>> +mptcp_send_reset(sk);
>>>>> +goto invalid_ack;
>>>>> +}
>>>>> +
>>>>> +mptcp_clean_rtx_infinite(skb, sk);
>>>>> +
>>>>> +return (skb);
>>>>> +invalid_ack:
>>>>> +__skb_unlink(skb, &sk->sk_receive_queue);
>>>>> +__kfree_skb(skb);
>>>>> +return (NULL);
>>>>> +
>>>>> +}
>>>>> +
>>>>> +static struct sk_buff *
>>>>> +mptcp_process_options_ack(struct sock *sk, struct sk_buff *skb)
>>>>> +{
>>>>> +struct tcp_sock *tp = tcp_sk(sk);
>>>>> +const struct tcphdr *th = tcp_hdr(skb);
>>>>> +
>>>>> +skb->mptcp_flags = 0;
>>>>> +skb->mptcp_dss_off = 0;
>>>>> +
>>>>> +tcp_parse_mptcp_options(skb, &tp->mptcp->rx_opt);
>>>>> +if (mptcp_handle_options(sk, th, skb)) {
>>>>> +mptcp_reset_mopt(tp);
>>>>> +__skb_unlink(skb, &sk->sk_receive_queue);
>>>>> +__kfree_skb(skb);
>>>>> +skb = NULL;
>>>>> +}
>>>>> +if ((skb != NULL) && skb->len == 0) {
>>>>> +skb = mptcp_process_ack(sk, skb);
>>>>> +if (skb != NULL && skb->len == 0) {
>>>>> +/* Pure ack */
>>>>> +__skb_unlink(skb, &sk->sk_receive_queue);
>>>>> +__kfree_skb(skb);
>>>>> +skb = NULL;
>>>>> +}
>>>>> +}
>>>>> +return (skb);
>>>>> +}
>>>>> +
>>>>> void mptcp_data_ready(struct sock *sk)
>>>>> {
>>>>> struct sock *meta_sk = mptcp_meta_sk(sk);
>>>>> @@ -1045,6 +1105,10 @@ restart:
>>>>> */
>>>>> skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
>>>>> int ret;
>>>>> +
>>>>> +skb = mptcp_process_options_ack(sk, skb);
>>>>> +if (skb == NULL)
>>>>> +continue;
>>>>> /* Pre-validation - e.g., early fallback */
>>>>> ret = mptcp_prevalidate_skb(sk, skb);
>>>>> if (ret < 0)
>>>>> @@ -1108,13 +1172,11 @@ int mptcp_check_req(struct sk_buff *skb,
>>>>> struct net *net)
>>>>> if (!meta_sk)
>>>>> return 0;
>>>>> -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>>> -
>>>>> bh_lock_sock_nested(meta_sk);
>>>>> if (sock_owned_by_user(meta_sk)) {
>>>>> -skb->sk = meta_sk;
>>>>> +skb->sk = (struct sock *)0xFEE1DEAD;
>>>>> if (unlikely(sk_add_backlog(meta_sk, skb,
>>>>> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>>> +meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>>> bh_unlock_sock(meta_sk);
>>>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>>> sock_put(meta_sk); /* Taken by mptcp_search_req */
>>>>> @@ -1122,10 +1184,14 @@ int mptcp_check_req(struct sk_buff *skb,
>>>>> struct net *net)
>>>>> return 1;
>>>>> }
>>>>> } else if (skb->protocol == htons(ETH_P_IP)) {
>>>>> -tcp_v4_do_rcv(meta_sk, skb);
>>>>> +/*
>>>>> +* call old mptcp_v4_do_rcv
>>>>> +*/
>>>>> +mptcp_v4_process_join_req(meta_sk, skb);
>>>>> #if IS_ENABLED(CONFIG_IPV6)
>>>>> } else { /* IPv6 */
>>>>> -tcp_v6_do_rcv(meta_sk, skb);
>>>>> +WARN_ON(1);
>>>>> +//mptcp_v6_handle_join_req(meta_sk, skb);
>>>>> #endif /* CONFIG_IPV6 */
>>>>> }
>>>>> bh_unlock_sock(meta_sk);
>>>>> @@ -1222,7 +1288,7 @@ int mptcp_lookup_join(struct sk_buff *skb,
>>>>> struct inet_timewait_sock *tw)
>>>>> inet_twsk_put(tw);
>>>>> }
>>>>> -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>>> +skb->mptcp_flags |= MPTCPHDR_JOIN;
>>>>> /* OK, this is a new syn/join, let's create a new open request and
>>>>> * send syn+ack
>>>>> */
>>>>> @@ -1279,7 +1345,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>>>> return -1;
>>>>> }
>>>>> -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>>> +//TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>>> /* OK, this is a new syn/join, let's create a new open request and
>>>>> * send syn+ack
>>>>> @@ -1303,7 +1369,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>>>> }
>>>>> if (sock_owned_by_user(meta_sk)) {
>>>>> -skb->sk = meta_sk;
>>>>> +skb->sk = (struct sock *)0xFEE1DEAD; //skb->sk = meta_sk;
>>>>> if (unlikely(sk_add_backlog(meta_sk, skb,
>>>>> meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf)))
>>>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>>> @@ -1319,10 +1385,12 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>>>> */
>>>>> skb_get(skb);
>>>>> if (skb->protocol == htons(ETH_P_IP)) {
>>>>> -tcp_v4_do_rcv(meta_sk, skb);
>>>>> +//tcp_v4_do_rcv(meta_sk, skb);
>>>>> +mptcp_v4_process_join_req(meta_sk, skb);
>>>>> #if IS_ENABLED(CONFIG_IPV6)
>>>>> } else { /* IPv6 */
>>>>> -tcp_v6_do_rcv(meta_sk, skb);
>>>>> +//mptcp_v6_process_join_req(meta_sk, skb);
>>>>> +//tcp_v6_do_rcv(meta_sk, skb);
>>>>> #endif /* CONFIG_IPV6 */
>>>>> }
>>>>> }
>>>>> @@ -1461,7 +1529,6 @@ static void mptcp_data_ack(struct sock *sk,
>>>>> const struct sk_buff *skb)
>>>>> {
>>>>> struct sock *meta_sk = mptcp_meta_sk(sk);
>>>>> struct tcp_sock *meta_tp = tcp_sk(meta_sk), *tp = tcp_sk(sk);
>>>>> -struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>>> u32 prior_snd_una = meta_tp->snd_una;
>>>>> int prior_packets;
>>>>> u32 nwin, data_ack, data_seq;
>>>>> @@ -1481,7 +1548,7 @@ static void mptcp_data_ack(struct sock *sk,
>>>>> const struct sk_buff *skb)
>>>>> /* If we are in infinite mapping mode, rx_opt.data_ack has been
>>>>> * set by mptcp_clean_rtx_infinite.
>>>>> */
>>>>> -if (!(tcb->mptcp_flags & MPTCPHDR_ACK) &&
>>>>> !tp->mpcb->infinite_mapping_snd)
>>>>> +if (!(skb->mptcp_flags & MPTCPHDR_ACK) &&
>>>>> !tp->mpcb->infinite_mapping_snd)
>>>>> goto exit;
>>>>> data_ack = tp->mptcp->rx_opt.data_ack;
>>>>> @@ -1647,10 +1714,11 @@ static inline bool
>>>>> is_valid_addropt_opsize(u8 mptcp_ver,
>>>>> void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>>>> struct mptcp_options_received *mopt,
>>>>> -const struct sk_buff *skb,
>>>>> +struct sk_buff *skb,
>>>>> struct tcp_sock *tp)
>>>>> {
>>>>> const struct mptcp_option *mp_opt = (struct mptcp_option *)ptr;
>>>>> +struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>>> /* If the socket is mp-capable we would have a mopt. */
>>>>> if (!mopt)
>>>>> @@ -1757,7 +1825,7 @@ void mptcp_parse_options(const uint8_t *ptr,
>>>>> int opsize,
>>>>> ptr += 4;
>>>>> if (mdss->A) {
>>>>> -tcb->mptcp_flags |= MPTCPHDR_ACK;
>>>>> +skb->mptcp_flags |= MPTCPHDR_ACK;
>>>>> if (mdss->a) {
>>>>> mopt->data_ack = (u32) get_unaligned_be64(ptr);
>>>>> @@ -1768,13 +1836,13 @@ void mptcp_parse_options(const uint8_t
>>>>> *ptr, int opsize,
>>>>> }
>>>>> }
>>>>> -tcb->dss_off = (ptr - skb_transport_header(skb));
>>>>> +skb->mptcp_dss_off = (ptr - skb_transport_header(skb));
>>>>> if (mdss->M) {
>>>>> if (mdss->m) {
>>>>> u64 data_seq64 = get_unaligned_be64(ptr);
>>>>> -tcb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
>>>>> +skb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
>>>>> mopt->data_seq = (u32) data_seq64;
>>>>> ptr += 12; /* 64-bit dseq + subseq */
>>>>> @@ -1784,15 +1852,16 @@ void mptcp_parse_options(const uint8_t
>>>>> *ptr, int opsize,
>>>>> }
>>>>> mopt->data_len = get_unaligned_be16(ptr);
>>>>> -tcb->mptcp_flags |= MPTCPHDR_SEQ;
>>>>> +skb->mptcp_flags |= MPTCPHDR_SEQ;
>>>>> /* Is a check-sum present? */
>>>>> -if (opsize == mptcp_sub_len_dss(mdss, 1))
>>>>> -tcb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
>>>>> +if (opsize == mptcp_sub_len_dss(mdss, 1)) {
>>>>> +skb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
>>>>> +}
>>>>> /* DATA_FIN only possible with DSS-mapping */
>>>>> if (mdss->F)
>>>>> -tcb->mptcp_flags |= MPTCPHDR_FIN;
>>>>> +skb->mptcp_flags |= MPTCPHDR_FIN;
>>>>> }
>>>>> break;
>>>>> @@ -1907,8 +1976,9 @@ void tcp_parse_mptcp_options(const struct
>>>>> sk_buff *skb,
>>>>> return;
>>>>> if (opsize > length)
>>>>> return;/* don't parse partial options */
>>>>> -if (opcode == TCPOPT_MPTCP)
>>>>> +if (opcode == TCPOPT_MPTCP) {
>>>>> mptcp_parse_options(ptr - 2, opsize, mopt, skb, NULL);
>>>>> +}
>>>>> }
>>>>> ptr += opsize - 2;
>>>>> length -= opsize;
>>>>> @@ -2168,6 +2238,8 @@ bool mptcp_handle_options(struct sock *sk,
>>>>> const struct tcphdr *th,
>>>>> struct tcp_sock *tp = tcp_sk(sk);
>>>>> struct mptcp_options_received *mopt = &tp->mptcp->rx_opt;
>>>>> +BUG_ON(sk == mptcp_meta_sk(sk));
>>>>> +
>>>>> if (tp->mpcb->infinite_mapping_rcv || tp->mpcb->infinite_mapping_snd)
>>>>> return false;
>>>>> @@ -2185,7 +2257,7 @@ bool mptcp_handle_options(struct sock *sk,
>>>>> const struct tcphdr *th,
>>>>> * receiver MUST close the subflow with a RST as it is considered
>>>>> broken.
>>>>> */
>>>>> if (mptcp_is_data_seq(skb) && tp->mpcb->dss_csum &&
>>>>> - !(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
>>>>> + !(skb->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
>>>>> mptcp_send_reset(sk);
>>>>> return true;
>>>>> }
>>>>> @@ -2330,6 +2402,7 @@ int mptcp_rcv_synsent_state_process(struct
>>>>> sock *sk, struct sock **skptr,
>>>>> /* Set this flag in order to postpone data sending
>>>>> * until the 4th ack arrives.
>>>>> */
>>>>> +printk("mptcp_rcv_synsent_state_process pre_established set \n");
>>>>> tp->mptcp->pre_established = 1;
>>>>> tp->mptcp->rcv_low_prio = tp->mptcp->rx_opt.low_prio;
>>>>> diff --git a/net/mptcp/mptcp_ipv4.c b/net/mptcp/mptcp_ipv4.c
>>>>> index a147b20..3e60ab5 100644
>>>>> --- a/net/mptcp/mptcp_ipv4.c
>>>>> +++ b/net/mptcp/mptcp_ipv4.c
>>>>> @@ -180,45 +180,12 @@ static int mptcp_v4_join_request(struct sock
>>>>> *meta_sk, struct sk_buff *skb)
>>>>> }
>>>>> /* We only process join requests here. (either the SYN or the
>>>>> final ACK) */
>>>>> -int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>>>> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct
>>>>> sk_buff *skb)
>>>>> {
>>>>> const struct mptcp_cb *mpcb = tcp_sk(meta_sk)->mpcb;
>>>>> struct sock *child, *rsk = NULL;
>>>>> int ret;
>>>>> -if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
>>>>> -struct tcphdr *th = tcp_hdr(skb);
>>>>> -const struct iphdr *iph = ip_hdr(skb);
>>>>> -struct sock *sk;
>>>>> -
>>>>> -sk = inet_lookup_established(sock_net(meta_sk), &tcp_hashinfo,
>>>>> - iph->saddr, th->source, iph->daddr,
>>>>> - th->dest, inet_iif(skb));
>>>>> -
>>>>> -if (!sk) {
>>>>> -kfree_skb(skb);
>>>>> -return 0;
>>>>> -}
>>>>> -if (is_meta_sk(sk)) {
>>>>> -WARN("%s Did not find a sub-sk - did found the meta!\n", __func__);
>>>>> -kfree_skb(skb);
>>>>> -sock_put(sk);
>>>>> -return 0;
>>>>> -}
>>>>> -
>>>>> -if (sk->sk_state == TCP_TIME_WAIT) {
>>>>> -inet_twsk_put(inet_twsk(sk));
>>>>> -kfree_skb(skb);
>>>>> -return 0;
>>>>> -}
>>>>> -
>>>>> -ret = tcp_v4_do_rcv(sk, skb);
>>>>> -sock_put(sk);
>>>>> -
>>>>> -return ret;
>>>>> -}
>>>>> -TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>>> -
>>>>> /* Has been removed from the tk-table. Thus, no new subflows.
>>>>> *
>>>>> * Check for close-state is necessary, because we may have been closed
>>>>> diff --git a/net/mptcp/mptcp_ipv6.c b/net/mptcp/mptcp_ipv6.c
>>>>> index 0de953d..1959d01 100644
>>>>> --- a/net/mptcp/mptcp_ipv6.c
>>>>> +++ b/net/mptcp/mptcp_ipv6.c
>>>>> @@ -199,7 +199,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk,
>>>>> struct sk_buff *skb)
>>>>> struct sock *child, *rsk = NULL;
>>>>> int ret;
>>>>> -if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
>>>>> +if (!(skb->mptcp_flags & MPTCPHDR_JOIN)) {
>>>>> struct tcphdr *th = tcp_hdr(skb);
>>>>> const struct ipv6hdr *ip6h = ipv6_hdr(skb);
>>>>> struct sock *sk;
>>>>> @@ -232,7 +232,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk,
>>>>> struct sk_buff *skb)
>>>>> return ret;
>>>>> }
>>>>> -TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>>> +skb->mptcp_flags = 0;
>>>>> /* Has been removed from the tk-table. Thus, no new subflows.
>>>>> *
>>>>> diff --git a/net/mptcp/mptcp_output.c b/net/mptcp/mptcp_output.c
>>>>> index 691ef6f..e7d340d 100644
>>>>> --- a/net/mptcp/mptcp_output.c
>>>>> +++ b/net/mptcp/mptcp_output.c
>>>>> @@ -59,39 +59,17 @@ EXPORT_SYMBOL(mptcp_sub_len_remove_addr_align);
>>>>> */
>>>>> static bool mptcp_reconstruct_mapping(struct sk_buff *skb)
>>>>> {
>>>>> -const struct mp_dss *mpdss = (struct mp_dss *)TCP_SKB_CB(skb)->dss;
>>>>> -u32 *p32;
>>>>> -u16 *p16;
>>>>> -
>>>>> if (!mptcp_is_data_seq(skb))
>>>>> return false;
>>>>> -if (!mpdss->M)
>>>>> -return false;
>>>>> -
>>>>> -/* Move the pointer to the data-seq */
>>>>> -p32 = (u32 *)mpdss;
>>>>> -p32++;
>>>>> -if (mpdss->A) {
>>>>> -p32++;
>>>>> -if (mpdss->a)
>>>>> -p32++;
>>>>> -}
>>>>> -
>>>>> -TCP_SKB_CB(skb)->seq = ntohl(*p32);
>>>>> -
>>>>> -/* Get the data_len to calculate the end_data_seq */
>>>>> -p32++;
>>>>> -p32++;
>>>>> -p16 = (u16 *)p32;
>>>>> -TCP_SKB_CB(skb)->end_seq = ntohs(*p16) + TCP_SKB_CB(skb)->seq;
>>>>> +TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->mptcp_data_seq;
>>>>> return true;
>>>>> }
>>>>> static bool mptcp_is_reinjected(const struct sk_buff *skb)
>>>>> {
>>>>> -return TCP_SKB_CB(skb)->mptcp_flags & MPTCP_REINJECT;
>>>>> +return skb->mptcp_flags & MPTCP_REINJECT;
>>>>> }
>>>>> static void mptcp_find_and_set_pathmask(const struct sock
>>>>> *meta_sk, struct sk_buff *skb)
>>>>> @@ -105,7 +83,7 @@ static void mptcp_find_and_set_pathmask(const
>>>>> struct sock *meta_sk, struct sk_bu
>>>>> break;
>>>>> if (TCP_SKB_CB(skb_it)->seq == TCP_SKB_CB(skb)->seq) {
>>>>> -TCP_SKB_CB(skb)->path_mask = TCP_SKB_CB(skb_it)->path_mask;
>>>>> +TCP_SKB_CB(skb)->mptcp_path_mask =
>>>>> TCP_SKB_CB(skb_it)->mptcp_path_mask;
>>>>> break;
>>>>> }
>>>>> }
>>>>> @@ -180,9 +158,9 @@ static void __mptcp_reinject_data(struct
>>>>> sk_buff *orig_skb, struct sock *meta_sk
>>>>> }
>>>>> /* Segment goes back to the MPTCP-layer. So, we need to zero the
>>>>> -* path_mask/dss.
>>>>> +* path_mask.
>>>>> */
>>>>> -memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
>>>>> +TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>>>> /* We need to find out the path-mask from the meta-write-queue
>>>>> * to properly select a subflow.
>>>>> @@ -272,14 +250,14 @@ void mptcp_reinject_data(struct sock *sk,
>>>>> int clone_it)
>>>>> if (mptcp_is_reinjected(skb_it))
>>>>> continue;
>>>>> -tcb->mptcp_flags |= MPTCP_REINJECT;
>>>>> +skb_it->mptcp_flags |= MPTCP_REINJECT;
>>>>> __mptcp_reinject_data(skb_it, meta_sk, sk, clone_it);
>>>>> }
>>>>> skb_it = tcp_write_queue_tail(meta_sk);
>>>>> /* If sk has sent the empty data-fin, we have to reinject it too. */
>>>>> if (skb_it && mptcp_is_data_fin(skb_it) && skb_it->len == 0 &&
>>>>> - TCP_SKB_CB(skb_it)->path_mask &
>>>>> mptcp_pi_to_flag(tp->mptcp->path_index)) {
>>>>> + TCP_SKB_CB(skb_it)->mptcp_path_mask &
>>>>> mptcp_pi_to_flag(tp->mptcp->path_index)) {
>>>>> __mptcp_reinject_data(skb_it, meta_sk, NULL, 1);
>>>>> }
>>>>> @@ -319,25 +297,43 @@ combine:
>>>>> }
>>>>> }
>>>>> -static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
>>>>> const struct sk_buff *skb,
>>>>> - __be32 *ptr)
>>>>> +/*
>>>>> + * RFC6824 states that once a particular subflow mapping has been
>>>>> sent
>>>>> + * out it must never be changed. However, packets may be split while
>>>>> + * they are in the retransmission queue (due to SACK or ACKs) and
>>>>> that
>>>>> + * arguably means that we would change the mapping (e.g. it
>>>>> splits it,
>>>>> + * our sends out a subset of the initial mapping).
>>>>> + *
>>>>> + * Furthermore, the skb checksum is not always preserved across
>>>>> splits
>>>>> + * (e.g. mptcp_fragment) which would mean that we need to recompute
>>>>> + * the DSS checksum in this case.
>>>>> + *
>>>>> + * To avoid this we save the initial DSS mapping which allows us to
>>>>> + * send the same DSS mapping even for fragmented retransmits.
>>>>> + */
>>>>> +
>>>>> +static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
>>>>> + const struct sk_buff *skb, __be32 *ptr)
>>>>> {
>>>>> const struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>>> -__be32 *start = ptr;
>>>>> __u16 data_len;
>>>>> -*ptr++ = htonl(tcb->seq); /* data_seq */
>>>>> +*ptr++ = htonl(tcb->mptcp_data_seq); /* data_seq */
>>>>> /* If it's a non-data DATA_FIN, we set subseq to 0 (draft v7) */
>>>>> if (mptcp_is_data_fin(skb) && skb->len == 0)
>>>>> *ptr++ = 0; /* subseq */
>>>>> else
>>>>> -*ptr++ = htonl(tp->write_seq - tp->mptcp->snt_isn); /* subseq */
>>>>> +*ptr++ = htonl(tcb->seq - tp->mptcp->snt_isn); /* subseq */
>>>>> -if (tcb->mptcp_flags & MPTCPHDR_INF)
>>>>> +if (skb->mptcp_flags & MPTCPHDR_INF)
>>>>> data_len = 0;
>>>>> -else
>>>>> +else {
>>>>> data_len = tcb->end_seq - tcb->seq;
>>>>> +/* mptcp_entail_skb adds one for FIN */
>>>>> +if (tcb->tcp_flags & TCPHDR_FIN)
>>>>> +data_len -= 1;
>>>>> +}
>>>>> if (tp->mpcb->dss_csum && data_len) {
>>>>> __be16 *p16 = (__be16 *)ptr;
>>>>> @@ -356,11 +352,11 @@ static int mptcp_write_dss_mapping(const
>>>>> struct tcp_sock *tp, const struct sk_bu
>>>>> (TCPOPT_NOP));
>>>>> }
>>>>> -return ptr - start;
>>>>> +return mptcp_dss_len/sizeof(*ptr);
>>>>> }
>>>>> -static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
>>>>> const struct sk_buff *skb,
>>>>> - __be32 *ptr)
>>>>> +static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
>>>>> + const struct sk_buff *skb, __be32 *ptr)
>>>>> {
>>>>> struct mp_dss *mdss = (struct mp_dss *)ptr;
>>>>> __be32 *start = ptr;
>>>>> @@ -377,54 +373,12 @@ static int mptcp_write_dss_data_ack(const
>>>>> struct tcp_sock *tp, const struct sk_b
>>>>> mdss->len = mptcp_sub_len_dss(mdss, tp->mpcb->dss_csum);
>>>>> ptr++;
>>>>> +/* data_ack */
>>>>> *ptr++ = htonl(mptcp_meta_tp(tp)->rcv_nxt);
>>>>> return ptr - start;
>>>>> }
>>>>> -/* RFC6824 states that once a particular subflow mapping has been
>>>>> sent
>>>>> - * out it must never be changed. However, packets may be split while
>>>>> - * they are in the retransmission queue (due to SACK or ACKs) and
>>>>> that
>>>>> - * arguably means that we would change the mapping (e.g. it
>>>>> splits it,
>>>>> - * our sends out a subset of the initial mapping).
>>>>> - *
>>>>> - * Furthermore, the skb checksum is not always preserved across
>>>>> splits
>>>>> - * (e.g. mptcp_fragment) which would mean that we need to recompute
>>>>> - * the DSS checksum in this case.
>>>>> - *
>>>>> - * To avoid this we save the initial DSS mapping which allows us to
>>>>> - * send the same DSS mapping even for fragmented retransmits.
>>>>> - */
>>>>> -static void mptcp_save_dss_data_seq(const struct tcp_sock *tp,
>>>>> struct sk_buff *skb)
>>>>> -{
>>>>> -struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>>> -__be32 *ptr = (__be32 *)tcb->dss;
>>>>> -
>>>>> -tcb->mptcp_flags |= MPTCPHDR_SEQ;
>>>>> -
>>>>> -ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>>>> -ptr += mptcp_write_dss_mapping(tp, skb, ptr);
>>>>> -}
>>>>> -
>>>>> -/* Write the saved DSS mapping to the header */
>>>>> -static int mptcp_write_dss_data_seq(const struct tcp_sock *tp,
>>>>> struct sk_buff *skb,
>>>>> - __be32 *ptr)
>>>>> -{
>>>>> -__be32 *start = ptr;
>>>>> -
>>>>> -memcpy(ptr, TCP_SKB_CB(skb)->dss, mptcp_dss_len);
>>>>> -
>>>>> -/* update the data_ack */
>>>>> -start[1] = htonl(mptcp_meta_tp(tp)->rcv_nxt);
>>>>> -
>>>>> -/* dss is in a union with inet_skb_parm and
>>>>> -* the IP layer expects zeroed IPCB fields.
>>>>> -*/
>>>>> -memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
>>>>> -
>>>>> -return mptcp_dss_len/sizeof(*ptr);
>>>>> -}
>>>>> -
>>>>> static bool mptcp_skb_entail(struct sock *sk, struct sk_buff
>>>>> *skb, int reinject)
>>>>> {
>>>>> struct tcp_sock *tp = tcp_sk(sk);
>>>>> @@ -434,7 +388,7 @@ static bool mptcp_skb_entail(struct sock *sk,
>>>>> struct sk_buff *skb, int reinject)
>>>>> struct sk_buff *subskb = NULL;
>>>>> if (!reinject)
>>>>> -TCP_SKB_CB(skb)->mptcp_flags |= (mpcb->snd_hiseq_index ?
>>>>> +skb->mptcp_flags |= (mpcb->snd_hiseq_index ?
>>>>> MPTCPHDR_SEQ64_INDEX : 0);
>>>>> subskb = pskb_copy_for_clone(skb, GFP_ATOMIC);
>>>>> @@ -447,7 +401,7 @@ static bool mptcp_skb_entail(struct sock *sk,
>>>>> struct sk_buff *skb, int reinject)
>>>>> */
>>>>> tcp_skb_pcount_set(subskb, 0);
>>>>> -TCP_SKB_CB(skb)->path_mask |=
>>>>> mptcp_pi_to_flag(tp->mptcp->path_index);
>>>>> +TCP_SKB_CB(skb)->mptcp_path_mask |=
>>>>> mptcp_pi_to_flag(tp->mptcp->path_index);
>>>>> if (!(sk->sk_route_caps & NETIF_F_ALL_CSUM) &&
>>>>> skb->ip_summed == CHECKSUM_PARTIAL) {
>>>>> @@ -463,13 +417,14 @@ static bool mptcp_skb_entail(struct sock
>>>>> *sk, struct sk_buff *skb, int reinject)
>>>>> tp->mptcp->fully_established = 1;
>>>>> tp->mpcb->infinite_mapping_snd = 1;
>>>>> tp->mptcp->infinite_cutoff_seq = tp->write_seq;
>>>>> -tcb->mptcp_flags |= MPTCPHDR_INF;
>>>>> +skb->mptcp_flags |= MPTCPHDR_INF;
>>>>> }
>>>>> if (mptcp_is_data_fin(subskb))
>>>>> mptcp_combine_dfin(subskb, meta_sk, sk);
>>>>> -mptcp_save_dss_data_seq(tp, subskb);
>>>>> +subskb->mptcp_flags |= MPTCPHDR_SEQ;
>>>>> +tcb->mptcp_data_seq = tcb->seq;
>>>>> tcb->seq = tp->write_seq;
>>>>> @@ -536,10 +491,10 @@ static int mptcp_fragment(struct sock
>>>>> *meta_sk, struct sk_buff *skb, u32 len,
>>>>> buff = skb->next;
>>>>> -flags = TCP_SKB_CB(skb)->mptcp_flags;
>>>>> -TCP_SKB_CB(skb)->mptcp_flags = flags & ~(MPTCPHDR_FIN);
>>>>> -TCP_SKB_CB(buff)->mptcp_flags = flags;
>>>>> -TCP_SKB_CB(buff)->path_mask = TCP_SKB_CB(skb)->path_mask;
>>>>> +flags = skb->mptcp_flags;
>>>>> +skb->mptcp_flags = flags & ~(MPTCPHDR_FIN);
>>>>> +buff->mptcp_flags = flags;
>>>>> +TCP_SKB_CB(buff)->mptcp_path_mask = TCP_SKB_CB(skb)->mptcp_path_mask;
>>>>> /* If reinject == 1, the buff will be added to the reinject
>>>>> * queue, which is currently not part of memory accounting. So
>>>>> @@ -927,8 +882,9 @@ void mptcp_established_options(struct sock
>>>>> *sk, struct sk_buff *skb,
>>>>> * It does not make sense to check for the options, because when the
>>>>> * segment gets sent, another subflow will be chosen.
>>>>> */
>>>>> -if (!skb && is_meta_sk(sk))
>>>>> +if (!skb && is_meta_sk(sk)) {
>>>>> return;
>>>>> +}
>>>>> /* In fallback mp_fail-mode, we have to repeat it until the fallback
>>>>> * has been done by the sender
>>>>> @@ -967,10 +923,11 @@ void mptcp_established_options(struct sock
>>>>> *sk, struct sk_buff *skb,
>>>>> if (unlikely(mpcb->infinite_mapping_snd) &&
>>>>> ((mpcb->send_infinite_mapping && tcb &&
>>>>> mptcp_is_data_seq(skb) &&
>>>>> - !(tcb->mptcp_flags & MPTCPHDR_INF) &&
>>>>> + !(skb->mptcp_flags & MPTCPHDR_INF) &&
>>>>> !before(tcb->seq, tp->mptcp->infinite_cutoff_seq)) ||
>>>>> - !mpcb->send_infinite_mapping))
>>>>> + !mpcb->send_infinite_mapping)) {
>>>>> return;
>>>>> +}
>>>>> if (unlikely(tp->mptcp->include_mpc)) {
>>>>> opts->options |= OPTION_MPTCP;
>>>>> @@ -995,9 +952,11 @@ void mptcp_established_options(struct sock
>>>>> *sk, struct sk_buff *skb,
>>>>> mpcb->mptcp_ver >= MPTCP_VERSION_1 && skb &&
>>>>> !mptcp_is_data_seq(skb)) {
>>>>> mpcb->pm_ops->addr_signal(sk, size, opts, skb);
>>>>> -if (opts->add_addr_v6)
>>>>> +if (opts->add_addr_v6) {
>>>>> +
>>>>> /* Skip subsequent options */
>>>>> return;
>>>>> +}
>>>>> }
>>>>> if (!tp->mptcp->include_mpc && !tp->mptcp->pre_established) {
>>>>> @@ -1197,10 +1156,11 @@ void mptcp_options_write(__be32 *ptr,
>>>>> struct tcp_sock *tp,
>>>>> }
>>>>> if (OPTION_DATA_ACK & opts->mptcp_options) {
>>>>> -if (!mptcp_is_data_seq(skb))
>>>>> -ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>>>> -else
>>>>> -ptr += mptcp_write_dss_data_seq(tp, skb, ptr);
>>>>> +ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>>>> +if (mptcp_is_data_seq(skb)) {
>>>>> +ptr += mptcp_write_dss_mapping(tp, skb, ptr);
>>>>> +}
>>>>> +skb->dev = NULL;
>>>>> }
>>>>> if (unlikely(OPTION_MP_PRIO & opts->mptcp_options)) {
>>>>> struct mp_prio *mpprio = (struct mp_prio *)ptr;
>>>>> @@ -1233,7 +1193,7 @@ void mptcp_send_fin(struct sock *meta_sk)
>>>>> mss_now = mptcp_current_mss(meta_sk);
>>>>> if (tcp_send_head(meta_sk) != NULL) {
>>>>> -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
>>>>> +skb->mptcp_flags |= MPTCPHDR_FIN;
>>>>> TCP_SKB_CB(skb)->end_seq++;
>>>>> meta_tp->write_seq++;
>>>>> } else {
>>>>> @@ -1250,7 +1210,7 @@ void mptcp_send_fin(struct sock *meta_sk)
>>>>> tcp_init_nondata_skb(skb, meta_tp->write_seq, TCPHDR_ACK);
>>>>> TCP_SKB_CB(skb)->end_seq++;
>>>>> -TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
>>>>> +skb->mptcp_flags |= MPTCPHDR_FIN;
>>>>> tcp_queue_skb(meta_sk, skb);
>>>>> }
>>>>> __tcp_push_pending_frames(meta_sk, mss_now, TCP_NAGLE_OFF);
>>>>> diff --git a/net/mptcp/mptcp_redundant.c b/net/mptcp/mptcp_redundant.c
>>>>> index 8fa2dba..37a13f4 100644
>>>>> --- a/net/mptcp/mptcp_redundant.c
>>>>> +++ b/net/mptcp/mptcp_redundant.c
>>>>> @@ -72,10 +72,10 @@ static bool redsched_use_subflow(struct sock
>>>>> *meta_sk,
>>>>> if (!skb || !mptcp_is_available((struct sock *)tp, skb, false))
>>>>> return false;
>>>>> -if (TCP_SKB_CB(skb)->path_mask != 0)
>>>>> +if (TCP_SKB_CB(skb)->mptcp_path_mask != 0)
>>>>> return subflow_is_active(tp);
>>>>> -if (TCP_SKB_CB(skb)->path_mask == 0) {
>>>>> +if (TCP_SKB_CB(skb)->mptcp_path_mask == 0) {
>>>>> if (active_valid_sks == -1)
>>>>> active_valid_sks = redsched_get_active_valid_sks(meta_sk);
>>>>> @@ -209,7 +209,7 @@ static struct sk_buff
>>>>> *redundant_next_segment(struct sock *meta_sk,
>>>>> cb_data->next_subflow = tp->mptcp->next;
>>>>> *subsk = (struct sock *)tp;
>>>>> -if (TCP_SKB_CB(skb)->path_mask)
>>>>> +if (TCP_SKB_CB(skb)->mptcp_path_mask)
>>>>> *reinject = -1;
>>>>> return skb;
>>>>> }
>>>>> diff --git a/net/mptcp/mptcp_rr.c b/net/mptcp/mptcp_rr.c
>>>>> index 8910ba9..83837f2 100644
>>>>> --- a/net/mptcp/mptcp_rr.c
>>>>> +++ b/net/mptcp/mptcp_rr.c
>>>>> @@ -93,7 +93,7 @@ static int mptcp_rr_dont_reinject_skb(const
>>>>> struct tcp_sock *tp, const struct sk
>>>>> */
>>>>> return skb &&
>>>>> /* Has the skb already been enqueued into this subsocket? */
>>>>> -mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
>>>>> +mptcp_pi_to_flag(tp->mptcp->path_index) &
>>>>> TCP_SKB_CB(skb)->mptcp_path_mask;
>>>>> }
>>>>> /* We just look for any subflow that is available */
>>>>> @@ -136,7 +136,7 @@ static struct sock
>>>>> *rr_get_available_subflow(struct sock *meta_sk,
>>>>> * chance again by restarting its pathmask.
>>>>> */
>>>>> if (skb)
>>>>> -TCP_SKB_CB(skb)->path_mask = 0;
>>>>> +TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>>>> sk = backupsk;
>>>>> }
>>>>> diff --git a/net/mptcp/mptcp_sched.c b/net/mptcp/mptcp_sched.c
>>>>> index 54408ff..5cbbf91 100644
>>>>> --- a/net/mptcp/mptcp_sched.c
>>>>> +++ b/net/mptcp/mptcp_sched.c
>>>>> @@ -118,7 +118,7 @@ static int mptcp_dont_reinject_skb(const
>>>>> struct tcp_sock *tp, const struct sk_bu
>>>>> */
>>>>> return skb &&
>>>>> /* Has the skb already been enqueued into this subsocket? */
>>>>> -mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
>>>>> +mptcp_pi_to_flag(tp->mptcp->path_index) &
>>>>> TCP_SKB_CB(skb)->mptcp_path_mask;
>>>>> }
>>>>> bool subflow_is_backup(const struct tcp_sock *tp)
>>>>> @@ -261,7 +261,7 @@ struct sock *get_available_subflow(struct sock
>>>>> *meta_sk, struct sk_buff *skb,
>>>>> * the skb passed through all the available active and backups
>>>>> * sks, so clean the path mask
>>>>> */
>>>>> -TCP_SKB_CB(skb)->path_mask = 0;
>>>>> +TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>>>> return sk;
>>>>> }
>>>>> EXPORT_SYMBOL_GPL(get_available_subflow);
>>>>> @@ -298,7 +298,7 @@ static struct sk_buff
>>>>> *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
>>>>> /* Half the cwnd of the slow flow */
>>>>> mptcp_for_each_tp(tp->mpcb, tp_it) {
>>>>> if (tp_it != tp &&
>>>>> - TCP_SKB_CB(skb_head)->path_mask &
>>>>> mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>>> + TCP_SKB_CB(skb_head)->mptcp_path_mask &
>>>>> mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>>> if (tp->srtt_us < tp_it->srtt_us && inet_csk((struct sock
>>>>> *)tp_it)->icsk_ca_state == TCP_CA_Open) {
>>>>> u32 prior_cwnd = tp_it->snd_cwnd;
>>>>> @@ -317,11 +317,11 @@ static struct sk_buff
>>>>> *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
>>>>> retrans:
>>>>> /* Segment not yet injected into this path? Take it!!! */
>>>>> -if (!(TCP_SKB_CB(skb_head)->path_mask &
>>>>> mptcp_pi_to_flag(tp->mptcp->path_index))) {
>>>>> +if (!(TCP_SKB_CB(skb_head)->mptcp_path_mask &
>>>>> mptcp_pi_to_flag(tp->mptcp->path_index))) {
>>>>> bool do_retrans = false;
>>>>> mptcp_for_each_tp(tp->mpcb, tp_it) {
>>>>> if (tp_it != tp &&
>>>>> - TCP_SKB_CB(skb_head)->path_mask &
>>>>> mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>>> + TCP_SKB_CB(skb_head)->mptcp_path_mask &
>>>>> mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>>> if (tp_it->snd_cwnd <= 4) {
>>>>> do_retrans = true;
>>>>> break;
>>>> _______________________________________________
>>>> mptcp mailing list
>>>> mptcp(a)lists.01.org <mailto:mptcp(a)lists.01.org>
>>>> https://lists.01.org/mailman/listinfo/mptcp
>>
>
[-- Attachment #2: attachment.html --]
[-- Type: text/html, Size: 241322 bytes --]
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-27 17:37 Christoph Paasch
0 siblings, 0 replies; 14+ messages in thread
From: Christoph Paasch @ 2017-06-27 17:37 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 60493 bytes --]
Hello Rao,
> On Jun 27, 2017, at 10:22 AM, Rao Shoaib <rao.shoaib(a)oracle.com> wrote:
>
> Hi Christoph,
>
>
> On 06/26/2017 11:27 PM, Christoph Paasch wrote:
>> Hello Rao,
>>
>> can you try to give some more details on how the datapath looks like with
>> this patch?
>>
>> For example, I wonder how data-acks are being processed. Because, I see in
>> mptcp_data_ready, that you now expects skbs with len 0, upon which you end
>> up calling mptcp_process_ack().
>>
>> I don't see how such zero-length skbs could end up in the receive-queue of
>> the subflows.
>>
>>
>> Thanks,
>
> I send every packet that is coming on an MPTCP based socket down and let MPTCP deal with it. In tcp data_queue(). I also removed the directive to go to the slow_path in tcp_rcv_established().
>
> static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
> {
> struct tcp_sock *tp = tcp_sk(sk);
> int eaten = -1;
> bool fragstolen = false;
>
> /*
> * send every packet to MPTCP
> */
> if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)) {
> goto drop;
> }
>
> There is only one case that I need investigate more is the following. In that the he only interesting case is (len == tcp_header_len) but in my unidirectional bulk data transfer tests I did not hit that case. So I need to investigate more later. The last resort would be to just directly go to the slow path.
>
> if (len <= tcp_header_len) { /* Bulk data transfer: sender */
>
> if (len == tcp_header_len) {
The problem is, how are these zero-len packets being queued in the receive-queue of the socket ? I am pretty sure that TCP won't like having such packets in the receive-queue, which means there will be quite some changes needed to support this.
I might be missing something here. A high-level description with some call-stacks of how the data-path looks like with your patch would be good. Or maybe try to split the patch in separate pieces.
>
> If there are other issues than let me know and I will work on resolving them. We obviously need to run extensive tests, that brings me to the question of, how does the MPTCP development team test changes. We need the same tests to validate the changes.
packetdrill is the best tool to reproduce specific scenarios: https://github.com/cpaasch/packetdrill_mptcp <https://github.com/cpaasch/packetdrill_mptcp> (tests are in there in example/mptcp/).
And, a testing-script is at https://github.com/multipath-tcp/mptcp-scripts/tree/master/testing <https://github.com/multipath-tcp/mptcp-scripts/tree/master/testing>.
It does a bunch of stress-testing (iperf, haproxy, apache-benchmark,...) on three machines that need to be inter-connected in a specific way. It's a bit tricky to setup. I have KVMs that I boot that have two links between each other. One is the client, one the router (sometimes acting as a haproxy), one is the server. They need tools like ab, apache, haproxy, iperf,...
Christoph
>
> Rao.
>
>> Christoph
>>
>>
>> On 26/06/17 - 15:34:09, Rao Shoaib wrote:
>>> I forgot to mention two things
>>>
>>> 1) Connection setup still has checks for MPTCP, Ideally these should be
>>> removed but at least we need to run some benchmarks and fix any issues. The
>>> mainstream folks will not accept any performance degradation in TCP. I can
>>> look into this next.
>>>
>>> 2) The code overloads dev field of skb, when it is not being used. IIRC
>>> there is precedence for this already. I will try to find it.
>>>
>>> Rao
>>>
>>>
>>> On 06/26/2017 02:13 PM, Rao Shoaib wrote:
>>>> This patch returns tcp_skb_cb to it's original size. It also refactors MPTCP code so that there are no MPTCP checks in the main Rx pathi, no performance overheads such as cpu prodiction issues. tcp_v4_rcv() and tcp_v4_do_rcv() do not have any MPTCP specific checks any more, niether does tcp_ack(). On the Rx path MPTCP options are not parsed till the data is being pushed up to the meta socket (mptcp_data_ready). on the Tx side there is one check to add MPTCP specific options but that's it, that should not be that bad as for regular TCP it is a simple check, but it would be good to remove it..
>>>>
>>>> I have tested the changes with ndiffports set to 2, so join works. I have also tested accessing multipath-tcp.org and downloading files from there and also ran the speed test.
>>>>
>>>> The Bad:
>>>>
>>>> The error cases still have MPTCP checks but that should be OK as they are error cases. I had to use a special marker 0xFEE1DEAD for indicate a special case. I had to introdue a new socket specfic function. IPv6 has not been changed yet. I am sure I have missed some corner cases and more testing will reveal more issues but we just have to fix them.
>>>>
>>>> I would like to hear comments from the list and if this direction seems reasonable we can take this as the starting point, port it to latest Linux and share the design with the mainstream folks.
