Content-Type: multipart/mixed; boundary="===============3084562577272721999==" MIME-Version: 1.0 From: Christoph Paasch To: mptcp at lists.01.org Subject: [MPTCP] [PATCH mptcp-net-next 07/14] mptcp: Remove cnt_subflows Date: Thu, 03 May 2018 14:04:51 -0700 Message-ID: <20180503210458.21524-8-cpaasch@apple.com> In-Reply-To: 20180503210458.21524-1-cpaasch@apple.com X-Status: X-Keywords: X-UID: 607 --===============3084562577272721999== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Our goal is to make subflow establishment lockless. cnt_subflows would need to either become an atomic variable, or we can remove it. Well, let's remove it! In the general case it is not needed at all. Some exotic schedulers need cnt_subflows, but we don't care if we add complexity in these schedulers. Something special in mptcp_verif_dss_csum(). There the access was actually wrong. Simply because cnt_subflows > 1, it doesn't mean we have a working subflow. So, we fix that. I don't think this issue is big enough to backport it. Finally mptcp_sched.c was also using cnt_subflows but merely for speeding up things to avoid going through the whole scheduler code when there is only one subflow. So, we can remove it and trade performance for a better design. Signed-off-by: Christoph Paasch Signed-off-by: Matthieu Baerts (cherry picked from commit b079a187260f0591ee292655f00526a5c8371cfe) --- include/net/mptcp.h | 12 +++++++++++- net/mptcp/mptcp_ctrl.c | 15 ++++++--------- net/mptcp/mptcp_input.c | 11 ++++++++++- net/mptcp/mptcp_ndiffports.c | 2 +- net/mptcp/mptcp_output.c | 2 +- net/mptcp/mptcp_sched.c | 11 ----------- 6 files changed, 29 insertions(+), 24 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 43f7f2ae1bad..b1ea946ea898 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -277,7 +277,6 @@ struct mptcp_cb { rcv_hiseq_index:1; /* Index in rcv_high_order of rcv_nxt */ = /* socket count in this connection */ - u8 cnt_subflows; u8 cnt_established; = #define MPTCP_SCHED_DATA_SIZE 8 @@ -1266,6 +1265,17 @@ static inline bool mptcp_can_new_subflow(const struc= t sock *meta_sk) !tcp_sk(meta_sk)->mpcb->send_infinite_mapping; } = +static inline int mptcp_subflow_count(const struct mptcp_cb *mpcb) +{ + struct sock *sk; + int i =3D 0; + + mptcp_for_each_sk(mpcb, sk) + i++; + + return i; +} + /* TCP and MPTCP mpc flag-depending functions */ u16 mptcp_select_window(struct sock *sk); void mptcp_tcp_set_rto(struct sock *sk); diff --git a/net/mptcp/mptcp_ctrl.c b/net/mptcp/mptcp_ctrl.c index c2aae9020d91..60e778ac362a 100644 --- a/net/mptcp/mptcp_ctrl.c +++ b/net/mptcp/mptcp_ctrl.c @@ -1379,7 +1379,6 @@ int mptcp_add_sock(struct sock *meta_sk, struct sock = *sk, u8 loc_id, u8 rem_id, mpcb->connection_list =3D tp; tp->mptcp->attached =3D 1; = - mpcb->cnt_subflows++; atomic_add(atomic_read(&((struct sock *)tp)->sk_rmem_alloc), &meta_sk->sk_rmem_alloc); = @@ -1399,23 +1398,21 @@ int mptcp_add_sock(struct sock *meta_sk, struct soc= k *sk, u8 loc_id, u8 rem_id, sk->sk_destruct =3D mptcp_sock_destruct; = if (sk->sk_family =3D=3D AF_INET) - mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d dst_addr:%pI4:%d, cnt= _subflows now %d\n", + mptcp_debug("%s: token %#x pi %d, src_addr:%pI4:%d dst_addr:%pI4:%d\n", __func__ , mpcb->mptcp_loc_token, tp->mptcp->path_index, &((struct inet_sock *)tp)->inet_saddr, ntohs(((struct inet_sock *)tp)->inet_sport), &((struct inet_sock *)tp)->inet_daddr, - ntohs(((struct inet_sock *)tp)->inet_dport), - mpcb->cnt_subflows); + ntohs(((struct inet_sock *)tp)->inet_dport)); #if IS_ENABLED(CONFIG_IPV6) else - mptcp_debug("%s: token %#x pi %d, src_addr:%pI6:%d dst_addr:%pI6:%d, cnt= _subflows now %d\n", + mptcp_debug("%s: token %#x pi %d, src_addr:%pI6:%d