summaryrefslogtreecommitdiff
path: root/net/mptcp/options.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp/options.c')
-rw-r--r--net/mptcp/options.c105
1 files changed, 84 insertions, 21 deletions
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 1603b3702e22..f24ae7d40e88 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -108,7 +108,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->suboptions |= OPTION_MPTCP_DSS;
mp_opt->use_map = 1;
mp_opt->mpc_map = 1;
- mp_opt->use_ack = 0;
mp_opt->data_len = get_unaligned_be16(ptr);
ptr += 2;
}
@@ -157,11 +156,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
pr_debug("DSS\n");
ptr++;
- /* we must clear 'mpc_map' be able to detect MP_CAPABLE
- * map vs DSS map in mptcp_incoming_options(), and reconstruct
- * map info accordingly
- */
- mp_opt->mpc_map = 0;
flags = (*ptr++) & MPTCP_DSS_FLAG_MASK;
mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0;
mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0;
@@ -369,8 +363,11 @@ void mptcp_get_options(const struct sk_buff *skb,
const unsigned char *ptr;
int length;
- /* initialize option status */
- mp_opt->suboptions = 0;
+ /* Ensure that casting the whole status to u32 is efficient and safe */
+ BUILD_BUG_ON(sizeof_field(struct mptcp_options_received, status) != sizeof(u32));
+ BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct mptcp_options_received, status),
+ sizeof(u32)));
+ *(u32 *)&mp_opt->status = 0;
length = (th->doff * 4) - sizeof(struct tcphdr);
ptr = (const unsigned char *)(th + 1);
@@ -435,7 +432,6 @@ static void clear_3rdack_retransmission(struct sock *sk)
struct inet_connection_sock *icsk = inet_csk(sk);
sk_stop_timer(sk, &icsk->icsk_delack_timer);
- icsk->icsk_ack.timeout = 0;
icsk->icsk_ack.ato = 0;
icsk->icsk_ack.pending &= ~(ICSK_ACK_SCHED | ICSK_ACK_TIMER);
}
@@ -607,7 +603,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
}
opts->ext_copy.use_ack = 1;
opts->suboptions = OPTION_MPTCP_DSS;
- WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
/* Add kind/length/subtype/flag overhead if mapping is not populated */
if (dss_size == 0)
@@ -655,6 +650,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
bool drop_other_suboptions = false;
unsigned int opt_size = *size;
+ struct mptcp_addr_info addr;
bool echo;
int len;
@@ -663,13 +659,20 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
*/
if (!mptcp_pm_should_add_signal(msk) ||
(opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) ||
- !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr,
+ !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &addr,
&echo, &drop_other_suboptions))
return false;
+ /*
+ * Later on, mptcp_write_options() will enforce mutually exclusion with
+ * DSS, bail out if such option is set and we can't drop it.
+ */
if (drop_other_suboptions)
remaining += opt_size;
- len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port);
+ else if (opts->suboptions & OPTION_MPTCP_DSS)
+ return false;
+
+ len = mptcp_add_addr_len(addr.family, echo, !!addr.port);
if (remaining < len)
return false;
@@ -686,6 +689,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
opts->ahmac = 0;
*size -= opt_size;
}
+ opts->addr = addr;
opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
if (!echo) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX);
@@ -834,8 +838,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
opts->suboptions = 0;
+ /* Force later mptcp_write_options(), but do not use any actual
+ * option space.
+ */
if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb)))
- return false;
+ return true;
if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) ||
@@ -974,18 +981,20 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
if (subflow->mp_join)
goto reset;
subflow->mp_capable = 0;
- pr_fallback(msk);
- mptcp_do_fallback(ssk);
+ if (!mptcp_try_fallback(ssk, MPTCP_MIB_MPCAPABLEDATAFALLBACK)) {
+ MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_FALLBACKFAILED);
+ goto reset;
+ }
return false;
}
- if (mp_opt->deny_join_id0)
- WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
-
if (unlikely(!READ_ONCE(msk->pm.server_side)))
pr_warn_once("bogus mpc option on established client sk");
set_fully_established:
+ if (mp_opt->deny_join_id0)
+ WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
+
mptcp_data_lock((struct sock *)msk);
__mptcp_subflow_fully_established(msk, subflow, mp_opt);
mptcp_data_unlock((struct sock *)msk);
@@ -1035,6 +1044,31 @@ static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una)
WRITE_ONCE(msk->snd_una, new_snd_una);
}
+static void rwin_update(struct mptcp_sock *msk, struct sock *ssk,
+ struct sk_buff *skb)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ struct tcp_sock *tp = tcp_sk(ssk);
+ u64 mptcp_rcv_wnd;
+
+ /* Avoid touching extra cachelines if TCP is going to accept this
+ * skb without filling the TCP-level window even with a possibly
+ * outdated mptcp-level rwin.
+ */
+ if (!skb->len || skb->len < tcp_receive_window(tp))
+ return;
+
+ mptcp_rcv_wnd = atomic64_read(&msk->rcv_wnd_sent);
+ if (!after64(mptcp_rcv_wnd, subflow->rcv_wnd_sent))
+ return;
+
+ /* Some other subflow grew the mptcp-level rwin since rcv_wup,
+ * resync.
+ */
+ tp->rcv_wnd += mptcp_rcv_wnd - subflow->rcv_wnd_sent;
+ subflow->rcv_wnd_sent = mptcp_rcv_wnd;
+}
+
static void ack_update_msk(struct mptcp_sock *msk,
struct sock *ssk,
struct mptcp_options_received *mp_opt)
@@ -1112,7 +1146,9 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
return hmac == mp_opt->ahmac;
}
-/* Return false if a subflow has been reset, else return true */
+/* Return false in case of error (or subflow has been reset),
+ * else return true.
+ */
bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -1200,6 +1236,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
*/
if (mp_opt.use_ack)
ack_update_msk(msk, sk, &mp_opt);
+ rwin_update(msk, sk, skb);
/* Zero-data-length packets are dropped by the caller and not
* propagated to the MPTCP layer, so the skb extension does not
@@ -1216,7 +1253,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (!mpext)
- return true;
+ return false;
memset(mpext, 0, sizeof(*mpext));
@@ -1281,11 +1318,15 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th)
}
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT);
}
- return;
+ goto update_wspace;
}
if (rcv_wnd_new != rcv_wnd_old) {
raise_win:
+ /* The msk-level rcv wnd is after the tcp level one,
+ * sync the latter.
+ */
+ rcv_wnd_new = rcv_wnd_old;
win = rcv_wnd_old - ack_seq;
tp->rcv_wnd = min_t(u64, win, U32_MAX);
new_win = tp->rcv_wnd;
@@ -1306,6 +1347,24 @@ raise_win:
th->window = htons(new_win);
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDSHARED);
}
+
+update_wspace:
+ WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
+ subflow->rcv_wnd_sent = rcv_wnd_new;
+}
+
+static void mptcp_track_rwin(struct tcp_sock *tp)
+{
+ const struct sock *ssk = (const struct sock *)tp;
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk;
+
+ if (!ssk)
+ return;
+
+ subflow = mptcp_subflow_ctx(ssk);
+ msk = mptcp_sk(subflow->conn);
+ WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
}
__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
@@ -1600,6 +1659,10 @@ mp_rst:
opts->reset_transient,
opts->reset_reason);
return;
+ } else if (unlikely(!opts->suboptions)) {
+ /* Fallback to TCP */
+ mptcp_track_rwin(tp);
+ return;
}
if (OPTION_MPTCP_PRIO & opts->suboptions) {
generated by cgit (git 2.34.1) at 2025-12-22 10:53:07 +0000