>>>>
>>>> Signed-off-by: Rao Shoaib <rao.shoaib(a)oracle.com>
>>>> ---
>>>> include/linux/skbuff.h | 8 ++-
>>>> include/net/mptcp.h | 21 +++---
>>>> include/net/mptcp_v4.h | 1 +
>>>> include/net/sock.h | 12 +++-
>>>> include/net/tcp.h | 23 +++----
>>>> net/ipv4/af_inet.c | 4 ++
>>>> net/ipv4/tcp_input.c | 37 ++--------
>>>> net/ipv4/tcp_ipv4.c | 135 +++++++++++++++++++++++--------------
>>>> net/ipv4/tcp_output.c | 1 +
>>>> net/ipv6/af_inet6.c | 4 ++
>>>> net/ipv6/tcp_ipv6.c | 4 --
>>>> net/mptcp/mptcp_ctrl.c | 21 ++++++
>>>> net/mptcp/mptcp_input.c | 131 ++++++++++++++++++++++++++++--------
>>>> net/mptcp/mptcp_ipv4.c | 35 +---------
>>>> net/mptcp/mptcp_ipv6.c | 4 +-
>>>> net/mptcp/mptcp_output.c | 160 +++++++++++++++++---------------------------
>>>> net/mptcp/mptcp_redundant.c | 6 +-
>>>> net/mptcp/mptcp_rr.c | 4 +-
>>>> net/mptcp/mptcp_sched.c | 10 +--
>>>> 19 files changed, 335 insertions(+), 286 deletions(-)
>>>>
>>>> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
>>>> index f66cd5e..348cbc1 100644
>>>> --- a/include/linux/skbuff.h
>>>> +++ b/include/linux/skbuff.h
>>>> @@ -532,7 +532,13 @@ struct sk_buff {
>>>> struct rb_node rbnode; /* used in netem & tcp stack */
>>>> };
>>>> struct sock *sk;
>>>> - struct net_device *dev;
>>>> + union {
>>>> + struct net_device *dev;
>>>> + struct {
>>>> + __u8 mptcp_flags;
>>>> + __u8 mptcp_dss_off;
>>>> + };
>>>> + };
>>>> /*
>>>> * This is the control buffer. It is free to use for every
>>>> diff --git a/include/net/mptcp.h b/include/net/mptcp.h
>>>> index 876f1e6..d087cb4 100644
>>>> --- a/include/net/mptcp.h
>>>> +++ b/include/net/mptcp.h
>>>> @@ -807,7 +807,7 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
>>>> struct mptcp_options_received *mopt);
>>>> void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>>> struct mptcp_options_received *mopt,
>>>> - const struct sk_buff *skb,
>>>> + struct sk_buff *skb,
>>>> struct tcp_sock *tp);
>>>> void mptcp_syn_options(const struct sock *sk, struct tcp_out_options *opts,
>>>> unsigned *remaining);
>>>> @@ -998,14 +998,15 @@ static inline void mptcp_sub_force_close_all(struct mptcp_cb *mpcb,
>>>> }
>>>> }
>>>> +/* currently tp is being used for Rx packets */
>>>> static inline bool mptcp_is_data_seq(const struct sk_buff *skb)
>>>> {
>>>> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ;
>>>> + return skb->mptcp_flags & MPTCPHDR_SEQ;
>>>> }
>>>> static inline bool mptcp_is_data_fin(const struct sk_buff *skb)
>>>> {
>>>> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_FIN;
>>>> + return skb->mptcp_flags & MPTCPHDR_FIN;
>>>> }
>>>> /* Is it a data-fin while in infinite mapping mode?
>>>> @@ -1034,17 +1035,17 @@ static inline u8 mptcp_get_64_bit(u64 data_seq, struct mptcp_cb *mpcb)
>>>> /* Sets the data_seq and returns pointer to the in-skb field of the data_seq.
>>>> * If the packet has a 64-bit dseq, the pointer points to the last 32 bits.
>>>> */
>>>> -static inline __u32 *mptcp_skb_set_data_seq(const struct sk_buff *skb,
>>>> +static inline __u32 *mptcp_skb_set_data_seq(struct sk_buff *skb,
>>>> u32 *data_seq,
>>>> struct mptcp_cb *mpcb)
>>>> {
>>>> - __u32 *ptr = (__u32 *)(skb_transport_header(skb) + TCP_SKB_CB(skb)->dss_off);
>>>> + __u32 *ptr = (__u32 *)(skb_transport_header(skb) + skb->mptcp_dss_off);
>>>> - if (TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ64_SET) {
>>>> + if (skb->mptcp_flags & MPTCPHDR_SEQ64_SET) {
>>>> u64 data_seq64 = get_unaligned_be64(ptr);
>>>> if (mpcb)
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
>>>> + skb->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
>>>> *data_seq = (u32)data_seq64;
>>>> ptr++;
>>>> @@ -1142,7 +1143,7 @@ static inline void mptcp_reset_mopt(struct tcp_sock *tp)
>>>> static inline __be32 mptcp_get_highorder_sndbits(const struct sk_buff *skb,
>>>> const struct mptcp_cb *mpcb)
>>>> {
>>>> - return htonl(mpcb->snd_high_order[(TCP_SKB_CB(skb)->mptcp_flags &
>>>> + return htonl(mpcb->snd_high_order[(skb->mptcp_flags &
>>>> MPTCPHDR_SEQ64_INDEX) ? 1 : 0]);
>>>> }
>>>> @@ -1404,8 +1405,8 @@ static inline void mptcp_set_rto(const struct sock *sk) {}
>>>> static inline void mptcp_send_fin(const struct sock *meta_sk) {}
>>>> static inline void mptcp_parse_options(const uint8_t *ptr, const int opsize,
>>>> struct mptcp_options_received *mopt,
>>>> - const struct sk_buff *skb,
>>>> - const struct tcp_sock *tp) {}
>>>> + struct sk_buff *skb,
>>>> + struct tcp_sock *tp) {}
>>>> static inline void mptcp_syn_options(const struct sock *sk,
>>>> struct tcp_out_options *opts,
>>>> unsigned *remaining) {}
>>>> diff --git a/include/net/mptcp_v4.h b/include/net/mptcp_v4.h
>>>> index c83dca0..46394a4 100644
>>>> --- a/include/net/mptcp_v4.h
>>>> +++ b/include/net/mptcp_v4.h
>>>> @@ -45,6 +45,7 @@ extern struct tcp_request_sock_ops mptcp_join_request_sock_ipv4_ops;
>>>> #ifdef CONFIG_MPTCP
>>>> int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb);
>>>> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb);
>>>> struct sock *mptcp_v4_search_req(const __be16 rport, const __be32 raddr,
>>>> const __be32 laddr, const struct net *net);
>>>> int mptcp_init4_subsockets(struct sock *meta_sk, const struct mptcp_loc4 *loc,
>>>> diff --git a/include/net/sock.h b/include/net/sock.h
>>>> index 0f12593..0d1bda5 100644
>>>> --- a/include/net/sock.h
>>>> +++ b/include/net/sock.h
>>>> @@ -296,6 +296,7 @@ struct cg_proto;
>>>> * @sk_write_space: callback to indicate there is bf sending space available
>>>> * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
>>>> * @sk_backlog_rcv: callback to process the backlog
>>>> + * @sk_prequeue: callback to prequeue
>>>> * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
>>>> */
>>>> struct sock {
>>>> @@ -437,7 +438,9 @@ struct sock {
>>>> void (*sk_write_space)(struct sock *sk);
>>>> void (*sk_error_report)(struct sock *sk);
>>>> int (*sk_backlog_rcv)(struct sock *sk,
>>>> - struct sk_buff *skb);
>>>> + struct sk_buff *skb);
>>>> + bool (*sk_prequeue)(struct sock *sk,
>>>> + struct sk_buff *skb);
>>>> void (*sk_destruct)(struct sock *sk);
>>>> };
>>>> @@ -853,6 +856,11 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
>>>> return sk->sk_backlog_rcv(sk, skb);
>>>> }
>>>> +static inline bool sk_prequeue(struct sock *sk, struct sk_buff *skb)
>>>> +{
>>>> + return (false);
>>>> +}
>>>> +
>>>> static inline void sk_incoming_cpu_update(struct sock *sk)
>>>> {
>>>> sk->sk_incoming_cpu = raw_smp_processor_id();
>>>> @@ -993,6 +1001,8 @@ struct proto {
>>>> int (*backlog_rcv) (struct sock *sk,
>>>> struct sk_buff *skb);
>>>> + bool (*prequeue) (struct sock *sk,
>>>> + struct sk_buff *skb);
>>>> void (*release_cb)(struct sock *sk);
>>>> diff --git a/include/net/tcp.h b/include/net/tcp.h
>>>> index 655ecd4..cbe8ef2 100644
>>>> --- a/include/net/tcp.h
>>>> +++ b/include/net/tcp.h
>>>> @@ -47,6 +47,9 @@
>>>> #include <linux/seq_file.h>
>>>> #include <linux/memcontrol.h>
>>>> +typedef int (* process_unclaimed)(struct sock *sk, struct sk_buff *skb);
>>>> +extern process_unclaimed tcp_process_unclaimed;
>>>> +
>>>> extern struct inet_hashinfo tcp_hashinfo;
>>>> extern struct percpu_counter tcp_orphan_count;
>>>> @@ -581,6 +584,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
>>>> struct request_sock *req,
>>>> struct dst_entry *dst);
>>>> int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
>>>> +
>>>> int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
>>>> int tcp_connect(struct sock *sk);
>>>> struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
>>>> @@ -842,11 +846,6 @@ struct tcp_skb_cb {
>>>> __u32 tcp_gso_segs;
>>>> };
>>>> -#ifdef CONFIG_MPTCP
>>>> - __u8 mptcp_flags; /* flags for the MPTCP layer */
>>>> - __u8 dss_off; /* Number of 4-byte words until
>>>> - * seq-number */
>>>> -#endif
>>>> __u8 tcp_flags; /* TCP header flags. (tcp[13]) */
>>>> __u8 sacked; /* State flags for SACK/FACK. */
>>>> @@ -859,9 +858,13 @@ struct tcp_skb_cb {
>>>> #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
>>>> TCPCB_REPAIRED)
>>>> - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
>>>> + __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
>>>> /* 1 byte hole */
>>>> - __u32 ack_seq; /* Sequence number ACK'd */
>>>> + union {
>>>> + __u32 ack_seq; /* Sequence number ACK'd */
>>>> + __u32 mptcp_data_seq;
>>>> + __u32 mptcp_path_mask;
>>>> + };
>>>> union {
>>>> union {
>>>> struct inet_skb_parm h4;
>>>> @@ -869,12 +872,6 @@ struct tcp_skb_cb {
>>>> struct inet6_skb_parm h6;
>>>> #endif
>>>> } header; /* For incoming frames */
>>>> -#ifdef CONFIG_MPTCP
>>>> - union { /* For MPTCP outgoing frames */
>>>> - __u32 path_mask; /* paths that tried to send this skb */
>>>> - __u32 dss[6]; /* DSS options */
>>>> - };
>>>> -#endif
>>>> };
>>>> };
>>>> diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
>>>> index 73480b9..1e7827f 100644
>>>> --- a/net/ipv4/af_inet.c
>>>> +++ b/net/ipv4/af_inet.c
>>>> @@ -356,6 +356,10 @@ lookup_protocol:
>>>> sk->sk_destruct = inet_sock_destruct;
>>>> sk->sk_protocol = protocol;
>>>> sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
>>>> + sk->sk_prequeue = sk->sk_prot->prequeue;
>>>> + if (sk->sk_prequeue == NULL) {
>>>> + sk->sk_prequeue = sk_prequeue;
>>>> + }
>>>> inet->uc_ttl = -1;
>>>> inet->mc_loop = 1;
>>>> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
>>>> index 16a7256..cb6bbf9 100644
>>>> --- a/net/ipv4/tcp_input.c
>>>> +++ b/net/ipv4/tcp_input.c
>>>> @@ -3133,8 +3133,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
>>>> */
>>>> if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
>>>> flag |= FLAG_DATA_ACKED;
>>>> - if (mptcp(tp) && mptcp_is_data_seq(skb))
>>>> - flag |= MPTCP_FLAG_DATA_ACKED;
>>>> } else {
>>>> flag |= FLAG_SYN_ACKED;
>>>> tp->retrans_stamp = 0;
>>>> @@ -3582,16 +3580,6 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
>>>> sack_rtt_us);
>>>> acked -= tp->packets_out;
>>>> - if (mptcp(tp)) {
>>>> - if (mptcp_fallback_infinite(sk, flag)) {
>>>> - pr_err("%s resetting flow\n", __func__);
>>>> - mptcp_send_reset(sk);
>>>> - goto invalid_ack;
>>>> - }
>>>> -
>>>> - mptcp_clean_rtx_infinite(skb, sk);
>>>> - }
>>>> -
>>>> /* Advance cwnd if state allows */
>>>> if (tcp_may_raise_cwnd(sk, flag))
>>>> tcp_cong_avoid(sk, ack, acked);
>>>> @@ -3824,8 +3812,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
>>>> if (tcp_parse_aligned_timestamp(tp, th))
>>>> return true;
>>>> }
>>>> - tcp_parse_options(skb, &tp->rx_opt,
>>>> - mptcp(tp) ? &tp->mptcp->rx_opt : NULL, 1, NULL, tp);
>>>> + tcp_parse_options(skb, &tp->rx_opt, NULL, 1, NULL, tp);
>>>> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
>>>> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>>>> @@ -4550,11 +4537,12 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
>>>> int eaten = -1;
>>>> bool fragstolen = false;
>>>> - /* If no data is present, but a data_fin is in the options, we still
>>>> - * have to call mptcp_queue_skb later on. */
>>>> - if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq &&
>>>> - !(mptcp(tp) && mptcp_is_data_fin(skb)))
>>>> + /*
>>>> + * send every packet to MPTCP
>>>> + */
>>>> + if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)) {
>>>> goto drop;
>>>> + }
>>>> skb_dst_drop(skb);
>>>> __skb_pull(skb, tcp_hdr(skb)->doff * 4);
>>>> @@ -5242,15 +5230,9 @@ syn_challenge:
>>>> goto discard;
>>>> }
>>>> - /* If valid: post process the received MPTCP options. */
>>>> - if (mptcp(tp) && mptcp_handle_options(sk, th, skb))
>>>> - goto discard;
>>>> -
>>>> return true;
>>>> discard:
>>>> - if (mptcp(tp))
>>>> - mptcp_reset_mopt(tp);
>>>> __kfree_skb(skb);
>>>> return false;
>>>> }
>>>> @@ -5302,10 +5284,6 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
>>>> tp->rx_opt.saw_tstamp = 0;
>>>> - /* MPTCP: force slowpath. */
>>>> - if (mptcp(tp))
>>>> - goto slow_path;
>>>> -
>>>> /* pred_flags is 0xS?10 << 16 + snd_wnd
>>>> * if header_prediction is to be made
>>>> * 'S' will always be tp->tcp_header_len >> 2
>>>> @@ -5585,8 +5563,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
>>>> struct mptcp_options_received mopt;
>>>> mptcp_init_mp_opt(&mopt);
>>>> - tcp_parse_options(skb, &tp->rx_opt,
>>>> - mptcp(tp) ? &tp->mptcp->rx_opt : &mopt, 0, &foc, tp);
>>>> + tcp_parse_options(skb, &tp->rx_opt, &mopt, 0, &foc, tp);
>>>> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
>>>> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>>>> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
>>>> index 6967a86..3329679 100644
>>>> --- a/net/ipv4/tcp_ipv4.c
>>>> +++ b/net/ipv4/tcp_ipv4.c
>>>> @@ -1420,6 +1420,71 @@ struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
>>>> return sk;
>>>> }
>>>> +int mptcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
>>>> +{
>>>> + struct net *net = dev_net(skb->dev);
>>>> + const struct tcphdr *th = tcp_hdr(skb);
>>>> + int ret;
>>>> + struct sock *meta_sk;
>>>> +
>>>> + if (sk == NULL) {
>>>> + if (th->syn && !th->ack) {
>>>> + int ret = mptcp_lookup_join(skb, NULL);
>>>> +
>>>> + if (ret < 0) {
>>>> + tcp_v4_send_reset(NULL, skb);
>>>> + kfree_skb(skb);
>>>> + return (1);
>>>> + } else if (ret > 0) {
>>>> + return (1);
>>>> + }
>>>> + }
>>>> + /* Is there a pending request sock for this segment ? */
>>>> + if (mptcp_check_req(skb, net)) {
>>>> + return(1);
>>>> + }
>>>> + return (0);
>>>> + }
>>>> +
>>>> + /* The socket passed in should never be the meta socket */
>>>> +
>>>> + BUG_ON(is_meta_sk(sk));
>>>> +
>>>> + /* Is there a pending request sock for this segment ? */
>>>> + if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
>>>> + return 0;
>>>> + }
>>>> +
>>>> + skb->dev = NULL;
>>>> + meta_sk = mptcp_meta_sk(sk);
>>>> +
>>>> + ret = 0;
>>>> + skb->sk = sk;
>>>> + bh_lock_sock_nested(meta_sk);
>>>> + if (sock_owned_by_user(meta_sk)) {
>>>> + if (unlikely(sk_add_backlog(meta_sk, skb,
>>>> + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>> +
>>>> + NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>> + kfree_skb(skb);
>>>> + }
>>>> + } else {
>>>> +
>>>> + if (is_meta_sk(sk)) {
>>>> + ret = mptcp_v4_process_join_req(sk, skb);
>>>> + goto done;
>>>> + }
>>>> + if (!meta_sk->sk_prequeue(meta_sk, skb)) {
>>>> + skb->sk = NULL;
>>>> + ret = tcp_v4_do_rcv(sk, skb);
>>>> + }
>>>> +
>>>> + }
>>>> +done:
>>>> + bh_unlock_sock(meta_sk);
>>>> + return (ret);
>>>> +}
>>>> +
>>>> /* The socket must have it's spinlock held when we get
>>>> * here.
>>>> *
>>>> @@ -1432,8 +1497,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
>>>> {
>>>> struct sock *rsk;
>>>> - if (is_meta_sk(sk))
>>>> - return mptcp_v4_do_rcv(sk, skb);
>>>> + BUG_ON(is_meta_sk(sk));
>>>> if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
>>>> struct dst_entry *dst = sk->sk_rx_dst;
>>>> @@ -1587,6 +1651,8 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
>>>> }
>>>> EXPORT_SYMBOL(tcp_prequeue);
>>>> +process_unclaimed tcp_process_unclaimed = NULL;
>>>> +
>>>> /*
>>>> * From tcp_input.c
>>>> */
>>>> @@ -1595,7 +1661,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
>>>> {
>>>> const struct iphdr *iph;
>>>> const struct tcphdr *th;
>>>> - struct sock *sk, *meta_sk = NULL;
>>>> + struct sock *sk = NULL;
>>>> int ret;
>>>> struct net *net = dev_net(skb->dev);
>>>> @@ -1636,10 +1702,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
>>>> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
>>>> skb->len - th->doff * 4);
>>>> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
>>>> -#ifdef CONFIG_MPTCP
>>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>> - TCP_SKB_CB(skb)->dss_off = 0;
>>>> -#endif
>>>> +
>>>> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
>>>> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
>>>> TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
>>>> @@ -1662,15 +1725,6 @@ process:
>>>> if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
>>>> goto discard_and_relse;
>>>> -#ifdef CONFIG_MPTCP
>>>> - /* Is there a pending request sock for this segment ? */
>>>> - if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
>>>> - if (sk)
>>>> - sock_put(sk);
>>>> - return 0;
>>>> - }
>>>> -#endif
>>>> -
>>>> #ifdef CONFIG_TCP_MD5SIG
>>>> /*
>>>> * We really want to reject the packet as early as possible
>>>> @@ -1688,30 +1742,21 @@ process:
>>>> goto discard_and_relse;
>>>> sk_incoming_cpu_update(sk);
>>>> - skb->dev = NULL;
>>>> - if (mptcp(tcp_sk(sk))) {
>>>> - meta_sk = mptcp_meta_sk(sk);
>>>> -
>>>> - bh_lock_sock_nested(meta_sk);
>>>> - if (sock_owned_by_user(meta_sk))
>>>> - skb->sk = sk;
>>>> - } else {
>>>> - meta_sk = sk;
>>>> - bh_lock_sock_nested(sk);
>>>> - }
>>>> + /* Do I have to set skb->dev to null ? */
>>>> + bh_lock_sock_nested(sk);
>>>> ret = 0;
>>>> - if (!sock_owned_by_user(meta_sk)) {
>>>> - if (!tcp_prequeue(meta_sk, skb))
>>>> - ret = tcp_v4_do_rcv(sk, skb);
>>>> - } else if (unlikely(sk_add_backlog(meta_sk, skb,
>>>> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>> - bh_unlock_sock(meta_sk);
>>>> + if (!sock_owned_by_user(sk)) {
>>>> + if (!sk->sk_prequeue(sk, skb))
>>>> + ret = sk->sk_backlog_rcv(sk, skb);
>>>> + } else if (unlikely(sk_add_backlog(sk, skb,
>>>> + sk->sk_rcvbuf + sk->sk_sndbuf))) {
>>>> + bh_unlock_sock(sk);
>>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>> goto discard_and_relse;
>>>> }
>>>> - bh_unlock_sock(meta_sk);
>>>> + bh_unlock_sock(sk);
>>>> sock_put(sk);
>>>> @@ -1721,26 +1766,11 @@ no_tcp_socket:
>>>> if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
>>>> goto discard_it;
>>>> -#ifdef CONFIG_MPTCP
>>>> - if (!sk && th->syn && !th->ack) {
>>>> - int ret = mptcp_lookup_join(skb, NULL);
>>>> -
>>>> - if (ret < 0) {
>>>> - tcp_v4_send_reset(NULL, skb);
>>>> - goto discard_it;
>>>> - } else if (ret > 0) {
>>>> - return 0;
>>>> - }
>>>> + if (unlikely (tcp_process_unclaimed != NULL)) {
>>>> + if ((tcp_process_unclaimed)(NULL, skb))
>>>> + return (0);
>>>> }
>>>> - /* Is there a pending request sock for this segment ? */
>>>> - if (!sk && mptcp_check_req(skb, net)) {
>>>> - if (sk)
>>>> - sock_put(sk);
>>>> - return 0;
>>>> - }
>>>> -#endif
>>>> -
>>>> if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
>>>> csum_error:
>>>> TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
>>>> @@ -2506,6 +2536,7 @@ struct proto tcp_prot = {
>>>> .sendmsg = tcp_sendmsg,
>>>> .sendpage = tcp_sendpage,
>>>> .backlog_rcv = tcp_v4_do_rcv,
>>>> + .prequeue = tcp_prequeue,
>>>> .release_cb = tcp_release_cb,
>>>> .hash = inet_hash,
>>>> .unhash = inet_unhash,
>>>> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
>>>> index a635483..41b8be8 100644
>>>> --- a/net/ipv4/tcp_output.c
>>>> +++ b/net/ipv4/tcp_output.c
>>>> @@ -3413,6 +3413,7 @@ void tcp_send_delayed_ack(struct sock *sk)
>>>> void tcp_send_ack(struct sock *sk)
>>>> {
>>>> struct sk_buff *buff;
>>>> + struct tcp_sock *tp = tcp_sk(sk);
>>>> /* If we have been reset, we may not send again. */
>>>> if (sk->sk_state == TCP_CLOSE)
>>>> diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
>>>> index 8c4dd4a..1554217 100644
>>>> --- a/net/ipv6/af_inet6.c
>>>> +++ b/net/ipv6/af_inet6.c
>>>> @@ -193,6 +193,10 @@ lookup_protocol:
>>>> sk->sk_protocol = protocol;
>>>> sk->sk_backlog_rcv = answer->prot->backlog_rcv;
>>>> + sk->sk_prequeue = answer->prot->prequeue;
>>>> + if (sk->sk_prequeue == NULL) {
>>>> + sk->sk_prequeue = sk_prequeue;
>>>> + }
>>>> inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
>>>> np->hop_limit = -1;
>>>> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
>>>> index eba2436..d360128 100644
>>>> --- a/net/ipv6/tcp_ipv6.c
>>>> +++ b/net/ipv6/tcp_ipv6.c
>>>> @@ -1412,10 +1412,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
>>>> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
>>>> skb->len - th->doff*4);
>>>> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
>>>> -#ifdef CONFIG_MPTCP
>>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>> - TCP_SKB_CB(skb)->dss_off = 0;
>>>> -#endif
>>>> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
>>>> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
>>>> TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
>>>> diff --git a/net/mptcp/mptcp_ctrl.c b/net/mptcp/mptcp_ctrl.c
>>>> index 28f348f..b1e780a 100644
>>>> --- a/net/mptcp/mptcp_ctrl.c
>>>> +++ b/net/mptcp/mptcp_ctrl.c
>>>> @@ -976,6 +976,20 @@ int mptcp_backlog_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>>> struct sock *sk = skb->sk ? skb->sk : meta_sk;
>>>> int ret = 0;
>>>> + /* socket was owned by the user in mptcp_check_req()
>>>> + */
>>>> + if (sk == (struct sock *)0xFEE1DEAD) {
>>>> + bh_lock_sock_nested(meta_sk);
>>>> + if (skb->protocol == htons(ETH_P_IP))
>>>> + mptcp_v4_process_join_req(meta_sk, skb);
>>>> +#if IS_ENABLED(CONFIG_IPV6)
>>>> + else
>>>> + //mptcp_v6_process_join_req(meta_sk, skb);
>>>> +#endif /* CONFIG_IPV6 */
>>>> + bh_unlock_sock(meta_sk);
>>>> + return(0);
>>>> + }
>>>> +
>>>> skb->sk = NULL;
>>>> if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
>>>> @@ -1297,6 +1311,10 @@ int mptcp_add_sock(struct sock *meta_sk, struct sock *sk, u8 loc_id, u8 rem_id,
>>>> sk->sk_write_space = mptcp_write_space;
>>>> sk->sk_state_change = mptcp_set_state;
>>>> sk->sk_destruct = mptcp_sock_destruct;
>>>> + /* MPTCP takes a different path in tcp_v4_rcv
>>>> + * thus not impacting main tcp code */
>>>> + sk->sk_backlog_rcv = mptcp_v4_do_rcv;
>>>> + sk->sk_prequeue = sk_prequeue;
>>>> if (sk->sk_family == AF_INET)
>>>> mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d dst_addr:%pI4:%d, cnt_subflows now %d\n",
>>>> @@ -2658,6 +2676,9 @@ void __init mptcp_init(void)
>>>> if (mptcp_pm_v4_init())
>>>> goto mptcp_pm_v4_failed;
>>>> + if ((cmpxchg(&tcp_process_unclaimed, NULL, mptcp_v4_do_rcv)) != NULL)
>>>> + printk("tcp_process_unclaimed not NULL \n");
>>>> +
>>>> mptcp_sysctl = register_net_sysctl(&init_net, "net/mptcp", mptcp_table);
>>>> if (!mptcp_sysctl)
>>>> goto register_sysctl_failed;
>>>> diff --git a/net/mptcp/mptcp_input.c b/net/mptcp/mptcp_input.c
>>>> index 51cbb06..0e09ddf 100644
>>>> --- a/net/mptcp/mptcp_input.c
>>>> +++ b/net/mptcp/mptcp_input.c
>>>> @@ -323,9 +323,8 @@ static int mptcp_verif_dss_csum(struct sock *sk)
>>>> * by 4 bytes, as the high-order 64-bits will be added
>>>> * in the final csum_partial-call.
>>>> */
>>>> - u32 offset = skb_transport_offset(tmp) +
>>>> - TCP_SKB_CB(tmp)->dss_off;
>>>> - if (TCP_SKB_CB(tmp)->mptcp_flags & MPTCPHDR_SEQ64_SET)
>>>> + u32 offset = skb_transport_offset(tmp) + tmp->mptcp_dss_off;
>>>> + if (tmp->mptcp_flags & MPTCPHDR_SEQ64_SET)
>>>> offset += 4;
>>>> csum_tcp = skb_checksum(tmp, offset,
>>>> @@ -758,7 +757,7 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
>>>> }
>>>> /* Does the DSS had 64-bit seqnum's ? */
>>>> - if (!(tcb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
>>>> + if (!(skb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
>>>> /* Wrapped around? */
>>>> if (unlikely(after(data_seq, meta_tp->rcv_nxt) && data_seq < meta_tp->rcv_nxt)) {
>>>> tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, !mpcb->rcv_hiseq_index, data_seq);
>>>> @@ -767,9 +766,9 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
>>>> tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, mpcb->rcv_hiseq_index, data_seq);
>>>> }
>>>> } else {
>>>> - tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (tcb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
>>>> + tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (skb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
>>>> - if (unlikely(tcb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
>>>> + if (unlikely(skb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
>>>> /* We make sure that the data_seq is invalid.
>>>> * It will be dropped later.
>>>> */
>>>> @@ -1020,6 +1019,67 @@ next:
>>>> return data_queued ? -1 : -2;
>>>> }
>>>> +static struct sk_buff *
>>>> +mptcp_process_ack(struct sock *sk, struct sk_buff *skb)
>>>> +{
>>>> + struct tcp_sock *tp = tcp_sk(sk);
>>>> + int flag = 0;
>>>> +
>>>> + /*
>>>> + * TCP takes care of invalid ack's
>>>> + * they will never show up here.
>>>> + */
>>>> +
>>>> + /* Is this skb acknowleding anything data */
>>>> +
>>>> + if (tp->mptcp->snt_isn + 1 != TCP_SKB_CB(skb)->ack_seq) {
>>>> + flag = MPTCP_FLAG_DATA_ACKED;
>>>> + }
>>>> +
>>>> + if (mptcp_fallback_infinite(sk, flag)) {
>>>> + pr_err("%s resetting flow\n", __func__);
>>>> + mptcp_send_reset(sk);
>>>> + goto invalid_ack;
>>>> + }
>>>> +
>>>> + mptcp_clean_rtx_infinite(skb, sk);
>>>> +
>>>> + return (skb);
>>>> +invalid_ack:
>>>> + __skb_unlink(skb, &sk->sk_receive_queue);
>>>> + __kfree_skb(skb);
>>>> + return (NULL);
>>>> +
>>>> +}
>>>> +
>>>> +static struct sk_buff *
>>>> +mptcp_process_options_ack(struct sock *sk, struct sk_buff *skb)
>>>> +{
>>>> + struct tcp_sock *tp = tcp_sk(sk);
>>>> + const struct tcphdr *th = tcp_hdr(skb);
>>>> +
>>>> + skb->mptcp_flags = 0;
>>>> + skb->mptcp_dss_off = 0;
>>>> +
>>>> + tcp_parse_mptcp_options(skb, &tp->mptcp->rx_opt);
>>>> + if (mptcp_handle_options(sk, th, skb)) {
>>>> + mptcp_reset_mopt(tp);
>>>> + __skb_unlink(skb, &sk->sk_receive_queue);
>>>> + __kfree_skb(skb);
>>>> + skb = NULL;
>>>> + }
>>>> + if ((skb != NULL) && skb->len == 0) {
>>>> + skb = mptcp_process_ack(sk, skb);
>>>> + if (skb != NULL && skb->len == 0) {
>>>> + /* Pure ack */
>>>> + __skb_unlink(skb, &sk->sk_receive_queue);
>>>> + __kfree_skb(skb);
>>>> + skb = NULL;
>>>> + }
>>>> + }
>>>> + return (skb);
>>>> +}
>>>> +
>>>> void mptcp_data_ready(struct sock *sk)
>>>> {
>>>> struct sock *meta_sk = mptcp_meta_sk(sk);
>>>> @@ -1045,6 +1105,10 @@ restart:
>>>> */
>>>> skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
>>>> int ret;
>>>> +
>>>> + skb = mptcp_process_options_ack(sk, skb);
>>>> + if (skb == NULL)
>>>> + continue;
>>>> /* Pre-validation - e.g., early fallback */
>>>> ret = mptcp_prevalidate_skb(sk, skb);
>>>> if (ret < 0)
>>>> @@ -1108,13 +1172,11 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
>>>> if (!meta_sk)
>>>> return 0;
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>> -
>>>> bh_lock_sock_nested(meta_sk);
>>>> if (sock_owned_by_user(meta_sk)) {
>>>> - skb->sk = meta_sk;
>>>> + skb->sk = (struct sock *)0xFEE1DEAD;
>>>> if (unlikely(sk_add_backlog(meta_sk, skb,
>>>> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>> + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>> bh_unlock_sock(meta_sk);
>>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>> sock_put(meta_sk); /* Taken by mptcp_search_req */
>>>> @@ -1122,10 +1184,14 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
>>>> return 1;
>>>> }
>>>> } else if (skb->protocol == htons(ETH_P_IP)) {
>>>> - tcp_v4_do_rcv(meta_sk, skb);
>>>> + /*
>>>> + * call old mptcp_v4_do_rcv
>>>> + */
>>>> + mptcp_v4_process_join_req(meta_sk, skb);
>>>> #if IS_ENABLED(CONFIG_IPV6)
>>>> } else { /* IPv6 */
>>>> - tcp_v6_do_rcv(meta_sk, skb);
>>>> + WARN_ON(1);
>>>> + //mptcp_v6_handle_join_req(meta_sk, skb);
>>>> #endif /* CONFIG_IPV6 */
>>>> }
>>>> bh_unlock_sock(meta_sk);
>>>> @@ -1222,7 +1288,7 @@ int mptcp_lookup_join(struct sk_buff *skb, struct inet_timewait_sock *tw)
>>>> inet_twsk_put(tw);
>>>> }
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>> + skb->mptcp_flags |= MPTCPHDR_JOIN;
>>>> /* OK, this is a new syn/join, let's create a new open request and
>>>> * send syn+ack
>>>> */
>>>> @@ -1279,7 +1345,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>>> return -1;
>>>> }
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>> + //TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>> /* OK, this is a new syn/join, let's create a new open request and
>>>> * send syn+ack
>>>> @@ -1303,7 +1369,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>>> }
>>>> if (sock_owned_by_user(meta_sk)) {
>>>> - skb->sk = meta_sk;
>>>> + skb->sk = (struct sock *)0xFEE1DEAD; //skb->sk = meta_sk;
>>>> if (unlikely(sk_add_backlog(meta_sk, skb,
>>>> meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf)))
>>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>> @@ -1319,10 +1385,12 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>>> */
>>>> skb_get(skb);
>>>> if (skb->protocol == htons(ETH_P_IP)) {
>>>> - tcp_v4_do_rcv(meta_sk, skb);
>>>> + //tcp_v4_do_rcv(meta_sk, skb);
>>>> + mptcp_v4_process_join_req(meta_sk, skb);
>>>> #if IS_ENABLED(CONFIG_IPV6)
>>>> } else { /* IPv6 */
>>>> - tcp_v6_do_rcv(meta_sk, skb);
>>>> + //mptcp_v6_process_join_req(meta_sk, skb);
>>>> + //tcp_v6_do_rcv(meta_sk, skb);
>>>> #endif /* CONFIG_IPV6 */
>>>> }
>>>> }
>>>> @@ -1461,7 +1529,6 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
>>>> {
>>>> struct sock *meta_sk = mptcp_meta_sk(sk);
>>>> struct tcp_sock *meta_tp = tcp_sk(meta_sk), *tp = tcp_sk(sk);
>>>> - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>> u32 prior_snd_una = meta_tp->snd_una;
>>>> int prior_packets;
>>>> u32 nwin, data_ack, data_seq;
>>>> @@ -1481,7 +1548,7 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
>>>> /* If we are in infinite mapping mode, rx_opt.data_ack has been
>>>> * set by mptcp_clean_rtx_infinite.
>>>> */
>>>> - if (!(tcb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
>>>> + if (!(skb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
>>>> goto exit;
>>>> data_ack = tp->mptcp->rx_opt.data_ack;
>>>> @@ -1647,10 +1714,11 @@ static inline bool is_valid_addropt_opsize(u8 mptcp_ver,
>>>> void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>>> struct mptcp_options_received *mopt,
>>>> - const struct sk_buff *skb,
>>>> + struct sk_buff *skb,
>>>> struct tcp_sock *tp)
>>>> {
>>>> const struct mptcp_option *mp_opt = (struct mptcp_option *)ptr;
>>>> + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>> /* If the socket is mp-capable we would have a mopt. */
>>>> if (!mopt)
>>>> @@ -1757,7 +1825,7 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>>> ptr += 4;
>>>> if (mdss->A) {
>>>> - tcb->mptcp_flags |= MPTCPHDR_ACK;
>>>> + skb->mptcp_flags |= MPTCPHDR_ACK;
>>>> if (mdss->a) {
>>>> mopt->data_ack = (u32) get_unaligned_be64(ptr);
>>>> @@ -1768,13 +1836,13 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>>> }
>>>> }
>>>> - tcb->dss_off = (ptr - skb_transport_header(skb));
>>>> + skb->mptcp_dss_off = (ptr - skb_transport_header(skb));
>>>> if (mdss->M) {
>>>> if (mdss->m) {
>>>> u64 data_seq64 = get_unaligned_be64(ptr);
>>>> - tcb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
>>>> + skb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
>>>> mopt->data_seq = (u32) data_seq64;
>>>> ptr += 12; /* 64-bit dseq + subseq */
>>>> @@ -1784,15 +1852,16 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>>> }
>>>> mopt->data_len = get_unaligned_be16(ptr);
>>>> - tcb->mptcp_flags |= MPTCPHDR_SEQ;
>>>> + skb->mptcp_flags |= MPTCPHDR_SEQ;
>>>> /* Is a check-sum present? */
>>>> - if (opsize == mptcp_sub_len_dss(mdss, 1))
>>>> - tcb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
>>>> + if (opsize == mptcp_sub_len_dss(mdss, 1)) {
>>>> + skb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
>>>> + }
>>>> /* DATA_FIN only possible with DSS-mapping */
>>>> if (mdss->F)
>>>> - tcb->mptcp_flags |= MPTCPHDR_FIN;
>>>> + skb->mptcp_flags |= MPTCPHDR_FIN;
>>>> }
>>>> break;
>>>> @@ -1907,8 +1976,9 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
>>>> return;
>>>> if (opsize > length)
>>>> return; /* don't parse partial options */
>>>> - if (opcode == TCPOPT_MPTCP)
>>>> + if (opcode == TCPOPT_MPTCP) {
>>>> mptcp_parse_options(ptr - 2, opsize, mopt, skb, NULL);
>>>> + }
>>>> }
>>>> ptr += opsize - 2;
>>>> length -= opsize;
>>>> @@ -2168,6 +2238,8 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
>>>> struct tcp_sock *tp = tcp_sk(sk);
>>>> struct mptcp_options_received *mopt = &tp->mptcp->rx_opt;
>>>> + BUG_ON(sk == mptcp_meta_sk(sk));
>>>> +
>>>> if (tp->mpcb->infinite_mapping_rcv || tp->mpcb->infinite_mapping_snd)
>>>> return false;
>>>> @@ -2185,7 +2257,7 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
>>>> * receiver MUST close the subflow with a RST as it is considered broken.
>>>> */
>>>> if (mptcp_is_data_seq(skb) && tp->mpcb->dss_csum &&
>>>> - !(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
>>>> + !(skb->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
>>>> mptcp_send_reset(sk);
>>>> return true;
>>>> }
>>>> @@ -2330,6 +2402,7 @@ int mptcp_rcv_synsent_state_process(struct sock *sk, struct sock **skptr,
>>>> /* Set this flag in order to postpone data sending
>>>> * until the 4th ack arrives.
>>>> */
>>>> +printk("mptcp_rcv_synsent_state_process pre_established set \n");
>>>> tp->mptcp->pre_established = 1;
>>>> tp->mptcp->rcv_low_prio = tp->mptcp->rx_opt.low_prio;
>>>> diff --git a/net/mptcp/mptcp_ipv4.c b/net/mptcp/mptcp_ipv4.c
>>>> index a147b20..3e60ab5 100644
>>>> --- a/net/mptcp/mptcp_ipv4.c
>>>> +++ b/net/mptcp/mptcp_ipv4.c
>>>> @@ -180,45 +180,12 @@ static int mptcp_v4_join_request(struct sock *meta_sk, struct sk_buff *skb)
>>>> }
>>>> /* We only process join requests here. (either the SYN or the final ACK) */
>>>> -int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>>> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb)
>>>> {
>>>> const struct mptcp_cb *mpcb = tcp_sk(meta_sk)->mpcb;
>>>> struct sock *child, *rsk = NULL;
>>>> int ret;
>>>> - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
>>>> - struct tcphdr *th = tcp_hdr(skb);
>>>> - const struct iphdr *iph = ip_hdr(skb);
>>>> - struct sock *sk;
>>>> -
>>>> - sk = inet_lookup_established(sock_net(meta_sk), &tcp_hashinfo,
>>>> - iph->saddr, th->source, iph->daddr,
>>>> - th->dest, inet_iif(skb));
>>>> -
>>>> - if (!sk) {
>>>> - kfree_skb(skb);
>>>> - return 0;
>>>> - }
>>>> - if (is_meta_sk(sk)) {
>>>> - WARN("%s Did not find a sub-sk - did found the meta!\n", __func__);
>>>> - kfree_skb(skb);
>>>> - sock_put(sk);
>>>> - return 0;
>>>> - }
>>>> -
>>>> - if (sk->sk_state == TCP_TIME_WAIT) {
>>>> - inet_twsk_put(inet_twsk(sk));
>>>> - kfree_skb(skb);
>>>> - return 0;
>>>> - }
>>>> -
>>>> - ret = tcp_v4_do_rcv(sk, skb);
>>>> - sock_put(sk);
>>>> -
>>>> - return ret;
>>>> - }
>>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>> -
>>>> /* Has been removed from the tk-table. Thus, no new subflows.
>>>> *
>>>> * Check for close-state is necessary, because we may have been closed
>>>> diff --git a/net/mptcp/mptcp_ipv6.c b/net/mptcp/mptcp_ipv6.c
>>>> index 0de953d..1959d01 100644
>>>> --- a/net/mptcp/mptcp_ipv6.c
>>>> +++ b/net/mptcp/mptcp_ipv6.c
>>>> @@ -199,7 +199,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>>> struct sock *child, *rsk = NULL;
>>>> int ret;
>>>> - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
>>>> + if (!(skb->mptcp_flags & MPTCPHDR_JOIN)) {
>>>> struct tcphdr *th = tcp_hdr(skb);
>>>> const struct ipv6hdr *ip6h = ipv6_hdr(skb);
>>>> struct sock *sk;
>>>> @@ -232,7 +232,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>>> return ret;
>>>> }
>>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>> + skb->mptcp_flags = 0;
>>>> /* Has been removed from the tk-table. Thus, no new subflows.
>>>> *
>>>> diff --git a/net/mptcp/mptcp_output.c b/net/mptcp/mptcp_output.c
>>>> index 691ef6f..e7d340d 100644
>>>> --- a/net/mptcp/mptcp_output.c
>>>> +++ b/net/mptcp/mptcp_output.c
>>>> @@ -59,39 +59,17 @@ EXPORT_SYMBOL(mptcp_sub_len_remove_addr_align);
>>>> */
>>>> static bool mptcp_reconstruct_mapping(struct sk_buff *skb)
>>>> {
>>>> - const struct mp_dss *mpdss = (struct mp_dss *)TCP_SKB_CB(skb)->dss;
>>>> - u32 *p32;
>>>> - u16 *p16;
>>>> -
>>>> if (!mptcp_is_data_seq(skb))
>>>> return false;
>>>> - if (!mpdss->M)
>>>> - return false;
>>>> -
>>>> - /* Move the pointer to the data-seq */
>>>> - p32 = (u32 *)mpdss;
>>>> - p32++;
>>>> - if (mpdss->A) {
>>>> - p32++;
>>>> - if (mpdss->a)
>>>> - p32++;
>>>> - }
>>>> -
>>>> - TCP_SKB_CB(skb)->seq = ntohl(*p32);
>>>> -
>>>> - /* Get the data_len to calculate the end_data_seq */
>>>> - p32++;
>>>> - p32++;
>>>> - p16 = (u16 *)p32;
>>>> - TCP_SKB_CB(skb)->end_seq = ntohs(*p16) + TCP_SKB_CB(skb)->seq;
>>>> + TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->mptcp_data_seq;
>>>> return true;
>>>> }
>>>> static bool mptcp_is_reinjected(const struct sk_buff *skb)
>>>> {
>>>> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCP_REINJECT;
>>>> + return skb->mptcp_flags & MPTCP_REINJECT;
>>>> }
>>>> static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_buff *skb)
>>>> @@ -105,7 +83,7 @@ static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_bu
>>>> break;
>>>> if (TCP_SKB_CB(skb_it)->seq == TCP_SKB_CB(skb)->seq) {
>>>> - TCP_SKB_CB(skb)->path_mask = TCP_SKB_CB(skb_it)->path_mask;
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask = TCP_SKB_CB(skb_it)->mptcp_path_mask;
>>>> break;
>>>> }
>>>> }
>>>> @@ -180,9 +158,9 @@ static void __mptcp_reinject_data(struct sk_buff *orig_skb, struct sock *meta_sk
>>>> }
>>>> /* Segment goes back to the MPTCP-layer. So, we need to zero the
>>>> - * path_mask/dss.
>>>> + * path_mask.
>>>> */
>>>> - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>>> /* We need to find out the path-mask from the meta-write-queue
>>>> * to properly select a subflow.
>>>> @@ -272,14 +250,14 @@ void mptcp_reinject_data(struct sock *sk, int clone_it)
>>>> if (mptcp_is_reinjected(skb_it))
>>>> continue;
>>>> - tcb->mptcp_flags |= MPTCP_REINJECT;
>>>> + skb_it->mptcp_flags |= MPTCP_REINJECT;
>>>> __mptcp_reinject_data(skb_it, meta_sk, sk, clone_it);
>>>> }
>>>> skb_it = tcp_write_queue_tail(meta_sk);
>>>> /* If sk has sent the empty data-fin, we have to reinject it too. */
>>>> if (skb_it && mptcp_is_data_fin(skb_it) && skb_it->len == 0 &&
>>>> - TCP_SKB_CB(skb_it)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
>>>> + TCP_SKB_CB(skb_it)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
>>>> __mptcp_reinject_data(skb_it, meta_sk, NULL, 1);
>>>> }
>>>> @@ -319,25 +297,43 @@ combine:
>>>> }
>>>> }
>>>> -static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_buff *skb,
>>>> - __be32 *ptr)
>>>> +/*
>>>> + * RFC6824 states that once a particular subflow mapping has been sent
>>>> + * out it must never be changed. However, packets may be split while
>>>> + * they are in the retransmission queue (due to SACK or ACKs) and that
>>>> + * arguably means that we would change the mapping (e.g. it splits it,
>>>> + * our sends out a subset of the initial mapping).