dst_addr:%pI6:%d\n", __func__ , mpcb->mptcp_loc_token, tp->mptcp->path_index, &inet6_sk(sk)->saddr, ntohs(((struct inet_sock *)tp)->inet_sport), &sk->sk_v6_daddr, - ntohs(((struct inet_sock *)tp)->inet_dport), - mpcb->cnt_subflows); + ntohs(((struct inet_sock *)tp)->inet_dport)); #endif = return 0; @@ -1449,7 +1446,6 @@ void mptcp_del_sock(struct sock *sk) } } } - mpcb->cnt_subflows--; if (tp->mptcp->establish_increased) mpcb->cnt_established--; = @@ -2813,8 +2809,9 @@ static int mptcp_pm_seq_show(struct seq_file *seq, vo= id *v) ntohs(isk->inet_dport)); #endif } + seq_printf(seq, " %02X %02X %08X:%08X %lu", - meta_sk->sk_state, mpcb->cnt_subflows, + meta_sk->sk_state, mptcp_subflow_count(mpcb), meta_tp->write_seq - meta_tp->snd_una, max_t(int, meta_tp->rcv_nxt - meta_tp->copied_seq, 0), diff --git a/net/mptcp/mptcp_input.c b/net/mptcp/mptcp_input.c index ba9e3fe62824..126c961ec55a 100644 --- a/net/mptcp/mptcp_input.c +++ b/net/mptcp/mptcp_input.c @@ -347,6 +347,8 @@ static int mptcp_verif_dss_csum(struct sock *sk) = /* Now, checksum must be 0 */ if (unlikely(csum_fold(csum_tcp))) { + struct sock *sk_it =3D NULL; + pr_err("%s csum is wrong: %#x tcp-seq %u dss_csum_added %d overflowed %d= iterations %d\n", __func__, csum_fold(csum_tcp), TCP_SKB_CB(last)->seq, dss_csum_added, overflowed, iter); @@ -359,7 +361,14 @@ static int mptcp_verif_dss_csum(struct sock *sk) */ tp->mpcb->csum_cutoff_seq =3D tp->mptcp->map_data_seq; = - if (tp->mpcb->cnt_subflows > 1) { + /* Search for another subflow that is fully established */ + mptcp_for_each_sk(tp->mpcb, sk_it) { + if (sk_it !=3D sk && + tcp_sk(sk_it)->mptcp->fully_established) + break; + } + + if (sk_it) { mptcp_send_reset(sk); ans =3D -1; } else { diff --git a/net/mptcp/mptcp_ndiffports.c b/net/mptcp/mptcp_ndiffports.c index 10147d5e3cca..58acf50df752 100644 --- a/net/mptcp/mptcp_ndiffports.c +++ b/net/mptcp/mptcp_ndiffports.c @@ -53,7 +53,7 @@ static void create_subflow_worker(struct work_struct *wor= k) !tcp_sk(mpcb->master_sk)->mptcp->fully_established) goto exit; = - if (num_subflows > iter && num_subflows > mpcb->cnt_subflows) { + if (num_subflows > iter && num_subflows > mptcp_subflow_count(mpcb)) { if (meta_sk->sk_family =3D=3D AF_INET || mptcp_v6_is_v4_mapped(meta_sk)) { struct mptcp_loc4 loc; diff --git a/net/mptcp/mptcp_output.c b/net/mptcp/mptcp_output.c index 3b99cef02c98..4b88b32d5954 100644 --- a/net/mptcp/mptcp_output.c +++ b/net/mptcp/mptcp_output.c @@ -1350,7 +1350,7 @@ void mptcp_send_active_reset(struct sock *meta_sk, gf= p_t priority) struct mptcp_cb *mpcb =3D meta_tp->mpcb; struct sock *sk; = - if (!mpcb->cnt_subflows) + if (!mpcb->connection_list) return; = WARN_ON(meta_tp->send_mp_fclose); diff --git a/net/mptcp/mptcp_sched.c b/net/mptcp/mptcp_sched.c index 1881eaec4f3e..a2543c60bd31 100644 --- a/net/mptcp/mptcp_sched.c +++ b/net/mptcp/mptcp_sched.c @@ -216,14 +216,6 @@ static struct sock *get_available_subflow(struct sock = *meta_sk, struct sock *sk; bool force; = - /* if there is only one subflow, bypass the scheduling function */ - if (mpcb->cnt_subflows =3D=3D 1) { - sk =3D (struct sock *)mpcb->connection_list; - if (!mptcp_is_available(sk, skb, zero_wnd_test)) - sk =3D NULL; - return sk; - } - /* Answer data_fin on same subflow!!! */ if (meta_sk->sk_shutdown & RCV_SHUTDOWN && skb && mptcp_is_data_fin(skb)) { @@ -264,9 +256,6 @@ static struct sk_buff *mptcp_rcv_buf_optimization(struc= t sock *sk, int penal) struct sk_buff *skb_head; struct defsched_priv *dsp =3D defsched_get_priv(tp); = - if (tp->mpcb->cnt_subflows =3D=3D 1) - return NULL; - meta_sk =3D mptcp_meta_sk(sk); skb_head =3D tcp_rtx_queue_head(meta_sk); = -- = 2.16.2 --===============3084562577272721999==--