>>>> + *
>>>> + * Furthermore, the skb checksum is not always preserved across splits
>>>> + * (e.g. mptcp_fragment) which would mean that we need to recompute
>>>> + * the DSS checksum in this case.
>>>> + *
>>>> + * To avoid this we save the initial DSS mapping which allows us to
>>>> + * send the same DSS mapping even for fragmented retransmits.
>>>> + */
>>>> +
>>>> +static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
>>>> + const struct sk_buff *skb, __be32 *ptr)
>>>> {
>>>> const struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>> - __be32 *start = ptr;
>>>> __u16 data_len;
>>>> - *ptr++ = htonl(tcb->seq); /* data_seq */
>>>> + *ptr++ = htonl(tcb->mptcp_data_seq); /* data_seq */
>>>> /* If it's a non-data DATA_FIN, we set subseq to 0 (draft v7) */
>>>> if (mptcp_is_data_fin(skb) && skb->len == 0)
>>>> *ptr++ = 0; /* subseq */
>>>> else
>>>> - *ptr++ = htonl(tp->write_seq - tp->mptcp->snt_isn); /* subseq */
>>>> + *ptr++ = htonl(tcb->seq - tp->mptcp->snt_isn); /* subseq */
>>>> - if (tcb->mptcp_flags & MPTCPHDR_INF)
>>>> + if (skb->mptcp_flags & MPTCPHDR_INF)
>>>> data_len = 0;
>>>> - else
>>>> + else {
>>>> data_len = tcb->end_seq - tcb->seq;
>>>> + /* mptcp_entail_skb adds one for FIN */
>>>> + if (tcb->tcp_flags & TCPHDR_FIN)
>>>> + data_len -= 1;
>>>> + }
>>>> if (tp->mpcb->dss_csum && data_len) {
>>>> __be16 *p16 = (__be16 *)ptr;
>>>> @@ -356,11 +352,11 @@ static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_bu
>>>> (TCPOPT_NOP));
>>>> }
>>>> - return ptr - start;
>>>> + return mptcp_dss_len/sizeof(*ptr);
>>>> }
>>>> -static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_buff *skb,
>>>> - __be32 *ptr)
>>>> +static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
>>>> + const struct sk_buff *skb, __be32 *ptr)
>>>> {
>>>> struct mp_dss *mdss = (struct mp_dss *)ptr;
>>>> __be32 *start = ptr;
>>>> @@ -377,54 +373,12 @@ static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_b
>>>> mdss->len = mptcp_sub_len_dss(mdss, tp->mpcb->dss_csum);
>>>> ptr++;
>>>> + /* data_ack */
>>>> *ptr++ = htonl(mptcp_meta_tp(tp)->rcv_nxt);
>>>> return ptr - start;
>>>> }
>>>> -/* RFC6824 states that once a particular subflow mapping has been sent
>>>> - * out it must never be changed. However, packets may be split while
>>>> - * they are in the retransmission queue (due to SACK or ACKs) and that
>>>> - * arguably means that we would change the mapping (e.g. it splits it,
>>>> - * our sends out a subset of the initial mapping).
>>>> - *
>>>> - * Furthermore, the skb checksum is not always preserved across splits
>>>> - * (e.g. mptcp_fragment) which would mean that we need to recompute
>>>> - * the DSS checksum in this case.
>>>> - *
>>>> - * To avoid this we save the initial DSS mapping which allows us to
>>>> - * send the same DSS mapping even for fragmented retransmits.
>>>> - */
>>>> -static void mptcp_save_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb)
>>>> -{
>>>> - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>> - __be32 *ptr = (__be32 *)tcb->dss;
>>>> -
>>>> - tcb->mptcp_flags |= MPTCPHDR_SEQ;
>>>> -
>>>> - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>>> - ptr += mptcp_write_dss_mapping(tp, skb, ptr);
>>>> -}
>>>> -
>>>> -/* Write the saved DSS mapping to the header */
>>>> -static int mptcp_write_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb,
>>>> - __be32 *ptr)
>>>> -{
>>>> - __be32 *start = ptr;
>>>> -
>>>> - memcpy(ptr, TCP_SKB_CB(skb)->dss, mptcp_dss_len);
>>>> -
>>>> - /* update the data_ack */
>>>> - start[1] = htonl(mptcp_meta_tp(tp)->rcv_nxt);
>>>> -
>>>> - /* dss is in a union with inet_skb_parm and
>>>> - * the IP layer expects zeroed IPCB fields.
>>>> - */
>>>> - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
>>>> -
>>>> - return mptcp_dss_len/sizeof(*ptr);
>>>> -}
>>>> -
>>>> static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
>>>> {
>>>> struct tcp_sock *tp = tcp_sk(sk);
>>>> @@ -434,7 +388,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
>>>> struct sk_buff *subskb = NULL;
>>>> if (!reinject)
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= (mpcb->snd_hiseq_index ?
>>>> + skb->mptcp_flags |= (mpcb->snd_hiseq_index ?
>>>> MPTCPHDR_SEQ64_INDEX : 0);
>>>> subskb = pskb_copy_for_clone(skb, GFP_ATOMIC);
>>>> @@ -447,7 +401,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
>>>> */
>>>> tcp_skb_pcount_set(subskb, 0);
>>>> - TCP_SKB_CB(skb)->path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
>>>> if (!(sk->sk_route_caps & NETIF_F_ALL_CSUM) &&
>>>> skb->ip_summed == CHECKSUM_PARTIAL) {
>>>> @@ -463,13 +417,14 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
>>>> tp->mptcp->fully_established = 1;
>>>> tp->mpcb->infinite_mapping_snd = 1;
>>>> tp->mptcp->infinite_cutoff_seq = tp->write_seq;
>>>> - tcb->mptcp_flags |= MPTCPHDR_INF;
>>>> + skb->mptcp_flags |= MPTCPHDR_INF;
>>>> }
>>>> if (mptcp_is_data_fin(subskb))
>>>> mptcp_combine_dfin(subskb, meta_sk, sk);
>>>> - mptcp_save_dss_data_seq(tp, subskb);
>>>> + subskb->mptcp_flags |= MPTCPHDR_SEQ;
>>>> + tcb->mptcp_data_seq = tcb->seq;
>>>> tcb->seq = tp->write_seq;
>>>> @@ -536,10 +491,10 @@ static int mptcp_fragment(struct sock *meta_sk, struct sk_buff *skb, u32 len,
>>>> buff = skb->next;
>>>> - flags = TCP_SKB_CB(skb)->mptcp_flags;
>>>> - TCP_SKB_CB(skb)->mptcp_flags = flags & ~(MPTCPHDR_FIN);
>>>> - TCP_SKB_CB(buff)->mptcp_flags = flags;
>>>> - TCP_SKB_CB(buff)->path_mask = TCP_SKB_CB(skb)->path_mask;
>>>> + flags = skb->mptcp_flags;
>>>> + skb->mptcp_flags = flags & ~(MPTCPHDR_FIN);
>>>> + buff->mptcp_flags = flags;
>>>> + TCP_SKB_CB(buff)->mptcp_path_mask = TCP_SKB_CB(skb)->mptcp_path_mask;
>>>> /* If reinject == 1, the buff will be added to the reinject
>>>> * queue, which is currently not part of memory accounting. So
>>>> @@ -927,8 +882,9 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
>>>> * It does not make sense to check for the options, because when the
>>>> * segment gets sent, another subflow will be chosen.
>>>> */
>>>> - if (!skb && is_meta_sk(sk))
>>>> + if (!skb && is_meta_sk(sk)) {
>>>> return;
>>>> + }
>>>> /* In fallback mp_fail-mode, we have to repeat it until the fallback
>>>> * has been done by the sender
>>>> @@ -967,10 +923,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
>>>> if (unlikely(mpcb->infinite_mapping_snd) &&
>>>> ((mpcb->send_infinite_mapping && tcb &&
>>>> mptcp_is_data_seq(skb) &&
>>>> - !(tcb->mptcp_flags & MPTCPHDR_INF) &&
>>>> + !(skb->mptcp_flags & MPTCPHDR_INF) &&
>>>> !before(tcb->seq, tp->mptcp->infinite_cutoff_seq)) ||
>>>> - !mpcb->send_infinite_mapping))
>>>> + !mpcb->send_infinite_mapping)) {
>>>> return;
>>>> + }
>>>> if (unlikely(tp->mptcp->include_mpc)) {
>>>> opts->options |= OPTION_MPTCP;
>>>> @@ -995,9 +952,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
>>>> mpcb->mptcp_ver >= MPTCP_VERSION_1 && skb && !mptcp_is_data_seq(skb)) {
>>>> mpcb->pm_ops->addr_signal(sk, size, opts, skb);
>>>> - if (opts->add_addr_v6)
>>>> + if (opts->add_addr_v6) {
>>>> +
>>>> /* Skip subsequent options */
>>>> return;
>>>> + }
>>>> }
>>>> if (!tp->mptcp->include_mpc && !tp->mptcp->pre_established) {
>>>> @@ -1197,10 +1156,11 @@ void mptcp_options_write(__be32 *ptr, struct tcp_sock *tp,
>>>> }
>>>> if (OPTION_DATA_ACK & opts->mptcp_options) {
>>>> - if (!mptcp_is_data_seq(skb))
>>>> - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>>> - else
>>>> - ptr += mptcp_write_dss_data_seq(tp, skb, ptr);
>>>> + ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>>> + if (mptcp_is_data_seq(skb)) {
>>>> + ptr += mptcp_write_dss_mapping(tp, skb, ptr);
>>>> + }
>>>> + skb->dev = NULL;
>>>> }
>>>> if (unlikely(OPTION_MP_PRIO & opts->mptcp_options)) {
>>>> struct mp_prio *mpprio = (struct mp_prio *)ptr;
>>>> @@ -1233,7 +1193,7 @@ void mptcp_send_fin(struct sock *meta_sk)
>>>> mss_now = mptcp_current_mss(meta_sk);
>>>> if (tcp_send_head(meta_sk) != NULL) {
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
>>>> + skb->mptcp_flags |= MPTCPHDR_FIN;
>>>> TCP_SKB_CB(skb)->end_seq++;
>>>> meta_tp->write_seq++;
>>>> } else {
>>>> @@ -1250,7 +1210,7 @@ void mptcp_send_fin(struct sock *meta_sk)
>>>> tcp_init_nondata_skb(skb, meta_tp->write_seq, TCPHDR_ACK);
>>>> TCP_SKB_CB(skb)->end_seq++;
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
>>>> + skb->mptcp_flags |= MPTCPHDR_FIN;
>>>> tcp_queue_skb(meta_sk, skb);
>>>> }
>>>> __tcp_push_pending_frames(meta_sk, mss_now, TCP_NAGLE_OFF);
>>>> diff --git a/net/mptcp/mptcp_redundant.c b/net/mptcp/mptcp_redundant.c
>>>> index 8fa2dba..37a13f4 100644
>>>> --- a/net/mptcp/mptcp_redundant.c
>>>> +++ b/net/mptcp/mptcp_redundant.c
>>>> @@ -72,10 +72,10 @@ static bool redsched_use_subflow(struct sock *meta_sk,
>>>> if (!skb || !mptcp_is_available((struct sock *)tp, skb, false))
>>>> return false;
>>>> - if (TCP_SKB_CB(skb)->path_mask != 0)
>>>> + if (TCP_SKB_CB(skb)->mptcp_path_mask != 0)
>>>> return subflow_is_active(tp);
>>>> - if (TCP_SKB_CB(skb)->path_mask == 0) {
>>>> + if (TCP_SKB_CB(skb)->mptcp_path_mask == 0) {
>>>> if (active_valid_sks == -1)
>>>> active_valid_sks = redsched_get_active_valid_sks(meta_sk);
>>>> @@ -209,7 +209,7 @@ static struct sk_buff *redundant_next_segment(struct sock *meta_sk,
>>>> cb_data->next_subflow = tp->mptcp->next;
>>>> *subsk = (struct sock *)tp;
>>>> - if (TCP_SKB_CB(skb)->path_mask)
>>>> + if (TCP_SKB_CB(skb)->mptcp_path_mask)
>>>> *reinject = -1;
>>>> return skb;
>>>> }
>>>> diff --git a/net/mptcp/mptcp_rr.c b/net/mptcp/mptcp_rr.c
>>>> index 8910ba9..83837f2 100644
>>>> --- a/net/mptcp/mptcp_rr.c
>>>> +++ b/net/mptcp/mptcp_rr.c
>>>> @@ -93,7 +93,7 @@ static int mptcp_rr_dont_reinject_skb(const struct tcp_sock *tp, const struct sk
>>>> */
>>>> return skb &&
>>>> /* Has the skb already been enqueued into this subsocket? */
>>>> - mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
>>>> + mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
>>>> }
>>>> /* We just look for any subflow that is available */
>>>> @@ -136,7 +136,7 @@ static struct sock *rr_get_available_subflow(struct sock *meta_sk,
>>>> * chance again by restarting its pathmask.
>>>> */
>>>> if (skb)
>>>> - TCP_SKB_CB(skb)->path_mask = 0;
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>>> sk = backupsk;
>>>> }
>>>> diff --git a/net/mptcp/mptcp_sched.c b/net/mptcp/mptcp_sched.c
>>>> index 54408ff..5cbbf91 100644
>>>> --- a/net/mptcp/mptcp_sched.c
>>>> +++ b/net/mptcp/mptcp_sched.c
>>>> @@ -118,7 +118,7 @@ static int mptcp_dont_reinject_skb(const struct tcp_sock *tp, const struct sk_bu
>>>> */
>>>> return skb &&
>>>> /* Has the skb already been enqueued into this subsocket? */
>>>> - mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
>>>> + mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
>>>> }
>>>> bool subflow_is_backup(const struct tcp_sock *tp)
>>>> @@ -261,7 +261,7 @@ struct sock *get_available_subflow(struct sock *meta_sk, struct sk_buff *skb,
>>>> * the skb passed through all the available active and backups
>>>> * sks, so clean the path mask
>>>> */
>>>> - TCP_SKB_CB(skb)->path_mask = 0;
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>>> return sk;
>>>> }
>>>> EXPORT_SYMBOL_GPL(get_available_subflow);
>>>> @@ -298,7 +298,7 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
>>>> /* Half the cwnd of the slow flow */
>>>> mptcp_for_each_tp(tp->mpcb, tp_it) {
>>>> if (tp_it != tp &&
>>>> - TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>> + TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>> if (tp->srtt_us < tp_it->srtt_us && inet_csk((struct sock *)tp_it)->icsk_ca_state == TCP_CA_Open) {
>>>> u32 prior_cwnd = tp_it->snd_cwnd;
>>>> @@ -317,11 +317,11 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
>>>> retrans:
>>>> /* Segment not yet injected into this path? Take it!!! */
>>>> - if (!(TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
>>>> + if (!(TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
>>>> bool do_retrans = false;
>>>> mptcp_for_each_tp(tp->mpcb, tp_it) {
>>>> if (tp_it != tp &&
>>>> - TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>> + TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>> if (tp_it->snd_cwnd <= 4) {
>>>> do_retrans = true;
>>>> break;
>>> _______________________________________________
>>> mptcp mailing list
>>> mptcp(a)lists.01.org
>>> https://lists.01.org/mailman/listinfo/mptcp
>
[-- Attachment #2: attachment.html --]
[-- Type: text/html, Size: 182186 bytes --]
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-27 17:25 Rao Shoaib
0 siblings, 0 replies; 14+ messages in thread
From: Rao Shoaib @ 2017-06-27 17:25 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 66144 bytes --]
Folks sorry for the typos, the dog was bugging me as it needed to go out.
Rao
On 06/27/2017 10:22 AM, Rao Shoaib wrote:
> Hi Christoph,
>
>
> On 06/26/2017 11:27 PM, Christoph Paasch wrote:
>> Hello Rao,
>>
>> can you try to give some more details on how the datapath looks like
>> with
>> this patch?
>>
>> For example, I wonder how data-acks are being processed. Because, I
>> see in
>> mptcp_data_ready, that you now expects skbs with len 0, upon which
>> you end
>> up calling mptcp_process_ack().
>>
>> I don't see how such zero-length skbs could end up in the
>> receive-queue of
>> the subflows.
>>
>>
>> Thanks,
>
> I send every packet that is coming on an MPTCP based socket down and
> let MPTCP deal with it. In tcp data_queue(). I also removed the
> directive to go to the slow_path in tcp_rcv_established().
>
> static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
> {
> struct tcp_sock *tp = tcp_sk(sk);
> int eaten = -1;
> bool fragstolen = false;
>
> /*
> * send every packet to MPTCP
> */
> if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq ==
> TCP_SKB_CB(skb)->end_seq)) {
> goto drop;
> }
>
> There is only one case that I need investigate more is the following.
> In that the he only interesting case is (len == tcp_header_len) but in
> my unidirectional bulk data transfer tests I did not hit that case. So
> I need to investigate more later. The last resort would be to just
> directly go to the slow path.
>
> if (len <= tcp_header_len) { /* Bulk data transfer: sender */
>
> if (len == tcp_header_len) {
>
> If there are other issues than let me know and I will work on
> resolving them. We obviously need to run extensive tests, that brings
> me to the question of, how does the MPTCP development team test
> changes. We need the same tests to validate the changes.
>
> Rao.
>
>> Christoph
>>
>>
>> On 26/06/17 - 15:34:09, Rao Shoaib wrote:
>>> I forgot to mention two things
>>>
>>> 1) Connection setup still has checks for MPTCP, Ideally these should be
>>> removed but at least we need to run some benchmarks and fix any
>>> issues. The
>>> mainstream folks will not accept any performance degradation in TCP.
>>> I can
>>> look into this next.
>>>
>>> 2) The code overloads dev field of skb, when it is not being used. IIRC
>>> there is precedence for this already. I will try to find it.
>>>
>>> Rao
>>>
>>>
>>> On 06/26/2017 02:13 PM, Rao Shoaib wrote:
>>>> This patch returns tcp_skb_cb to it's original size. It also
>>>> refactors MPTCP code so that there are no MPTCP checks in the main
>>>> Rx pathi, no performance overheads such as cpu prodiction issues.
>>>> tcp_v4_rcv() and tcp_v4_do_rcv() do not have any MPTCP specific
>>>> checks any more, niether does tcp_ack(). On the Rx path MPTCP
>>>> options are not parsed till the data is being pushed up to the meta
>>>> socket (mptcp_data_ready). on the Tx side there is one check to add
>>>> MPTCP specific options but that's it, that should not be that bad
>>>> as for regular TCP it is a simple check, but it would be good to
>>>> remove it..
>>>>
>>>> I have tested the changes with ndiffports set to 2, so join works.
>>>> I have also tested accessing multipath-tcp.org and downloading
>>>> files from there and also ran the speed test.
>>>>
>>>> The Bad:
>>>>
>>>> The error cases still have MPTCP checks but that should be OK as
>>>> they are error cases. I had to use a special marker 0xFEE1DEAD for
>>>> indicate a special case. I had to introdue a new socket specfic
>>>> function. IPv6 has not been changed yet. I am sure I have missed
>>>> some corner cases and more testing will reveal more issues but we
>>>> just have to fix them.
>>>>
>>>> I would like to hear comments from the list and if this direction
>>>> seems reasonable we can take this as the starting point, port it to
>>>> latest Linux and share the design with the mainstream folks.
>>>>
>>>> Signed-off-by: Rao Shoaib <rao.shoaib(a)oracle.com>
>>>> ---
>>>> include/linux/skbuff.h | 8 ++-
>>>> include/net/mptcp.h | 21 +++---
>>>> include/net/mptcp_v4.h | 1 +
>>>> include/net/sock.h | 12 +++-
>>>> include/net/tcp.h | 23 +++----
>>>> net/ipv4/af_inet.c | 4 ++
>>>> net/ipv4/tcp_input.c | 37 ++--------
>>>> net/ipv4/tcp_ipv4.c | 135
>>>> +++++++++++++++++++++++--------------
>>>> net/ipv4/tcp_output.c | 1 +
>>>> net/ipv6/af_inet6.c | 4 ++
>>>> net/ipv6/tcp_ipv6.c | 4 --
>>>> net/mptcp/mptcp_ctrl.c | 21 ++++++
>>>> net/mptcp/mptcp_input.c | 131
>>>> ++++++++++++++++++++++++++++--------
>>>> net/mptcp/mptcp_ipv4.c | 35 +---------
>>>> net/mptcp/mptcp_ipv6.c | 4 +-
>>>> net/mptcp/mptcp_output.c | 160
>>>> +++++++++++++++++---------------------------
>>>> net/mptcp/mptcp_redundant.c | 6 +-
>>>> net/mptcp/mptcp_rr.c | 4 +-
>>>> net/mptcp/mptcp_sched.c | 10 +--
>>>> 19 files changed, 335 insertions(+), 286 deletions(-)
>>>>
>>>> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
>>>> index f66cd5e..348cbc1 100644
>>>> --- a/include/linux/skbuff.h
>>>> +++ b/include/linux/skbuff.h
>>>> @@ -532,7 +532,13 @@ struct sk_buff {
>>>> struct rb_node rbnode; /* used in netem & tcp stack */
>>>> };
>>>> struct sock *sk;
>>>> - struct net_device *dev;
>>>> + union {
>>>> + struct net_device *dev;
>>>> + struct {
>>>> + __u8 mptcp_flags;
>>>> + __u8 mptcp_dss_off;
>>>> + };
>>>> + };
>>>> /*
>>>> * This is the control buffer. It is free to use for every
>>>> diff --git a/include/net/mptcp.h b/include/net/mptcp.h
>>>> index 876f1e6..d087cb4 100644
>>>> --- a/include/net/mptcp.h
>>>> +++ b/include/net/mptcp.h
>>>> @@ -807,7 +807,7 @@ void tcp_parse_mptcp_options(const struct
>>>> sk_buff *skb,
>>>> struct mptcp_options_received *mopt);
>>>> void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>>> struct mptcp_options_received *mopt,
>>>> - const struct sk_buff *skb,
>>>> + struct sk_buff *skb,
>>>> struct tcp_sock *tp);
>>>> void mptcp_syn_options(const struct sock *sk, struct
>>>> tcp_out_options *opts,
>>>> unsigned *remaining);
>>>> @@ -998,14 +998,15 @@ static inline void
>>>> mptcp_sub_force_close_all(struct mptcp_cb *mpcb,
>>>> }
>>>> }
>>>> +/* currently tp is being used for Rx packets */
>>>> static inline bool mptcp_is_data_seq(const struct sk_buff *skb)
>>>> {
>>>> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ;
>>>> + return skb->mptcp_flags & MPTCPHDR_SEQ;
>>>> }
>>>> static inline bool mptcp_is_data_fin(const struct sk_buff *skb)
>>>> {
>>>> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_FIN;
>>>> + return skb->mptcp_flags & MPTCPHDR_FIN;
>>>> }
>>>> /* Is it a data-fin while in infinite mapping mode?
>>>> @@ -1034,17 +1035,17 @@ static inline u8 mptcp_get_64_bit(u64
>>>> data_seq, struct mptcp_cb *mpcb)
>>>> /* Sets the data_seq and returns pointer to the in-skb field of
>>>> the data_seq.
>>>> * If the packet has a 64-bit dseq, the pointer points to the
>>>> last 32 bits.
>>>> */
>>>> -static inline __u32 *mptcp_skb_set_data_seq(const struct sk_buff
>>>> *skb,
>>>> +static inline __u32 *mptcp_skb_set_data_seq(struct sk_buff *skb,
>>>> u32 *data_seq,
>>>> struct mptcp_cb *mpcb)
>>>> {
>>>> - __u32 *ptr = (__u32 *)(skb_transport_header(skb) +
>>>> TCP_SKB_CB(skb)->dss_off);
>>>> + __u32 *ptr = (__u32 *)(skb_transport_header(skb) +
>>>> skb->mptcp_dss_off);
>>>> - if (TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ64_SET) {
>>>> + if (skb->mptcp_flags & MPTCPHDR_SEQ64_SET) {
>>>> u64 data_seq64 = get_unaligned_be64(ptr);
>>>> if (mpcb)
>>>> - TCP_SKB_CB(skb)->mptcp_flags |=
>>>> mptcp_get_64_bit(data_seq64, mpcb);
>>>> + skb->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
>>>> *data_seq = (u32)data_seq64;
>>>> ptr++;
>>>> @@ -1142,7 +1143,7 @@ static inline void mptcp_reset_mopt(struct
>>>> tcp_sock *tp)
>>>> static inline __be32 mptcp_get_highorder_sndbits(const struct
>>>> sk_buff *skb,
>>>> const struct mptcp_cb *mpcb)
>>>> {
>>>> - return htonl(mpcb->snd_high_order[(TCP_SKB_CB(skb)->mptcp_flags &
>>>> + return htonl(mpcb->snd_high_order[(skb->mptcp_flags &
>>>> MPTCPHDR_SEQ64_INDEX) ? 1 : 0]);
>>>> }
>>>> @@ -1404,8 +1405,8 @@ static inline void mptcp_set_rto(const struct
>>>> sock *sk) {}
>>>> static inline void mptcp_send_fin(const struct sock *meta_sk) {}
>>>> static inline void mptcp_parse_options(const uint8_t *ptr, const
>>>> int opsize,
>>>> struct mptcp_options_received *mopt,
>>>> - const struct sk_buff *skb,
>>>> - const struct tcp_sock *tp) {}
>>>> + struct sk_buff *skb,
>>>> + struct tcp_sock *tp) {}
>>>> static inline void mptcp_syn_options(const struct sock *sk,
>>>> struct tcp_out_options *opts,
>>>> unsigned *remaining) {}
>>>> diff --git a/include/net/mptcp_v4.h b/include/net/mptcp_v4.h
>>>> index c83dca0..46394a4 100644
>>>> --- a/include/net/mptcp_v4.h
>>>> +++ b/include/net/mptcp_v4.h
>>>> @@ -45,6 +45,7 @@ extern struct tcp_request_sock_ops
>>>> mptcp_join_request_sock_ipv4_ops;
>>>> #ifdef CONFIG_MPTCP
>>>> int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb);
>>>> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff
>>>> *skb);
>>>> struct sock *mptcp_v4_search_req(const __be16 rport, const
>>>> __be32 raddr,
>>>> const __be32 laddr, const struct net *net);
>>>> int mptcp_init4_subsockets(struct sock *meta_sk, const struct
>>>> mptcp_loc4 *loc,
>>>> diff --git a/include/net/sock.h b/include/net/sock.h
>>>> index 0f12593..0d1bda5 100644
>>>> --- a/include/net/sock.h
>>>> +++ b/include/net/sock.h
>>>> @@ -296,6 +296,7 @@ struct cg_proto;
>>>> * @sk_write_space: callback to indicate there is bf sending
>>>> space available
>>>> * @sk_error_report: callback to indicate errors (e.g.
>>>> %MSG_ERRQUEUE)
>>>> * @sk_backlog_rcv: callback to process the backlog
>>>> + * @sk_prequeue: callback to prequeue
>>>> * @sk_destruct: called at sock freeing time, i.e. when all
>>>> refcnt == 0
>>>> */
>>>> struct sock {
>>>> @@ -437,7 +438,9 @@ struct sock {
>>>> void (*sk_write_space)(struct sock *sk);
>>>> void (*sk_error_report)(struct sock *sk);
>>>> int (*sk_backlog_rcv)(struct sock *sk,
>>>> - struct sk_buff *skb);
>>>> + struct sk_buff *skb);
>>>> + bool (*sk_prequeue)(struct sock *sk,
>>>> + struct sk_buff *skb);
>>>> void (*sk_destruct)(struct sock *sk);
>>>> };
>>>> @@ -853,6 +856,11 @@ static inline int sk_backlog_rcv(struct sock
>>>> *sk, struct sk_buff *skb)
>>>> return sk->sk_backlog_rcv(sk, skb);
>>>> }
>>>> +static inline bool sk_prequeue(struct sock *sk, struct sk_buff *skb)
>>>> +{
>>>> + return (false);
>>>> +}
>>>> +
>>>> static inline void sk_incoming_cpu_update(struct sock *sk)
>>>> {
>>>> sk->sk_incoming_cpu = raw_smp_processor_id();
>>>> @@ -993,6 +1001,8 @@ struct proto {
>>>> int (*backlog_rcv) (struct sock *sk,
>>>> struct sk_buff *skb);
>>>> + bool (*prequeue) (struct sock *sk,
>>>> + struct sk_buff *skb);
>>>> void (*release_cb)(struct sock *sk);
>>>> diff --git a/include/net/tcp.h b/include/net/tcp.h
>>>> index 655ecd4..cbe8ef2 100644
>>>> --- a/include/net/tcp.h
>>>> +++ b/include/net/tcp.h
>>>> @@ -47,6 +47,9 @@
>>>> #include <linux/seq_file.h>
>>>> #include <linux/memcontrol.h>
>>>> +typedef int (* process_unclaimed)(struct sock *sk, struct sk_buff
>>>> *skb);
>>>> +extern process_unclaimed tcp_process_unclaimed;
>>>> +
>>>> extern struct inet_hashinfo tcp_hashinfo;
>>>> extern struct percpu_counter tcp_orphan_count;
>>>> @@ -581,6 +584,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock
>>>> *sk, struct sk_buff *skb,
>>>> struct request_sock *req,
>>>> struct dst_entry *dst);
>>>> int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
>>>> +
>>>> int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int
>>>> addr_len);
>>>> int tcp_connect(struct sock *sk);
>>>> struct sk_buff *tcp_make_synack(struct sock *sk, struct
>>>> dst_entry *dst,
>>>> @@ -842,11 +846,6 @@ struct tcp_skb_cb {
>>>> __u32 tcp_gso_segs;
>>>> };
>>>> -#ifdef CONFIG_MPTCP
>>>> - __u8 mptcp_flags; /* flags for the MPTCP layer */
>>>> - __u8 dss_off; /* Number of 4-byte words until
>>>> - * seq-number */
>>>> -#endif
>>>> __u8 tcp_flags; /* TCP header flags. (tcp[13]) */
>>>> __u8 sacked; /* State flags for SACK/FACK. */
>>>> @@ -859,9 +858,13 @@ struct tcp_skb_cb {
>>>> #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
>>>> TCPCB_REPAIRED)
>>>> - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
>>>> + __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
>>>> /* 1 byte hole */
>>>> - __u32 ack_seq; /* Sequence number ACK'd */
>>>> + union {
>>>> + __u32 ack_seq; /* Sequence number ACK'd */
>>>> + __u32 mptcp_data_seq;
>>>> + __u32 mptcp_path_mask;
>>>> + };
>>>> union {
>>>> union {
>>>> struct inet_skb_parm h4;
>>>> @@ -869,12 +872,6 @@ struct tcp_skb_cb {
>>>> struct inet6_skb_parm h6;
>>>> #endif
>>>> } header; /* For incoming frames */
>>>> -#ifdef CONFIG_MPTCP
>>>> - union { /* For MPTCP outgoing frames */
>>>> - __u32 path_mask; /* paths that tried to send this skb */
>>>> - __u32 dss[6]; /* DSS options */
>>>> - };
>>>> -#endif
>>>> };
>>>> };
>>>> diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
>>>> index 73480b9..1e7827f 100644
>>>> --- a/net/ipv4/af_inet.c
>>>> +++ b/net/ipv4/af_inet.c
>>>> @@ -356,6 +356,10 @@ lookup_protocol:
>>>> sk->sk_destruct = inet_sock_destruct;
>>>> sk->sk_protocol = protocol;
>>>> sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
>>>> + sk->sk_prequeue = sk->sk_prot->prequeue;
>>>> + if (sk->sk_prequeue == NULL) {
>>>> + sk->sk_prequeue = sk_prequeue;
>>>> + }
>>>> inet->uc_ttl = -1;
>>>> inet->mc_loop = 1;
>>>> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
>>>> index 16a7256..cb6bbf9 100644
>>>> --- a/net/ipv4/tcp_input.c
>>>> +++ b/net/ipv4/tcp_input.c
>>>> @@ -3133,8 +3133,6 @@ static int tcp_clean_rtx_queue(struct sock
>>>> *sk, int prior_fackets,
>>>> */
>>>> if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
>>>> flag |= FLAG_DATA_ACKED;
>>>> - if (mptcp(tp) && mptcp_is_data_seq(skb))
>>>> - flag |= MPTCP_FLAG_DATA_ACKED;
>>>> } else {
>>>> flag |= FLAG_SYN_ACKED;
>>>> tp->retrans_stamp = 0;
>>>> @@ -3582,16 +3580,6 @@ static int tcp_ack(struct sock *sk, struct
>>>> sk_buff *skb, int flag)
>>>> sack_rtt_us);
>>>> acked -= tp->packets_out;
>>>> - if (mptcp(tp)) {
>>>> - if (mptcp_fallback_infinite(sk, flag)) {
>>>> - pr_err("%s resetting flow\n", __func__);
>>>> - mptcp_send_reset(sk);
>>>> - goto invalid_ack;
>>>> - }
>>>> -
>>>> - mptcp_clean_rtx_infinite(skb, sk);
>>>> - }
>>>> -
>>>> /* Advance cwnd if state allows */
>>>> if (tcp_may_raise_cwnd(sk, flag))
>>>> tcp_cong_avoid(sk, ack, acked);
>>>> @@ -3824,8 +3812,7 @@ static bool tcp_fast_parse_options(const
>>>> struct sk_buff *skb,
>>>> if (tcp_parse_aligned_timestamp(tp, th))
>>>> return true;
>>>> }
>>>> - tcp_parse_options(skb, &tp->rx_opt,
>>>> - mptcp(tp) ? &tp->mptcp->rx_opt : NULL, 1, NULL, tp);
>>>> + tcp_parse_options(skb, &tp->rx_opt, NULL, 1, NULL, tp);
>>>> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
>>>> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>>>> @@ -4550,11 +4537,12 @@ static void tcp_data_queue(struct sock *sk,
>>>> struct sk_buff *skb)
>>>> int eaten = -1;
>>>> bool fragstolen = false;
>>>> - /* If no data is present, but a data_fin is in the options, we
>>>> still
>>>> - * have to call mptcp_queue_skb later on. */
>>>> - if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq &&
>>>> - !(mptcp(tp) && mptcp_is_data_fin(skb)))
>>>> + /*
>>>> + * send every packet to MPTCP
>>>> + */
>>>> + if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq ==
>>>> TCP_SKB_CB(skb)->end_seq)) {
>>>> goto drop;
>>>> + }
>>>> skb_dst_drop(skb);
>>>> __skb_pull(skb, tcp_hdr(skb)->doff * 4);
>>>> @@ -5242,15 +5230,9 @@ syn_challenge:
>>>> goto discard;
>>>> }
>>>> - /* If valid: post process the received MPTCP options. */
>>>> - if (mptcp(tp) && mptcp_handle_options(sk, th, skb))
>>>> - goto discard;
>>>> -
>>>> return true;
>>>> discard:
>>>> - if (mptcp(tp))
>>>> - mptcp_reset_mopt(tp);
>>>> __kfree_skb(skb);
>>>> return false;
>>>> }
>>>> @@ -5302,10 +5284,6 @@ void tcp_rcv_established(struct sock *sk,
>>>> struct sk_buff *skb,
>>>> tp->rx_opt.saw_tstamp = 0;
>>>> - /* MPTCP: force slowpath. */
>>>> - if (mptcp(tp))
>>>> - goto slow_path;
>>>> -
>>>> /* pred_flags is 0xS?10 << 16 + snd_wnd
>>>> * if header_prediction is to be made
>>>> * 'S' will always be tp->tcp_header_len >> 2
>>>> @@ -5585,8 +5563,7 @@ static int
>>>> tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
>>>> struct mptcp_options_received mopt;
>>>> mptcp_init_mp_opt(&mopt);
>>>> - tcp_parse_options(skb, &tp->rx_opt,
>>>> - mptcp(tp) ? &tp->mptcp->rx_opt : &mopt, 0, &foc, tp);
>>>> + tcp_parse_options(skb, &tp->rx_opt, &mopt, 0, &foc, tp);
>>>> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
>>>> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>>>> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
>>>> index 6967a86..3329679 100644
>>>> --- a/net/ipv4/tcp_ipv4.c
>>>> +++ b/net/ipv4/tcp_ipv4.c
>>>> @@ -1420,6 +1420,71 @@ struct sock *tcp_v4_hnd_req(struct sock *sk,
>>>> struct sk_buff *skb)
>>>> return sk;
>>>> }
>>>> +int mptcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
>>>> +{
>>>> + struct net *net = dev_net(skb->dev);
>>>> + const struct tcphdr *th = tcp_hdr(skb);
>>>> + int ret;
>>>> + struct sock *meta_sk;
>>>> +
>>>> + if (sk == NULL) {
>>>> + if (th->syn && !th->ack) {
>>>> + int ret = mptcp_lookup_join(skb, NULL);
>>>> +
>>>> + if (ret < 0) {
>>>> + tcp_v4_send_reset(NULL, skb);
>>>> + kfree_skb(skb);
>>>> + return (1);
>>>> + } else if (ret > 0) {
>>>> + return (1);
>>>> + }
>>>> + }
>>>> + /* Is there a pending request sock for this segment ? */
>>>> + if (mptcp_check_req(skb, net)) {
>>>> + return(1);
>>>> + }
>>>> + return (0);
>>>> + }
>>>> +
>>>> + /* The socket passed in should never be the meta socket */
>>>> +
>>>> + BUG_ON(is_meta_sk(sk));
>>>> +
>>>> + /* Is there a pending request sock for this segment ? */
>>>> + if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
>>>> + return 0;
>>>> + }
>>>> +
>>>> + skb->dev = NULL;
>>>> + meta_sk = mptcp_meta_sk(sk);
>>>> +
>>>> + ret = 0;
>>>> + skb->sk = sk;
>>>> + bh_lock_sock_nested(meta_sk);
>>>> + if (sock_owned_by_user(meta_sk)) {
>>>> + if (unlikely(sk_add_backlog(meta_sk, skb,
>>>> + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>> +
>>>> + NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>> + kfree_skb(skb);
>>>> + }
>>>> + } else {
>>>> +
>>>> + if (is_meta_sk(sk)) {
>>>> + ret = mptcp_v4_process_join_req(sk, skb);
>>>> + goto done;
>>>> + }
>>>> + if (!meta_sk->sk_prequeue(meta_sk, skb)) {
>>>> + skb->sk = NULL;
>>>> + ret = tcp_v4_do_rcv(sk, skb);
>>>> + }
>>>> +
>>>> + }
>>>> +done:
>>>> + bh_unlock_sock(meta_sk);
>>>> + return (ret);
>>>> +}
>>>> +
>>>> /* The socket must have it's spinlock held when we get
>>>> * here.
>>>> *
>>>> @@ -1432,8 +1497,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct
>>>> sk_buff *skb)
>>>> {
>>>> struct sock *rsk;
>>>> - if (is_meta_sk(sk))
>>>> - return mptcp_v4_do_rcv(sk, skb);
>>>> + BUG_ON(is_meta_sk(sk));
>>>> if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
>>>> struct dst_entry *dst = sk->sk_rx_dst;
>>>> @@ -1587,6 +1651,8 @@ bool tcp_prequeue(struct sock *sk, struct
>>>> sk_buff *skb)
>>>> }
>>>> EXPORT_SYMBOL(tcp_prequeue);
>>>> +process_unclaimed tcp_process_unclaimed = NULL;
>>>> +
>>>> /*
>>>> * From tcp_input.c
>>>> */
>>>> @@ -1595,7 +1661,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
>>>> {
>>>> const struct iphdr *iph;
>>>> const struct tcphdr *th;
>>>> - struct sock *sk, *meta_sk = NULL;
>>>> + struct sock *sk = NULL;
>>>> int ret;
>>>> struct net *net = dev_net(skb->dev);
>>>> @@ -1636,10 +1702,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
>>>> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn +
>>>> th->fin +
>>>> skb->len - th->doff * 4);
>>>> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
>>>> -#ifdef CONFIG_MPTCP
>>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>> - TCP_SKB_CB(skb)->dss_off = 0;
>>>> -#endif
>>>> +
>>>> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
>>>> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
>>>> TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
>>>> @@ -1662,15 +1725,6 @@ process:
>>>> if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
>>>> goto discard_and_relse;
>>>> -#ifdef CONFIG_MPTCP
>>>> - /* Is there a pending request sock for this segment ? */
>>>> - if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
>>>> - if (sk)
>>>> - sock_put(sk);
>>>> - return 0;
>>>> - }
>>>> -#endif
>>>> -
>>>> #ifdef CONFIG_TCP_MD5SIG
>>>> /*
>>>> * We really want to reject the packet as early as possible
>>>> @@ -1688,30 +1742,21 @@ process:
>>>> goto discard_and_relse;
>>>> sk_incoming_cpu_update(sk);
>>>> - skb->dev = NULL;
>>>> - if (mptcp(tcp_sk(sk))) {
>>>> - meta_sk = mptcp_meta_sk(sk);
>>>> -
>>>> - bh_lock_sock_nested(meta_sk);
>>>> - if (sock_owned_by_user(meta_sk))
>>>> - skb->sk = sk;
>>>> - } else {
>>>> - meta_sk = sk;
>>>> - bh_lock_sock_nested(sk);
>>>> - }
>>>> + /* Do I have to set skb->dev to null ? */
>>>> + bh_lock_sock_nested(sk);
>>>> ret = 0;
>>>> - if (!sock_owned_by_user(meta_sk)) {
>>>> - if (!tcp_prequeue(meta_sk, skb))
>>>> - ret = tcp_v4_do_rcv(sk, skb);
>>>> - } else if (unlikely(sk_add_backlog(meta_sk, skb,
>>>> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>> - bh_unlock_sock(meta_sk);
>>>> + if (!sock_owned_by_user(sk)) {
>>>> + if (!sk->sk_prequeue(sk, skb))
>>>> + ret = sk->sk_backlog_rcv(sk, skb);
>>>> + } else if (unlikely(sk_add_backlog(sk, skb,
>>>> + sk->sk_rcvbuf + sk->sk_sndbuf))) {
>>>> + bh_unlock_sock(sk);
>>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>> goto discard_and_relse;
>>>> }
>>>> - bh_unlock_sock(meta_sk);
>>>> + bh_unlock_sock(sk);
>>>> sock_put(sk);
>>>> @@ -1721,26 +1766,11 @@ no_tcp_socket:
>>>> if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
>>>> goto discard_it;
>>>> -#ifdef CONFIG_MPTCP
>>>> - if (!sk && th->syn && !th->ack) {
>>>> - int ret = mptcp_lookup_join(skb, NULL);
>>>> -
>>>> - if (ret < 0) {
>>>> - tcp_v4_send_reset(NULL, skb);
>>>> - goto discard_it;
>>>> - } else if (ret > 0) {
>>>> - return 0;
>>>> - }
>>>> + if (unlikely (tcp_process_unclaimed != NULL)) {
>>>> + if ((tcp_process_unclaimed)(NULL, skb))
>>>> + return (0);
>>>> }
>>>> - /* Is there a pending request sock for this segment ? */
>>>> - if (!sk && mptcp_check_req(skb, net)) {
>>>> - if (sk)
>>>> - sock_put(sk);
>>>> - return 0;
>>>> - }
>>>> -#endif
>>>> -
>>>> if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
>>>> csum_error:
>>>> TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
>>>> @@ -2506,6 +2536,7 @@ struct proto tcp_prot = {
>>>> .sendmsg = tcp_sendmsg,
>>>> .sendpage = tcp_sendpage,
>>>> .backlog_rcv = tcp_v4_do_rcv,
>>>> + .prequeue = tcp_prequeue,
>>>> .release_cb = tcp_release_cb,
>>>> .hash = inet_hash,
>>>> .unhash = inet_unhash,
>>>> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
>>>> index a635483..41b8be8 100644
>>>> --- a/net/ipv4/tcp_output.c
>>>> +++ b/net/ipv4/tcp_output.c
>>>> @@ -3413,6 +3413,7 @@ void tcp_send_delayed_ack(struct sock *sk)
>>>> void tcp_send_ack(struct sock *sk)
>>>> {
>>>> struct sk_buff *buff;
>>>> + struct tcp_sock *tp = tcp_sk(sk);
>>>> /* If we have been reset, we may not send again. */
>>>> if (sk->sk_state == TCP_CLOSE)
>>>> diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
>>>> index 8c4dd4a..1554217 100644
>>>> --- a/net/ipv6/af_inet6.c
>>>> +++ b/net/ipv6/af_inet6.c
>>>> @@ -193,6 +193,10 @@ lookup_protocol:
>>>> sk->sk_protocol = protocol;
>>>> sk->sk_backlog_rcv = answer->prot->backlog_rcv;
>>>> + sk->sk_prequeue = answer->prot->prequeue;
>>>> + if (sk->sk_prequeue == NULL) {
>>>> + sk->sk_prequeue = sk_prequeue;
>>>> + }
>>>> inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
>>>> np->hop_limit = -1;
>>>> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
>>>> index eba2436..d360128 100644
>>>> --- a/net/ipv6/tcp_ipv6.c
>>>> +++ b/net/ipv6/tcp_ipv6.c
>>>> @@ -1412,10 +1412,6 @@ static void tcp_v6_fill_cb(struct sk_buff
>>>> *skb, const struct ipv6hdr *hdr,
>>>> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn +
>>>> th->fin +
>>>> skb->len - th->doff*4);
>>>> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
>>>> -#ifdef CONFIG_MPTCP
>>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>> - TCP_SKB_CB(skb)->dss_off = 0;
>>>> -#endif
>>>> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
>>>> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
>>>> TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
>>>> diff --git a/net/mptcp/mptcp_ctrl.c b/net/mptcp/mptcp_ctrl.c
>>>> index 28f348f..b1e780a 100644
>>>> --- a/net/mptcp/mptcp_ctrl.c
>>>> +++ b/net/mptcp/mptcp_ctrl.c
>>>> @@ -976,6 +976,20 @@ int mptcp_backlog_rcv(struct sock *meta_sk,
>>>> struct sk_buff *skb)
>>>> struct sock *sk = skb->sk ? skb->sk : meta_sk;
>>>> int ret = 0;
>>>> + /* socket was owned by the user in mptcp_check_req()
>>>> + */
>>>> + if (sk == (struct sock *)0xFEE1DEAD) {
>>>> + bh_lock_sock_nested(meta_sk);
>>>> + if (skb->protocol == htons(ETH_P_IP))
>>>> + mptcp_v4_process_join_req(meta_sk, skb);
>>>> +#if IS_ENABLED(CONFIG_IPV6)
>>>> + else
>>>> + //mptcp_v6_process_join_req(meta_sk, skb);
>>>> +#endif /* CONFIG_IPV6 */
>>>> + bh_unlock_sock(meta_sk);
>>>> + return(0);
>>>> + }
>>>> +
>>>> skb->sk = NULL;
>>>> if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
>>>> @@ -1297,6 +1311,10 @@ int mptcp_add_sock(struct sock *meta_sk,
>>>> struct sock *sk, u8 loc_id, u8 rem_id,
>>>> sk->sk_write_space = mptcp_write_space;
>>>> sk->sk_state_change = mptcp_set_state;
>>>> sk->sk_destruct = mptcp_sock_destruct;
>>>> + /* MPTCP takes a different path in tcp_v4_rcv
>>>> + * thus not impacting main tcp code */
>>>> + sk->sk_backlog_rcv = mptcp_v4_do_rcv;
>>>> + sk->sk_prequeue = sk_prequeue;
>>>> if (sk->sk_family == AF_INET)
>>>> mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d
>>>> dst_addr:%pI4:%d, cnt_subflows now %d\n",
>>>> @@ -2658,6 +2676,9 @@ void __init mptcp_init(void)
>>>> if (mptcp_pm_v4_init())
>>>> goto mptcp_pm_v4_failed;
>>>> + if ((cmpxchg(&tcp_process_unclaimed, NULL, mptcp_v4_do_rcv))
>>>> != NULL)
>>>> + printk("tcp_process_unclaimed not NULL \n");
>>>> +
>>>> mptcp_sysctl = register_net_sysctl(&init_net, "net/mptcp",
>>>> mptcp_table);
>>>> if (!mptcp_sysctl)
>>>> goto register_sysctl_failed;
>>>> diff --git a/net/mptcp/mptcp_input.c b/net/mptcp/mptcp_input.c
>>>> index 51cbb06..0e09ddf 100644
>>>> --- a/net/mptcp/mptcp_input.c
>>>> +++ b/net/mptcp/mptcp_input.c
>>>> @@ -323,9 +323,8 @@ static int mptcp_verif_dss_csum(struct sock *sk)
>>>> * by 4 bytes, as the high-order 64-bits will be added
>>>> * in the final csum_partial-call.
>>>> */
>>>> - u32 offset = skb_transport_offset(tmp) +
>>>> - TCP_SKB_CB(tmp)->dss_off;
>>>> - if (TCP_SKB_CB(tmp)->mptcp_flags & MPTCPHDR_SEQ64_SET)
>>>> + u32 offset = skb_transport_offset(tmp) +
>>>> tmp->mptcp_dss_off;
>>>> + if (tmp->mptcp_flags & MPTCPHDR_SEQ64_SET)
>>>> offset += 4;
>>>> csum_tcp = skb_checksum(tmp, offset,
>>>> @@ -758,7 +757,7 @@ static int mptcp_detect_mapping(struct sock
>>>> *sk, struct sk_buff *skb)
>>>> }
>>>> /* Does the DSS had 64-bit seqnum's ? */
>>>> - if (!(tcb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
>>>> + if (!(skb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
>>>> /* Wrapped around? */
>>>> if (unlikely(after(data_seq, meta_tp->rcv_nxt) &&
>>>> data_seq < meta_tp->rcv_nxt)) {
>>>> tp->mptcp->map_data_seq =
>>>> mptcp_get_data_seq_64(mpcb, !mpcb->rcv_hiseq_index, data_seq);
>>>> @@ -767,9 +766,9 @@ static int mptcp_detect_mapping(struct sock
>>>> *sk, struct sk_buff *skb)
>>>> tp->mptcp->map_data_seq =
>>>> mptcp_get_data_seq_64(mpcb, mpcb->rcv_hiseq_index, data_seq);
>>>> }
>>>> } else {
>>>> - tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
>>>> (tcb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
>>>> + tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb,
>>>> (skb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
>>>> - if (unlikely(tcb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
>>>> + if (unlikely(skb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
>>>> /* We make sure that the data_seq is invalid.
>>>> * It will be dropped later.
>>>> */
>>>> @@ -1020,6 +1019,67 @@ next:
>>>> return data_queued ? -1 : -2;
>>>> }
>>>> +static struct sk_buff *
>>>> +mptcp_process_ack(struct sock *sk, struct sk_buff *skb)
>>>> +{
>>>> + struct tcp_sock *tp = tcp_sk(sk);
>>>> + int flag = 0;
>>>> +
>>>> + /*
>>>> + * TCP takes care of invalid ack's
>>>> + * they will never show up here.
>>>> + */
>>>> +
>>>> + /* Is this skb acknowleding anything data */
>>>> +
>>>> + if (tp->mptcp->snt_isn + 1 != TCP_SKB_CB(skb)->ack_seq) {
>>>> + flag = MPTCP_FLAG_DATA_ACKED;
>>>> + }
>>>> +
>>>> + if (mptcp_fallback_infinite(sk, flag)) {
>>>> + pr_err("%s resetting flow\n", __func__);
>>>> + mptcp_send_reset(sk);
>>>> + goto invalid_ack;
>>>> + }
>>>> +
>>>> + mptcp_clean_rtx_infinite(skb, sk);
>>>> +
>>>> + return (skb);
>>>> +invalid_ack:
>>>> + __skb_unlink(skb, &sk->sk_receive_queue);
>>>> + __kfree_skb(skb);
>>>> + return (NULL);
>>>> +
>>>> +}
>>>> +
>>>> +static struct sk_buff *
>>>> +mptcp_process_options_ack(struct sock *sk, struct sk_buff *skb)
>>>> +{
>>>> + struct tcp_sock *tp = tcp_sk(sk);
>>>> + const struct tcphdr *th = tcp_hdr(skb);
>>>> +
>>>> + skb->mptcp_flags = 0;
>>>> + skb->mptcp_dss_off = 0;
>>>> +
>>>> + tcp_parse_mptcp_options(skb, &tp->mptcp->rx_opt);
>>>> + if (mptcp_handle_options(sk, th, skb)) {
>>>> + mptcp_reset_mopt(tp);
>>>> + __skb_unlink(skb, &sk->sk_receive_queue);
>>>> + __kfree_skb(skb);
>>>> + skb = NULL;
>>>> + }
>>>> + if ((skb != NULL) && skb->len == 0) {
>>>> + skb = mptcp_process_ack(sk, skb);
>>>> + if (skb != NULL && skb->len == 0) {
>>>> + /* Pure ack */
>>>> + __skb_unlink(skb, &sk->sk_receive_queue);
>>>> + __kfree_skb(skb);
>>>> + skb = NULL;
>>>> + }
>>>> + }
>>>> + return (skb);
>>>> +}
>>>> +
>>>> void mptcp_data_ready(struct sock *sk)
>>>> {
>>>> struct sock *meta_sk = mptcp_meta_sk(sk);
>>>> @@ -1045,6 +1105,10 @@ restart:
>>>> */
>>>> skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
>>>> int ret;
>>>> +
>>>> + skb = mptcp_process_options_ack(sk, skb);
>>>> + if (skb == NULL)
>>>> + continue;
>>>> /* Pre-validation - e.g., early fallback */
>>>> ret = mptcp_prevalidate_skb(sk, skb);
>>>> if (ret < 0)
>>>> @@ -1108,13 +1172,11 @@ int mptcp_check_req(struct sk_buff *skb,
>>>> struct net *net)
>>>> if (!meta_sk)
>>>> return 0;
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>> -
>>>> bh_lock_sock_nested(meta_sk);
>>>> if (sock_owned_by_user(meta_sk)) {
>>>> - skb->sk = meta_sk;
>>>> + skb->sk = (struct sock *)0xFEE1DEAD;
>>>> if (unlikely(sk_add_backlog(meta_sk, skb,
>>>> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>> + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>>> bh_unlock_sock(meta_sk);
>>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>> sock_put(meta_sk); /* Taken by mptcp_search_req */
>>>> @@ -1122,10 +1184,14 @@ int mptcp_check_req(struct sk_buff *skb,
>>>> struct net *net)
>>>> return 1;
>>>> }
>>>> } else if (skb->protocol == htons(ETH_P_IP)) {
>>>> - tcp_v4_do_rcv(meta_sk, skb);
>>>> + /*
>>>> + * call old mptcp_v4_do_rcv
>>>> + */
>>>> + mptcp_v4_process_join_req(meta_sk, skb);
>>>> #if IS_ENABLED(CONFIG_IPV6)
>>>> } else { /* IPv6 */
>>>> - tcp_v6_do_rcv(meta_sk, skb);
>>>> + WARN_ON(1);
>>>> + //mptcp_v6_handle_join_req(meta_sk, skb);
>>>> #endif /* CONFIG_IPV6 */
>>>> }
>>>> bh_unlock_sock(meta_sk);
>>>> @@ -1222,7 +1288,7 @@ int mptcp_lookup_join(struct sk_buff *skb,
>>>> struct inet_timewait_sock *tw)
>>>> inet_twsk_put(tw);
>>>> }
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>> + skb->mptcp_flags |= MPTCPHDR_JOIN;
>>>> /* OK, this is a new syn/join, let's create a new open
>>>> request and
>>>> * send syn+ack
>>>> */
>>>> @@ -1279,7 +1345,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>>> return -1;
>>>> }
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>> + //TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>>> /* OK, this is a new syn/join, let's create a new open
>>>> request and
>>>> * send syn+ack
>>>> @@ -1303,7 +1369,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>>> }
>>>> if (sock_owned_by_user(meta_sk)) {
>>>> - skb->sk = meta_sk;
>>>> + skb->sk = (struct sock *)0xFEE1DEAD; //skb->sk = meta_sk;
>>>> if (unlikely(sk_add_backlog(meta_sk, skb,
>>>> meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf)))
>>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>>> @@ -1319,10 +1385,12 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>>> */
>>>> skb_get(skb);
>>>> if (skb->protocol == htons(ETH_P_IP)) {
>>>> - tcp_v4_do_rcv(meta_sk, skb);
>>>> + //tcp_v4_do_rcv(meta_sk, skb);
>>>> + mptcp_v4_process_join_req(meta_sk, skb);
>>>> #if IS_ENABLED(CONFIG_IPV6)
>>>> } else { /* IPv6 */
>>>> - tcp_v6_do_rcv(meta_sk, skb);
>>>> + //mptcp_v6_process_join_req(meta_sk, skb);
>>>> + //tcp_v6_do_rcv(meta_sk, skb);
>>>> #endif /* CONFIG_IPV6 */
>>>> }
>>>> }
>>>> @@ -1461,7 +1529,6 @@ static void mptcp_data_ack(struct sock *sk,
>>>> const struct sk_buff *skb)
>>>> {
>>>> struct sock *meta_sk = mptcp_meta_sk(sk);
>>>> struct tcp_sock *meta_tp = tcp_sk(meta_sk), *tp = tcp_sk(sk);
>>>> - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>> u32 prior_snd_una = meta_tp->snd_una;
>>>> int prior_packets;
>>>> u32 nwin, data_ack, data_seq;
>>>> @@ -1481,7 +1548,7 @@ static void mptcp_data_ack(struct sock *sk,
>>>> const struct sk_buff *skb)
>>>> /* If we are in infinite mapping mode, rx_opt.data_ack has been
>>>> * set by mptcp_clean_rtx_infinite.
>>>> */
>>>> - if (!(tcb->mptcp_flags & MPTCPHDR_ACK) &&
>>>> !tp->mpcb->infinite_mapping_snd)
>>>> + if (!(skb->mptcp_flags & MPTCPHDR_ACK) &&
>>>> !tp->mpcb->infinite_mapping_snd)
>>>> goto exit;
>>>> data_ack = tp->mptcp->rx_opt.data_ack;
>>>> @@ -1647,10 +1714,11 @@ static inline bool
>>>> is_valid_addropt_opsize(u8 mptcp_ver,
>>>> void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>>> struct mptcp_options_received *mopt,
>>>> - const struct sk_buff *skb,
>>>> + struct sk_buff *skb,
>>>> struct tcp_sock *tp)
>>>> {
>>>> const struct mptcp_option *mp_opt = (struct mptcp_option *)ptr;
>>>> + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>> /* If the socket is mp-capable we would have a mopt. */
>>>> if (!mopt)
>>>> @@ -1757,7 +1825,7 @@ void mptcp_parse_options(const uint8_t *ptr,
>>>> int opsize,
>>>> ptr += 4;
>>>> if (mdss->A) {
>>>> - tcb->mptcp_flags |= MPTCPHDR_ACK;
>>>> + skb->mptcp_flags |= MPTCPHDR_ACK;
>>>> if (mdss->a) {
>>>> mopt->data_ack = (u32) get_unaligned_be64(ptr);
>>>> @@ -1768,13 +1836,13 @@ void mptcp_parse_options(const uint8_t
>>>> *ptr, int opsize,
>>>> }
>>>> }
>>>> - tcb->dss_off = (ptr - skb_transport_header(skb));
>>>> + skb->mptcp_dss_off = (ptr - skb_transport_header(skb));
>>>> if (mdss->M) {
>>>> if (mdss->m) {
>>>> u64 data_seq64 = get_unaligned_be64(ptr);
>>>> - tcb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
>>>> + skb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
>>>> mopt->data_seq = (u32) data_seq64;
>>>> ptr += 12; /* 64-bit dseq + subseq */
>>>> @@ -1784,15 +1852,16 @@ void mptcp_parse_options(const uint8_t
>>>> *ptr, int opsize,
>>>> }
>>>> mopt->data_len = get_unaligned_be16(ptr);
>>>> - tcb->mptcp_flags |= MPTCPHDR_SEQ;
>>>> + skb->mptcp_flags |= MPTCPHDR_SEQ;
>>>> /* Is a check-sum present? */
>>>> - if (opsize == mptcp_sub_len_dss(mdss, 1))
>>>> - tcb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
>>>> + if (opsize == mptcp_sub_len_dss(mdss, 1)) {
>>>> + skb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
>>>> + }
>>>> /* DATA_FIN only possible with DSS-mapping */
>>>> if (mdss->F)
>>>> - tcb->mptcp_flags |= MPTCPHDR_FIN;
>>>> + skb->mptcp_flags |= MPTCPHDR_FIN;
>>>> }
>>>> break;
>>>> @@ -1907,8 +1976,9 @@ void tcp_parse_mptcp_options(const struct
>>>> sk_buff *skb,
>>>> return;
>>>> if (opsize > length)
>>>> return; /* don't parse partial options */
>>>> - if (opcode == TCPOPT_MPTCP)
>>>> + if (opcode == TCPOPT_MPTCP) {
>>>> mptcp_parse_options(ptr - 2, opsize, mopt, skb,
>>>> NULL);
>>>> + }
>>>> }
>>>> ptr += opsize - 2;
>>>> length -= opsize;
>>>> @@ -2168,6 +2238,8 @@ bool mptcp_handle_options(struct sock *sk,
>>>> const struct tcphdr *th,
>>>> struct tcp_sock *tp = tcp_sk(sk);
>>>> struct mptcp_options_received *mopt = &tp->mptcp->rx_opt;
>>>> + BUG_ON(sk == mptcp_meta_sk(sk));
>>>> +
>>>> if (tp->mpcb->infinite_mapping_rcv ||
>>>> tp->mpcb->infinite_mapping_snd)
>>>> return false;
>>>> @@ -2185,7 +2257,7 @@ bool mptcp_handle_options(struct sock *sk,
>>>> const struct tcphdr *th,
>>>> * receiver MUST close the subflow with a RST as it is
>>>> considered broken.
>>>> */
>>>> if (mptcp_is_data_seq(skb) && tp->mpcb->dss_csum &&
>>>> - !(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
>>>> + !(skb->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
>>>> mptcp_send_reset(sk);
>>>> return true;
>>>> }
>>>> @@ -2330,6 +2402,7 @@ int mptcp_rcv_synsent_state_process(struct
>>>> sock *sk, struct sock **skptr,
>>>> /* Set this flag in order to postpone data sending
>>>> * until the 4th ack arrives.
>>>> */
>>>> +printk("mptcp_rcv_synsent_state_process pre_established set \n");
>>>> tp->mptcp->pre_established = 1;
>>>> tp->mptcp->rcv_low_prio = tp->mptcp->rx_opt.low_prio;
>>>> diff --git a/net/mptcp/mptcp_ipv4.c b/net/mptcp/mptcp_ipv4.c
>>>> index a147b20..3e60ab5 100644
>>>> --- a/net/mptcp/mptcp_ipv4.c
>>>> +++ b/net/mptcp/mptcp_ipv4.c
>>>> @@ -180,45 +180,12 @@ static int mptcp_v4_join_request(struct sock
>>>> *meta_sk, struct sk_buff *skb)
>>>> }
>>>> /* We only process join requests here. (either the SYN or the
>>>> final ACK) */
>>>> -int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>>> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff
>>>> *skb)
>>>> {
>>>> const struct mptcp_cb *mpcb = tcp_sk(meta_sk)->mpcb;
>>>> struct sock *child, *rsk = NULL;
>>>> int ret;
>>>> - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
>>>> - struct tcphdr *th = tcp_hdr(skb);
>>>> - const struct iphdr *iph = ip_hdr(skb);
>>>> - struct sock *sk;
>>>> -
>>>> - sk = inet_lookup_established(sock_net(meta_sk),
>>>> &tcp_hashinfo,
>>>> - iph->saddr, th->source, iph->daddr,
>>>> - th->dest, inet_iif(skb));
>>>> -
>>>> - if (!sk) {
>>>> - kfree_skb(skb);
>>>> - return 0;
>>>> - }
>>>> - if (is_meta_sk(sk)) {
>>>> - WARN("%s Did not find a sub-sk - did found the
>>>> meta!\n", __func__);
>>>> - kfree_skb(skb);
>>>> - sock_put(sk);
>>>> - return 0;
>>>> - }
>>>> -
>>>> - if (sk->sk_state == TCP_TIME_WAIT) {
>>>> - inet_twsk_put(inet_twsk(sk));
>>>> - kfree_skb(skb);
>>>> - return 0;
>>>> - }
>>>> -
>>>> - ret = tcp_v4_do_rcv(sk, skb);
>>>> - sock_put(sk);
>>>> -
>>>> - return ret;
>>>> - }
>>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>> -
>>>> /* Has been removed from the tk-table. Thus, no new subflows.
>>>> *
>>>> * Check for close-state is necessary, because we may have
>>>> been closed
>>>> diff --git a/net/mptcp/mptcp_ipv6.c b/net/mptcp/mptcp_ipv6.c
>>>> index 0de953d..1959d01 100644
>>>> --- a/net/mptcp/mptcp_ipv6.c
>>>> +++ b/net/mptcp/mptcp_ipv6.c
>>>> @@ -199,7 +199,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk,
>>>> struct sk_buff *skb)
>>>> struct sock *child, *rsk = NULL;
>>>> int ret;
>>>> - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
>>>> + if (!(skb->mptcp_flags & MPTCPHDR_JOIN)) {
>>>> struct tcphdr *th = tcp_hdr(skb);
>>>> const struct ipv6hdr *ip6h = ipv6_hdr(skb);
>>>> struct sock *sk;
>>>> @@ -232,7 +232,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk,
>>>> struct sk_buff *skb)
>>>> return ret;
>>>> }
>>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>>> + skb->mptcp_flags = 0;
>>>> /* Has been removed from the tk-table. Thus, no new subflows.
>>>> *
>>>> diff --git a/net/mptcp/mptcp_output.c b/net/mptcp/mptcp_output.c
>>>> index 691ef6f..e7d340d 100644
>>>> --- a/net/mptcp/mptcp_output.c
>>>> +++ b/net/mptcp/mptcp_output.c
>>>> @@ -59,39 +59,17 @@ EXPORT_SYMBOL(mptcp_sub_len_remove_addr_align);
>>>> */
>>>> static bool mptcp_reconstruct_mapping(struct sk_buff *skb)
>>>> {
>>>> - const struct mp_dss *mpdss = (struct mp_dss
>>>> *)TCP_SKB_CB(skb)->dss;
>>>> - u32 *p32;
>>>> - u16 *p16;
>>>> -
>>>> if (!mptcp_is_data_seq(skb))
>>>> return false;
>>>> - if (!mpdss->M)
>>>> - return false;
>>>> -
>>>> - /* Move the pointer to the data-seq */
>>>> - p32 = (u32 *)mpdss;
>>>> - p32++;
>>>> - if (mpdss->A) {
>>>> - p32++;
>>>> - if (mpdss->a)
>>>> - p32++;
>>>> - }
>>>> -
>>>> - TCP_SKB_CB(skb)->seq = ntohl(*p32);
>>>> -
>>>> - /* Get the data_len to calculate the end_data_seq */
>>>> - p32++;
>>>> - p32++;
>>>> - p16 = (u16 *)p32;
>>>> - TCP_SKB_CB(skb)->end_seq = ntohs(*p16) + TCP_SKB_CB(skb)->seq;
>>>> + TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->mptcp_data_seq;
>>>> return true;
>>>> }
>>>> static bool mptcp_is_reinjected(const struct sk_buff *skb)
>>>> {
>>>> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCP_REINJECT;
>>>> + return skb->mptcp_flags & MPTCP_REINJECT;
>>>> }
>>>> static void mptcp_find_and_set_pathmask(const struct sock
>>>> *meta_sk, struct sk_buff *skb)
>>>> @@ -105,7 +83,7 @@ static void mptcp_find_and_set_pathmask(const
>>>> struct sock *meta_sk, struct sk_bu
>>>> break;
>>>> if (TCP_SKB_CB(skb_it)->seq == TCP_SKB_CB(skb)->seq) {
>>>> - TCP_SKB_CB(skb)->path_mask =
>>>> TCP_SKB_CB(skb_it)->path_mask;
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask =
>>>> TCP_SKB_CB(skb_it)->mptcp_path_mask;
>>>> break;
>>>> }
>>>> }
>>>> @@ -180,9 +158,9 @@ static void __mptcp_reinject_data(struct
>>>> sk_buff *orig_skb, struct sock *meta_sk
>>>> }
>>>> /* Segment goes back to the MPTCP-layer. So, we need to zero
>>>> the
>>>> - * path_mask/dss.
>>>> + * path_mask.
>>>> */
>>>> - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>>> /* We need to find out the path-mask from the meta-write-queue
>>>> * to properly select a subflow.
>>>> @@ -272,14 +250,14 @@ void mptcp_reinject_data(struct sock *sk, int
>>>> clone_it)
>>>> if (mptcp_is_reinjected(skb_it))
>>>> continue;
>>>> - tcb->mptcp_flags |= MPTCP_REINJECT;
>>>> + skb_it->mptcp_flags |= MPTCP_REINJECT;
>>>> __mptcp_reinject_data(skb_it, meta_sk, sk, clone_it);
>>>> }
>>>> skb_it = tcp_write_queue_tail(meta_sk);
>>>> /* If sk has sent the empty data-fin, we have to reinject it
>>>> too. */
>>>> if (skb_it && mptcp_is_data_fin(skb_it) && skb_it->len == 0 &&
>>>> - TCP_SKB_CB(skb_it)->path_mask &
>>>> mptcp_pi_to_flag(tp->mptcp->path_index)) {
>>>> + TCP_SKB_CB(skb_it)->mptcp_path_mask &
>>>> mptcp_pi_to_flag(tp->mptcp->path_index)) {
>>>> __mptcp_reinject_data(skb_it, meta_sk, NULL, 1);
>>>> }
>>>> @@ -319,25 +297,43 @@ combine:
>>>> }
>>>> }
>>>> -static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
>>>> const struct sk_buff *skb,
>>>> - __be32 *ptr)
>>>> +/*
>>>> + * RFC6824 states that once a particular subflow mapping has been
>>>> sent
>>>> + * out it must never be changed. However, packets may be split while
>>>> + * they are in the retransmission queue (due to SACK or ACKs) and
>>>> that
>>>> + * arguably means that we would change the mapping (e.g. it splits
>>>> it,
>>>> + * our sends out a subset of the initial mapping).
>>>> + *
>>>> + * Furthermore, the skb checksum is not always preserved across
>>>> splits
>>>> + * (e.g. mptcp_fragment) which would mean that we need to recompute
>>>> + * the DSS checksum in this case.
>>>> + *
>>>> + * To avoid this we save the initial DSS mapping which allows us to
>>>> + * send the same DSS mapping even for fragmented retransmits.
>>>> + */
>>>> +
>>>> +static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
>>>> + const struct sk_buff *skb, __be32 *ptr)
>>>> {
>>>> const struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>> - __be32 *start = ptr;
>>>> __u16 data_len;
>>>> - *ptr++ = htonl(tcb->seq); /* data_seq */
>>>> + *ptr++ = htonl(tcb->mptcp_data_seq); /* data_seq */
>>>> /* If it's a non-data DATA_FIN, we set subseq to 0 (draft
>>>> v7) */
>>>> if (mptcp_is_data_fin(skb) && skb->len == 0)
>>>> *ptr++ = 0; /* subseq */
>>>> else
>>>> - *ptr++ = htonl(tp->write_seq - tp->mptcp->snt_isn); /*
>>>> subseq */
>>>> + *ptr++ = htonl(tcb->seq - tp->mptcp->snt_isn); /* subseq */
>>>> - if (tcb->mptcp_flags & MPTCPHDR_INF)
>>>> + if (skb->mptcp_flags & MPTCPHDR_INF)
>>>> data_len = 0;
>>>> - else
>>>> + else {
>>>> data_len = tcb->end_seq - tcb->seq;
>>>> + /* mptcp_entail_skb adds one for FIN */
>>>> + if (tcb->tcp_flags & TCPHDR_FIN)
>>>> + data_len -= 1;
>>>> + }
>>>> if (tp->mpcb->dss_csum && data_len) {
>>>> __be16 *p16 = (__be16 *)ptr;
>>>> @@ -356,11 +352,11 @@ static int mptcp_write_dss_mapping(const
>>>> struct tcp_sock *tp, const struct sk_bu
>>>> (TCPOPT_NOP));
>>>> }
>>>> - return ptr - start;
>>>> + return mptcp_dss_len/sizeof(*ptr);
>>>> }
>>>> -static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
>>>> const struct sk_buff *skb,
>>>> - __be32 *ptr)
>>>> +static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
>>>> + const struct sk_buff *skb, __be32 *ptr)
>>>> {
>>>> struct mp_dss *mdss = (struct mp_dss *)ptr;
>>>> __be32 *start = ptr;
>>>> @@ -377,54 +373,12 @@ static int mptcp_write_dss_data_ack(const
>>>> struct tcp_sock *tp, const struct sk_b
>>>> mdss->len = mptcp_sub_len_dss(mdss, tp->mpcb->dss_csum);
>>>> ptr++;
>>>> + /* data_ack */
>>>> *ptr++ = htonl(mptcp_meta_tp(tp)->rcv_nxt);
>>>> return ptr - start;
>>>> }
>>>> -/* RFC6824 states that once a particular subflow mapping has been
>>>> sent
>>>> - * out it must never be changed. However, packets may be split while
>>>> - * they are in the retransmission queue (due to SACK or ACKs) and
>>>> that
>>>> - * arguably means that we would change the mapping (e.g. it splits
>>>> it,
>>>> - * our sends out a subset of the initial mapping).
>>>> - *
>>>> - * Furthermore, the skb checksum is not always preserved across
>>>> splits
>>>> - * (e.g. mptcp_fragment) which would mean that we need to recompute
>>>> - * the DSS checksum in this case.
>>>> - *
>>>> - * To avoid this we save the initial DSS mapping which allows us to
>>>> - * send the same DSS mapping even for fragmented retransmits.
>>>> - */
>>>> -static void mptcp_save_dss_data_seq(const struct tcp_sock *tp,
>>>> struct sk_buff *skb)
>>>> -{
>>>> - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>>> - __be32 *ptr = (__be32 *)tcb->dss;
>>>> -
>>>> - tcb->mptcp_flags |= MPTCPHDR_SEQ;
>>>> -
>>>> - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>>> - ptr += mptcp_write_dss_mapping(tp, skb, ptr);
>>>> -}
>>>> -
>>>> -/* Write the saved DSS mapping to the header */
>>>> -static int mptcp_write_dss_data_seq(const struct tcp_sock *tp,
>>>> struct sk_buff *skb,
>>>> - __be32 *ptr)
>>>> -{
>>>> - __be32 *start = ptr;
>>>> -
>>>> - memcpy(ptr, TCP_SKB_CB(skb)->dss, mptcp_dss_len);
>>>> -
>>>> - /* update the data_ack */
>>>> - start[1] = htonl(mptcp_meta_tp(tp)->rcv_nxt);
>>>> -
>>>> - /* dss is in a union with inet_skb_parm and
>>>> - * the IP layer expects zeroed IPCB fields.
>>>> - */
>>>> - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
>>>> -
>>>> - return mptcp_dss_len/sizeof(*ptr);
>>>> -}
>>>> -
>>>> static bool mptcp_skb_entail(struct sock *sk, struct sk_buff
>>>> *skb, int reinject)
>>>> {
>>>> struct tcp_sock *tp = tcp_sk(sk);
>>>> @@ -434,7 +388,7 @@ static bool mptcp_skb_entail(struct sock *sk,
>>>> struct sk_buff *skb, int reinject)
>>>> struct sk_buff *subskb = NULL;
>>>> if (!reinject)
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= (mpcb->snd_hiseq_index ?
>>>> + skb->mptcp_flags |= (mpcb->snd_hiseq_index ?
>>>> MPTCPHDR_SEQ64_INDEX : 0);
>>>> subskb = pskb_copy_for_clone(skb, GFP_ATOMIC);
>>>> @@ -447,7 +401,7 @@ static bool mptcp_skb_entail(struct sock *sk,
>>>> struct sk_buff *skb, int reinject)
>>>> */
>>>> tcp_skb_pcount_set(subskb, 0);
>>>> - TCP_SKB_CB(skb)->path_mask |=
>>>> mptcp_pi_to_flag(tp->mptcp->path_index);
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask |=
>>>> mptcp_pi_to_flag(tp->mptcp->path_index);
>>>> if (!(sk->sk_route_caps & NETIF_F_ALL_CSUM) &&
>>>> skb->ip_summed == CHECKSUM_PARTIAL) {
>>>> @@ -463,13 +417,14 @@ static bool mptcp_skb_entail(struct sock *sk,
>>>> struct sk_buff *skb, int reinject)
>>>> tp->mptcp->fully_established = 1;
>>>> tp->mpcb->infinite_mapping_snd = 1;
>>>> tp->mptcp->infinite_cutoff_seq = tp->write_seq;
>>>> - tcb->mptcp_flags |= MPTCPHDR_INF;
>>>> + skb->mptcp_flags |= MPTCPHDR_INF;
>>>> }
>>>> if (mptcp_is_data_fin(subskb))
>>>> mptcp_combine_dfin(subskb, meta_sk, sk);
>>>> - mptcp_save_dss_data_seq(tp, subskb);
>>>> + subskb->mptcp_flags |= MPTCPHDR_SEQ;
>>>> + tcb->mptcp_data_seq = tcb->seq;
>>>> tcb->seq = tp->write_seq;
>>>> @@ -536,10 +491,10 @@ static int mptcp_fragment(struct sock
>>>> *meta_sk, struct sk_buff *skb, u32 len,
>>>> buff = skb->next;
>>>> - flags = TCP_SKB_CB(skb)->mptcp_flags;
>>>> - TCP_SKB_CB(skb)->mptcp_flags = flags & ~(MPTCPHDR_FIN);
>>>> - TCP_SKB_CB(buff)->mptcp_flags = flags;
>>>> - TCP_SKB_CB(buff)->path_mask = TCP_SKB_CB(skb)->path_mask;
>>>> + flags = skb->mptcp_flags;
>>>> + skb->mptcp_flags = flags & ~(MPTCPHDR_FIN);
>>>> + buff->mptcp_flags = flags;
>>>> + TCP_SKB_CB(buff)->mptcp_path_mask =
>>>> TCP_SKB_CB(skb)->mptcp_path_mask;
>>>> /* If reinject == 1, the buff will be added to the reinject
>>>> * queue, which is currently not part of memory accounting. So
>>>> @@ -927,8 +882,9 @@ void mptcp_established_options(struct sock *sk,
>>>> struct sk_buff *skb,
>>>> * It does not make sense to check for the options, because
>>>> when the
>>>> * segment gets sent, another subflow will be chosen.
>>>> */
>>>> - if (!skb && is_meta_sk(sk))
>>>> + if (!skb && is_meta_sk(sk)) {
>>>> return;
>>>> + }
>>>> /* In fallback mp_fail-mode, we have to repeat it until the
>>>> fallback
>>>> * has been done by the sender
>>>> @@ -967,10 +923,11 @@ void mptcp_established_options(struct sock
>>>> *sk, struct sk_buff *skb,
>>>> if (unlikely(mpcb->infinite_mapping_snd) &&
>>>> ((mpcb->send_infinite_mapping && tcb &&
>>>> mptcp_is_data_seq(skb) &&
>>>> - !(tcb->mptcp_flags & MPTCPHDR_INF) &&
>>>> + !(skb->mptcp_flags & MPTCPHDR_INF) &&
>>>> !before(tcb->seq, tp->mptcp->infinite_cutoff_seq)) ||
>>>> - !mpcb->send_infinite_mapping))
>>>> + !mpcb->send_infinite_mapping)) {
>>>> return;
>>>> + }
>>>> if (unlikely(tp->mptcp->include_mpc)) {
>>>> opts->options |= OPTION_MPTCP;
>>>> @@ -995,9 +952,11 @@ void mptcp_established_options(struct sock
>>>> *sk, struct sk_buff *skb,
>>>> mpcb->mptcp_ver >= MPTCP_VERSION_1 && skb &&
>>>> !mptcp_is_data_seq(skb)) {
>>>> mpcb->pm_ops->addr_signal(sk, size, opts, skb);
>>>> - if (opts->add_addr_v6)
>>>> + if (opts->add_addr_v6) {
>>>> +
>>>> /* Skip subsequent options */
>>>> return;
>>>> + }
>>>> }
>>>> if (!tp->mptcp->include_mpc && !tp->mptcp->pre_established) {
>>>> @@ -1197,10 +1156,11 @@ void mptcp_options_write(__be32 *ptr,
>>>> struct tcp_sock *tp,
>>>> }
>>>> if (OPTION_DATA_ACK & opts->mptcp_options) {
>>>> - if (!mptcp_is_data_seq(skb))
>>>> - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>>> - else
>>>> - ptr += mptcp_write_dss_data_seq(tp, skb, ptr);
>>>> + ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>>> + if (mptcp_is_data_seq(skb)) {
>>>> + ptr += mptcp_write_dss_mapping(tp, skb, ptr);
>>>> + }
>>>> + skb->dev = NULL;
>>>> }
>>>> if (unlikely(OPTION_MP_PRIO & opts->mptcp_options)) {
>>>> struct mp_prio *mpprio = (struct mp_prio *)ptr;
>>>> @@ -1233,7 +1193,7 @@ void mptcp_send_fin(struct sock *meta_sk)
>>>> mss_now = mptcp_current_mss(meta_sk);
>>>> if (tcp_send_head(meta_sk) != NULL) {
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
>>>> + skb->mptcp_flags |= MPTCPHDR_FIN;
>>>> TCP_SKB_CB(skb)->end_seq++;
>>>> meta_tp->write_seq++;
>>>> } else {
>>>> @@ -1250,7 +1210,7 @@ void mptcp_send_fin(struct sock *meta_sk)
>>>> tcp_init_nondata_skb(skb, meta_tp->write_seq, TCPHDR_ACK);
>>>> TCP_SKB_CB(skb)->end_seq++;
>>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
>>>> + skb->mptcp_flags |= MPTCPHDR_FIN;
>>>> tcp_queue_skb(meta_sk, skb);
>>>> }
>>>> __tcp_push_pending_frames(meta_sk, mss_now, TCP_NAGLE_OFF);
>>>> diff --git a/net/mptcp/mptcp_redundant.c b/net/mptcp/mptcp_redundant.c
>>>> index 8fa2dba..37a13f4 100644
>>>> --- a/net/mptcp/mptcp_redundant.c
>>>> +++ b/net/mptcp/mptcp_redundant.c
>>>> @@ -72,10 +72,10 @@ static bool redsched_use_subflow(struct sock
>>>> *meta_sk,
>>>> if (!skb || !mptcp_is_available((struct sock *)tp, skb, false))
>>>> return false;
>>>> - if (TCP_SKB_CB(skb)->path_mask != 0)
>>>> + if (TCP_SKB_CB(skb)->mptcp_path_mask != 0)
>>>> return subflow_is_active(tp);
>>>> - if (TCP_SKB_CB(skb)->path_mask == 0) {
>>>> + if (TCP_SKB_CB(skb)->mptcp_path_mask == 0) {
>>>> if (active_valid_sks == -1)
>>>> active_valid_sks =
>>>> redsched_get_active_valid_sks(meta_sk);
>>>> @@ -209,7 +209,7 @@ static struct sk_buff
>>>> *redundant_next_segment(struct sock *meta_sk,
>>>> cb_data->next_subflow = tp->mptcp->next;
>>>> *subsk = (struct sock *)tp;
>>>> - if (TCP_SKB_CB(skb)->path_mask)
>>>> + if (TCP_SKB_CB(skb)->mptcp_path_mask)
>>>> *reinject = -1;
>>>> return skb;
>>>> }
>>>> diff --git a/net/mptcp/mptcp_rr.c b/net/mptcp/mptcp_rr.c
>>>> index 8910ba9..83837f2 100644
>>>> --- a/net/mptcp/mptcp_rr.c
>>>> +++ b/net/mptcp/mptcp_rr.c
>>>> @@ -93,7 +93,7 @@ static int mptcp_rr_dont_reinject_skb(const
>>>> struct tcp_sock *tp, const struct sk
>>>> */
>>>> return skb &&
>>>> /* Has the skb already been enqueued into this
>>>> subsocket? */
>>>> - mptcp_pi_to_flag(tp->mptcp->path_index) &
>>>> TCP_SKB_CB(skb)->path_mask;
>>>> + mptcp_pi_to_flag(tp->mptcp->path_index) &
>>>> TCP_SKB_CB(skb)->mptcp_path_mask;
>>>> }
>>>> /* We just look for any subflow that is available */
>>>> @@ -136,7 +136,7 @@ static struct sock
>>>> *rr_get_available_subflow(struct sock *meta_sk,
>>>> * chance again by restarting its pathmask.
>>>> */
>>>> if (skb)
>>>> - TCP_SKB_CB(skb)->path_mask = 0;
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>>> sk = backupsk;
>>>> }
>>>> diff --git a/net/mptcp/mptcp_sched.c b/net/mptcp/mptcp_sched.c
>>>> index 54408ff..5cbbf91 100644
>>>> --- a/net/mptcp/mptcp_sched.c
>>>> +++ b/net/mptcp/mptcp_sched.c
>>>> @@ -118,7 +118,7 @@ static int mptcp_dont_reinject_skb(const struct
>>>> tcp_sock *tp, const struct sk_bu
>>>> */
>>>> return skb &&
>>>> /* Has the skb already been enqueued into this
>>>> subsocket? */
>>>> - mptcp_pi_to_flag(tp->mptcp->path_index) &
>>>> TCP_SKB_CB(skb)->path_mask;
>>>> + mptcp_pi_to_flag(tp->mptcp->path_index) &
>>>> TCP_SKB_CB(skb)->mptcp_path_mask;
>>>> }
>>>> bool subflow_is_backup(const struct tcp_sock *tp)
>>>> @@ -261,7 +261,7 @@ struct sock *get_available_subflow(struct sock
>>>> *meta_sk, struct sk_buff *skb,
>>>> * the skb passed through all the available active and
>>>> backups
>>>> * sks, so clean the path mask
>>>> */
>>>> - TCP_SKB_CB(skb)->path_mask = 0;
>>>> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>>> return sk;
>>>> }
>>>> EXPORT_SYMBOL_GPL(get_available_subflow);
>>>> @@ -298,7 +298,7 @@ static struct sk_buff
>>>> *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
>>>> /* Half the cwnd of the slow flow */
>>>> mptcp_for_each_tp(tp->mpcb, tp_it) {
>>>> if (tp_it != tp &&
>>>> - TCP_SKB_CB(skb_head)->path_mask &
>>>> mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>> + TCP_SKB_CB(skb_head)->mptcp_path_mask &
>>>> mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>> if (tp->srtt_us < tp_it->srtt_us && inet_csk((struct
>>>> sock *)tp_it)->icsk_ca_state == TCP_CA_Open) {
>>>> u32 prior_cwnd = tp_it->snd_cwnd;
>>>> @@ -317,11 +317,11 @@ static struct sk_buff
>>>> *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
>>>> retrans:
>>>> /* Segment not yet injected into this path? Take it!!! */
>>>> - if (!(TCP_SKB_CB(skb_head)->path_mask &
>>>> mptcp_pi_to_flag(tp->mptcp->path_index))) {
>>>> + if (!(TCP_SKB_CB(skb_head)->mptcp_path_mask &
>>>> mptcp_pi_to_flag(tp->mptcp->path_index))) {
>>>> bool do_retrans = false;
>>>> mptcp_for_each_tp(tp->mpcb, tp_it) {
>>>> if (tp_it != tp &&
>>>> - TCP_SKB_CB(skb_head)->path_mask &
>>>> mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>> + TCP_SKB_CB(skb_head)->mptcp_path_mask &
>>>> mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>>> if (tp_it->snd_cwnd <= 4) {
>>>> do_retrans = true;
>>>> break;
>>> _______________________________________________
>>> mptcp mailing list
>>> mptcp(a)lists.01.org
>>> https://lists.01.org/mailman/listinfo/mptcp
>
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-27 17:22 Rao Shoaib
0 siblings, 0 replies; 14+ messages in thread
From: Rao Shoaib @ 2017-06-27 17:22 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 58317 bytes --]
Hi Christoph,
On 06/26/2017 11:27 PM, Christoph Paasch wrote:
> Hello Rao,
>
> can you try to give some more details on how the datapath looks like with
> this patch?
>
> For example, I wonder how data-acks are being processed. Because, I see in
> mptcp_data_ready, that you now expects skbs with len 0, upon which you end
> up calling mptcp_process_ack().
>
> I don't see how such zero-length skbs could end up in the receive-queue of
> the subflows.
>
>
> Thanks,
I send every packet that is coming on an MPTCP based socket down and let
MPTCP deal with it. In tcp data_queue(). I also removed the directive to
go to the slow_path in tcp_rcv_established().
static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
int eaten = -1;
bool fragstolen = false;
/*
* send every packet to MPTCP
*/
if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq ==
TCP_SKB_CB(skb)->end_seq)) {
goto drop;
}
There is only one case that I need investigate more is the following.
In that the he only interesting case is (len == tcp_header_len) but in
my unidirectional bulk data transfer tests I did not hit that case. So I
need to investigate more later. The last resort would be to just
directly go to the slow path.
if (len <= tcp_header_len) { /* Bulk data transfer: sender */
if (len == tcp_header_len) {
If there are other issues than let me know and I will work on resolving
them. We obviously need to run extensive tests, that brings me to the
question of, how does the MPTCP development team test changes. We need
the same tests to validate the changes.
Rao.
> Christoph
>
>
> On 26/06/17 - 15:34:09, Rao Shoaib wrote:
>> I forgot to mention two things
>>
>> 1) Connection setup still has checks for MPTCP, Ideally these should be
>> removed but at least we need to run some benchmarks and fix any issues. The
>> mainstream folks will not accept any performance degradation in TCP. I can
>> look into this next.
>>
>> 2) The code overloads dev field of skb, when it is not being used. IIRC
>> there is precedence for this already. I will try to find it.
>>
>> Rao
>>
>>
>> On 06/26/2017 02:13 PM, Rao Shoaib wrote:
>>> This patch returns tcp_skb_cb to it's original size. It also refactors MPTCP code so that there are no MPTCP checks in the main Rx pathi, no performance overheads such as cpu prodiction issues. tcp_v4_rcv() and tcp_v4_do_rcv() do not have any MPTCP specific checks any more, niether does tcp_ack(). On the Rx path MPTCP options are not parsed till the data is being pushed up to the meta socket (mptcp_data_ready). on the Tx side there is one check to add MPTCP specific options but that's it, that should not be that bad as for regular TCP it is a simple check, but it would be good to remove it..
>>>
>>> I have tested the changes with ndiffports set to 2, so join works. I have also tested accessing multipath-tcp.org and downloading files from there and also ran the speed test.
>>>
>>> The Bad:
>>>
>>> The error cases still have MPTCP checks but that should be OK as they are error cases. I had to use a special marker 0xFEE1DEAD for indicate a special case. I had to introdue a new socket specfic function. IPv6 has not been changed yet. I am sure I have missed some corner cases and more testing will reveal more issues but we just have to fix them.
>>>
>>> I would like to hear comments from the list and if this direction seems reasonable we can take this as the starting point, port it to latest Linux and share the design with the mainstream folks.
>>>
>>> Signed-off-by: Rao Shoaib <rao.shoaib(a)oracle.com>
>>> ---
>>> include/linux/skbuff.h | 8 ++-
>>> include/net/mptcp.h | 21 +++---
>>> include/net/mptcp_v4.h | 1 +
>>> include/net/sock.h | 12 +++-
>>> include/net/tcp.h | 23 +++----
>>> net/ipv4/af_inet.c | 4 ++
>>> net/ipv4/tcp_input.c | 37 ++--------
>>> net/ipv4/tcp_ipv4.c | 135 +++++++++++++++++++++++--------------
>>> net/ipv4/tcp_output.c | 1 +
>>> net/ipv6/af_inet6.c | 4 ++
>>> net/ipv6/tcp_ipv6.c | 4 --
>>> net/mptcp/mptcp_ctrl.c | 21 ++++++
>>> net/mptcp/mptcp_input.c | 131 ++++++++++++++++++++++++++++--------
>>> net/mptcp/mptcp_ipv4.c | 35 +---------
>>> net/mptcp/mptcp_ipv6.c | 4 +-
>>> net/mptcp/mptcp_output.c | 160 +++++++++++++++++---------------------------
>>> net/mptcp/mptcp_redundant.c | 6 +-
>>> net/mptcp/mptcp_rr.c | 4 +-
>>> net/mptcp/mptcp_sched.c | 10 +--
>>> 19 files changed, 335 insertions(+), 286 deletions(-)
>>>
>>> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
>>> index f66cd5e..348cbc1 100644
>>> --- a/include/linux/skbuff.h
>>> +++ b/include/linux/skbuff.h
>>> @@ -532,7 +532,13 @@ struct sk_buff {
>>> struct rb_node rbnode; /* used in netem & tcp stack */
>>> };
>>> struct sock *sk;
>>> - struct net_device *dev;
>>> + union {
>>> + struct net_device *dev;
>>> + struct {
>>> + __u8 mptcp_flags;
>>> + __u8 mptcp_dss_off;
>>> + };
>>> + };
>>> /*
>>> * This is the control buffer. It is free to use for every
>>> diff --git a/include/net/mptcp.h b/include/net/mptcp.h
>>> index 876f1e6..d087cb4 100644
>>> --- a/include/net/mptcp.h
>>> +++ b/include/net/mptcp.h
>>> @@ -807,7 +807,7 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
>>> struct mptcp_options_received *mopt);
>>> void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>> struct mptcp_options_received *mopt,
>>> - const struct sk_buff *skb,
>>> + struct sk_buff *skb,
>>> struct tcp_sock *tp);
>>> void mptcp_syn_options(const struct sock *sk, struct tcp_out_options *opts,
>>> unsigned *remaining);
>>> @@ -998,14 +998,15 @@ static inline void mptcp_sub_force_close_all(struct mptcp_cb *mpcb,
>>> }
>>> }
>>> +/* currently tp is being used for Rx packets */
>>> static inline bool mptcp_is_data_seq(const struct sk_buff *skb)
>>> {
>>> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ;
>>> + return skb->mptcp_flags & MPTCPHDR_SEQ;
>>> }
>>> static inline bool mptcp_is_data_fin(const struct sk_buff *skb)
>>> {
>>> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_FIN;
>>> + return skb->mptcp_flags & MPTCPHDR_FIN;
>>> }
>>> /* Is it a data-fin while in infinite mapping mode?
>>> @@ -1034,17 +1035,17 @@ static inline u8 mptcp_get_64_bit(u64 data_seq, struct mptcp_cb *mpcb)
>>> /* Sets the data_seq and returns pointer to the in-skb field of the data_seq.
>>> * If the packet has a 64-bit dseq, the pointer points to the last 32 bits.
>>> */
>>> -static inline __u32 *mptcp_skb_set_data_seq(const struct sk_buff *skb,
>>> +static inline __u32 *mptcp_skb_set_data_seq(struct sk_buff *skb,
>>> u32 *data_seq,
>>> struct mptcp_cb *mpcb)
>>> {
>>> - __u32 *ptr = (__u32 *)(skb_transport_header(skb) + TCP_SKB_CB(skb)->dss_off);
>>> + __u32 *ptr = (__u32 *)(skb_transport_header(skb) + skb->mptcp_dss_off);
>>> - if (TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ64_SET) {
>>> + if (skb->mptcp_flags & MPTCPHDR_SEQ64_SET) {
>>> u64 data_seq64 = get_unaligned_be64(ptr);
>>> if (mpcb)
>>> - TCP_SKB_CB(skb)->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
>>> + skb->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
>>> *data_seq = (u32)data_seq64;
>>> ptr++;
>>> @@ -1142,7 +1143,7 @@ static inline void mptcp_reset_mopt(struct tcp_sock *tp)
>>> static inline __be32 mptcp_get_highorder_sndbits(const struct sk_buff *skb,
>>> const struct mptcp_cb *mpcb)
>>> {
>>> - return htonl(mpcb->snd_high_order[(TCP_SKB_CB(skb)->mptcp_flags &
>>> + return htonl(mpcb->snd_high_order[(skb->mptcp_flags &
>>> MPTCPHDR_SEQ64_INDEX) ? 1 : 0]);
>>> }
>>> @@ -1404,8 +1405,8 @@ static inline void mptcp_set_rto(const struct sock *sk) {}
>>> static inline void mptcp_send_fin(const struct sock *meta_sk) {}
>>> static inline void mptcp_parse_options(const uint8_t *ptr, const int opsize,
>>> struct mptcp_options_received *mopt,
>>> - const struct sk_buff *skb,
>>> - const struct tcp_sock *tp) {}
>>> + struct sk_buff *skb,
>>> + struct tcp_sock *tp) {}
>>> static inline void mptcp_syn_options(const struct sock *sk,
>>> struct tcp_out_options *opts,
>>> unsigned *remaining) {}
>>> diff --git a/include/net/mptcp_v4.h b/include/net/mptcp_v4.h
>>> index c83dca0..46394a4 100644
>>> --- a/include/net/mptcp_v4.h
>>> +++ b/include/net/mptcp_v4.h
>>> @@ -45,6 +45,7 @@ extern struct tcp_request_sock_ops mptcp_join_request_sock_ipv4_ops;
>>> #ifdef CONFIG_MPTCP
>>> int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb);
>>> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb);
>>> struct sock *mptcp_v4_search_req(const __be16 rport, const __be32 raddr,
>>> const __be32 laddr, const struct net *net);
>>> int mptcp_init4_subsockets(struct sock *meta_sk, const struct mptcp_loc4 *loc,
>>> diff --git a/include/net/sock.h b/include/net/sock.h
>>> index 0f12593..0d1bda5 100644
>>> --- a/include/net/sock.h
>>> +++ b/include/net/sock.h
>>> @@ -296,6 +296,7 @@ struct cg_proto;
>>> * @sk_write_space: callback to indicate there is bf sending space available
>>> * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
>>> * @sk_backlog_rcv: callback to process the backlog
>>> + * @sk_prequeue: callback to prequeue
>>> * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
>>> */
>>> struct sock {
>>> @@ -437,7 +438,9 @@ struct sock {
>>> void (*sk_write_space)(struct sock *sk);
>>> void (*sk_error_report)(struct sock *sk);
>>> int (*sk_backlog_rcv)(struct sock *sk,
>>> - struct sk_buff *skb);
>>> + struct sk_buff *skb);
>>> + bool (*sk_prequeue)(struct sock *sk,
>>> + struct sk_buff *skb);
>>> void (*sk_destruct)(struct sock *sk);
>>> };
>>> @@ -853,6 +856,11 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
>>> return sk->sk_backlog_rcv(sk, skb);
>>> }
>>> +static inline bool sk_prequeue(struct sock *sk, struct sk_buff *skb)
>>> +{
>>> + return (false);
>>> +}
>>> +
>>> static inline void sk_incoming_cpu_update(struct sock *sk)
>>> {
>>> sk->sk_incoming_cpu = raw_smp_processor_id();
>>> @@ -993,6 +1001,8 @@ struct proto {
>>> int (*backlog_rcv) (struct sock *sk,
>>> struct sk_buff *skb);
>>> + bool (*prequeue) (struct sock *sk,
>>> + struct sk_buff *skb);
>>> void (*release_cb)(struct sock *sk);
>>> diff --git a/include/net/tcp.h b/include/net/tcp.h
>>> index 655ecd4..cbe8ef2 100644
>>> --- a/include/net/tcp.h
>>> +++ b/include/net/tcp.h
>>> @@ -47,6 +47,9 @@
>>> #include <linux/seq_file.h>
>>> #include <linux/memcontrol.h>
>>> +typedef int (* process_unclaimed)(struct sock *sk, struct sk_buff *skb);
>>> +extern process_unclaimed tcp_process_unclaimed;
>>> +
>>> extern struct inet_hashinfo tcp_hashinfo;
>>> extern struct percpu_counter tcp_orphan_count;
>>> @@ -581,6 +584,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
>>> struct request_sock *req,
>>> struct dst_entry *dst);
>>> int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
>>> +
>>> int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
>>> int tcp_connect(struct sock *sk);
>>> struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
>>> @@ -842,11 +846,6 @@ struct tcp_skb_cb {
>>> __u32 tcp_gso_segs;
>>> };
>>> -#ifdef CONFIG_MPTCP
>>> - __u8 mptcp_flags; /* flags for the MPTCP layer */
>>> - __u8 dss_off; /* Number of 4-byte words until
>>> - * seq-number */
>>> -#endif
>>> __u8 tcp_flags; /* TCP header flags. (tcp[13]) */
>>> __u8 sacked; /* State flags for SACK/FACK. */
>>> @@ -859,9 +858,13 @@ struct tcp_skb_cb {
>>> #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
>>> TCPCB_REPAIRED)
>>> - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
>>> + __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
>>> /* 1 byte hole */
>>> - __u32 ack_seq; /* Sequence number ACK'd */
>>> + union {
>>> + __u32 ack_seq; /* Sequence number ACK'd */
>>> + __u32 mptcp_data_seq;
>>> + __u32 mptcp_path_mask;
>>> + };
>>> union {
>>> union {
>>> struct inet_skb_parm h4;
>>> @@ -869,12 +872,6 @@ struct tcp_skb_cb {
>>> struct inet6_skb_parm h6;
>>> #endif
>>> } header; /* For incoming frames */
>>> -#ifdef CONFIG_MPTCP
>>> - union { /* For MPTCP outgoing frames */
>>> - __u32 path_mask; /* paths that tried to send this skb */
>>> - __u32 dss[6]; /* DSS options */
>>> - };
>>> -#endif
>>> };
>>> };
>>> diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
>>> index 73480b9..1e7827f 100644
>>> --- a/net/ipv4/af_inet.c
>>> +++ b/net/ipv4/af_inet.c
>>> @@ -356,6 +356,10 @@ lookup_protocol:
>>> sk->sk_destruct = inet_sock_destruct;
>>> sk->sk_protocol = protocol;
>>> sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
>>> + sk->sk_prequeue = sk->sk_prot->prequeue;
>>> + if (sk->sk_prequeue == NULL) {
>>> + sk->sk_prequeue = sk_prequeue;
>>> + }
>>> inet->uc_ttl = -1;
>>> inet->mc_loop = 1;
>>> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
>>> index 16a7256..cb6bbf9 100644
>>> --- a/net/ipv4/tcp_input.c
>>> +++ b/net/ipv4/tcp_input.c
>>> @@ -3133,8 +3133,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
>>> */
>>> if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
>>> flag |= FLAG_DATA_ACKED;
>>> - if (mptcp(tp) && mptcp_is_data_seq(skb))
>>> - flag |= MPTCP_FLAG_DATA_ACKED;
>>> } else {
>>> flag |= FLAG_SYN_ACKED;
>>> tp->retrans_stamp = 0;
>>> @@ -3582,16 +3580,6 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
>>> sack_rtt_us);
>>> acked -= tp->packets_out;
>>> - if (mptcp(tp)) {
>>> - if (mptcp_fallback_infinite(sk, flag)) {
>>> - pr_err("%s resetting flow\n", __func__);
>>> - mptcp_send_reset(sk);
>>> - goto invalid_ack;
>>> - }
>>> -
>>> - mptcp_clean_rtx_infinite(skb, sk);
>>> - }
>>> -
>>> /* Advance cwnd if state allows */
>>> if (tcp_may_raise_cwnd(sk, flag))
>>> tcp_cong_avoid(sk, ack, acked);
>>> @@ -3824,8 +3812,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
>>> if (tcp_parse_aligned_timestamp(tp, th))
>>> return true;
>>> }
>>> - tcp_parse_options(skb, &tp->rx_opt,
>>> - mptcp(tp) ? &tp->mptcp->rx_opt : NULL, 1, NULL, tp);
>>> + tcp_parse_options(skb, &tp->rx_opt, NULL, 1, NULL, tp);
>>> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
>>> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>>> @@ -4550,11 +4537,12 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
>>> int eaten = -1;
>>> bool fragstolen = false;
>>> - /* If no data is present, but a data_fin is in the options, we still
>>> - * have to call mptcp_queue_skb later on. */
>>> - if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq &&
>>> - !(mptcp(tp) && mptcp_is_data_fin(skb)))
>>> + /*
>>> + * send every packet to MPTCP
>>> + */
>>> + if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)) {
>>> goto drop;
>>> + }
>>> skb_dst_drop(skb);
>>> __skb_pull(skb, tcp_hdr(skb)->doff * 4);
>>> @@ -5242,15 +5230,9 @@ syn_challenge:
>>> goto discard;
>>> }
>>> - /* If valid: post process the received MPTCP options. */
>>> - if (mptcp(tp) && mptcp_handle_options(sk, th, skb))
>>> - goto discard;
>>> -
>>> return true;
>>> discard:
>>> - if (mptcp(tp))
>>> - mptcp_reset_mopt(tp);
>>> __kfree_skb(skb);
>>> return false;
>>> }
>>> @@ -5302,10 +5284,6 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
>>> tp->rx_opt.saw_tstamp = 0;
>>> - /* MPTCP: force slowpath. */
>>> - if (mptcp(tp))
>>> - goto slow_path;
>>> -
>>> /* pred_flags is 0xS?10 << 16 + snd_wnd
>>> * if header_prediction is to be made
>>> * 'S' will always be tp->tcp_header_len >> 2
>>> @@ -5585,8 +5563,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
>>> struct mptcp_options_received mopt;
>>> mptcp_init_mp_opt(&mopt);
>>> - tcp_parse_options(skb, &tp->rx_opt,
>>> - mptcp(tp) ? &tp->mptcp->rx_opt : &mopt, 0, &foc, tp);
>>> + tcp_parse_options(skb, &tp->rx_opt, &mopt, 0, &foc, tp);
>>> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
>>> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>>> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
>>> index 6967a86..3329679 100644
>>> --- a/net/ipv4/tcp_ipv4.c
>>> +++ b/net/ipv4/tcp_ipv4.c
>>> @@ -1420,6 +1420,71 @@ struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
>>> return sk;
>>> }
>>> +int mptcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
>>> +{
>>> + struct net *net = dev_net(skb->dev);
>>> + const struct tcphdr *th = tcp_hdr(skb);
>>> + int ret;
>>> + struct sock *meta_sk;
>>> +
>>> + if (sk == NULL) {
>>> + if (th->syn && !th->ack) {
>>> + int ret = mptcp_lookup_join(skb, NULL);
>>> +
>>> + if (ret < 0) {
>>> + tcp_v4_send_reset(NULL, skb);
>>> + kfree_skb(skb);
>>> + return (1);
>>> + } else if (ret > 0) {
>>> + return (1);
>>> + }
>>> + }
>>> + /* Is there a pending request sock for this segment ? */
>>> + if (mptcp_check_req(skb, net)) {
>>> + return(1);
>>> + }
>>> + return (0);
>>> + }
>>> +
>>> + /* The socket passed in should never be the meta socket */
>>> +
>>> + BUG_ON(is_meta_sk(sk));
>>> +
>>> + /* Is there a pending request sock for this segment ? */
>>> + if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
>>> + return 0;
>>> + }
>>> +
>>> + skb->dev = NULL;
>>> + meta_sk = mptcp_meta_sk(sk);
>>> +
>>> + ret = 0;
>>> + skb->sk = sk;
>>> + bh_lock_sock_nested(meta_sk);
>>> + if (sock_owned_by_user(meta_sk)) {
>>> + if (unlikely(sk_add_backlog(meta_sk, skb,
>>> + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>> +
>>> + NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>> + kfree_skb(skb);
>>> + }
>>> + } else {
>>> +
>>> + if (is_meta_sk(sk)) {
>>> + ret = mptcp_v4_process_join_req(sk, skb);
>>> + goto done;
>>> + }
>>> + if (!meta_sk->sk_prequeue(meta_sk, skb)) {
>>> + skb->sk = NULL;
>>> + ret = tcp_v4_do_rcv(sk, skb);
>>> + }
>>> +
>>> + }
>>> +done:
>>> + bh_unlock_sock(meta_sk);
>>> + return (ret);
>>> +}
>>> +
>>> /* The socket must have it's spinlock held when we get
>>> * here.
>>> *
>>> @@ -1432,8 +1497,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
>>> {
>>> struct sock *rsk;
>>> - if (is_meta_sk(sk))
>>> - return mptcp_v4_do_rcv(sk, skb);
>>> + BUG_ON(is_meta_sk(sk));
>>> if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
>>> struct dst_entry *dst = sk->sk_rx_dst;
>>> @@ -1587,6 +1651,8 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
>>> }
>>> EXPORT_SYMBOL(tcp_prequeue);
>>> +process_unclaimed tcp_process_unclaimed = NULL;
>>> +
>>> /*
>>> * From tcp_input.c
>>> */
>>> @@ -1595,7 +1661,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
>>> {
>>> const struct iphdr *iph;
>>> const struct tcphdr *th;
>>> - struct sock *sk, *meta_sk = NULL;
>>> + struct sock *sk = NULL;
>>> int ret;
>>> struct net *net = dev_net(skb->dev);
>>> @@ -1636,10 +1702,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
>>> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
>>> skb->len - th->doff * 4);
>>> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
>>> -#ifdef CONFIG_MPTCP
>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>> - TCP_SKB_CB(skb)->dss_off = 0;
>>> -#endif
>>> +
>>> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
>>> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
>>> TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
>>> @@ -1662,15 +1725,6 @@ process:
>>> if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
>>> goto discard_and_relse;
>>> -#ifdef CONFIG_MPTCP
>>> - /* Is there a pending request sock for this segment ? */
>>> - if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
>>> - if (sk)
>>> - sock_put(sk);
>>> - return 0;
>>> - }
>>> -#endif
>>> -
>>> #ifdef CONFIG_TCP_MD5SIG
>>> /*
>>> * We really want to reject the packet as early as possible
>>> @@ -1688,30 +1742,21 @@ process:
>>> goto discard_and_relse;
>>> sk_incoming_cpu_update(sk);
>>> - skb->dev = NULL;
>>> - if (mptcp(tcp_sk(sk))) {
>>> - meta_sk = mptcp_meta_sk(sk);
>>> -
>>> - bh_lock_sock_nested(meta_sk);
>>> - if (sock_owned_by_user(meta_sk))
>>> - skb->sk = sk;
>>> - } else {
>>> - meta_sk = sk;
>>> - bh_lock_sock_nested(sk);
>>> - }
>>> + /* Do I have to set skb->dev to null ? */
>>> + bh_lock_sock_nested(sk);
>>> ret = 0;
>>> - if (!sock_owned_by_user(meta_sk)) {
>>> - if (!tcp_prequeue(meta_sk, skb))
>>> - ret = tcp_v4_do_rcv(sk, skb);
>>> - } else if (unlikely(sk_add_backlog(meta_sk, skb,
>>> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>> - bh_unlock_sock(meta_sk);
>>> + if (!sock_owned_by_user(sk)) {
>>> + if (!sk->sk_prequeue(sk, skb))
>>> + ret = sk->sk_backlog_rcv(sk, skb);
>>> + } else if (unlikely(sk_add_backlog(sk, skb,
>>> + sk->sk_rcvbuf + sk->sk_sndbuf))) {
>>> + bh_unlock_sock(sk);
>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>> goto discard_and_relse;
>>> }
>>> - bh_unlock_sock(meta_sk);
>>> + bh_unlock_sock(sk);
>>> sock_put(sk);
>>> @@ -1721,26 +1766,11 @@ no_tcp_socket:
>>> if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
>>> goto discard_it;
>>> -#ifdef CONFIG_MPTCP
>>> - if (!sk && th->syn && !th->ack) {
>>> - int ret = mptcp_lookup_join(skb, NULL);
>>> -
>>> - if (ret < 0) {
>>> - tcp_v4_send_reset(NULL, skb);
>>> - goto discard_it;
>>> - } else if (ret > 0) {
>>> - return 0;
>>> - }
>>> + if (unlikely (tcp_process_unclaimed != NULL)) {
>>> + if ((tcp_process_unclaimed)(NULL, skb))
>>> + return (0);
>>> }
>>> - /* Is there a pending request sock for this segment ? */
>>> - if (!sk && mptcp_check_req(skb, net)) {
>>> - if (sk)
>>> - sock_put(sk);
>>> - return 0;
>>> - }
>>> -#endif
>>> -
>>> if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
>>> csum_error:
>>> TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
>>> @@ -2506,6 +2536,7 @@ struct proto tcp_prot = {
>>> .sendmsg = tcp_sendmsg,
>>> .sendpage = tcp_sendpage,
>>> .backlog_rcv = tcp_v4_do_rcv,
>>> + .prequeue = tcp_prequeue,
>>> .release_cb = tcp_release_cb,
>>> .hash = inet_hash,
>>> .unhash = inet_unhash,
>>> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
>>> index a635483..41b8be8 100644
>>> --- a/net/ipv4/tcp_output.c
>>> +++ b/net/ipv4/tcp_output.c
>>> @@ -3413,6 +3413,7 @@ void tcp_send_delayed_ack(struct sock *sk)
>>> void tcp_send_ack(struct sock *sk)
>>> {
>>> struct sk_buff *buff;
>>> + struct tcp_sock *tp = tcp_sk(sk);
>>> /* If we have been reset, we may not send again. */
>>> if (sk->sk_state == TCP_CLOSE)
>>> diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
>>> index 8c4dd4a..1554217 100644
>>> --- a/net/ipv6/af_inet6.c
>>> +++ b/net/ipv6/af_inet6.c
>>> @@ -193,6 +193,10 @@ lookup_protocol:
>>> sk->sk_protocol = protocol;
>>> sk->sk_backlog_rcv = answer->prot->backlog_rcv;
>>> + sk->sk_prequeue = answer->prot->prequeue;
>>> + if (sk->sk_prequeue == NULL) {
>>> + sk->sk_prequeue = sk_prequeue;
>>> + }
>>> inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
>>> np->hop_limit = -1;
>>> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
>>> index eba2436..d360128 100644
>>> --- a/net/ipv6/tcp_ipv6.c
>>> +++ b/net/ipv6/tcp_ipv6.c
>>> @@ -1412,10 +1412,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
>>> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
>>> skb->len - th->doff*4);
>>> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
>>> -#ifdef CONFIG_MPTCP
>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>> - TCP_SKB_CB(skb)->dss_off = 0;
>>> -#endif
>>> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
>>> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
>>> TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
>>> diff --git a/net/mptcp/mptcp_ctrl.c b/net/mptcp/mptcp_ctrl.c
>>> index 28f348f..b1e780a 100644
>>> --- a/net/mptcp/mptcp_ctrl.c
>>> +++ b/net/mptcp/mptcp_ctrl.c
>>> @@ -976,6 +976,20 @@ int mptcp_backlog_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>> struct sock *sk = skb->sk ? skb->sk : meta_sk;
>>> int ret = 0;
>>> + /* socket was owned by the user in mptcp_check_req()
>>> + */
>>> + if (sk == (struct sock *)0xFEE1DEAD) {
>>> + bh_lock_sock_nested(meta_sk);
>>> + if (skb->protocol == htons(ETH_P_IP))
>>> + mptcp_v4_process_join_req(meta_sk, skb);
>>> +#if IS_ENABLED(CONFIG_IPV6)
>>> + else
>>> + //mptcp_v6_process_join_req(meta_sk, skb);
>>> +#endif /* CONFIG_IPV6 */
>>> + bh_unlock_sock(meta_sk);
>>> + return(0);
>>> + }
>>> +
>>> skb->sk = NULL;
>>> if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
>>> @@ -1297,6 +1311,10 @@ int mptcp_add_sock(struct sock *meta_sk, struct sock *sk, u8 loc_id, u8 rem_id,
>>> sk->sk_write_space = mptcp_write_space;
>>> sk->sk_state_change = mptcp_set_state;
>>> sk->sk_destruct = mptcp_sock_destruct;
>>> + /* MPTCP takes a different path in tcp_v4_rcv
>>> + * thus not impacting main tcp code */
>>> + sk->sk_backlog_rcv = mptcp_v4_do_rcv;
>>> + sk->sk_prequeue = sk_prequeue;
>>> if (sk->sk_family == AF_INET)
>>> mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d dst_addr:%pI4:%d, cnt_subflows now %d\n",
>>> @@ -2658,6 +2676,9 @@ void __init mptcp_init(void)
>>> if (mptcp_pm_v4_init())
>>> goto mptcp_pm_v4_failed;
>>> + if ((cmpxchg(&tcp_process_unclaimed, NULL, mptcp_v4_do_rcv)) != NULL)
>>> + printk("tcp_process_unclaimed not NULL \n");
>>> +
>>> mptcp_sysctl = register_net_sysctl(&init_net, "net/mptcp", mptcp_table);
>>> if (!mptcp_sysctl)
>>> goto register_sysctl_failed;
>>> diff --git a/net/mptcp/mptcp_input.c b/net/mptcp/mptcp_input.c
>>> index 51cbb06..0e09ddf 100644
>>> --- a/net/mptcp/mptcp_input.c
>>> +++ b/net/mptcp/mptcp_input.c
>>> @@ -323,9 +323,8 @@ static int mptcp_verif_dss_csum(struct sock *sk)
>>> * by 4 bytes, as the high-order 64-bits will be added
>>> * in the final csum_partial-call.
>>> */
>>> - u32 offset = skb_transport_offset(tmp) +
>>> - TCP_SKB_CB(tmp)->dss_off;
>>> - if (TCP_SKB_CB(tmp)->mptcp_flags & MPTCPHDR_SEQ64_SET)
>>> + u32 offset = skb_transport_offset(tmp) + tmp->mptcp_dss_off;
>>> + if (tmp->mptcp_flags & MPTCPHDR_SEQ64_SET)
>>> offset += 4;
>>> csum_tcp = skb_checksum(tmp, offset,
>>> @@ -758,7 +757,7 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
>>> }
>>> /* Does the DSS had 64-bit seqnum's ? */
>>> - if (!(tcb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
>>> + if (!(skb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
>>> /* Wrapped around? */
>>> if (unlikely(after(data_seq, meta_tp->rcv_nxt) && data_seq < meta_tp->rcv_nxt)) {
>>> tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, !mpcb->rcv_hiseq_index, data_seq);
>>> @@ -767,9 +766,9 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
>>> tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, mpcb->rcv_hiseq_index, data_seq);
>>> }
>>> } else {
>>> - tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (tcb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
>>> + tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (skb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
>>> - if (unlikely(tcb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
>>> + if (unlikely(skb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
>>> /* We make sure that the data_seq is invalid.
>>> * It will be dropped later.
>>> */
>>> @@ -1020,6 +1019,67 @@ next:
>>> return data_queued ? -1 : -2;
>>> }
>>> +static struct sk_buff *
>>> +mptcp_process_ack(struct sock *sk, struct sk_buff *skb)
>>> +{
>>> + struct tcp_sock *tp = tcp_sk(sk);
>>> + int flag = 0;
>>> +
>>> + /*
>>> + * TCP takes care of invalid ack's
>>> + * they will never show up here.
>>> + */
>>> +
>>> + /* Is this skb acknowleding anything data */
>>> +
>>> + if (tp->mptcp->snt_isn + 1 != TCP_SKB_CB(skb)->ack_seq) {
>>> + flag = MPTCP_FLAG_DATA_ACKED;
>>> + }
>>> +
>>> + if (mptcp_fallback_infinite(sk, flag)) {
>>> + pr_err("%s resetting flow\n", __func__);
>>> + mptcp_send_reset(sk);
>>> + goto invalid_ack;
>>> + }
>>> +
>>> + mptcp_clean_rtx_infinite(skb, sk);
>>> +
>>> + return (skb);
>>> +invalid_ack:
>>> + __skb_unlink(skb, &sk->sk_receive_queue);
>>> + __kfree_skb(skb);
>>> + return (NULL);
>>> +
>>> +}
>>> +
>>> +static struct sk_buff *
>>> +mptcp_process_options_ack(struct sock *sk, struct sk_buff *skb)
>>> +{
>>> + struct tcp_sock *tp = tcp_sk(sk);
>>> + const struct tcphdr *th = tcp_hdr(skb);
>>> +
>>> + skb->mptcp_flags = 0;
>>> + skb->mptcp_dss_off = 0;
>>> +
>>> + tcp_parse_mptcp_options(skb, &tp->mptcp->rx_opt);
>>> + if (mptcp_handle_options(sk, th, skb)) {
>>> + mptcp_reset_mopt(tp);
>>> + __skb_unlink(skb, &sk->sk_receive_queue);
>>> + __kfree_skb(skb);
>>> + skb = NULL;
>>> + }
>>> + if ((skb != NULL) && skb->len == 0) {
>>> + skb = mptcp_process_ack(sk, skb);
>>> + if (skb != NULL && skb->len == 0) {
>>> + /* Pure ack */
>>> + __skb_unlink(skb, &sk->sk_receive_queue);
>>> + __kfree_skb(skb);
>>> + skb = NULL;
>>> + }
>>> + }
>>> + return (skb);
>>> +}
>>> +
>>> void mptcp_data_ready(struct sock *sk)
>>> {
>>> struct sock *meta_sk = mptcp_meta_sk(sk);
>>> @@ -1045,6 +1105,10 @@ restart:
>>> */
>>> skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
>>> int ret;
>>> +
>>> + skb = mptcp_process_options_ack(sk, skb);
>>> + if (skb == NULL)
>>> + continue;
>>> /* Pre-validation - e.g., early fallback */
>>> ret = mptcp_prevalidate_skb(sk, skb);
>>> if (ret < 0)
>>> @@ -1108,13 +1172,11 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
>>> if (!meta_sk)
>>> return 0;
>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>> -
>>> bh_lock_sock_nested(meta_sk);
>>> if (sock_owned_by_user(meta_sk)) {
>>> - skb->sk = meta_sk;
>>> + skb->sk = (struct sock *)0xFEE1DEAD;
>>> if (unlikely(sk_add_backlog(meta_sk, skb,
>>> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>> + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
>>> bh_unlock_sock(meta_sk);
>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>> sock_put(meta_sk); /* Taken by mptcp_search_req */
>>> @@ -1122,10 +1184,14 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
>>> return 1;
>>> }
>>> } else if (skb->protocol == htons(ETH_P_IP)) {
>>> - tcp_v4_do_rcv(meta_sk, skb);
>>> + /*
>>> + * call old mptcp_v4_do_rcv
>>> + */
>>> + mptcp_v4_process_join_req(meta_sk, skb);
>>> #if IS_ENABLED(CONFIG_IPV6)
>>> } else { /* IPv6 */
>>> - tcp_v6_do_rcv(meta_sk, skb);
>>> + WARN_ON(1);
>>> + //mptcp_v6_handle_join_req(meta_sk, skb);
>>> #endif /* CONFIG_IPV6 */
>>> }
>>> bh_unlock_sock(meta_sk);
>>> @@ -1222,7 +1288,7 @@ int mptcp_lookup_join(struct sk_buff *skb, struct inet_timewait_sock *tw)
>>> inet_twsk_put(tw);
>>> }
>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>> + skb->mptcp_flags |= MPTCPHDR_JOIN;
>>> /* OK, this is a new syn/join, let's create a new open request and
>>> * send syn+ack
>>> */
>>> @@ -1279,7 +1345,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>> return -1;
>>> }
>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>> + //TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>>> /* OK, this is a new syn/join, let's create a new open request and
>>> * send syn+ack
>>> @@ -1303,7 +1369,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>> }
>>> if (sock_owned_by_user(meta_sk)) {
>>> - skb->sk = meta_sk;
>>> + skb->sk = (struct sock *)0xFEE1DEAD; //skb->sk = meta_sk;
>>> if (unlikely(sk_add_backlog(meta_sk, skb,
>>> meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf)))
>>> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
>>> @@ -1319,10 +1385,12 @@ int mptcp_do_join_short(struct sk_buff *skb,
>>> */
>>> skb_get(skb);
>>> if (skb->protocol == htons(ETH_P_IP)) {
>>> - tcp_v4_do_rcv(meta_sk, skb);
>>> + //tcp_v4_do_rcv(meta_sk, skb);
>>> + mptcp_v4_process_join_req(meta_sk, skb);
>>> #if IS_ENABLED(CONFIG_IPV6)
>>> } else { /* IPv6 */
>>> - tcp_v6_do_rcv(meta_sk, skb);
>>> + //mptcp_v6_process_join_req(meta_sk, skb);
>>> + //tcp_v6_do_rcv(meta_sk, skb);
>>> #endif /* CONFIG_IPV6 */
>>> }
>>> }
>>> @@ -1461,7 +1529,6 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
>>> {
>>> struct sock *meta_sk = mptcp_meta_sk(sk);
>>> struct tcp_sock *meta_tp = tcp_sk(meta_sk), *tp = tcp_sk(sk);
>>> - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>> u32 prior_snd_una = meta_tp->snd_una;
>>> int prior_packets;
>>> u32 nwin, data_ack, data_seq;
>>> @@ -1481,7 +1548,7 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
>>> /* If we are in infinite mapping mode, rx_opt.data_ack has been
>>> * set by mptcp_clean_rtx_infinite.
>>> */
>>> - if (!(tcb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
>>> + if (!(skb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
>>> goto exit;
>>> data_ack = tp->mptcp->rx_opt.data_ack;
>>> @@ -1647,10 +1714,11 @@ static inline bool is_valid_addropt_opsize(u8 mptcp_ver,
>>> void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>> struct mptcp_options_received *mopt,
>>> - const struct sk_buff *skb,
>>> + struct sk_buff *skb,
>>> struct tcp_sock *tp)
>>> {
>>> const struct mptcp_option *mp_opt = (struct mptcp_option *)ptr;
>>> + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>> /* If the socket is mp-capable we would have a mopt. */
>>> if (!mopt)
>>> @@ -1757,7 +1825,7 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>> ptr += 4;
>>> if (mdss->A) {
>>> - tcb->mptcp_flags |= MPTCPHDR_ACK;
>>> + skb->mptcp_flags |= MPTCPHDR_ACK;
>>> if (mdss->a) {
>>> mopt->data_ack = (u32) get_unaligned_be64(ptr);
>>> @@ -1768,13 +1836,13 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>> }
>>> }
>>> - tcb->dss_off = (ptr - skb_transport_header(skb));
>>> + skb->mptcp_dss_off = (ptr - skb_transport_header(skb));
>>> if (mdss->M) {
>>> if (mdss->m) {
>>> u64 data_seq64 = get_unaligned_be64(ptr);
>>> - tcb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
>>> + skb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
>>> mopt->data_seq = (u32) data_seq64;
>>> ptr += 12; /* 64-bit dseq + subseq */
>>> @@ -1784,15 +1852,16 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
>>> }
>>> mopt->data_len = get_unaligned_be16(ptr);
>>> - tcb->mptcp_flags |= MPTCPHDR_SEQ;
>>> + skb->mptcp_flags |= MPTCPHDR_SEQ;
>>> /* Is a check-sum present? */
>>> - if (opsize == mptcp_sub_len_dss(mdss, 1))
>>> - tcb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
>>> + if (opsize == mptcp_sub_len_dss(mdss, 1)) {
>>> + skb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
>>> + }
>>> /* DATA_FIN only possible with DSS-mapping */
>>> if (mdss->F)
>>> - tcb->mptcp_flags |= MPTCPHDR_FIN;
>>> + skb->mptcp_flags |= MPTCPHDR_FIN;
>>> }
>>> break;
>>> @@ -1907,8 +1976,9 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
>>> return;
>>> if (opsize > length)
>>> return; /* don't parse partial options */
>>> - if (opcode == TCPOPT_MPTCP)
>>> + if (opcode == TCPOPT_MPTCP) {
>>> mptcp_parse_options(ptr - 2, opsize, mopt, skb, NULL);
>>> + }
>>> }
>>> ptr += opsize - 2;
>>> length -= opsize;
>>> @@ -2168,6 +2238,8 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
>>> struct tcp_sock *tp = tcp_sk(sk);
>>> struct mptcp_options_received *mopt = &tp->mptcp->rx_opt;
>>> + BUG_ON(sk == mptcp_meta_sk(sk));
>>> +
>>> if (tp->mpcb->infinite_mapping_rcv || tp->mpcb->infinite_mapping_snd)
>>> return false;
>>> @@ -2185,7 +2257,7 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
>>> * receiver MUST close the subflow with a RST as it is considered broken.
>>> */
>>> if (mptcp_is_data_seq(skb) && tp->mpcb->dss_csum &&
>>> - !(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
>>> + !(skb->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
>>> mptcp_send_reset(sk);
>>> return true;
>>> }
>>> @@ -2330,6 +2402,7 @@ int mptcp_rcv_synsent_state_process(struct sock *sk, struct sock **skptr,
>>> /* Set this flag in order to postpone data sending
>>> * until the 4th ack arrives.
>>> */
>>> +printk("mptcp_rcv_synsent_state_process pre_established set \n");
>>> tp->mptcp->pre_established = 1;
>>> tp->mptcp->rcv_low_prio = tp->mptcp->rx_opt.low_prio;
>>> diff --git a/net/mptcp/mptcp_ipv4.c b/net/mptcp/mptcp_ipv4.c
>>> index a147b20..3e60ab5 100644
>>> --- a/net/mptcp/mptcp_ipv4.c
>>> +++ b/net/mptcp/mptcp_ipv4.c
>>> @@ -180,45 +180,12 @@ static int mptcp_v4_join_request(struct sock *meta_sk, struct sk_buff *skb)
>>> }
>>> /* We only process join requests here. (either the SYN or the final ACK) */
>>> -int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb)
>>> {
>>> const struct mptcp_cb *mpcb = tcp_sk(meta_sk)->mpcb;
>>> struct sock *child, *rsk = NULL;
>>> int ret;
>>> - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
>>> - struct tcphdr *th = tcp_hdr(skb);
>>> - const struct iphdr *iph = ip_hdr(skb);
>>> - struct sock *sk;
>>> -
>>> - sk = inet_lookup_established(sock_net(meta_sk), &tcp_hashinfo,
>>> - iph->saddr, th->source, iph->daddr,
>>> - th->dest, inet_iif(skb));
>>> -
>>> - if (!sk) {
>>> - kfree_skb(skb);
>>> - return 0;
>>> - }
>>> - if (is_meta_sk(sk)) {
>>> - WARN("%s Did not find a sub-sk - did found the meta!\n", __func__);
>>> - kfree_skb(skb);
>>> - sock_put(sk);
>>> - return 0;
>>> - }
>>> -
>>> - if (sk->sk_state == TCP_TIME_WAIT) {
>>> - inet_twsk_put(inet_twsk(sk));
>>> - kfree_skb(skb);
>>> - return 0;
>>> - }
>>> -
>>> - ret = tcp_v4_do_rcv(sk, skb);
>>> - sock_put(sk);
>>> -
>>> - return ret;
>>> - }
>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>> -
>>> /* Has been removed from the tk-table. Thus, no new subflows.
>>> *
>>> * Check for close-state is necessary, because we may have been closed
>>> diff --git a/net/mptcp/mptcp_ipv6.c b/net/mptcp/mptcp_ipv6.c
>>> index 0de953d..1959d01 100644
>>> --- a/net/mptcp/mptcp_ipv6.c
>>> +++ b/net/mptcp/mptcp_ipv6.c
>>> @@ -199,7 +199,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>> struct sock *child, *rsk = NULL;
>>> int ret;
>>> - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
>>> + if (!(skb->mptcp_flags & MPTCPHDR_JOIN)) {
>>> struct tcphdr *th = tcp_hdr(skb);
>>> const struct ipv6hdr *ip6h = ipv6_hdr(skb);
>>> struct sock *sk;
>>> @@ -232,7 +232,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
>>> return ret;
>>> }
>>> - TCP_SKB_CB(skb)->mptcp_flags = 0;
>>> + skb->mptcp_flags = 0;
>>> /* Has been removed from the tk-table. Thus, no new subflows.
>>> *
>>> diff --git a/net/mptcp/mptcp_output.c b/net/mptcp/mptcp_output.c
>>> index 691ef6f..e7d340d 100644
>>> --- a/net/mptcp/mptcp_output.c
>>> +++ b/net/mptcp/mptcp_output.c
>>> @@ -59,39 +59,17 @@ EXPORT_SYMBOL(mptcp_sub_len_remove_addr_align);
>>> */
>>> static bool mptcp_reconstruct_mapping(struct sk_buff *skb)
>>> {
>>> - const struct mp_dss *mpdss = (struct mp_dss *)TCP_SKB_CB(skb)->dss;
>>> - u32 *p32;
>>> - u16 *p16;
>>> -
>>> if (!mptcp_is_data_seq(skb))
>>> return false;
>>> - if (!mpdss->M)
>>> - return false;
>>> -
>>> - /* Move the pointer to the data-seq */
>>> - p32 = (u32 *)mpdss;
>>> - p32++;
>>> - if (mpdss->A) {
>>> - p32++;
>>> - if (mpdss->a)
>>> - p32++;
>>> - }
>>> -
>>> - TCP_SKB_CB(skb)->seq = ntohl(*p32);
>>> -
>>> - /* Get the data_len to calculate the end_data_seq */
>>> - p32++;
>>> - p32++;
>>> - p16 = (u16 *)p32;
>>> - TCP_SKB_CB(skb)->end_seq = ntohs(*p16) + TCP_SKB_CB(skb)->seq;
>>> + TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->mptcp_data_seq;
>>> return true;
>>> }
>>> static bool mptcp_is_reinjected(const struct sk_buff *skb)
>>> {
>>> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCP_REINJECT;
>>> + return skb->mptcp_flags & MPTCP_REINJECT;
>>> }
>>> static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_buff *skb)
>>> @@ -105,7 +83,7 @@ static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_bu
>>> break;
>>> if (TCP_SKB_CB(skb_it)->seq == TCP_SKB_CB(skb)->seq) {
>>> - TCP_SKB_CB(skb)->path_mask = TCP_SKB_CB(skb_it)->path_mask;
>>> + TCP_SKB_CB(skb)->mptcp_path_mask = TCP_SKB_CB(skb_it)->mptcp_path_mask;
>>> break;
>>> }
>>> }
>>> @@ -180,9 +158,9 @@ static void __mptcp_reinject_data(struct sk_buff *orig_skb, struct sock *meta_sk
>>> }
>>> /* Segment goes back to the MPTCP-layer. So, we need to zero the
>>> - * path_mask/dss.
>>> + * path_mask.
>>> */
>>> - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
>>> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>> /* We need to find out the path-mask from the meta-write-queue
>>> * to properly select a subflow.
>>> @@ -272,14 +250,14 @@ void mptcp_reinject_data(struct sock *sk, int clone_it)
>>> if (mptcp_is_reinjected(skb_it))
>>> continue;
>>> - tcb->mptcp_flags |= MPTCP_REINJECT;
>>> + skb_it->mptcp_flags |= MPTCP_REINJECT;
>>> __mptcp_reinject_data(skb_it, meta_sk, sk, clone_it);
>>> }
>>> skb_it = tcp_write_queue_tail(meta_sk);
>>> /* If sk has sent the empty data-fin, we have to reinject it too. */
>>> if (skb_it && mptcp_is_data_fin(skb_it) && skb_it->len == 0 &&
>>> - TCP_SKB_CB(skb_it)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
>>> + TCP_SKB_CB(skb_it)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
>>> __mptcp_reinject_data(skb_it, meta_sk, NULL, 1);
>>> }
>>> @@ -319,25 +297,43 @@ combine:
>>> }
>>> }
>>> -static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_buff *skb,
>>> - __be32 *ptr)
>>> +/*
>>> + * RFC6824 states that once a particular subflow mapping has been sent
>>> + * out it must never be changed. However, packets may be split while
>>> + * they are in the retransmission queue (due to SACK or ACKs) and that
>>> + * arguably means that we would change the mapping (e.g. it splits it,
>>> + * our sends out a subset of the initial mapping).
>>> + *
>>> + * Furthermore, the skb checksum is not always preserved across splits
>>> + * (e.g. mptcp_fragment) which would mean that we need to recompute
>>> + * the DSS checksum in this case.
>>> + *
>>> + * To avoid this we save the initial DSS mapping which allows us to
>>> + * send the same DSS mapping even for fragmented retransmits.
>>> + */
>>> +
>>> +static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
>>> + const struct sk_buff *skb, __be32 *ptr)
>>> {
>>> const struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>> - __be32 *start = ptr;
>>> __u16 data_len;
>>> - *ptr++ = htonl(tcb->seq); /* data_seq */
>>> + *ptr++ = htonl(tcb->mptcp_data_seq); /* data_seq */
>>> /* If it's a non-data DATA_FIN, we set subseq to 0 (draft v7) */
>>> if (mptcp_is_data_fin(skb) && skb->len == 0)
>>> *ptr++ = 0; /* subseq */
>>> else
>>> - *ptr++ = htonl(tp->write_seq - tp->mptcp->snt_isn); /* subseq */
>>> + *ptr++ = htonl(tcb->seq - tp->mptcp->snt_isn); /* subseq */
>>> - if (tcb->mptcp_flags & MPTCPHDR_INF)
>>> + if (skb->mptcp_flags & MPTCPHDR_INF)
>>> data_len = 0;
>>> - else
>>> + else {
>>> data_len = tcb->end_seq - tcb->seq;
>>> + /* mptcp_entail_skb adds one for FIN */
>>> + if (tcb->tcp_flags & TCPHDR_FIN)
>>> + data_len -= 1;
>>> + }
>>> if (tp->mpcb->dss_csum && data_len) {
>>> __be16 *p16 = (__be16 *)ptr;
>>> @@ -356,11 +352,11 @@ static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_bu
>>> (TCPOPT_NOP));
>>> }
>>> - return ptr - start;
>>> + return mptcp_dss_len/sizeof(*ptr);
>>> }
>>> -static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_buff *skb,
>>> - __be32 *ptr)
>>> +static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
>>> + const struct sk_buff *skb, __be32 *ptr)
>>> {
>>> struct mp_dss *mdss = (struct mp_dss *)ptr;
>>> __be32 *start = ptr;
>>> @@ -377,54 +373,12 @@ static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_b
>>> mdss->len = mptcp_sub_len_dss(mdss, tp->mpcb->dss_csum);
>>> ptr++;
>>> + /* data_ack */
>>> *ptr++ = htonl(mptcp_meta_tp(tp)->rcv_nxt);
>>> return ptr - start;
>>> }
>>> -/* RFC6824 states that once a particular subflow mapping has been sent
>>> - * out it must never be changed. However, packets may be split while
>>> - * they are in the retransmission queue (due to SACK or ACKs) and that
>>> - * arguably means that we would change the mapping (e.g. it splits it,
>>> - * our sends out a subset of the initial mapping).
>>> - *
>>> - * Furthermore, the skb checksum is not always preserved across splits
>>> - * (e.g. mptcp_fragment) which would mean that we need to recompute
>>> - * the DSS checksum in this case.
>>> - *
>>> - * To avoid this we save the initial DSS mapping which allows us to
>>> - * send the same DSS mapping even for fragmented retransmits.
>>> - */
>>> -static void mptcp_save_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb)
>>> -{
>>> - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>>> - __be32 *ptr = (__be32 *)tcb->dss;
>>> -
>>> - tcb->mptcp_flags |= MPTCPHDR_SEQ;
>>> -
>>> - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>> - ptr += mptcp_write_dss_mapping(tp, skb, ptr);
>>> -}
>>> -
>>> -/* Write the saved DSS mapping to the header */
>>> -static int mptcp_write_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb,
>>> - __be32 *ptr)
>>> -{
>>> - __be32 *start = ptr;
>>> -
>>> - memcpy(ptr, TCP_SKB_CB(skb)->dss, mptcp_dss_len);
>>> -
>>> - /* update the data_ack */
>>> - start[1] = htonl(mptcp_meta_tp(tp)->rcv_nxt);
>>> -
>>> - /* dss is in a union with inet_skb_parm and
>>> - * the IP layer expects zeroed IPCB fields.
>>> - */
>>> - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
>>> -
>>> - return mptcp_dss_len/sizeof(*ptr);
>>> -}
>>> -
>>> static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
>>> {
>>> struct tcp_sock *tp = tcp_sk(sk);
>>> @@ -434,7 +388,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
>>> struct sk_buff *subskb = NULL;
>>> if (!reinject)
>>> - TCP_SKB_CB(skb)->mptcp_flags |= (mpcb->snd_hiseq_index ?
>>> + skb->mptcp_flags |= (mpcb->snd_hiseq_index ?
>>> MPTCPHDR_SEQ64_INDEX : 0);
>>> subskb = pskb_copy_for_clone(skb, GFP_ATOMIC);
>>> @@ -447,7 +401,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
>>> */
>>> tcp_skb_pcount_set(subskb, 0);
>>> - TCP_SKB_CB(skb)->path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
>>> + TCP_SKB_CB(skb)->mptcp_path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
>>> if (!(sk->sk_route_caps & NETIF_F_ALL_CSUM) &&
>>> skb->ip_summed == CHECKSUM_PARTIAL) {
>>> @@ -463,13 +417,14 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
>>> tp->mptcp->fully_established = 1;
>>> tp->mpcb->infinite_mapping_snd = 1;
>>> tp->mptcp->infinite_cutoff_seq = tp->write_seq;
>>> - tcb->mptcp_flags |= MPTCPHDR_INF;
>>> + skb->mptcp_flags |= MPTCPHDR_INF;
>>> }
>>> if (mptcp_is_data_fin(subskb))
>>> mptcp_combine_dfin(subskb, meta_sk, sk);
>>> - mptcp_save_dss_data_seq(tp, subskb);
>>> + subskb->mptcp_flags |= MPTCPHDR_SEQ;
>>> + tcb->mptcp_data_seq = tcb->seq;
>>> tcb->seq = tp->write_seq;
>>> @@ -536,10 +491,10 @@ static int mptcp_fragment(struct sock *meta_sk, struct sk_buff *skb, u32 len,
>>> buff = skb->next;
>>> - flags = TCP_SKB_CB(skb)->mptcp_flags;
>>> - TCP_SKB_CB(skb)->mptcp_flags = flags & ~(MPTCPHDR_FIN);
>>> - TCP_SKB_CB(buff)->mptcp_flags = flags;
>>> - TCP_SKB_CB(buff)->path_mask = TCP_SKB_CB(skb)->path_mask;
>>> + flags = skb->mptcp_flags;
>>> + skb->mptcp_flags = flags & ~(MPTCPHDR_FIN);
>>> + buff->mptcp_flags = flags;
>>> + TCP_SKB_CB(buff)->mptcp_path_mask = TCP_SKB_CB(skb)->mptcp_path_mask;
>>> /* If reinject == 1, the buff will be added to the reinject
>>> * queue, which is currently not part of memory accounting. So
>>> @@ -927,8 +882,9 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
>>> * It does not make sense to check for the options, because when the
>>> * segment gets sent, another subflow will be chosen.
>>> */
>>> - if (!skb && is_meta_sk(sk))
>>> + if (!skb && is_meta_sk(sk)) {
>>> return;
>>> + }
>>> /* In fallback mp_fail-mode, we have to repeat it until the fallback
>>> * has been done by the sender
>>> @@ -967,10 +923,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
>>> if (unlikely(mpcb->infinite_mapping_snd) &&
>>> ((mpcb->send_infinite_mapping && tcb &&
>>> mptcp_is_data_seq(skb) &&
>>> - !(tcb->mptcp_flags & MPTCPHDR_INF) &&
>>> + !(skb->mptcp_flags & MPTCPHDR_INF) &&
>>> !before(tcb->seq, tp->mptcp->infinite_cutoff_seq)) ||
>>> - !mpcb->send_infinite_mapping))
>>> + !mpcb->send_infinite_mapping)) {
>>> return;
>>> + }
>>> if (unlikely(tp->mptcp->include_mpc)) {
>>> opts->options |= OPTION_MPTCP;
>>> @@ -995,9 +952,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
>>> mpcb->mptcp_ver >= MPTCP_VERSION_1 && skb && !mptcp_is_data_seq(skb)) {
>>> mpcb->pm_ops->addr_signal(sk, size, opts, skb);
>>> - if (opts->add_addr_v6)
>>> + if (opts->add_addr_v6) {
>>> +
>>> /* Skip subsequent options */
>>> return;
>>> + }
>>> }
>>> if (!tp->mptcp->include_mpc && !tp->mptcp->pre_established) {
>>> @@ -1197,10 +1156,11 @@ void mptcp_options_write(__be32 *ptr, struct tcp_sock *tp,
>>> }
>>> if (OPTION_DATA_ACK & opts->mptcp_options) {
>>> - if (!mptcp_is_data_seq(skb))
>>> - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>> - else
>>> - ptr += mptcp_write_dss_data_seq(tp, skb, ptr);
>>> + ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
>>> + if (mptcp_is_data_seq(skb)) {
>>> + ptr += mptcp_write_dss_mapping(tp, skb, ptr);
>>> + }
>>> + skb->dev = NULL;
>>> }
>>> if (unlikely(OPTION_MP_PRIO & opts->mptcp_options)) {
>>> struct mp_prio *mpprio = (struct mp_prio *)ptr;
>>> @@ -1233,7 +1193,7 @@ void mptcp_send_fin(struct sock *meta_sk)
>>> mss_now = mptcp_current_mss(meta_sk);
>>> if (tcp_send_head(meta_sk) != NULL) {
>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
>>> + skb->mptcp_flags |= MPTCPHDR_FIN;
>>> TCP_SKB_CB(skb)->end_seq++;
>>> meta_tp->write_seq++;
>>> } else {
>>> @@ -1250,7 +1210,7 @@ void mptcp_send_fin(struct sock *meta_sk)
>>> tcp_init_nondata_skb(skb, meta_tp->write_seq, TCPHDR_ACK);
>>> TCP_SKB_CB(skb)->end_seq++;
>>> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
>>> + skb->mptcp_flags |= MPTCPHDR_FIN;
>>> tcp_queue_skb(meta_sk, skb);
>>> }
>>> __tcp_push_pending_frames(meta_sk, mss_now, TCP_NAGLE_OFF);
>>> diff --git a/net/mptcp/mptcp_redundant.c b/net/mptcp/mptcp_redundant.c
>>> index 8fa2dba..37a13f4 100644
>>> --- a/net/mptcp/mptcp_redundant.c
>>> +++ b/net/mptcp/mptcp_redundant.c
>>> @@ -72,10 +72,10 @@ static bool redsched_use_subflow(struct sock *meta_sk,
>>> if (!skb || !mptcp_is_available((struct sock *)tp, skb, false))
>>> return false;
>>> - if (TCP_SKB_CB(skb)->path_mask != 0)
>>> + if (TCP_SKB_CB(skb)->mptcp_path_mask != 0)
>>> return subflow_is_active(tp);
>>> - if (TCP_SKB_CB(skb)->path_mask == 0) {
>>> + if (TCP_SKB_CB(skb)->mptcp_path_mask == 0) {
>>> if (active_valid_sks == -1)
>>> active_valid_sks = redsched_get_active_valid_sks(meta_sk);
>>> @@ -209,7 +209,7 @@ static struct sk_buff *redundant_next_segment(struct sock *meta_sk,
>>> cb_data->next_subflow = tp->mptcp->next;
>>> *subsk = (struct sock *)tp;
>>> - if (TCP_SKB_CB(skb)->path_mask)
>>> + if (TCP_SKB_CB(skb)->mptcp_path_mask)
>>> *reinject = -1;
>>> return skb;
>>> }
>>> diff --git a/net/mptcp/mptcp_rr.c b/net/mptcp/mptcp_rr.c
>>> index 8910ba9..83837f2 100644
>>> --- a/net/mptcp/mptcp_rr.c
>>> +++ b/net/mptcp/mptcp_rr.c
>>> @@ -93,7 +93,7 @@ static int mptcp_rr_dont_reinject_skb(const struct tcp_sock *tp, const struct sk
>>> */
>>> return skb &&
>>> /* Has the skb already been enqueued into this subsocket? */
>>> - mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
>>> + mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
>>> }
>>> /* We just look for any subflow that is available */
>>> @@ -136,7 +136,7 @@ static struct sock *rr_get_available_subflow(struct sock *meta_sk,
>>> * chance again by restarting its pathmask.
>>> */
>>> if (skb)
>>> - TCP_SKB_CB(skb)->path_mask = 0;
>>> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>> sk = backupsk;
>>> }
>>> diff --git a/net/mptcp/mptcp_sched.c b/net/mptcp/mptcp_sched.c
>>> index 54408ff..5cbbf91 100644
>>> --- a/net/mptcp/mptcp_sched.c
>>> +++ b/net/mptcp/mptcp_sched.c
>>> @@ -118,7 +118,7 @@ static int mptcp_dont_reinject_skb(const struct tcp_sock *tp, const struct sk_bu
>>> */
>>> return skb &&
>>> /* Has the skb already been enqueued into this subsocket? */
>>> - mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
>>> + mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
>>> }
>>> bool subflow_is_backup(const struct tcp_sock *tp)
>>> @@ -261,7 +261,7 @@ struct sock *get_available_subflow(struct sock *meta_sk, struct sk_buff *skb,
>>> * the skb passed through all the available active and backups
>>> * sks, so clean the path mask
>>> */
>>> - TCP_SKB_CB(skb)->path_mask = 0;
>>> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>>> return sk;
>>> }
>>> EXPORT_SYMBOL_GPL(get_available_subflow);
>>> @@ -298,7 +298,7 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
>>> /* Half the cwnd of the slow flow */
>>> mptcp_for_each_tp(tp->mpcb, tp_it) {
>>> if (tp_it != tp &&
>>> - TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>> + TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>> if (tp->srtt_us < tp_it->srtt_us && inet_csk((struct sock *)tp_it)->icsk_ca_state == TCP_CA_Open) {
>>> u32 prior_cwnd = tp_it->snd_cwnd;
>>> @@ -317,11 +317,11 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
>>> retrans:
>>> /* Segment not yet injected into this path? Take it!!! */
>>> - if (!(TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
>>> + if (!(TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
>>> bool do_retrans = false;
>>> mptcp_for_each_tp(tp->mpcb, tp_it) {
>>> if (tp_it != tp &&
>>> - TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>> + TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
>>> if (tp_it->snd_cwnd <= 4) {
>>> do_retrans = true;
>>> break;
>> _______________________________________________
>> mptcp mailing list
>> mptcp(a)lists.01.org
>> https://lists.01.org/mailman/listinfo/mptcp
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-27 6:27 Christoph Paasch
0 siblings, 0 replies; 14+ messages in thread
From: Christoph Paasch @ 2017-06-27 6:27 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 56407 bytes --]
Hello Rao,
can you try to give some more details on how the datapath looks like with
this patch?
For example, I wonder how data-acks are being processed. Because, I see in
mptcp_data_ready, that you now expects skbs with len 0, upon which you end
up calling mptcp_process_ack().
I don't see how such zero-length skbs could end up in the receive-queue of
the subflows.
Thanks,
Christoph
On 26/06/17 - 15:34:09, Rao Shoaib wrote:
> I forgot to mention two things
>
> 1) Connection setup still has checks for MPTCP, Ideally these should be
> removed but at least we need to run some benchmarks and fix any issues. The
> mainstream folks will not accept any performance degradation in TCP. I can
> look into this next.
>
> 2) The code overloads dev field of skb, when it is not being used. IIRC
> there is precedence for this already. I will try to find it.
>
> Rao
>
>
> On 06/26/2017 02:13 PM, Rao Shoaib wrote:
> > This patch returns tcp_skb_cb to it's original size. It also refactors MPTCP code so that there are no MPTCP checks in the main Rx pathi, no performance overheads such as cpu prodiction issues. tcp_v4_rcv() and tcp_v4_do_rcv() do not have any MPTCP specific checks any more, niether does tcp_ack(). On the Rx path MPTCP options are not parsed till the data is being pushed up to the meta socket (mptcp_data_ready). on the Tx side there is one check to add MPTCP specific options but that's it, that should not be that bad as for regular TCP it is a simple check, but it would be good to remove it..
> >
> > I have tested the changes with ndiffports set to 2, so join works. I have also tested accessing multipath-tcp.org and downloading files from there and also ran the speed test.
> >
> > The Bad:
> >
> > The error cases still have MPTCP checks but that should be OK as they are error cases. I had to use a special marker 0xFEE1DEAD for indicate a special case. I had to introdue a new socket specfic function. IPv6 has not been changed yet. I am sure I have missed some corner cases and more testing will reveal more issues but we just have to fix them.
> >
> > I would like to hear comments from the list and if this direction seems reasonable we can take this as the starting point, port it to latest Linux and share the design with the mainstream folks.
> >
> > Signed-off-by: Rao Shoaib <rao.shoaib(a)oracle.com>
> > ---
> > include/linux/skbuff.h | 8 ++-
> > include/net/mptcp.h | 21 +++---
> > include/net/mptcp_v4.h | 1 +
> > include/net/sock.h | 12 +++-
> > include/net/tcp.h | 23 +++----
> > net/ipv4/af_inet.c | 4 ++
> > net/ipv4/tcp_input.c | 37 ++--------
> > net/ipv4/tcp_ipv4.c | 135 +++++++++++++++++++++++--------------
> > net/ipv4/tcp_output.c | 1 +
> > net/ipv6/af_inet6.c | 4 ++
> > net/ipv6/tcp_ipv6.c | 4 --
> > net/mptcp/mptcp_ctrl.c | 21 ++++++
> > net/mptcp/mptcp_input.c | 131 ++++++++++++++++++++++++++++--------
> > net/mptcp/mptcp_ipv4.c | 35 +---------
> > net/mptcp/mptcp_ipv6.c | 4 +-
> > net/mptcp/mptcp_output.c | 160 +++++++++++++++++---------------------------
> > net/mptcp/mptcp_redundant.c | 6 +-
> > net/mptcp/mptcp_rr.c | 4 +-
> > net/mptcp/mptcp_sched.c | 10 +--
> > 19 files changed, 335 insertions(+), 286 deletions(-)
> >
> > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> > index f66cd5e..348cbc1 100644
> > --- a/include/linux/skbuff.h
> > +++ b/include/linux/skbuff.h
> > @@ -532,7 +532,13 @@ struct sk_buff {
> > struct rb_node rbnode; /* used in netem & tcp stack */
> > };
> > struct sock *sk;
> > - struct net_device *dev;
> > + union {
> > + struct net_device *dev;
> > + struct {
> > + __u8 mptcp_flags;
> > + __u8 mptcp_dss_off;
> > + };
> > + };
> > /*
> > * This is the control buffer. It is free to use for every
> > diff --git a/include/net/mptcp.h b/include/net/mptcp.h
> > index 876f1e6..d087cb4 100644
> > --- a/include/net/mptcp.h
> > +++ b/include/net/mptcp.h
> > @@ -807,7 +807,7 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
> > struct mptcp_options_received *mopt);
> > void mptcp_parse_options(const uint8_t *ptr, int opsize,
> > struct mptcp_options_received *mopt,
> > - const struct sk_buff *skb,
> > + struct sk_buff *skb,
> > struct tcp_sock *tp);
> > void mptcp_syn_options(const struct sock *sk, struct tcp_out_options *opts,
> > unsigned *remaining);
> > @@ -998,14 +998,15 @@ static inline void mptcp_sub_force_close_all(struct mptcp_cb *mpcb,
> > }
> > }
> > +/* currently tp is being used for Rx packets */
> > static inline bool mptcp_is_data_seq(const struct sk_buff *skb)
> > {
> > - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ;
> > + return skb->mptcp_flags & MPTCPHDR_SEQ;
> > }
> > static inline bool mptcp_is_data_fin(const struct sk_buff *skb)
> > {
> > - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_FIN;
> > + return skb->mptcp_flags & MPTCPHDR_FIN;
> > }
> > /* Is it a data-fin while in infinite mapping mode?
> > @@ -1034,17 +1035,17 @@ static inline u8 mptcp_get_64_bit(u64 data_seq, struct mptcp_cb *mpcb)
> > /* Sets the data_seq and returns pointer to the in-skb field of the data_seq.
> > * If the packet has a 64-bit dseq, the pointer points to the last 32 bits.
> > */
> > -static inline __u32 *mptcp_skb_set_data_seq(const struct sk_buff *skb,
> > +static inline __u32 *mptcp_skb_set_data_seq(struct sk_buff *skb,
> > u32 *data_seq,
> > struct mptcp_cb *mpcb)
> > {
> > - __u32 *ptr = (__u32 *)(skb_transport_header(skb) + TCP_SKB_CB(skb)->dss_off);
> > + __u32 *ptr = (__u32 *)(skb_transport_header(skb) + skb->mptcp_dss_off);
> > - if (TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ64_SET) {
> > + if (skb->mptcp_flags & MPTCPHDR_SEQ64_SET) {
> > u64 data_seq64 = get_unaligned_be64(ptr);
> > if (mpcb)
> > - TCP_SKB_CB(skb)->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
> > + skb->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
> > *data_seq = (u32)data_seq64;
> > ptr++;
> > @@ -1142,7 +1143,7 @@ static inline void mptcp_reset_mopt(struct tcp_sock *tp)
> > static inline __be32 mptcp_get_highorder_sndbits(const struct sk_buff *skb,
> > const struct mptcp_cb *mpcb)
> > {
> > - return htonl(mpcb->snd_high_order[(TCP_SKB_CB(skb)->mptcp_flags &
> > + return htonl(mpcb->snd_high_order[(skb->mptcp_flags &
> > MPTCPHDR_SEQ64_INDEX) ? 1 : 0]);
> > }
> > @@ -1404,8 +1405,8 @@ static inline void mptcp_set_rto(const struct sock *sk) {}
> > static inline void mptcp_send_fin(const struct sock *meta_sk) {}
> > static inline void mptcp_parse_options(const uint8_t *ptr, const int opsize,
> > struct mptcp_options_received *mopt,
> > - const struct sk_buff *skb,
> > - const struct tcp_sock *tp) {}
> > + struct sk_buff *skb,
> > + struct tcp_sock *tp) {}
> > static inline void mptcp_syn_options(const struct sock *sk,
> > struct tcp_out_options *opts,
> > unsigned *remaining) {}
> > diff --git a/include/net/mptcp_v4.h b/include/net/mptcp_v4.h
> > index c83dca0..46394a4 100644
> > --- a/include/net/mptcp_v4.h
> > +++ b/include/net/mptcp_v4.h
> > @@ -45,6 +45,7 @@ extern struct tcp_request_sock_ops mptcp_join_request_sock_ipv4_ops;
> > #ifdef CONFIG_MPTCP
> > int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb);
> > +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb);
> > struct sock *mptcp_v4_search_req(const __be16 rport, const __be32 raddr,
> > const __be32 laddr, const struct net *net);
> > int mptcp_init4_subsockets(struct sock *meta_sk, const struct mptcp_loc4 *loc,
> > diff --git a/include/net/sock.h b/include/net/sock.h
> > index 0f12593..0d1bda5 100644
> > --- a/include/net/sock.h
> > +++ b/include/net/sock.h
> > @@ -296,6 +296,7 @@ struct cg_proto;
> > * @sk_write_space: callback to indicate there is bf sending space available
> > * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
> > * @sk_backlog_rcv: callback to process the backlog
> > + * @sk_prequeue: callback to prequeue
> > * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
> > */
> > struct sock {
> > @@ -437,7 +438,9 @@ struct sock {
> > void (*sk_write_space)(struct sock *sk);
> > void (*sk_error_report)(struct sock *sk);
> > int (*sk_backlog_rcv)(struct sock *sk,
> > - struct sk_buff *skb);
> > + struct sk_buff *skb);
> > + bool (*sk_prequeue)(struct sock *sk,
> > + struct sk_buff *skb);
> > void (*sk_destruct)(struct sock *sk);
> > };
> > @@ -853,6 +856,11 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
> > return sk->sk_backlog_rcv(sk, skb);
> > }
> > +static inline bool sk_prequeue(struct sock *sk, struct sk_buff *skb)
> > +{
> > + return (false);
> > +}
> > +
> > static inline void sk_incoming_cpu_update(struct sock *sk)
> > {
> > sk->sk_incoming_cpu = raw_smp_processor_id();
> > @@ -993,6 +1001,8 @@ struct proto {
> > int (*backlog_rcv) (struct sock *sk,
> > struct sk_buff *skb);
> > + bool (*prequeue) (struct sock *sk,
> > + struct sk_buff *skb);
> > void (*release_cb)(struct sock *sk);
> > diff --git a/include/net/tcp.h b/include/net/tcp.h
> > index 655ecd4..cbe8ef2 100644
> > --- a/include/net/tcp.h
> > +++ b/include/net/tcp.h
> > @@ -47,6 +47,9 @@
> > #include <linux/seq_file.h>
> > #include <linux/memcontrol.h>
> > +typedef int (* process_unclaimed)(struct sock *sk, struct sk_buff *skb);
> > +extern process_unclaimed tcp_process_unclaimed;
> > +
> > extern struct inet_hashinfo tcp_hashinfo;
> > extern struct percpu_counter tcp_orphan_count;
> > @@ -581,6 +584,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
> > struct request_sock *req,
> > struct dst_entry *dst);
> > int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
> > +
> > int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
> > int tcp_connect(struct sock *sk);
> > struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
> > @@ -842,11 +846,6 @@ struct tcp_skb_cb {
> > __u32 tcp_gso_segs;
> > };
> > -#ifdef CONFIG_MPTCP
> > - __u8 mptcp_flags; /* flags for the MPTCP layer */
> > - __u8 dss_off; /* Number of 4-byte words until
> > - * seq-number */
> > -#endif
> > __u8 tcp_flags; /* TCP header flags. (tcp[13]) */
> > __u8 sacked; /* State flags for SACK/FACK. */
> > @@ -859,9 +858,13 @@ struct tcp_skb_cb {
> > #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
> > TCPCB_REPAIRED)
> > - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
> > + __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
> > /* 1 byte hole */
> > - __u32 ack_seq; /* Sequence number ACK'd */
> > + union {
> > + __u32 ack_seq; /* Sequence number ACK'd */
> > + __u32 mptcp_data_seq;
> > + __u32 mptcp_path_mask;
> > + };
> > union {
> > union {
> > struct inet_skb_parm h4;
> > @@ -869,12 +872,6 @@ struct tcp_skb_cb {
> > struct inet6_skb_parm h6;
> > #endif
> > } header; /* For incoming frames */
> > -#ifdef CONFIG_MPTCP
> > - union { /* For MPTCP outgoing frames */
> > - __u32 path_mask; /* paths that tried to send this skb */
> > - __u32 dss[6]; /* DSS options */
> > - };
> > -#endif
> > };
> > };
> > diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
> > index 73480b9..1e7827f 100644
> > --- a/net/ipv4/af_inet.c
> > +++ b/net/ipv4/af_inet.c
> > @@ -356,6 +356,10 @@ lookup_protocol:
> > sk->sk_destruct = inet_sock_destruct;
> > sk->sk_protocol = protocol;
> > sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
> > + sk->sk_prequeue = sk->sk_prot->prequeue;
> > + if (sk->sk_prequeue == NULL) {
> > + sk->sk_prequeue = sk_prequeue;
> > + }
> > inet->uc_ttl = -1;
> > inet->mc_loop = 1;
> > diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> > index 16a7256..cb6bbf9 100644
> > --- a/net/ipv4/tcp_input.c
> > +++ b/net/ipv4/tcp_input.c
> > @@ -3133,8 +3133,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
> > */
> > if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
> > flag |= FLAG_DATA_ACKED;
> > - if (mptcp(tp) && mptcp_is_data_seq(skb))
> > - flag |= MPTCP_FLAG_DATA_ACKED;
> > } else {
> > flag |= FLAG_SYN_ACKED;
> > tp->retrans_stamp = 0;
> > @@ -3582,16 +3580,6 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
> > sack_rtt_us);
> > acked -= tp->packets_out;
> > - if (mptcp(tp)) {
> > - if (mptcp_fallback_infinite(sk, flag)) {
> > - pr_err("%s resetting flow\n", __func__);
> > - mptcp_send_reset(sk);
> > - goto invalid_ack;
> > - }
> > -
> > - mptcp_clean_rtx_infinite(skb, sk);
> > - }
> > -
> > /* Advance cwnd if state allows */
> > if (tcp_may_raise_cwnd(sk, flag))
> > tcp_cong_avoid(sk, ack, acked);
> > @@ -3824,8 +3812,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
> > if (tcp_parse_aligned_timestamp(tp, th))
> > return true;
> > }
> > - tcp_parse_options(skb, &tp->rx_opt,
> > - mptcp(tp) ? &tp->mptcp->rx_opt : NULL, 1, NULL, tp);
> > + tcp_parse_options(skb, &tp->rx_opt, NULL, 1, NULL, tp);
> > if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
> > tp->rx_opt.rcv_tsecr -= tp->tsoffset;
> > @@ -4550,11 +4537,12 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
> > int eaten = -1;
> > bool fragstolen = false;
> > - /* If no data is present, but a data_fin is in the options, we still
> > - * have to call mptcp_queue_skb later on. */
> > - if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq &&
> > - !(mptcp(tp) && mptcp_is_data_fin(skb)))
> > + /*
> > + * send every packet to MPTCP
> > + */
> > + if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)) {
> > goto drop;
> > + }
> > skb_dst_drop(skb);
> > __skb_pull(skb, tcp_hdr(skb)->doff * 4);
> > @@ -5242,15 +5230,9 @@ syn_challenge:
> > goto discard;
> > }
> > - /* If valid: post process the received MPTCP options. */
> > - if (mptcp(tp) && mptcp_handle_options(sk, th, skb))
> > - goto discard;
> > -
> > return true;
> > discard:
> > - if (mptcp(tp))
> > - mptcp_reset_mopt(tp);
> > __kfree_skb(skb);
> > return false;
> > }
> > @@ -5302,10 +5284,6 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
> > tp->rx_opt.saw_tstamp = 0;
> > - /* MPTCP: force slowpath. */
> > - if (mptcp(tp))
> > - goto slow_path;
> > -
> > /* pred_flags is 0xS?10 << 16 + snd_wnd
> > * if header_prediction is to be made
> > * 'S' will always be tp->tcp_header_len >> 2
> > @@ -5585,8 +5563,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
> > struct mptcp_options_received mopt;
> > mptcp_init_mp_opt(&mopt);
> > - tcp_parse_options(skb, &tp->rx_opt,
> > - mptcp(tp) ? &tp->mptcp->rx_opt : &mopt, 0, &foc, tp);
> > + tcp_parse_options(skb, &tp->rx_opt, &mopt, 0, &foc, tp);
> > if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
> > tp->rx_opt.rcv_tsecr -= tp->tsoffset;
> > diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> > index 6967a86..3329679 100644
> > --- a/net/ipv4/tcp_ipv4.c
> > +++ b/net/ipv4/tcp_ipv4.c
> > @@ -1420,6 +1420,71 @@ struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
> > return sk;
> > }
> > +int mptcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
> > +{
> > + struct net *net = dev_net(skb->dev);
> > + const struct tcphdr *th = tcp_hdr(skb);
> > + int ret;
> > + struct sock *meta_sk;
> > +
> > + if (sk == NULL) {
> > + if (th->syn && !th->ack) {
> > + int ret = mptcp_lookup_join(skb, NULL);
> > +
> > + if (ret < 0) {
> > + tcp_v4_send_reset(NULL, skb);
> > + kfree_skb(skb);
> > + return (1);
> > + } else if (ret > 0) {
> > + return (1);
> > + }
> > + }
> > + /* Is there a pending request sock for this segment ? */
> > + if (mptcp_check_req(skb, net)) {
> > + return(1);
> > + }
> > + return (0);
> > + }
> > +
> > + /* The socket passed in should never be the meta socket */
> > +
> > + BUG_ON(is_meta_sk(sk));
> > +
> > + /* Is there a pending request sock for this segment ? */
> > + if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
> > + return 0;
> > + }
> > +
> > + skb->dev = NULL;
> > + meta_sk = mptcp_meta_sk(sk);
> > +
> > + ret = 0;
> > + skb->sk = sk;
> > + bh_lock_sock_nested(meta_sk);
> > + if (sock_owned_by_user(meta_sk)) {
> > + if (unlikely(sk_add_backlog(meta_sk, skb,
> > + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> > +
> > + NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> > + kfree_skb(skb);
> > + }
> > + } else {
> > +
> > + if (is_meta_sk(sk)) {
> > + ret = mptcp_v4_process_join_req(sk, skb);
> > + goto done;
> > + }
> > + if (!meta_sk->sk_prequeue(meta_sk, skb)) {
> > + skb->sk = NULL;
> > + ret = tcp_v4_do_rcv(sk, skb);
> > + }
> > +
> > + }
> > +done:
> > + bh_unlock_sock(meta_sk);
> > + return (ret);
> > +}
> > +
> > /* The socket must have it's spinlock held when we get
> > * here.
> > *
> > @@ -1432,8 +1497,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
> > {
> > struct sock *rsk;
> > - if (is_meta_sk(sk))
> > - return mptcp_v4_do_rcv(sk, skb);
> > + BUG_ON(is_meta_sk(sk));
> > if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
> > struct dst_entry *dst = sk->sk_rx_dst;
> > @@ -1587,6 +1651,8 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
> > }
> > EXPORT_SYMBOL(tcp_prequeue);
> > +process_unclaimed tcp_process_unclaimed = NULL;
> > +
> > /*
> > * From tcp_input.c
> > */
> > @@ -1595,7 +1661,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
> > {
> > const struct iphdr *iph;
> > const struct tcphdr *th;
> > - struct sock *sk, *meta_sk = NULL;
> > + struct sock *sk = NULL;
> > int ret;
> > struct net *net = dev_net(skb->dev);
> > @@ -1636,10 +1702,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
> > TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
> > skb->len - th->doff * 4);
> > TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
> > -#ifdef CONFIG_MPTCP
> > - TCP_SKB_CB(skb)->mptcp_flags = 0;
> > - TCP_SKB_CB(skb)->dss_off = 0;
> > -#endif
> > +
> > TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
> > TCP_SKB_CB(skb)->tcp_tw_isn = 0;
> > TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
> > @@ -1662,15 +1725,6 @@ process:
> > if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
> > goto discard_and_relse;
> > -#ifdef CONFIG_MPTCP
> > - /* Is there a pending request sock for this segment ? */
> > - if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
> > - if (sk)
> > - sock_put(sk);
> > - return 0;
> > - }
> > -#endif
> > -
> > #ifdef CONFIG_TCP_MD5SIG
> > /*
> > * We really want to reject the packet as early as possible
> > @@ -1688,30 +1742,21 @@ process:
> > goto discard_and_relse;
> > sk_incoming_cpu_update(sk);
> > - skb->dev = NULL;
> > - if (mptcp(tcp_sk(sk))) {
> > - meta_sk = mptcp_meta_sk(sk);
> > -
> > - bh_lock_sock_nested(meta_sk);
> > - if (sock_owned_by_user(meta_sk))
> > - skb->sk = sk;
> > - } else {
> > - meta_sk = sk;
> > - bh_lock_sock_nested(sk);
> > - }
> > + /* Do I have to set skb->dev to null ? */
> > + bh_lock_sock_nested(sk);
> > ret = 0;
> > - if (!sock_owned_by_user(meta_sk)) {
> > - if (!tcp_prequeue(meta_sk, skb))
> > - ret = tcp_v4_do_rcv(sk, skb);
> > - } else if (unlikely(sk_add_backlog(meta_sk, skb,
> > - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> > - bh_unlock_sock(meta_sk);
> > + if (!sock_owned_by_user(sk)) {
> > + if (!sk->sk_prequeue(sk, skb))
> > + ret = sk->sk_backlog_rcv(sk, skb);
> > + } else if (unlikely(sk_add_backlog(sk, skb,
> > + sk->sk_rcvbuf + sk->sk_sndbuf))) {
> > + bh_unlock_sock(sk);
> > NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> > goto discard_and_relse;
> > }
> > - bh_unlock_sock(meta_sk);
> > + bh_unlock_sock(sk);
> > sock_put(sk);
> > @@ -1721,26 +1766,11 @@ no_tcp_socket:
> > if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
> > goto discard_it;
> > -#ifdef CONFIG_MPTCP
> > - if (!sk && th->syn && !th->ack) {
> > - int ret = mptcp_lookup_join(skb, NULL);
> > -
> > - if (ret < 0) {
> > - tcp_v4_send_reset(NULL, skb);
> > - goto discard_it;
> > - } else if (ret > 0) {
> > - return 0;
> > - }
> > + if (unlikely (tcp_process_unclaimed != NULL)) {
> > + if ((tcp_process_unclaimed)(NULL, skb))
> > + return (0);
> > }
> > - /* Is there a pending request sock for this segment ? */
> > - if (!sk && mptcp_check_req(skb, net)) {
> > - if (sk)
> > - sock_put(sk);
> > - return 0;
> > - }
> > -#endif
> > -
> > if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
> > csum_error:
> > TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
> > @@ -2506,6 +2536,7 @@ struct proto tcp_prot = {
> > .sendmsg = tcp_sendmsg,
> > .sendpage = tcp_sendpage,
> > .backlog_rcv = tcp_v4_do_rcv,
> > + .prequeue = tcp_prequeue,
> > .release_cb = tcp_release_cb,
> > .hash = inet_hash,
> > .unhash = inet_unhash,
> > diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> > index a635483..41b8be8 100644
> > --- a/net/ipv4/tcp_output.c
> > +++ b/net/ipv4/tcp_output.c
> > @@ -3413,6 +3413,7 @@ void tcp_send_delayed_ack(struct sock *sk)
> > void tcp_send_ack(struct sock *sk)
> > {
> > struct sk_buff *buff;
> > + struct tcp_sock *tp = tcp_sk(sk);
> > /* If we have been reset, we may not send again. */
> > if (sk->sk_state == TCP_CLOSE)
> > diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
> > index 8c4dd4a..1554217 100644
> > --- a/net/ipv6/af_inet6.c
> > +++ b/net/ipv6/af_inet6.c
> > @@ -193,6 +193,10 @@ lookup_protocol:
> > sk->sk_protocol = protocol;
> > sk->sk_backlog_rcv = answer->prot->backlog_rcv;
> > + sk->sk_prequeue = answer->prot->prequeue;
> > + if (sk->sk_prequeue == NULL) {
> > + sk->sk_prequeue = sk_prequeue;
> > + }
> > inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
> > np->hop_limit = -1;
> > diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> > index eba2436..d360128 100644
> > --- a/net/ipv6/tcp_ipv6.c
> > +++ b/net/ipv6/tcp_ipv6.c
> > @@ -1412,10 +1412,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
> > TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
> > skb->len - th->doff*4);
> > TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
> > -#ifdef CONFIG_MPTCP
> > - TCP_SKB_CB(skb)->mptcp_flags = 0;
> > - TCP_SKB_CB(skb)->dss_off = 0;
> > -#endif
> > TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
> > TCP_SKB_CB(skb)->tcp_tw_isn = 0;
> > TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
> > diff --git a/net/mptcp/mptcp_ctrl.c b/net/mptcp/mptcp_ctrl.c
> > index 28f348f..b1e780a 100644
> > --- a/net/mptcp/mptcp_ctrl.c
> > +++ b/net/mptcp/mptcp_ctrl.c
> > @@ -976,6 +976,20 @@ int mptcp_backlog_rcv(struct sock *meta_sk, struct sk_buff *skb)
> > struct sock *sk = skb->sk ? skb->sk : meta_sk;
> > int ret = 0;
> > + /* socket was owned by the user in mptcp_check_req()
> > + */
> > + if (sk == (struct sock *)0xFEE1DEAD) {
> > + bh_lock_sock_nested(meta_sk);
> > + if (skb->protocol == htons(ETH_P_IP))
> > + mptcp_v4_process_join_req(meta_sk, skb);
> > +#if IS_ENABLED(CONFIG_IPV6)
> > + else
> > + //mptcp_v6_process_join_req(meta_sk, skb);
> > +#endif /* CONFIG_IPV6 */
> > + bh_unlock_sock(meta_sk);
> > + return(0);
> > + }
> > +
> > skb->sk = NULL;
> > if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
> > @@ -1297,6 +1311,10 @@ int mptcp_add_sock(struct sock *meta_sk, struct sock *sk, u8 loc_id, u8 rem_id,
> > sk->sk_write_space = mptcp_write_space;
> > sk->sk_state_change = mptcp_set_state;
> > sk->sk_destruct = mptcp_sock_destruct;
> > + /* MPTCP takes a different path in tcp_v4_rcv
> > + * thus not impacting main tcp code */
> > + sk->sk_backlog_rcv = mptcp_v4_do_rcv;
> > + sk->sk_prequeue = sk_prequeue;
> > if (sk->sk_family == AF_INET)
> > mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d dst_addr:%pI4:%d, cnt_subflows now %d\n",
> > @@ -2658,6 +2676,9 @@ void __init mptcp_init(void)
> > if (mptcp_pm_v4_init())
> > goto mptcp_pm_v4_failed;
> > + if ((cmpxchg(&tcp_process_unclaimed, NULL, mptcp_v4_do_rcv)) != NULL)
> > + printk("tcp_process_unclaimed not NULL \n");
> > +
> > mptcp_sysctl = register_net_sysctl(&init_net, "net/mptcp", mptcp_table);
> > if (!mptcp_sysctl)
> > goto register_sysctl_failed;
> > diff --git a/net/mptcp/mptcp_input.c b/net/mptcp/mptcp_input.c
> > index 51cbb06..0e09ddf 100644
> > --- a/net/mptcp/mptcp_input.c
> > +++ b/net/mptcp/mptcp_input.c
> > @@ -323,9 +323,8 @@ static int mptcp_verif_dss_csum(struct sock *sk)
> > * by 4 bytes, as the high-order 64-bits will be added
> > * in the final csum_partial-call.
> > */
> > - u32 offset = skb_transport_offset(tmp) +
> > - TCP_SKB_CB(tmp)->dss_off;
> > - if (TCP_SKB_CB(tmp)->mptcp_flags & MPTCPHDR_SEQ64_SET)
> > + u32 offset = skb_transport_offset(tmp) + tmp->mptcp_dss_off;
> > + if (tmp->mptcp_flags & MPTCPHDR_SEQ64_SET)
> > offset += 4;
> > csum_tcp = skb_checksum(tmp, offset,
> > @@ -758,7 +757,7 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
> > }
> > /* Does the DSS had 64-bit seqnum's ? */
> > - if (!(tcb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
> > + if (!(skb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
> > /* Wrapped around? */
> > if (unlikely(after(data_seq, meta_tp->rcv_nxt) && data_seq < meta_tp->rcv_nxt)) {
> > tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, !mpcb->rcv_hiseq_index, data_seq);
> > @@ -767,9 +766,9 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
> > tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, mpcb->rcv_hiseq_index, data_seq);
> > }
> > } else {
> > - tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (tcb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
> > + tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (skb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
> > - if (unlikely(tcb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
> > + if (unlikely(skb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
> > /* We make sure that the data_seq is invalid.
> > * It will be dropped later.
> > */
> > @@ -1020,6 +1019,67 @@ next:
> > return data_queued ? -1 : -2;
> > }
> > +static struct sk_buff *
> > +mptcp_process_ack(struct sock *sk, struct sk_buff *skb)
> > +{
> > + struct tcp_sock *tp = tcp_sk(sk);
> > + int flag = 0;
> > +
> > + /*
> > + * TCP takes care of invalid ack's
> > + * they will never show up here.
> > + */
> > +
> > + /* Is this skb acknowleding anything data */
> > +
> > + if (tp->mptcp->snt_isn + 1 != TCP_SKB_CB(skb)->ack_seq) {
> > + flag = MPTCP_FLAG_DATA_ACKED;
> > + }
> > +
> > + if (mptcp_fallback_infinite(sk, flag)) {
> > + pr_err("%s resetting flow\n", __func__);
> > + mptcp_send_reset(sk);
> > + goto invalid_ack;
> > + }
> > +
> > + mptcp_clean_rtx_infinite(skb, sk);
> > +
> > + return (skb);
> > +invalid_ack:
> > + __skb_unlink(skb, &sk->sk_receive_queue);
> > + __kfree_skb(skb);
> > + return (NULL);
> > +
> > +}
> > +
> > +static struct sk_buff *
> > +mptcp_process_options_ack(struct sock *sk, struct sk_buff *skb)
> > +{
> > + struct tcp_sock *tp = tcp_sk(sk);
> > + const struct tcphdr *th = tcp_hdr(skb);
> > +
> > + skb->mptcp_flags = 0;
> > + skb->mptcp_dss_off = 0;
> > +
> > + tcp_parse_mptcp_options(skb, &tp->mptcp->rx_opt);
> > + if (mptcp_handle_options(sk, th, skb)) {
> > + mptcp_reset_mopt(tp);
> > + __skb_unlink(skb, &sk->sk_receive_queue);
> > + __kfree_skb(skb);
> > + skb = NULL;
> > + }
> > + if ((skb != NULL) && skb->len == 0) {
> > + skb = mptcp_process_ack(sk, skb);
> > + if (skb != NULL && skb->len == 0) {
> > + /* Pure ack */
> > + __skb_unlink(skb, &sk->sk_receive_queue);
> > + __kfree_skb(skb);
> > + skb = NULL;
> > + }
> > + }
> > + return (skb);
> > +}
> > +
> > void mptcp_data_ready(struct sock *sk)
> > {
> > struct sock *meta_sk = mptcp_meta_sk(sk);
> > @@ -1045,6 +1105,10 @@ restart:
> > */
> > skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
> > int ret;
> > +
> > + skb = mptcp_process_options_ack(sk, skb);
> > + if (skb == NULL)
> > + continue;
> > /* Pre-validation - e.g., early fallback */
> > ret = mptcp_prevalidate_skb(sk, skb);
> > if (ret < 0)
> > @@ -1108,13 +1172,11 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
> > if (!meta_sk)
> > return 0;
> > - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> > -
> > bh_lock_sock_nested(meta_sk);
> > if (sock_owned_by_user(meta_sk)) {
> > - skb->sk = meta_sk;
> > + skb->sk = (struct sock *)0xFEE1DEAD;
> > if (unlikely(sk_add_backlog(meta_sk, skb,
> > - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> > + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> > bh_unlock_sock(meta_sk);
> > NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> > sock_put(meta_sk); /* Taken by mptcp_search_req */
> > @@ -1122,10 +1184,14 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
> > return 1;
> > }
> > } else if (skb->protocol == htons(ETH_P_IP)) {
> > - tcp_v4_do_rcv(meta_sk, skb);
> > + /*
> > + * call old mptcp_v4_do_rcv
> > + */
> > + mptcp_v4_process_join_req(meta_sk, skb);
> > #if IS_ENABLED(CONFIG_IPV6)
> > } else { /* IPv6 */
> > - tcp_v6_do_rcv(meta_sk, skb);
> > + WARN_ON(1);
> > + //mptcp_v6_handle_join_req(meta_sk, skb);
> > #endif /* CONFIG_IPV6 */
> > }
> > bh_unlock_sock(meta_sk);
> > @@ -1222,7 +1288,7 @@ int mptcp_lookup_join(struct sk_buff *skb, struct inet_timewait_sock *tw)
> > inet_twsk_put(tw);
> > }
> > - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> > + skb->mptcp_flags |= MPTCPHDR_JOIN;
> > /* OK, this is a new syn/join, let's create a new open request and
> > * send syn+ack
> > */
> > @@ -1279,7 +1345,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
> > return -1;
> > }
> > - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> > + //TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> > /* OK, this is a new syn/join, let's create a new open request and
> > * send syn+ack
> > @@ -1303,7 +1369,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
> > }
> > if (sock_owned_by_user(meta_sk)) {
> > - skb->sk = meta_sk;
> > + skb->sk = (struct sock *)0xFEE1DEAD; //skb->sk = meta_sk;
> > if (unlikely(sk_add_backlog(meta_sk, skb,
> > meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf)))
> > NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> > @@ -1319,10 +1385,12 @@ int mptcp_do_join_short(struct sk_buff *skb,
> > */
> > skb_get(skb);
> > if (skb->protocol == htons(ETH_P_IP)) {
> > - tcp_v4_do_rcv(meta_sk, skb);
> > + //tcp_v4_do_rcv(meta_sk, skb);
> > + mptcp_v4_process_join_req(meta_sk, skb);
> > #if IS_ENABLED(CONFIG_IPV6)
> > } else { /* IPv6 */
> > - tcp_v6_do_rcv(meta_sk, skb);
> > + //mptcp_v6_process_join_req(meta_sk, skb);
> > + //tcp_v6_do_rcv(meta_sk, skb);
> > #endif /* CONFIG_IPV6 */
> > }
> > }
> > @@ -1461,7 +1529,6 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
> > {
> > struct sock *meta_sk = mptcp_meta_sk(sk);
> > struct tcp_sock *meta_tp = tcp_sk(meta_sk), *tp = tcp_sk(sk);
> > - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> > u32 prior_snd_una = meta_tp->snd_una;
> > int prior_packets;
> > u32 nwin, data_ack, data_seq;
> > @@ -1481,7 +1548,7 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
> > /* If we are in infinite mapping mode, rx_opt.data_ack has been
> > * set by mptcp_clean_rtx_infinite.
> > */
> > - if (!(tcb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
> > + if (!(skb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
> > goto exit;
> > data_ack = tp->mptcp->rx_opt.data_ack;
> > @@ -1647,10 +1714,11 @@ static inline bool is_valid_addropt_opsize(u8 mptcp_ver,
> > void mptcp_parse_options(const uint8_t *ptr, int opsize,
> > struct mptcp_options_received *mopt,
> > - const struct sk_buff *skb,
> > + struct sk_buff *skb,
> > struct tcp_sock *tp)
> > {
> > const struct mptcp_option *mp_opt = (struct mptcp_option *)ptr;
> > + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> > /* If the socket is mp-capable we would have a mopt. */
> > if (!mopt)
> > @@ -1757,7 +1825,7 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
> > ptr += 4;
> > if (mdss->A) {
> > - tcb->mptcp_flags |= MPTCPHDR_ACK;
> > + skb->mptcp_flags |= MPTCPHDR_ACK;
> > if (mdss->a) {
> > mopt->data_ack = (u32) get_unaligned_be64(ptr);
> > @@ -1768,13 +1836,13 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
> > }
> > }
> > - tcb->dss_off = (ptr - skb_transport_header(skb));
> > + skb->mptcp_dss_off = (ptr - skb_transport_header(skb));
> > if (mdss->M) {
> > if (mdss->m) {
> > u64 data_seq64 = get_unaligned_be64(ptr);
> > - tcb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
> > + skb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
> > mopt->data_seq = (u32) data_seq64;
> > ptr += 12; /* 64-bit dseq + subseq */
> > @@ -1784,15 +1852,16 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
> > }
> > mopt->data_len = get_unaligned_be16(ptr);
> > - tcb->mptcp_flags |= MPTCPHDR_SEQ;
> > + skb->mptcp_flags |= MPTCPHDR_SEQ;
> > /* Is a check-sum present? */
> > - if (opsize == mptcp_sub_len_dss(mdss, 1))
> > - tcb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
> > + if (opsize == mptcp_sub_len_dss(mdss, 1)) {
> > + skb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
> > + }
> > /* DATA_FIN only possible with DSS-mapping */
> > if (mdss->F)
> > - tcb->mptcp_flags |= MPTCPHDR_FIN;
> > + skb->mptcp_flags |= MPTCPHDR_FIN;
> > }
> > break;
> > @@ -1907,8 +1976,9 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
> > return;
> > if (opsize > length)
> > return; /* don't parse partial options */
> > - if (opcode == TCPOPT_MPTCP)
> > + if (opcode == TCPOPT_MPTCP) {
> > mptcp_parse_options(ptr - 2, opsize, mopt, skb, NULL);
> > + }
> > }
> > ptr += opsize - 2;
> > length -= opsize;
> > @@ -2168,6 +2238,8 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
> > struct tcp_sock *tp = tcp_sk(sk);
> > struct mptcp_options_received *mopt = &tp->mptcp->rx_opt;
> > + BUG_ON(sk == mptcp_meta_sk(sk));
> > +
> > if (tp->mpcb->infinite_mapping_rcv || tp->mpcb->infinite_mapping_snd)
> > return false;
> > @@ -2185,7 +2257,7 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
> > * receiver MUST close the subflow with a RST as it is considered broken.
> > */
> > if (mptcp_is_data_seq(skb) && tp->mpcb->dss_csum &&
> > - !(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
> > + !(skb->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
> > mptcp_send_reset(sk);
> > return true;
> > }
> > @@ -2330,6 +2402,7 @@ int mptcp_rcv_synsent_state_process(struct sock *sk, struct sock **skptr,
> > /* Set this flag in order to postpone data sending
> > * until the 4th ack arrives.
> > */
> > +printk("mptcp_rcv_synsent_state_process pre_established set \n");
> > tp->mptcp->pre_established = 1;
> > tp->mptcp->rcv_low_prio = tp->mptcp->rx_opt.low_prio;
> > diff --git a/net/mptcp/mptcp_ipv4.c b/net/mptcp/mptcp_ipv4.c
> > index a147b20..3e60ab5 100644
> > --- a/net/mptcp/mptcp_ipv4.c
> > +++ b/net/mptcp/mptcp_ipv4.c
> > @@ -180,45 +180,12 @@ static int mptcp_v4_join_request(struct sock *meta_sk, struct sk_buff *skb)
> > }
> > /* We only process join requests here. (either the SYN or the final ACK) */
> > -int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
> > +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb)
> > {
> > const struct mptcp_cb *mpcb = tcp_sk(meta_sk)->mpcb;
> > struct sock *child, *rsk = NULL;
> > int ret;
> > - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
> > - struct tcphdr *th = tcp_hdr(skb);
> > - const struct iphdr *iph = ip_hdr(skb);
> > - struct sock *sk;
> > -
> > - sk = inet_lookup_established(sock_net(meta_sk), &tcp_hashinfo,
> > - iph->saddr, th->source, iph->daddr,
> > - th->dest, inet_iif(skb));
> > -
> > - if (!sk) {
> > - kfree_skb(skb);
> > - return 0;
> > - }
> > - if (is_meta_sk(sk)) {
> > - WARN("%s Did not find a sub-sk - did found the meta!\n", __func__);
> > - kfree_skb(skb);
> > - sock_put(sk);
> > - return 0;
> > - }
> > -
> > - if (sk->sk_state == TCP_TIME_WAIT) {
> > - inet_twsk_put(inet_twsk(sk));
> > - kfree_skb(skb);
> > - return 0;
> > - }
> > -
> > - ret = tcp_v4_do_rcv(sk, skb);
> > - sock_put(sk);
> > -
> > - return ret;
> > - }
> > - TCP_SKB_CB(skb)->mptcp_flags = 0;
> > -
> > /* Has been removed from the tk-table. Thus, no new subflows.
> > *
> > * Check for close-state is necessary, because we may have been closed
> > diff --git a/net/mptcp/mptcp_ipv6.c b/net/mptcp/mptcp_ipv6.c
> > index 0de953d..1959d01 100644
> > --- a/net/mptcp/mptcp_ipv6.c
> > +++ b/net/mptcp/mptcp_ipv6.c
> > @@ -199,7 +199,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
> > struct sock *child, *rsk = NULL;
> > int ret;
> > - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
> > + if (!(skb->mptcp_flags & MPTCPHDR_JOIN)) {
> > struct tcphdr *th = tcp_hdr(skb);
> > const struct ipv6hdr *ip6h = ipv6_hdr(skb);
> > struct sock *sk;
> > @@ -232,7 +232,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
> > return ret;
> > }
> > - TCP_SKB_CB(skb)->mptcp_flags = 0;
> > + skb->mptcp_flags = 0;
> > /* Has been removed from the tk-table. Thus, no new subflows.
> > *
> > diff --git a/net/mptcp/mptcp_output.c b/net/mptcp/mptcp_output.c
> > index 691ef6f..e7d340d 100644
> > --- a/net/mptcp/mptcp_output.c
> > +++ b/net/mptcp/mptcp_output.c
> > @@ -59,39 +59,17 @@ EXPORT_SYMBOL(mptcp_sub_len_remove_addr_align);
> > */
> > static bool mptcp_reconstruct_mapping(struct sk_buff *skb)
> > {
> > - const struct mp_dss *mpdss = (struct mp_dss *)TCP_SKB_CB(skb)->dss;
> > - u32 *p32;
> > - u16 *p16;
> > -
> > if (!mptcp_is_data_seq(skb))
> > return false;
> > - if (!mpdss->M)
> > - return false;
> > -
> > - /* Move the pointer to the data-seq */
> > - p32 = (u32 *)mpdss;
> > - p32++;
> > - if (mpdss->A) {
> > - p32++;
> > - if (mpdss->a)
> > - p32++;
> > - }
> > -
> > - TCP_SKB_CB(skb)->seq = ntohl(*p32);
> > -
> > - /* Get the data_len to calculate the end_data_seq */
> > - p32++;
> > - p32++;
> > - p16 = (u16 *)p32;
> > - TCP_SKB_CB(skb)->end_seq = ntohs(*p16) + TCP_SKB_CB(skb)->seq;
> > + TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->mptcp_data_seq;
> > return true;
> > }
> > static bool mptcp_is_reinjected(const struct sk_buff *skb)
> > {
> > - return TCP_SKB_CB(skb)->mptcp_flags & MPTCP_REINJECT;
> > + return skb->mptcp_flags & MPTCP_REINJECT;
> > }
> > static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_buff *skb)
> > @@ -105,7 +83,7 @@ static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_bu
> > break;
> > if (TCP_SKB_CB(skb_it)->seq == TCP_SKB_CB(skb)->seq) {
> > - TCP_SKB_CB(skb)->path_mask = TCP_SKB_CB(skb_it)->path_mask;
> > + TCP_SKB_CB(skb)->mptcp_path_mask = TCP_SKB_CB(skb_it)->mptcp_path_mask;
> > break;
> > }
> > }
> > @@ -180,9 +158,9 @@ static void __mptcp_reinject_data(struct sk_buff *orig_skb, struct sock *meta_sk
> > }
> > /* Segment goes back to the MPTCP-layer. So, we need to zero the
> > - * path_mask/dss.
> > + * path_mask.
> > */
> > - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
> > + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
> > /* We need to find out the path-mask from the meta-write-queue
> > * to properly select a subflow.
> > @@ -272,14 +250,14 @@ void mptcp_reinject_data(struct sock *sk, int clone_it)
> > if (mptcp_is_reinjected(skb_it))
> > continue;
> > - tcb->mptcp_flags |= MPTCP_REINJECT;
> > + skb_it->mptcp_flags |= MPTCP_REINJECT;
> > __mptcp_reinject_data(skb_it, meta_sk, sk, clone_it);
> > }
> > skb_it = tcp_write_queue_tail(meta_sk);
> > /* If sk has sent the empty data-fin, we have to reinject it too. */
> > if (skb_it && mptcp_is_data_fin(skb_it) && skb_it->len == 0 &&
> > - TCP_SKB_CB(skb_it)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
> > + TCP_SKB_CB(skb_it)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
> > __mptcp_reinject_data(skb_it, meta_sk, NULL, 1);
> > }
> > @@ -319,25 +297,43 @@ combine:
> > }
> > }
> > -static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_buff *skb,
> > - __be32 *ptr)
> > +/*
> > + * RFC6824 states that once a particular subflow mapping has been sent
> > + * out it must never be changed. However, packets may be split while
> > + * they are in the retransmission queue (due to SACK or ACKs) and that
> > + * arguably means that we would change the mapping (e.g. it splits it,
> > + * our sends out a subset of the initial mapping).
> > + *
> > + * Furthermore, the skb checksum is not always preserved across splits
> > + * (e.g. mptcp_fragment) which would mean that we need to recompute
> > + * the DSS checksum in this case.
> > + *
> > + * To avoid this we save the initial DSS mapping which allows us to
> > + * send the same DSS mapping even for fragmented retransmits.
> > + */
> > +
> > +static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
> > + const struct sk_buff *skb, __be32 *ptr)
> > {
> > const struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> > - __be32 *start = ptr;
> > __u16 data_len;
> > - *ptr++ = htonl(tcb->seq); /* data_seq */
> > + *ptr++ = htonl(tcb->mptcp_data_seq); /* data_seq */
> > /* If it's a non-data DATA_FIN, we set subseq to 0 (draft v7) */
> > if (mptcp_is_data_fin(skb) && skb->len == 0)
> > *ptr++ = 0; /* subseq */
> > else
> > - *ptr++ = htonl(tp->write_seq - tp->mptcp->snt_isn); /* subseq */
> > + *ptr++ = htonl(tcb->seq - tp->mptcp->snt_isn); /* subseq */
> > - if (tcb->mptcp_flags & MPTCPHDR_INF)
> > + if (skb->mptcp_flags & MPTCPHDR_INF)
> > data_len = 0;
> > - else
> > + else {
> > data_len = tcb->end_seq - tcb->seq;
> > + /* mptcp_entail_skb adds one for FIN */
> > + if (tcb->tcp_flags & TCPHDR_FIN)
> > + data_len -= 1;
> > + }
> > if (tp->mpcb->dss_csum && data_len) {
> > __be16 *p16 = (__be16 *)ptr;
> > @@ -356,11 +352,11 @@ static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_bu
> > (TCPOPT_NOP));
> > }
> > - return ptr - start;
> > + return mptcp_dss_len/sizeof(*ptr);
> > }
> > -static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_buff *skb,
> > - __be32 *ptr)
> > +static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
> > + const struct sk_buff *skb, __be32 *ptr)
> > {
> > struct mp_dss *mdss = (struct mp_dss *)ptr;
> > __be32 *start = ptr;
> > @@ -377,54 +373,12 @@ static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_b
> > mdss->len = mptcp_sub_len_dss(mdss, tp->mpcb->dss_csum);
> > ptr++;
> > + /* data_ack */
> > *ptr++ = htonl(mptcp_meta_tp(tp)->rcv_nxt);
> > return ptr - start;
> > }
> > -/* RFC6824 states that once a particular subflow mapping has been sent
> > - * out it must never be changed. However, packets may be split while
> > - * they are in the retransmission queue (due to SACK or ACKs) and that
> > - * arguably means that we would change the mapping (e.g. it splits it,
> > - * our sends out a subset of the initial mapping).
> > - *
> > - * Furthermore, the skb checksum is not always preserved across splits
> > - * (e.g. mptcp_fragment) which would mean that we need to recompute
> > - * the DSS checksum in this case.
> > - *
> > - * To avoid this we save the initial DSS mapping which allows us to
> > - * send the same DSS mapping even for fragmented retransmits.
> > - */
> > -static void mptcp_save_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb)
> > -{
> > - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> > - __be32 *ptr = (__be32 *)tcb->dss;
> > -
> > - tcb->mptcp_flags |= MPTCPHDR_SEQ;
> > -
> > - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
> > - ptr += mptcp_write_dss_mapping(tp, skb, ptr);
> > -}
> > -
> > -/* Write the saved DSS mapping to the header */
> > -static int mptcp_write_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb,
> > - __be32 *ptr)
> > -{
> > - __be32 *start = ptr;
> > -
> > - memcpy(ptr, TCP_SKB_CB(skb)->dss, mptcp_dss_len);
> > -
> > - /* update the data_ack */
> > - start[1] = htonl(mptcp_meta_tp(tp)->rcv_nxt);
> > -
> > - /* dss is in a union with inet_skb_parm and
> > - * the IP layer expects zeroed IPCB fields.
> > - */
> > - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
> > -
> > - return mptcp_dss_len/sizeof(*ptr);
> > -}
> > -
> > static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
> > {
> > struct tcp_sock *tp = tcp_sk(sk);
> > @@ -434,7 +388,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
> > struct sk_buff *subskb = NULL;
> > if (!reinject)
> > - TCP_SKB_CB(skb)->mptcp_flags |= (mpcb->snd_hiseq_index ?
> > + skb->mptcp_flags |= (mpcb->snd_hiseq_index ?
> > MPTCPHDR_SEQ64_INDEX : 0);
> > subskb = pskb_copy_for_clone(skb, GFP_ATOMIC);
> > @@ -447,7 +401,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
> > */
> > tcp_skb_pcount_set(subskb, 0);
> > - TCP_SKB_CB(skb)->path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
> > + TCP_SKB_CB(skb)->mptcp_path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
> > if (!(sk->sk_route_caps & NETIF_F_ALL_CSUM) &&
> > skb->ip_summed == CHECKSUM_PARTIAL) {
> > @@ -463,13 +417,14 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
> > tp->mptcp->fully_established = 1;
> > tp->mpcb->infinite_mapping_snd = 1;
> > tp->mptcp->infinite_cutoff_seq = tp->write_seq;
> > - tcb->mptcp_flags |= MPTCPHDR_INF;
> > + skb->mptcp_flags |= MPTCPHDR_INF;
> > }
> > if (mptcp_is_data_fin(subskb))
> > mptcp_combine_dfin(subskb, meta_sk, sk);
> > - mptcp_save_dss_data_seq(tp, subskb);
> > + subskb->mptcp_flags |= MPTCPHDR_SEQ;
> > + tcb->mptcp_data_seq = tcb->seq;
> > tcb->seq = tp->write_seq;
> > @@ -536,10 +491,10 @@ static int mptcp_fragment(struct sock *meta_sk, struct sk_buff *skb, u32 len,
> > buff = skb->next;
> > - flags = TCP_SKB_CB(skb)->mptcp_flags;
> > - TCP_SKB_CB(skb)->mptcp_flags = flags & ~(MPTCPHDR_FIN);
> > - TCP_SKB_CB(buff)->mptcp_flags = flags;
> > - TCP_SKB_CB(buff)->path_mask = TCP_SKB_CB(skb)->path_mask;
> > + flags = skb->mptcp_flags;
> > + skb->mptcp_flags = flags & ~(MPTCPHDR_FIN);
> > + buff->mptcp_flags = flags;
> > + TCP_SKB_CB(buff)->mptcp_path_mask = TCP_SKB_CB(skb)->mptcp_path_mask;
> > /* If reinject == 1, the buff will be added to the reinject
> > * queue, which is currently not part of memory accounting. So
> > @@ -927,8 +882,9 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
> > * It does not make sense to check for the options, because when the
> > * segment gets sent, another subflow will be chosen.
> > */
> > - if (!skb && is_meta_sk(sk))
> > + if (!skb && is_meta_sk(sk)) {
> > return;
> > + }
> > /* In fallback mp_fail-mode, we have to repeat it until the fallback
> > * has been done by the sender
> > @@ -967,10 +923,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
> > if (unlikely(mpcb->infinite_mapping_snd) &&
> > ((mpcb->send_infinite_mapping && tcb &&
> > mptcp_is_data_seq(skb) &&
> > - !(tcb->mptcp_flags & MPTCPHDR_INF) &&
> > + !(skb->mptcp_flags & MPTCPHDR_INF) &&
> > !before(tcb->seq, tp->mptcp->infinite_cutoff_seq)) ||
> > - !mpcb->send_infinite_mapping))
> > + !mpcb->send_infinite_mapping)) {
> > return;
> > + }
> > if (unlikely(tp->mptcp->include_mpc)) {
> > opts->options |= OPTION_MPTCP;
> > @@ -995,9 +952,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
> > mpcb->mptcp_ver >= MPTCP_VERSION_1 && skb && !mptcp_is_data_seq(skb)) {
> > mpcb->pm_ops->addr_signal(sk, size, opts, skb);
> > - if (opts->add_addr_v6)
> > + if (opts->add_addr_v6) {
> > +
> > /* Skip subsequent options */
> > return;
> > + }
> > }
> > if (!tp->mptcp->include_mpc && !tp->mptcp->pre_established) {
> > @@ -1197,10 +1156,11 @@ void mptcp_options_write(__be32 *ptr, struct tcp_sock *tp,
> > }
> > if (OPTION_DATA_ACK & opts->mptcp_options) {
> > - if (!mptcp_is_data_seq(skb))
> > - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
> > - else
> > - ptr += mptcp_write_dss_data_seq(tp, skb, ptr);
> > + ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
> > + if (mptcp_is_data_seq(skb)) {
> > + ptr += mptcp_write_dss_mapping(tp, skb, ptr);
> > + }
> > + skb->dev = NULL;
> > }
> > if (unlikely(OPTION_MP_PRIO & opts->mptcp_options)) {
> > struct mp_prio *mpprio = (struct mp_prio *)ptr;
> > @@ -1233,7 +1193,7 @@ void mptcp_send_fin(struct sock *meta_sk)
> > mss_now = mptcp_current_mss(meta_sk);
> > if (tcp_send_head(meta_sk) != NULL) {
> > - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
> > + skb->mptcp_flags |= MPTCPHDR_FIN;
> > TCP_SKB_CB(skb)->end_seq++;
> > meta_tp->write_seq++;
> > } else {
> > @@ -1250,7 +1210,7 @@ void mptcp_send_fin(struct sock *meta_sk)
> > tcp_init_nondata_skb(skb, meta_tp->write_seq, TCPHDR_ACK);
> > TCP_SKB_CB(skb)->end_seq++;
> > - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
> > + skb->mptcp_flags |= MPTCPHDR_FIN;
> > tcp_queue_skb(meta_sk, skb);
> > }
> > __tcp_push_pending_frames(meta_sk, mss_now, TCP_NAGLE_OFF);
> > diff --git a/net/mptcp/mptcp_redundant.c b/net/mptcp/mptcp_redundant.c
> > index 8fa2dba..37a13f4 100644
> > --- a/net/mptcp/mptcp_redundant.c
> > +++ b/net/mptcp/mptcp_redundant.c
> > @@ -72,10 +72,10 @@ static bool redsched_use_subflow(struct sock *meta_sk,
> > if (!skb || !mptcp_is_available((struct sock *)tp, skb, false))
> > return false;
> > - if (TCP_SKB_CB(skb)->path_mask != 0)
> > + if (TCP_SKB_CB(skb)->mptcp_path_mask != 0)
> > return subflow_is_active(tp);
> > - if (TCP_SKB_CB(skb)->path_mask == 0) {
> > + if (TCP_SKB_CB(skb)->mptcp_path_mask == 0) {
> > if (active_valid_sks == -1)
> > active_valid_sks = redsched_get_active_valid_sks(meta_sk);
> > @@ -209,7 +209,7 @@ static struct sk_buff *redundant_next_segment(struct sock *meta_sk,
> > cb_data->next_subflow = tp->mptcp->next;
> > *subsk = (struct sock *)tp;
> > - if (TCP_SKB_CB(skb)->path_mask)
> > + if (TCP_SKB_CB(skb)->mptcp_path_mask)
> > *reinject = -1;
> > return skb;
> > }
> > diff --git a/net/mptcp/mptcp_rr.c b/net/mptcp/mptcp_rr.c
> > index 8910ba9..83837f2 100644
> > --- a/net/mptcp/mptcp_rr.c
> > +++ b/net/mptcp/mptcp_rr.c
> > @@ -93,7 +93,7 @@ static int mptcp_rr_dont_reinject_skb(const struct tcp_sock *tp, const struct sk
> > */
> > return skb &&
> > /* Has the skb already been enqueued into this subsocket? */
> > - mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
> > + mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
> > }
> > /* We just look for any subflow that is available */
> > @@ -136,7 +136,7 @@ static struct sock *rr_get_available_subflow(struct sock *meta_sk,
> > * chance again by restarting its pathmask.
> > */
> > if (skb)
> > - TCP_SKB_CB(skb)->path_mask = 0;
> > + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
> > sk = backupsk;
> > }
> > diff --git a/net/mptcp/mptcp_sched.c b/net/mptcp/mptcp_sched.c
> > index 54408ff..5cbbf91 100644
> > --- a/net/mptcp/mptcp_sched.c
> > +++ b/net/mptcp/mptcp_sched.c
> > @@ -118,7 +118,7 @@ static int mptcp_dont_reinject_skb(const struct tcp_sock *tp, const struct sk_bu
> > */
> > return skb &&
> > /* Has the skb already been enqueued into this subsocket? */
> > - mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
> > + mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
> > }
> > bool subflow_is_backup(const struct tcp_sock *tp)
> > @@ -261,7 +261,7 @@ struct sock *get_available_subflow(struct sock *meta_sk, struct sk_buff *skb,
> > * the skb passed through all the available active and backups
> > * sks, so clean the path mask
> > */
> > - TCP_SKB_CB(skb)->path_mask = 0;
> > + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
> > return sk;
> > }
> > EXPORT_SYMBOL_GPL(get_available_subflow);
> > @@ -298,7 +298,7 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
> > /* Half the cwnd of the slow flow */
> > mptcp_for_each_tp(tp->mpcb, tp_it) {
> > if (tp_it != tp &&
> > - TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> > + TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> > if (tp->srtt_us < tp_it->srtt_us && inet_csk((struct sock *)tp_it)->icsk_ca_state == TCP_CA_Open) {
> > u32 prior_cwnd = tp_it->snd_cwnd;
> > @@ -317,11 +317,11 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
> > retrans:
> > /* Segment not yet injected into this path? Take it!!! */
> > - if (!(TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
> > + if (!(TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
> > bool do_retrans = false;
> > mptcp_for_each_tp(tp->mpcb, tp_it) {
> > if (tp_it != tp &&
> > - TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> > + TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> > if (tp_it->snd_cwnd <= 4) {
> > do_retrans = true;
> > break;
>
> _______________________________________________
> mptcp mailing list
> mptcp(a)lists.01.org
> https://lists.01.org/mailman/listinfo/mptcp
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code.
@ 2017-06-26 22:34 Rao Shoaib
0 siblings, 0 replies; 14+ messages in thread
From: Rao Shoaib @ 2017-06-26 22:34 UTC (permalink / raw)
To: mptcp
[-- Attachment #1: Type: text/plain, Size: 53904 bytes --]
I forgot to mention two things
1) Connection setup still has checks for MPTCP, Ideally these should be
removed but at least we need to run some benchmarks and fix any issues.
The mainstream folks will not accept any performance degradation in TCP.
I can look into this next.
2) The code overloads dev field of skb, when it is not being used. IIRC
there is precedence for this already. I will try to find it.
Rao
On 06/26/2017 02:13 PM, Rao Shoaib wrote:
> This patch returns tcp_skb_cb to it's original size. It also refactors MPTCP code so that there are no MPTCP checks in the main Rx pathi, no performance overheads such as cpu prodiction issues. tcp_v4_rcv() and tcp_v4_do_rcv() do not have any MPTCP specific checks any more, niether does tcp_ack(). On the Rx path MPTCP options are not parsed till the data is being pushed up to the meta socket (mptcp_data_ready). on the Tx side there is one check to add MPTCP specific options but that's it, that should not be that bad as for regular TCP it is a simple check, but it would be good to remove it..
>
> I have tested the changes with ndiffports set to 2, so join works. I have also tested accessing multipath-tcp.org and downloading files from there and also ran the speed test.
>
> The Bad:
>
> The error cases still have MPTCP checks but that should be OK as they are error cases. I had to use a special marker 0xFEE1DEAD for indicate a special case. I had to introdue a new socket specfic function. IPv6 has not been changed yet. I am sure I have missed some corner cases and more testing will reveal more issues but we just have to fix them.
>
> I would like to hear comments from the list and if this direction seems reasonable we can take this as the starting point, port it to latest Linux and share the design with the mainstream folks.
>
> Signed-off-by: Rao Shoaib <rao.shoaib(a)oracle.com>
> ---
> include/linux/skbuff.h | 8 ++-
> include/net/mptcp.h | 21 +++---
> include/net/mptcp_v4.h | 1 +
> include/net/sock.h | 12 +++-
> include/net/tcp.h | 23 +++----
> net/ipv4/af_inet.c | 4 ++
> net/ipv4/tcp_input.c | 37 ++--------
> net/ipv4/tcp_ipv4.c | 135 +++++++++++++++++++++++--------------
> net/ipv4/tcp_output.c | 1 +
> net/ipv6/af_inet6.c | 4 ++
> net/ipv6/tcp_ipv6.c | 4 --
> net/mptcp/mptcp_ctrl.c | 21 ++++++
> net/mptcp/mptcp_input.c | 131 ++++++++++++++++++++++++++++--------
> net/mptcp/mptcp_ipv4.c | 35 +---------
> net/mptcp/mptcp_ipv6.c | 4 +-
> net/mptcp/mptcp_output.c | 160 +++++++++++++++++---------------------------
> net/mptcp/mptcp_redundant.c | 6 +-
> net/mptcp/mptcp_rr.c | 4 +-
> net/mptcp/mptcp_sched.c | 10 +--
> 19 files changed, 335 insertions(+), 286 deletions(-)
>
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index f66cd5e..348cbc1 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -532,7 +532,13 @@ struct sk_buff {
> struct rb_node rbnode; /* used in netem & tcp stack */
> };
> struct sock *sk;
> - struct net_device *dev;
> + union {
> + struct net_device *dev;
> + struct {
> + __u8 mptcp_flags;
> + __u8 mptcp_dss_off;
> + };
> + };
>
> /*
> * This is the control buffer. It is free to use for every
> diff --git a/include/net/mptcp.h b/include/net/mptcp.h
> index 876f1e6..d087cb4 100644
> --- a/include/net/mptcp.h
> +++ b/include/net/mptcp.h
> @@ -807,7 +807,7 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
> struct mptcp_options_received *mopt);
> void mptcp_parse_options(const uint8_t *ptr, int opsize,
> struct mptcp_options_received *mopt,
> - const struct sk_buff *skb,
> + struct sk_buff *skb,
> struct tcp_sock *tp);
> void mptcp_syn_options(const struct sock *sk, struct tcp_out_options *opts,
> unsigned *remaining);
> @@ -998,14 +998,15 @@ static inline void mptcp_sub_force_close_all(struct mptcp_cb *mpcb,
> }
> }
>
> +/* currently tp is being used for Rx packets */
> static inline bool mptcp_is_data_seq(const struct sk_buff *skb)
> {
> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ;
> + return skb->mptcp_flags & MPTCPHDR_SEQ;
> }
>
> static inline bool mptcp_is_data_fin(const struct sk_buff *skb)
> {
> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_FIN;
> + return skb->mptcp_flags & MPTCPHDR_FIN;
> }
>
> /* Is it a data-fin while in infinite mapping mode?
> @@ -1034,17 +1035,17 @@ static inline u8 mptcp_get_64_bit(u64 data_seq, struct mptcp_cb *mpcb)
> /* Sets the data_seq and returns pointer to the in-skb field of the data_seq.
> * If the packet has a 64-bit dseq, the pointer points to the last 32 bits.
> */
> -static inline __u32 *mptcp_skb_set_data_seq(const struct sk_buff *skb,
> +static inline __u32 *mptcp_skb_set_data_seq(struct sk_buff *skb,
> u32 *data_seq,
> struct mptcp_cb *mpcb)
> {
> - __u32 *ptr = (__u32 *)(skb_transport_header(skb) + TCP_SKB_CB(skb)->dss_off);
> + __u32 *ptr = (__u32 *)(skb_transport_header(skb) + skb->mptcp_dss_off);
>
> - if (TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_SEQ64_SET) {
> + if (skb->mptcp_flags & MPTCPHDR_SEQ64_SET) {
> u64 data_seq64 = get_unaligned_be64(ptr);
>
> if (mpcb)
> - TCP_SKB_CB(skb)->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
> + skb->mptcp_flags |= mptcp_get_64_bit(data_seq64, mpcb);
>
> *data_seq = (u32)data_seq64;
> ptr++;
> @@ -1142,7 +1143,7 @@ static inline void mptcp_reset_mopt(struct tcp_sock *tp)
> static inline __be32 mptcp_get_highorder_sndbits(const struct sk_buff *skb,
> const struct mptcp_cb *mpcb)
> {
> - return htonl(mpcb->snd_high_order[(TCP_SKB_CB(skb)->mptcp_flags &
> + return htonl(mpcb->snd_high_order[(skb->mptcp_flags &
> MPTCPHDR_SEQ64_INDEX) ? 1 : 0]);
> }
>
> @@ -1404,8 +1405,8 @@ static inline void mptcp_set_rto(const struct sock *sk) {}
> static inline void mptcp_send_fin(const struct sock *meta_sk) {}
> static inline void mptcp_parse_options(const uint8_t *ptr, const int opsize,
> struct mptcp_options_received *mopt,
> - const struct sk_buff *skb,
> - const struct tcp_sock *tp) {}
> + struct sk_buff *skb,
> + struct tcp_sock *tp) {}
> static inline void mptcp_syn_options(const struct sock *sk,
> struct tcp_out_options *opts,
> unsigned *remaining) {}
> diff --git a/include/net/mptcp_v4.h b/include/net/mptcp_v4.h
> index c83dca0..46394a4 100644
> --- a/include/net/mptcp_v4.h
> +++ b/include/net/mptcp_v4.h
> @@ -45,6 +45,7 @@ extern struct tcp_request_sock_ops mptcp_join_request_sock_ipv4_ops;
> #ifdef CONFIG_MPTCP
>
> int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb);
> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb);
> struct sock *mptcp_v4_search_req(const __be16 rport, const __be32 raddr,
> const __be32 laddr, const struct net *net);
> int mptcp_init4_subsockets(struct sock *meta_sk, const struct mptcp_loc4 *loc,
> diff --git a/include/net/sock.h b/include/net/sock.h
> index 0f12593..0d1bda5 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -296,6 +296,7 @@ struct cg_proto;
> * @sk_write_space: callback to indicate there is bf sending space available
> * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
> * @sk_backlog_rcv: callback to process the backlog
> + * @sk_prequeue: callback to prequeue
> * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
> */
> struct sock {
> @@ -437,7 +438,9 @@ struct sock {
> void (*sk_write_space)(struct sock *sk);
> void (*sk_error_report)(struct sock *sk);
> int (*sk_backlog_rcv)(struct sock *sk,
> - struct sk_buff *skb);
> + struct sk_buff *skb);
> + bool (*sk_prequeue)(struct sock *sk,
> + struct sk_buff *skb);
> void (*sk_destruct)(struct sock *sk);
> };
>
> @@ -853,6 +856,11 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
> return sk->sk_backlog_rcv(sk, skb);
> }
>
> +static inline bool sk_prequeue(struct sock *sk, struct sk_buff *skb)
> +{
> + return (false);
> +}
> +
> static inline void sk_incoming_cpu_update(struct sock *sk)
> {
> sk->sk_incoming_cpu = raw_smp_processor_id();
> @@ -993,6 +1001,8 @@ struct proto {
>
> int (*backlog_rcv) (struct sock *sk,
> struct sk_buff *skb);
> + bool (*prequeue) (struct sock *sk,
> + struct sk_buff *skb);
>
> void (*release_cb)(struct sock *sk);
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 655ecd4..cbe8ef2 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -47,6 +47,9 @@
> #include <linux/seq_file.h>
> #include <linux/memcontrol.h>
>
> +typedef int (* process_unclaimed)(struct sock *sk, struct sk_buff *skb);
> +extern process_unclaimed tcp_process_unclaimed;
> +
> extern struct inet_hashinfo tcp_hashinfo;
>
> extern struct percpu_counter tcp_orphan_count;
> @@ -581,6 +584,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
> struct request_sock *req,
> struct dst_entry *dst);
> int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
> +
> int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
> int tcp_connect(struct sock *sk);
> struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
> @@ -842,11 +846,6 @@ struct tcp_skb_cb {
> __u32 tcp_gso_segs;
> };
>
> -#ifdef CONFIG_MPTCP
> - __u8 mptcp_flags; /* flags for the MPTCP layer */
> - __u8 dss_off; /* Number of 4-byte words until
> - * seq-number */
> -#endif
> __u8 tcp_flags; /* TCP header flags. (tcp[13]) */
>
> __u8 sacked; /* State flags for SACK/FACK. */
> @@ -859,9 +858,13 @@ struct tcp_skb_cb {
> #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
> TCPCB_REPAIRED)
>
> - __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
> + __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */
> /* 1 byte hole */
> - __u32 ack_seq; /* Sequence number ACK'd */
> + union {
> + __u32 ack_seq; /* Sequence number ACK'd */
> + __u32 mptcp_data_seq;
> + __u32 mptcp_path_mask;
> + };
> union {
> union {
> struct inet_skb_parm h4;
> @@ -869,12 +872,6 @@ struct tcp_skb_cb {
> struct inet6_skb_parm h6;
> #endif
> } header; /* For incoming frames */
> -#ifdef CONFIG_MPTCP
> - union { /* For MPTCP outgoing frames */
> - __u32 path_mask; /* paths that tried to send this skb */
> - __u32 dss[6]; /* DSS options */
> - };
> -#endif
> };
> };
>
> diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
> index 73480b9..1e7827f 100644
> --- a/net/ipv4/af_inet.c
> +++ b/net/ipv4/af_inet.c
> @@ -356,6 +356,10 @@ lookup_protocol:
> sk->sk_destruct = inet_sock_destruct;
> sk->sk_protocol = protocol;
> sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
> + sk->sk_prequeue = sk->sk_prot->prequeue;
> + if (sk->sk_prequeue == NULL) {
> + sk->sk_prequeue = sk_prequeue;
> + }
>
> inet->uc_ttl = -1;
> inet->mc_loop = 1;
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index 16a7256..cb6bbf9 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -3133,8 +3133,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
> */
> if (likely(!(scb->tcp_flags & TCPHDR_SYN))) {
> flag |= FLAG_DATA_ACKED;
> - if (mptcp(tp) && mptcp_is_data_seq(skb))
> - flag |= MPTCP_FLAG_DATA_ACKED;
> } else {
> flag |= FLAG_SYN_ACKED;
> tp->retrans_stamp = 0;
> @@ -3582,16 +3580,6 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
> sack_rtt_us);
> acked -= tp->packets_out;
>
> - if (mptcp(tp)) {
> - if (mptcp_fallback_infinite(sk, flag)) {
> - pr_err("%s resetting flow\n", __func__);
> - mptcp_send_reset(sk);
> - goto invalid_ack;
> - }
> -
> - mptcp_clean_rtx_infinite(skb, sk);
> - }
> -
> /* Advance cwnd if state allows */
> if (tcp_may_raise_cwnd(sk, flag))
> tcp_cong_avoid(sk, ack, acked);
> @@ -3824,8 +3812,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
> if (tcp_parse_aligned_timestamp(tp, th))
> return true;
> }
> - tcp_parse_options(skb, &tp->rx_opt,
> - mptcp(tp) ? &tp->mptcp->rx_opt : NULL, 1, NULL, tp);
> + tcp_parse_options(skb, &tp->rx_opt, NULL, 1, NULL, tp);
> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>
> @@ -4550,11 +4537,12 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
> int eaten = -1;
> bool fragstolen = false;
>
> - /* If no data is present, but a data_fin is in the options, we still
> - * have to call mptcp_queue_skb later on. */
> - if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq &&
> - !(mptcp(tp) && mptcp_is_data_fin(skb)))
> + /*
> + * send every packet to MPTCP
> + */
> + if (!mptcp(tp) && (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)) {
> goto drop;
> + }
>
> skb_dst_drop(skb);
> __skb_pull(skb, tcp_hdr(skb)->doff * 4);
> @@ -5242,15 +5230,9 @@ syn_challenge:
> goto discard;
> }
>
> - /* If valid: post process the received MPTCP options. */
> - if (mptcp(tp) && mptcp_handle_options(sk, th, skb))
> - goto discard;
> -
> return true;
>
> discard:
> - if (mptcp(tp))
> - mptcp_reset_mopt(tp);
> __kfree_skb(skb);
> return false;
> }
> @@ -5302,10 +5284,6 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
>
> tp->rx_opt.saw_tstamp = 0;
>
> - /* MPTCP: force slowpath. */
> - if (mptcp(tp))
> - goto slow_path;
> -
> /* pred_flags is 0xS?10 << 16 + snd_wnd
> * if header_prediction is to be made
> * 'S' will always be tp->tcp_header_len >> 2
> @@ -5585,8 +5563,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
> struct mptcp_options_received mopt;
> mptcp_init_mp_opt(&mopt);
>
> - tcp_parse_options(skb, &tp->rx_opt,
> - mptcp(tp) ? &tp->mptcp->rx_opt : &mopt, 0, &foc, tp);
> + tcp_parse_options(skb, &tp->rx_opt, &mopt, 0, &foc, tp);
> if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
> tp->rx_opt.rcv_tsecr -= tp->tsoffset;
>
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index 6967a86..3329679 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -1420,6 +1420,71 @@ struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
> return sk;
> }
>
> +int mptcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
> +{
> + struct net *net = dev_net(skb->dev);
> + const struct tcphdr *th = tcp_hdr(skb);
> + int ret;
> + struct sock *meta_sk;
> +
> + if (sk == NULL) {
> + if (th->syn && !th->ack) {
> + int ret = mptcp_lookup_join(skb, NULL);
> +
> + if (ret < 0) {
> + tcp_v4_send_reset(NULL, skb);
> + kfree_skb(skb);
> + return (1);
> + } else if (ret > 0) {
> + return (1);
> + }
> + }
> + /* Is there a pending request sock for this segment ? */
> + if (mptcp_check_req(skb, net)) {
> + return(1);
> + }
> + return (0);
> + }
> +
> + /* The socket passed in should never be the meta socket */
> +
> + BUG_ON(is_meta_sk(sk));
> +
> + /* Is there a pending request sock for this segment ? */
> + if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
> + return 0;
> + }
> +
> + skb->dev = NULL;
> + meta_sk = mptcp_meta_sk(sk);
> +
> + ret = 0;
> + skb->sk = sk;
> + bh_lock_sock_nested(meta_sk);
> + if (sock_owned_by_user(meta_sk)) {
> + if (unlikely(sk_add_backlog(meta_sk, skb,
> + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> +
> + NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> + kfree_skb(skb);
> + }
> + } else {
> +
> + if (is_meta_sk(sk)) {
> + ret = mptcp_v4_process_join_req(sk, skb);
> + goto done;
> + }
> + if (!meta_sk->sk_prequeue(meta_sk, skb)) {
> + skb->sk = NULL;
> + ret = tcp_v4_do_rcv(sk, skb);
> + }
> +
> + }
> +done:
> + bh_unlock_sock(meta_sk);
> + return (ret);
> +}
> +
> /* The socket must have it's spinlock held when we get
> * here.
> *
> @@ -1432,8 +1497,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
> {
> struct sock *rsk;
>
> - if (is_meta_sk(sk))
> - return mptcp_v4_do_rcv(sk, skb);
> + BUG_ON(is_meta_sk(sk));
>
> if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
> struct dst_entry *dst = sk->sk_rx_dst;
> @@ -1587,6 +1651,8 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
> }
> EXPORT_SYMBOL(tcp_prequeue);
>
> +process_unclaimed tcp_process_unclaimed = NULL;
> +
> /*
> * From tcp_input.c
> */
> @@ -1595,7 +1661,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
> {
> const struct iphdr *iph;
> const struct tcphdr *th;
> - struct sock *sk, *meta_sk = NULL;
> + struct sock *sk = NULL;
> int ret;
> struct net *net = dev_net(skb->dev);
>
> @@ -1636,10 +1702,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
> skb->len - th->doff * 4);
> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
> -#ifdef CONFIG_MPTCP
> - TCP_SKB_CB(skb)->mptcp_flags = 0;
> - TCP_SKB_CB(skb)->dss_off = 0;
> -#endif
> +
> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
> TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
> @@ -1662,15 +1725,6 @@ process:
> if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
> goto discard_and_relse;
>
> -#ifdef CONFIG_MPTCP
> - /* Is there a pending request sock for this segment ? */
> - if (sk->sk_state == TCP_LISTEN && mptcp_check_req(skb, net)) {
> - if (sk)
> - sock_put(sk);
> - return 0;
> - }
> -#endif
> -
> #ifdef CONFIG_TCP_MD5SIG
> /*
> * We really want to reject the packet as early as possible
> @@ -1688,30 +1742,21 @@ process:
> goto discard_and_relse;
>
> sk_incoming_cpu_update(sk);
> - skb->dev = NULL;
>
> - if (mptcp(tcp_sk(sk))) {
> - meta_sk = mptcp_meta_sk(sk);
> -
> - bh_lock_sock_nested(meta_sk);
> - if (sock_owned_by_user(meta_sk))
> - skb->sk = sk;
> - } else {
> - meta_sk = sk;
> - bh_lock_sock_nested(sk);
> - }
> + /* Do I have to set skb->dev to null ? */
> + bh_lock_sock_nested(sk);
>
> ret = 0;
> - if (!sock_owned_by_user(meta_sk)) {
> - if (!tcp_prequeue(meta_sk, skb))
> - ret = tcp_v4_do_rcv(sk, skb);
> - } else if (unlikely(sk_add_backlog(meta_sk, skb,
> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> - bh_unlock_sock(meta_sk);
> + if (!sock_owned_by_user(sk)) {
> + if (!sk->sk_prequeue(sk, skb))
> + ret = sk->sk_backlog_rcv(sk, skb);
> + } else if (unlikely(sk_add_backlog(sk, skb,
> + sk->sk_rcvbuf + sk->sk_sndbuf))) {
> + bh_unlock_sock(sk);
> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> goto discard_and_relse;
> }
> - bh_unlock_sock(meta_sk);
> + bh_unlock_sock(sk);
>
> sock_put(sk);
>
> @@ -1721,26 +1766,11 @@ no_tcp_socket:
> if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
> goto discard_it;
>
> -#ifdef CONFIG_MPTCP
> - if (!sk && th->syn && !th->ack) {
> - int ret = mptcp_lookup_join(skb, NULL);
> -
> - if (ret < 0) {
> - tcp_v4_send_reset(NULL, skb);
> - goto discard_it;
> - } else if (ret > 0) {
> - return 0;
> - }
> + if (unlikely (tcp_process_unclaimed != NULL)) {
> + if ((tcp_process_unclaimed)(NULL, skb))
> + return (0);
> }
>
> - /* Is there a pending request sock for this segment ? */
> - if (!sk && mptcp_check_req(skb, net)) {
> - if (sk)
> - sock_put(sk);
> - return 0;
> - }
> -#endif
> -
> if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
> csum_error:
> TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
> @@ -2506,6 +2536,7 @@ struct proto tcp_prot = {
> .sendmsg = tcp_sendmsg,
> .sendpage = tcp_sendpage,
> .backlog_rcv = tcp_v4_do_rcv,
> + .prequeue = tcp_prequeue,
> .release_cb = tcp_release_cb,
> .hash = inet_hash,
> .unhash = inet_unhash,
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index a635483..41b8be8 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -3413,6 +3413,7 @@ void tcp_send_delayed_ack(struct sock *sk)
> void tcp_send_ack(struct sock *sk)
> {
> struct sk_buff *buff;
> + struct tcp_sock *tp = tcp_sk(sk);
>
> /* If we have been reset, we may not send again. */
> if (sk->sk_state == TCP_CLOSE)
> diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
> index 8c4dd4a..1554217 100644
> --- a/net/ipv6/af_inet6.c
> +++ b/net/ipv6/af_inet6.c
> @@ -193,6 +193,10 @@ lookup_protocol:
> sk->sk_protocol = protocol;
>
> sk->sk_backlog_rcv = answer->prot->backlog_rcv;
> + sk->sk_prequeue = answer->prot->prequeue;
> + if (sk->sk_prequeue == NULL) {
> + sk->sk_prequeue = sk_prequeue;
> + }
>
> inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk);
> np->hop_limit = -1;
> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> index eba2436..d360128 100644
> --- a/net/ipv6/tcp_ipv6.c
> +++ b/net/ipv6/tcp_ipv6.c
> @@ -1412,10 +1412,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
> TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
> skb->len - th->doff*4);
> TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
> -#ifdef CONFIG_MPTCP
> - TCP_SKB_CB(skb)->mptcp_flags = 0;
> - TCP_SKB_CB(skb)->dss_off = 0;
> -#endif
> TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
> TCP_SKB_CB(skb)->tcp_tw_isn = 0;
> TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
> diff --git a/net/mptcp/mptcp_ctrl.c b/net/mptcp/mptcp_ctrl.c
> index 28f348f..b1e780a 100644
> --- a/net/mptcp/mptcp_ctrl.c
> +++ b/net/mptcp/mptcp_ctrl.c
> @@ -976,6 +976,20 @@ int mptcp_backlog_rcv(struct sock *meta_sk, struct sk_buff *skb)
> struct sock *sk = skb->sk ? skb->sk : meta_sk;
> int ret = 0;
>
> + /* socket was owned by the user in mptcp_check_req()
> + */
> + if (sk == (struct sock *)0xFEE1DEAD) {
> + bh_lock_sock_nested(meta_sk);
> + if (skb->protocol == htons(ETH_P_IP))
> + mptcp_v4_process_join_req(meta_sk, skb);
> +#if IS_ENABLED(CONFIG_IPV6)
> + else
> + //mptcp_v6_process_join_req(meta_sk, skb);
> +#endif /* CONFIG_IPV6 */
> + bh_unlock_sock(meta_sk);
> + return(0);
> + }
> +
> skb->sk = NULL;
>
> if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
> @@ -1297,6 +1311,10 @@ int mptcp_add_sock(struct sock *meta_sk, struct sock *sk, u8 loc_id, u8 rem_id,
> sk->sk_write_space = mptcp_write_space;
> sk->sk_state_change = mptcp_set_state;
> sk->sk_destruct = mptcp_sock_destruct;
> + /* MPTCP takes a different path in tcp_v4_rcv
> + * thus not impacting main tcp code */
> + sk->sk_backlog_rcv = mptcp_v4_do_rcv;
> + sk->sk_prequeue = sk_prequeue;
>
> if (sk->sk_family == AF_INET)
> mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d dst_addr:%pI4:%d, cnt_subflows now %d\n",
> @@ -2658,6 +2676,9 @@ void __init mptcp_init(void)
> if (mptcp_pm_v4_init())
> goto mptcp_pm_v4_failed;
>
> + if ((cmpxchg(&tcp_process_unclaimed, NULL, mptcp_v4_do_rcv)) != NULL)
> + printk("tcp_process_unclaimed not NULL \n");
> +
> mptcp_sysctl = register_net_sysctl(&init_net, "net/mptcp", mptcp_table);
> if (!mptcp_sysctl)
> goto register_sysctl_failed;
> diff --git a/net/mptcp/mptcp_input.c b/net/mptcp/mptcp_input.c
> index 51cbb06..0e09ddf 100644
> --- a/net/mptcp/mptcp_input.c
> +++ b/net/mptcp/mptcp_input.c
> @@ -323,9 +323,8 @@ static int mptcp_verif_dss_csum(struct sock *sk)
> * by 4 bytes, as the high-order 64-bits will be added
> * in the final csum_partial-call.
> */
> - u32 offset = skb_transport_offset(tmp) +
> - TCP_SKB_CB(tmp)->dss_off;
> - if (TCP_SKB_CB(tmp)->mptcp_flags & MPTCPHDR_SEQ64_SET)
> + u32 offset = skb_transport_offset(tmp) + tmp->mptcp_dss_off;
> + if (tmp->mptcp_flags & MPTCPHDR_SEQ64_SET)
> offset += 4;
>
> csum_tcp = skb_checksum(tmp, offset,
> @@ -758,7 +757,7 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
> }
>
> /* Does the DSS had 64-bit seqnum's ? */
> - if (!(tcb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
> + if (!(skb->mptcp_flags & MPTCPHDR_SEQ64_SET)) {
> /* Wrapped around? */
> if (unlikely(after(data_seq, meta_tp->rcv_nxt) && data_seq < meta_tp->rcv_nxt)) {
> tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, !mpcb->rcv_hiseq_index, data_seq);
> @@ -767,9 +766,9 @@ static int mptcp_detect_mapping(struct sock *sk, struct sk_buff *skb)
> tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, mpcb->rcv_hiseq_index, data_seq);
> }
> } else {
> - tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (tcb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
> + tp->mptcp->map_data_seq = mptcp_get_data_seq_64(mpcb, (skb->mptcp_flags & MPTCPHDR_SEQ64_INDEX) ? 1 : 0, data_seq);
>
> - if (unlikely(tcb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
> + if (unlikely(skb->mptcp_flags & MPTCPHDR_SEQ64_OFO)) {
> /* We make sure that the data_seq is invalid.
> * It will be dropped later.
> */
> @@ -1020,6 +1019,67 @@ next:
> return data_queued ? -1 : -2;
> }
>
> +static struct sk_buff *
> +mptcp_process_ack(struct sock *sk, struct sk_buff *skb)
> +{
> + struct tcp_sock *tp = tcp_sk(sk);
> + int flag = 0;
> +
> + /*
> + * TCP takes care of invalid ack's
> + * they will never show up here.
> + */
> +
> + /* Is this skb acknowleding anything data */
> +
> + if (tp->mptcp->snt_isn + 1 != TCP_SKB_CB(skb)->ack_seq) {
> + flag = MPTCP_FLAG_DATA_ACKED;
> + }
> +
> + if (mptcp_fallback_infinite(sk, flag)) {
> + pr_err("%s resetting flow\n", __func__);
> + mptcp_send_reset(sk);
> + goto invalid_ack;
> + }
> +
> + mptcp_clean_rtx_infinite(skb, sk);
> +
> + return (skb);
> +invalid_ack:
> + __skb_unlink(skb, &sk->sk_receive_queue);
> + __kfree_skb(skb);
> + return (NULL);
> +
> +}
> +
> +static struct sk_buff *
> +mptcp_process_options_ack(struct sock *sk, struct sk_buff *skb)
> +{
> + struct tcp_sock *tp = tcp_sk(sk);
> + const struct tcphdr *th = tcp_hdr(skb);
> +
> + skb->mptcp_flags = 0;
> + skb->mptcp_dss_off = 0;
> +
> + tcp_parse_mptcp_options(skb, &tp->mptcp->rx_opt);
> + if (mptcp_handle_options(sk, th, skb)) {
> + mptcp_reset_mopt(tp);
> + __skb_unlink(skb, &sk->sk_receive_queue);
> + __kfree_skb(skb);
> + skb = NULL;
> + }
> + if ((skb != NULL) && skb->len == 0) {
> + skb = mptcp_process_ack(sk, skb);
> + if (skb != NULL && skb->len == 0) {
> + /* Pure ack */
> + __skb_unlink(skb, &sk->sk_receive_queue);
> + __kfree_skb(skb);
> + skb = NULL;
> + }
> + }
> + return (skb);
> +}
> +
> void mptcp_data_ready(struct sock *sk)
> {
> struct sock *meta_sk = mptcp_meta_sk(sk);
> @@ -1045,6 +1105,10 @@ restart:
> */
> skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
> int ret;
> +
> + skb = mptcp_process_options_ack(sk, skb);
> + if (skb == NULL)
> + continue;
> /* Pre-validation - e.g., early fallback */
> ret = mptcp_prevalidate_skb(sk, skb);
> if (ret < 0)
> @@ -1108,13 +1172,11 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
> if (!meta_sk)
> return 0;
>
> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> -
> bh_lock_sock_nested(meta_sk);
> if (sock_owned_by_user(meta_sk)) {
> - skb->sk = meta_sk;
> + skb->sk = (struct sock *)0xFEE1DEAD;
> if (unlikely(sk_add_backlog(meta_sk, skb,
> - meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> + meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf))) {
> bh_unlock_sock(meta_sk);
> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> sock_put(meta_sk); /* Taken by mptcp_search_req */
> @@ -1122,10 +1184,14 @@ int mptcp_check_req(struct sk_buff *skb, struct net *net)
> return 1;
> }
> } else if (skb->protocol == htons(ETH_P_IP)) {
> - tcp_v4_do_rcv(meta_sk, skb);
> + /*
> + * call old mptcp_v4_do_rcv
> + */
> + mptcp_v4_process_join_req(meta_sk, skb);
> #if IS_ENABLED(CONFIG_IPV6)
> } else { /* IPv6 */
> - tcp_v6_do_rcv(meta_sk, skb);
> + WARN_ON(1);
> + //mptcp_v6_handle_join_req(meta_sk, skb);
> #endif /* CONFIG_IPV6 */
> }
> bh_unlock_sock(meta_sk);
> @@ -1222,7 +1288,7 @@ int mptcp_lookup_join(struct sk_buff *skb, struct inet_timewait_sock *tw)
> inet_twsk_put(tw);
> }
>
> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> + skb->mptcp_flags |= MPTCPHDR_JOIN;
> /* OK, this is a new syn/join, let's create a new open request and
> * send syn+ack
> */
> @@ -1279,7 +1345,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
> return -1;
> }
>
> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
> + //TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_JOIN;
>
> /* OK, this is a new syn/join, let's create a new open request and
> * send syn+ack
> @@ -1303,7 +1369,7 @@ int mptcp_do_join_short(struct sk_buff *skb,
> }
>
> if (sock_owned_by_user(meta_sk)) {
> - skb->sk = meta_sk;
> + skb->sk = (struct sock *)0xFEE1DEAD; //skb->sk = meta_sk;
> if (unlikely(sk_add_backlog(meta_sk, skb,
> meta_sk->sk_rcvbuf + meta_sk->sk_sndbuf)))
> NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
> @@ -1319,10 +1385,12 @@ int mptcp_do_join_short(struct sk_buff *skb,
> */
> skb_get(skb);
> if (skb->protocol == htons(ETH_P_IP)) {
> - tcp_v4_do_rcv(meta_sk, skb);
> + //tcp_v4_do_rcv(meta_sk, skb);
> + mptcp_v4_process_join_req(meta_sk, skb);
> #if IS_ENABLED(CONFIG_IPV6)
> } else { /* IPv6 */
> - tcp_v6_do_rcv(meta_sk, skb);
> + //mptcp_v6_process_join_req(meta_sk, skb);
> + //tcp_v6_do_rcv(meta_sk, skb);
> #endif /* CONFIG_IPV6 */
> }
> }
> @@ -1461,7 +1529,6 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
> {
> struct sock *meta_sk = mptcp_meta_sk(sk);
> struct tcp_sock *meta_tp = tcp_sk(meta_sk), *tp = tcp_sk(sk);
> - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> u32 prior_snd_una = meta_tp->snd_una;
> int prior_packets;
> u32 nwin, data_ack, data_seq;
> @@ -1481,7 +1548,7 @@ static void mptcp_data_ack(struct sock *sk, const struct sk_buff *skb)
> /* If we are in infinite mapping mode, rx_opt.data_ack has been
> * set by mptcp_clean_rtx_infinite.
> */
> - if (!(tcb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
> + if (!(skb->mptcp_flags & MPTCPHDR_ACK) && !tp->mpcb->infinite_mapping_snd)
> goto exit;
>
> data_ack = tp->mptcp->rx_opt.data_ack;
> @@ -1647,10 +1714,11 @@ static inline bool is_valid_addropt_opsize(u8 mptcp_ver,
>
> void mptcp_parse_options(const uint8_t *ptr, int opsize,
> struct mptcp_options_received *mopt,
> - const struct sk_buff *skb,
> + struct sk_buff *skb,
> struct tcp_sock *tp)
> {
> const struct mptcp_option *mp_opt = (struct mptcp_option *)ptr;
> + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
>
> /* If the socket is mp-capable we would have a mopt. */
> if (!mopt)
> @@ -1757,7 +1825,7 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
> ptr += 4;
>
> if (mdss->A) {
> - tcb->mptcp_flags |= MPTCPHDR_ACK;
> + skb->mptcp_flags |= MPTCPHDR_ACK;
>
> if (mdss->a) {
> mopt->data_ack = (u32) get_unaligned_be64(ptr);
> @@ -1768,13 +1836,13 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
> }
> }
>
> - tcb->dss_off = (ptr - skb_transport_header(skb));
> + skb->mptcp_dss_off = (ptr - skb_transport_header(skb));
>
> if (mdss->M) {
> if (mdss->m) {
> u64 data_seq64 = get_unaligned_be64(ptr);
>
> - tcb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
> + skb->mptcp_flags |= MPTCPHDR_SEQ64_SET;
> mopt->data_seq = (u32) data_seq64;
>
> ptr += 12; /* 64-bit dseq + subseq */
> @@ -1784,15 +1852,16 @@ void mptcp_parse_options(const uint8_t *ptr, int opsize,
> }
> mopt->data_len = get_unaligned_be16(ptr);
>
> - tcb->mptcp_flags |= MPTCPHDR_SEQ;
> + skb->mptcp_flags |= MPTCPHDR_SEQ;
>
> /* Is a check-sum present? */
> - if (opsize == mptcp_sub_len_dss(mdss, 1))
> - tcb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
> + if (opsize == mptcp_sub_len_dss(mdss, 1)) {
> + skb->mptcp_flags |= MPTCPHDR_DSS_CSUM;
> + }
>
> /* DATA_FIN only possible with DSS-mapping */
> if (mdss->F)
> - tcb->mptcp_flags |= MPTCPHDR_FIN;
> + skb->mptcp_flags |= MPTCPHDR_FIN;
> }
>
> break;
> @@ -1907,8 +1976,9 @@ void tcp_parse_mptcp_options(const struct sk_buff *skb,
> return;
> if (opsize > length)
> return; /* don't parse partial options */
> - if (opcode == TCPOPT_MPTCP)
> + if (opcode == TCPOPT_MPTCP) {
> mptcp_parse_options(ptr - 2, opsize, mopt, skb, NULL);
> + }
> }
> ptr += opsize - 2;
> length -= opsize;
> @@ -2168,6 +2238,8 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
> struct tcp_sock *tp = tcp_sk(sk);
> struct mptcp_options_received *mopt = &tp->mptcp->rx_opt;
>
> + BUG_ON(sk == mptcp_meta_sk(sk));
> +
> if (tp->mpcb->infinite_mapping_rcv || tp->mpcb->infinite_mapping_snd)
> return false;
>
> @@ -2185,7 +2257,7 @@ bool mptcp_handle_options(struct sock *sk, const struct tcphdr *th,
> * receiver MUST close the subflow with a RST as it is considered broken.
> */
> if (mptcp_is_data_seq(skb) && tp->mpcb->dss_csum &&
> - !(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
> + !(skb->mptcp_flags & MPTCPHDR_DSS_CSUM)) {
> mptcp_send_reset(sk);
> return true;
> }
> @@ -2330,6 +2402,7 @@ int mptcp_rcv_synsent_state_process(struct sock *sk, struct sock **skptr,
> /* Set this flag in order to postpone data sending
> * until the 4th ack arrives.
> */
> +printk("mptcp_rcv_synsent_state_process pre_established set \n");
> tp->mptcp->pre_established = 1;
> tp->mptcp->rcv_low_prio = tp->mptcp->rx_opt.low_prio;
>
> diff --git a/net/mptcp/mptcp_ipv4.c b/net/mptcp/mptcp_ipv4.c
> index a147b20..3e60ab5 100644
> --- a/net/mptcp/mptcp_ipv4.c
> +++ b/net/mptcp/mptcp_ipv4.c
> @@ -180,45 +180,12 @@ static int mptcp_v4_join_request(struct sock *meta_sk, struct sk_buff *skb)
> }
>
> /* We only process join requests here. (either the SYN or the final ACK) */
> -int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
> +int mptcp_v4_process_join_req(struct sock *meta_sk, struct sk_buff *skb)
> {
> const struct mptcp_cb *mpcb = tcp_sk(meta_sk)->mpcb;
> struct sock *child, *rsk = NULL;
> int ret;
>
> - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
> - struct tcphdr *th = tcp_hdr(skb);
> - const struct iphdr *iph = ip_hdr(skb);
> - struct sock *sk;
> -
> - sk = inet_lookup_established(sock_net(meta_sk), &tcp_hashinfo,
> - iph->saddr, th->source, iph->daddr,
> - th->dest, inet_iif(skb));
> -
> - if (!sk) {
> - kfree_skb(skb);
> - return 0;
> - }
> - if (is_meta_sk(sk)) {
> - WARN("%s Did not find a sub-sk - did found the meta!\n", __func__);
> - kfree_skb(skb);
> - sock_put(sk);
> - return 0;
> - }
> -
> - if (sk->sk_state == TCP_TIME_WAIT) {
> - inet_twsk_put(inet_twsk(sk));
> - kfree_skb(skb);
> - return 0;
> - }
> -
> - ret = tcp_v4_do_rcv(sk, skb);
> - sock_put(sk);
> -
> - return ret;
> - }
> - TCP_SKB_CB(skb)->mptcp_flags = 0;
> -
> /* Has been removed from the tk-table. Thus, no new subflows.
> *
> * Check for close-state is necessary, because we may have been closed
> diff --git a/net/mptcp/mptcp_ipv6.c b/net/mptcp/mptcp_ipv6.c
> index 0de953d..1959d01 100644
> --- a/net/mptcp/mptcp_ipv6.c
> +++ b/net/mptcp/mptcp_ipv6.c
> @@ -199,7 +199,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
> struct sock *child, *rsk = NULL;
> int ret;
>
> - if (!(TCP_SKB_CB(skb)->mptcp_flags & MPTCPHDR_JOIN)) {
> + if (!(skb->mptcp_flags & MPTCPHDR_JOIN)) {
> struct tcphdr *th = tcp_hdr(skb);
> const struct ipv6hdr *ip6h = ipv6_hdr(skb);
> struct sock *sk;
> @@ -232,7 +232,7 @@ int mptcp_v6_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
>
> return ret;
> }
> - TCP_SKB_CB(skb)->mptcp_flags = 0;
> + skb->mptcp_flags = 0;
>
> /* Has been removed from the tk-table. Thus, no new subflows.
> *
> diff --git a/net/mptcp/mptcp_output.c b/net/mptcp/mptcp_output.c
> index 691ef6f..e7d340d 100644
> --- a/net/mptcp/mptcp_output.c
> +++ b/net/mptcp/mptcp_output.c
> @@ -59,39 +59,17 @@ EXPORT_SYMBOL(mptcp_sub_len_remove_addr_align);
> */
> static bool mptcp_reconstruct_mapping(struct sk_buff *skb)
> {
> - const struct mp_dss *mpdss = (struct mp_dss *)TCP_SKB_CB(skb)->dss;
> - u32 *p32;
> - u16 *p16;
> -
> if (!mptcp_is_data_seq(skb))
> return false;
>
> - if (!mpdss->M)
> - return false;
> -
> - /* Move the pointer to the data-seq */
> - p32 = (u32 *)mpdss;
> - p32++;
> - if (mpdss->A) {
> - p32++;
> - if (mpdss->a)
> - p32++;
> - }
> -
> - TCP_SKB_CB(skb)->seq = ntohl(*p32);
> -
> - /* Get the data_len to calculate the end_data_seq */
> - p32++;
> - p32++;
> - p16 = (u16 *)p32;
> - TCP_SKB_CB(skb)->end_seq = ntohs(*p16) + TCP_SKB_CB(skb)->seq;
> + TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->mptcp_data_seq;
>
> return true;
> }
>
> static bool mptcp_is_reinjected(const struct sk_buff *skb)
> {
> - return TCP_SKB_CB(skb)->mptcp_flags & MPTCP_REINJECT;
> + return skb->mptcp_flags & MPTCP_REINJECT;
> }
>
> static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_buff *skb)
> @@ -105,7 +83,7 @@ static void mptcp_find_and_set_pathmask(const struct sock *meta_sk, struct sk_bu
> break;
>
> if (TCP_SKB_CB(skb_it)->seq == TCP_SKB_CB(skb)->seq) {
> - TCP_SKB_CB(skb)->path_mask = TCP_SKB_CB(skb_it)->path_mask;
> + TCP_SKB_CB(skb)->mptcp_path_mask = TCP_SKB_CB(skb_it)->mptcp_path_mask;
> break;
> }
> }
> @@ -180,9 +158,9 @@ static void __mptcp_reinject_data(struct sk_buff *orig_skb, struct sock *meta_sk
> }
>
> /* Segment goes back to the MPTCP-layer. So, we need to zero the
> - * path_mask/dss.
> + * path_mask.
> */
> - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
>
> /* We need to find out the path-mask from the meta-write-queue
> * to properly select a subflow.
> @@ -272,14 +250,14 @@ void mptcp_reinject_data(struct sock *sk, int clone_it)
> if (mptcp_is_reinjected(skb_it))
> continue;
>
> - tcb->mptcp_flags |= MPTCP_REINJECT;
> + skb_it->mptcp_flags |= MPTCP_REINJECT;
> __mptcp_reinject_data(skb_it, meta_sk, sk, clone_it);
> }
>
> skb_it = tcp_write_queue_tail(meta_sk);
> /* If sk has sent the empty data-fin, we have to reinject it too. */
> if (skb_it && mptcp_is_data_fin(skb_it) && skb_it->len == 0 &&
> - TCP_SKB_CB(skb_it)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
> + TCP_SKB_CB(skb_it)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index)) {
> __mptcp_reinject_data(skb_it, meta_sk, NULL, 1);
> }
>
> @@ -319,25 +297,43 @@ combine:
> }
> }
>
> -static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_buff *skb,
> - __be32 *ptr)
> +/*
> + * RFC6824 states that once a particular subflow mapping has been sent
> + * out it must never be changed. However, packets may be split while
> + * they are in the retransmission queue (due to SACK or ACKs) and that
> + * arguably means that we would change the mapping (e.g. it splits it,
> + * our sends out a subset of the initial mapping).
> + *
> + * Furthermore, the skb checksum is not always preserved across splits
> + * (e.g. mptcp_fragment) which would mean that we need to recompute
> + * the DSS checksum in this case.
> + *
> + * To avoid this we save the initial DSS mapping which allows us to
> + * send the same DSS mapping even for fragmented retransmits.
> + */
> +
> +static int mptcp_write_dss_mapping(const struct tcp_sock *tp,
> + const struct sk_buff *skb, __be32 *ptr)
> {
> const struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> - __be32 *start = ptr;
> __u16 data_len;
>
> - *ptr++ = htonl(tcb->seq); /* data_seq */
> + *ptr++ = htonl(tcb->mptcp_data_seq); /* data_seq */
>
> /* If it's a non-data DATA_FIN, we set subseq to 0 (draft v7) */
> if (mptcp_is_data_fin(skb) && skb->len == 0)
> *ptr++ = 0; /* subseq */
> else
> - *ptr++ = htonl(tp->write_seq - tp->mptcp->snt_isn); /* subseq */
> + *ptr++ = htonl(tcb->seq - tp->mptcp->snt_isn); /* subseq */
>
> - if (tcb->mptcp_flags & MPTCPHDR_INF)
> + if (skb->mptcp_flags & MPTCPHDR_INF)
> data_len = 0;
> - else
> + else {
> data_len = tcb->end_seq - tcb->seq;
> + /* mptcp_entail_skb adds one for FIN */
> + if (tcb->tcp_flags & TCPHDR_FIN)
> + data_len -= 1;
> + }
>
> if (tp->mpcb->dss_csum && data_len) {
> __be16 *p16 = (__be16 *)ptr;
> @@ -356,11 +352,11 @@ static int mptcp_write_dss_mapping(const struct tcp_sock *tp, const struct sk_bu
> (TCPOPT_NOP));
> }
>
> - return ptr - start;
> + return mptcp_dss_len/sizeof(*ptr);
> }
>
> -static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_buff *skb,
> - __be32 *ptr)
> +static int mptcp_write_dss_data_ack(const struct tcp_sock *tp,
> + const struct sk_buff *skb, __be32 *ptr)
> {
> struct mp_dss *mdss = (struct mp_dss *)ptr;
> __be32 *start = ptr;
> @@ -377,54 +373,12 @@ static int mptcp_write_dss_data_ack(const struct tcp_sock *tp, const struct sk_b
> mdss->len = mptcp_sub_len_dss(mdss, tp->mpcb->dss_csum);
> ptr++;
>
> + /* data_ack */
> *ptr++ = htonl(mptcp_meta_tp(tp)->rcv_nxt);
>
> return ptr - start;
> }
>
> -/* RFC6824 states that once a particular subflow mapping has been sent
> - * out it must never be changed. However, packets may be split while
> - * they are in the retransmission queue (due to SACK or ACKs) and that
> - * arguably means that we would change the mapping (e.g. it splits it,
> - * our sends out a subset of the initial mapping).
> - *
> - * Furthermore, the skb checksum is not always preserved across splits
> - * (e.g. mptcp_fragment) which would mean that we need to recompute
> - * the DSS checksum in this case.
> - *
> - * To avoid this we save the initial DSS mapping which allows us to
> - * send the same DSS mapping even for fragmented retransmits.
> - */
> -static void mptcp_save_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb)
> -{
> - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
> - __be32 *ptr = (__be32 *)tcb->dss;
> -
> - tcb->mptcp_flags |= MPTCPHDR_SEQ;
> -
> - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
> - ptr += mptcp_write_dss_mapping(tp, skb, ptr);
> -}
> -
> -/* Write the saved DSS mapping to the header */
> -static int mptcp_write_dss_data_seq(const struct tcp_sock *tp, struct sk_buff *skb,
> - __be32 *ptr)
> -{
> - __be32 *start = ptr;
> -
> - memcpy(ptr, TCP_SKB_CB(skb)->dss, mptcp_dss_len);
> -
> - /* update the data_ack */
> - start[1] = htonl(mptcp_meta_tp(tp)->rcv_nxt);
> -
> - /* dss is in a union with inet_skb_parm and
> - * the IP layer expects zeroed IPCB fields.
> - */
> - memset(TCP_SKB_CB(skb)->dss, 0 , mptcp_dss_len);
> -
> - return mptcp_dss_len/sizeof(*ptr);
> -}
> -
> static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
> {
> struct tcp_sock *tp = tcp_sk(sk);
> @@ -434,7 +388,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
> struct sk_buff *subskb = NULL;
>
> if (!reinject)
> - TCP_SKB_CB(skb)->mptcp_flags |= (mpcb->snd_hiseq_index ?
> + skb->mptcp_flags |= (mpcb->snd_hiseq_index ?
> MPTCPHDR_SEQ64_INDEX : 0);
>
> subskb = pskb_copy_for_clone(skb, GFP_ATOMIC);
> @@ -447,7 +401,7 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
> */
> tcp_skb_pcount_set(subskb, 0);
>
> - TCP_SKB_CB(skb)->path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
> + TCP_SKB_CB(skb)->mptcp_path_mask |= mptcp_pi_to_flag(tp->mptcp->path_index);
>
> if (!(sk->sk_route_caps & NETIF_F_ALL_CSUM) &&
> skb->ip_summed == CHECKSUM_PARTIAL) {
> @@ -463,13 +417,14 @@ static bool mptcp_skb_entail(struct sock *sk, struct sk_buff *skb, int reinject)
> tp->mptcp->fully_established = 1;
> tp->mpcb->infinite_mapping_snd = 1;
> tp->mptcp->infinite_cutoff_seq = tp->write_seq;
> - tcb->mptcp_flags |= MPTCPHDR_INF;
> + skb->mptcp_flags |= MPTCPHDR_INF;
> }
>
> if (mptcp_is_data_fin(subskb))
> mptcp_combine_dfin(subskb, meta_sk, sk);
>
> - mptcp_save_dss_data_seq(tp, subskb);
> + subskb->mptcp_flags |= MPTCPHDR_SEQ;
> + tcb->mptcp_data_seq = tcb->seq;
>
> tcb->seq = tp->write_seq;
>
> @@ -536,10 +491,10 @@ static int mptcp_fragment(struct sock *meta_sk, struct sk_buff *skb, u32 len,
>
> buff = skb->next;
>
> - flags = TCP_SKB_CB(skb)->mptcp_flags;
> - TCP_SKB_CB(skb)->mptcp_flags = flags & ~(MPTCPHDR_FIN);
> - TCP_SKB_CB(buff)->mptcp_flags = flags;
> - TCP_SKB_CB(buff)->path_mask = TCP_SKB_CB(skb)->path_mask;
> + flags = skb->mptcp_flags;
> + skb->mptcp_flags = flags & ~(MPTCPHDR_FIN);
> + buff->mptcp_flags = flags;
> + TCP_SKB_CB(buff)->mptcp_path_mask = TCP_SKB_CB(skb)->mptcp_path_mask;
>
> /* If reinject == 1, the buff will be added to the reinject
> * queue, which is currently not part of memory accounting. So
> @@ -927,8 +882,9 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
> * It does not make sense to check for the options, because when the
> * segment gets sent, another subflow will be chosen.
> */
> - if (!skb && is_meta_sk(sk))
> + if (!skb && is_meta_sk(sk)) {
> return;
> + }
>
> /* In fallback mp_fail-mode, we have to repeat it until the fallback
> * has been done by the sender
> @@ -967,10 +923,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
> if (unlikely(mpcb->infinite_mapping_snd) &&
> ((mpcb->send_infinite_mapping && tcb &&
> mptcp_is_data_seq(skb) &&
> - !(tcb->mptcp_flags & MPTCPHDR_INF) &&
> + !(skb->mptcp_flags & MPTCPHDR_INF) &&
> !before(tcb->seq, tp->mptcp->infinite_cutoff_seq)) ||
> - !mpcb->send_infinite_mapping))
> + !mpcb->send_infinite_mapping)) {
> return;
> + }
>
> if (unlikely(tp->mptcp->include_mpc)) {
> opts->options |= OPTION_MPTCP;
> @@ -995,9 +952,11 @@ void mptcp_established_options(struct sock *sk, struct sk_buff *skb,
> mpcb->mptcp_ver >= MPTCP_VERSION_1 && skb && !mptcp_is_data_seq(skb)) {
> mpcb->pm_ops->addr_signal(sk, size, opts, skb);
>
> - if (opts->add_addr_v6)
> + if (opts->add_addr_v6) {
> +
> /* Skip subsequent options */
> return;
> + }
> }
>
> if (!tp->mptcp->include_mpc && !tp->mptcp->pre_established) {
> @@ -1197,10 +1156,11 @@ void mptcp_options_write(__be32 *ptr, struct tcp_sock *tp,
> }
>
> if (OPTION_DATA_ACK & opts->mptcp_options) {
> - if (!mptcp_is_data_seq(skb))
> - ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
> - else
> - ptr += mptcp_write_dss_data_seq(tp, skb, ptr);
> + ptr += mptcp_write_dss_data_ack(tp, skb, ptr);
> + if (mptcp_is_data_seq(skb)) {
> + ptr += mptcp_write_dss_mapping(tp, skb, ptr);
> + }
> + skb->dev = NULL;
> }
> if (unlikely(OPTION_MP_PRIO & opts->mptcp_options)) {
> struct mp_prio *mpprio = (struct mp_prio *)ptr;
> @@ -1233,7 +1193,7 @@ void mptcp_send_fin(struct sock *meta_sk)
> mss_now = mptcp_current_mss(meta_sk);
>
> if (tcp_send_head(meta_sk) != NULL) {
> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
> + skb->mptcp_flags |= MPTCPHDR_FIN;
> TCP_SKB_CB(skb)->end_seq++;
> meta_tp->write_seq++;
> } else {
> @@ -1250,7 +1210,7 @@ void mptcp_send_fin(struct sock *meta_sk)
>
> tcp_init_nondata_skb(skb, meta_tp->write_seq, TCPHDR_ACK);
> TCP_SKB_CB(skb)->end_seq++;
> - TCP_SKB_CB(skb)->mptcp_flags |= MPTCPHDR_FIN;
> + skb->mptcp_flags |= MPTCPHDR_FIN;
> tcp_queue_skb(meta_sk, skb);
> }
> __tcp_push_pending_frames(meta_sk, mss_now, TCP_NAGLE_OFF);
> diff --git a/net/mptcp/mptcp_redundant.c b/net/mptcp/mptcp_redundant.c
> index 8fa2dba..37a13f4 100644
> --- a/net/mptcp/mptcp_redundant.c
> +++ b/net/mptcp/mptcp_redundant.c
> @@ -72,10 +72,10 @@ static bool redsched_use_subflow(struct sock *meta_sk,
> if (!skb || !mptcp_is_available((struct sock *)tp, skb, false))
> return false;
>
> - if (TCP_SKB_CB(skb)->path_mask != 0)
> + if (TCP_SKB_CB(skb)->mptcp_path_mask != 0)
> return subflow_is_active(tp);
>
> - if (TCP_SKB_CB(skb)->path_mask == 0) {
> + if (TCP_SKB_CB(skb)->mptcp_path_mask == 0) {
> if (active_valid_sks == -1)
> active_valid_sks = redsched_get_active_valid_sks(meta_sk);
>
> @@ -209,7 +209,7 @@ static struct sk_buff *redundant_next_segment(struct sock *meta_sk,
> cb_data->next_subflow = tp->mptcp->next;
> *subsk = (struct sock *)tp;
>
> - if (TCP_SKB_CB(skb)->path_mask)
> + if (TCP_SKB_CB(skb)->mptcp_path_mask)
> *reinject = -1;
> return skb;
> }
> diff --git a/net/mptcp/mptcp_rr.c b/net/mptcp/mptcp_rr.c
> index 8910ba9..83837f2 100644
> --- a/net/mptcp/mptcp_rr.c
> +++ b/net/mptcp/mptcp_rr.c
> @@ -93,7 +93,7 @@ static int mptcp_rr_dont_reinject_skb(const struct tcp_sock *tp, const struct sk
> */
> return skb &&
> /* Has the skb already been enqueued into this subsocket? */
> - mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
> + mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
> }
>
> /* We just look for any subflow that is available */
> @@ -136,7 +136,7 @@ static struct sock *rr_get_available_subflow(struct sock *meta_sk,
> * chance again by restarting its pathmask.
> */
> if (skb)
> - TCP_SKB_CB(skb)->path_mask = 0;
> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
> sk = backupsk;
> }
>
> diff --git a/net/mptcp/mptcp_sched.c b/net/mptcp/mptcp_sched.c
> index 54408ff..5cbbf91 100644
> --- a/net/mptcp/mptcp_sched.c
> +++ b/net/mptcp/mptcp_sched.c
> @@ -118,7 +118,7 @@ static int mptcp_dont_reinject_skb(const struct tcp_sock *tp, const struct sk_bu
> */
> return skb &&
> /* Has the skb already been enqueued into this subsocket? */
> - mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->path_mask;
> + mptcp_pi_to_flag(tp->mptcp->path_index) & TCP_SKB_CB(skb)->mptcp_path_mask;
> }
>
> bool subflow_is_backup(const struct tcp_sock *tp)
> @@ -261,7 +261,7 @@ struct sock *get_available_subflow(struct sock *meta_sk, struct sk_buff *skb,
> * the skb passed through all the available active and backups
> * sks, so clean the path mask
> */
> - TCP_SKB_CB(skb)->path_mask = 0;
> + TCP_SKB_CB(skb)->mptcp_path_mask = 0;
> return sk;
> }
> EXPORT_SYMBOL_GPL(get_available_subflow);
> @@ -298,7 +298,7 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
> /* Half the cwnd of the slow flow */
> mptcp_for_each_tp(tp->mpcb, tp_it) {
> if (tp_it != tp &&
> - TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> + TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> if (tp->srtt_us < tp_it->srtt_us && inet_csk((struct sock *)tp_it)->icsk_ca_state == TCP_CA_Open) {
> u32 prior_cwnd = tp_it->snd_cwnd;
>
> @@ -317,11 +317,11 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struct sock *sk, int penal)
> retrans:
>
> /* Segment not yet injected into this path? Take it!!! */
> - if (!(TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
> + if (!(TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp->mptcp->path_index))) {
> bool do_retrans = false;
> mptcp_for_each_tp(tp->mpcb, tp_it) {
> if (tp_it != tp &&
> - TCP_SKB_CB(skb_head)->path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> + TCP_SKB_CB(skb_head)->mptcp_path_mask & mptcp_pi_to_flag(tp_it->mptcp->path_index)) {
> if (tp_it->snd_cwnd <= 4) {
> do_retrans = true;
> break;
^ permalink raw reply [flat|nested] 14+ messages in thread
end of thread, other threads:[~2017-06-28 20:13 UTC | newest]
Thread overview: 14+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-06-26 21:13 [MPTCP] [PATCH] Revert tcp_skb_cb to it's original size and cleanup main TCP Rx code from MPTCP specific code Rao Shoaib
2017-06-26 22:34 Rao Shoaib
2017-06-27 6:27 Christoph Paasch
2017-06-27 17:22 Rao Shoaib
2017-06-27 17:25 Rao Shoaib
2017-06-27 17:37 Christoph Paasch
2017-06-27 18:51 Rao Shoaib
2017-06-27 23:22 Mat Martineau
2017-06-27 23:35 Mat Martineau
2017-06-28 4:53 Christoph Paasch
2017-06-28 19:13 Rao Shoaib
2017-06-28 19:41 Christoph Paasch
2017-06-28 20:10 Rao Shoaib
2017-06-28 20:13 Rao Shoaib
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.