summaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/bpf.c2
-rw-r--r--net/mptcp/ctrl.c18
-rw-r--r--net/mptcp/fastopen.c4
-rw-r--r--net/mptcp/options.c177
-rw-r--r--net/mptcp/pm.c288
-rw-r--r--net/mptcp/pm_kernel.c109
-rw-r--r--net/mptcp/pm_userspace.c27
-rw-r--r--net/mptcp/protocol.c72
-rw-r--r--net/mptcp/protocol.h47
-rw-r--r--net/mptcp/sockopt.c39
-rw-r--r--net/mptcp/subflow.c8
11 files changed, 465 insertions, 326 deletions
diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 8a16672b94e2..4cc16cbeb328 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -14,7 +14,7 @@
struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk)
{
- if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk_is_mptcp(sk))
+ if (sk && sk_fullsock(sk) && sk_is_tcp(sk) && sk_is_mptcp(sk))
return mptcp_sk(mptcp_subflow_ctx(sk)->conn);
return NULL;
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index d96130e49942..63c5747f0f63 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -32,12 +32,13 @@ struct mptcp_pernet {
unsigned int close_timeout;
unsigned int stale_loss_cnt;
atomic_t active_disable_times;
- u8 syn_retrans_before_tcp_fallback;
unsigned long active_disable_stamp;
+ u8 syn_retrans_before_tcp_fallback;
u8 mptcp_enabled;
u8 checksum_enabled;
u8 allow_join_initial_addr_port;
u8 pm_type;
+ u8 add_addr_v6_port_drop_ts;
char scheduler[MPTCP_SCHED_NAME_MAX];
char path_manager[MPTCP_PM_NAME_MAX];
};
@@ -94,6 +95,11 @@ const char *mptcp_get_scheduler(const struct net *net)
return mptcp_get_pernet(net)->scheduler;
}
+unsigned int mptcp_add_addr_v6_port_drop_ts(const struct net *net)
+{
+ return READ_ONCE(mptcp_get_pernet(net)->add_addr_v6_port_drop_ts);
+}
+
static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
{
pernet->mptcp_enabled = 1;
@@ -108,6 +114,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
pernet->pm_type = MPTCP_PM_TYPE_KERNEL;
strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler));
strscpy(pernet->path_manager, "kernel", sizeof(pernet->path_manager));
+ pernet->add_addr_v6_port_drop_ts = 1;
}
#ifdef CONFIG_SYSCTL
@@ -362,6 +369,14 @@ static struct ctl_table mptcp_sysctl_table[] = {
.mode = 0444,
.proc_handler = proc_available_path_managers,
},
+ {
+ .procname = "add_addr_v6_port_drop_ts",
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
+ },
};
static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -389,6 +404,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
table[10].data = &pernet->syn_retrans_before_tcp_fallback;
table[11].data = &pernet->path_manager;
/* table[12] is for available_path_managers which is read-only info */
+ table[13].data = &pernet->add_addr_v6_port_drop_ts;
hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
ARRAY_SIZE(mptcp_sysctl_table));
diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index 82ec15bcfd7f..082c46c0f50e 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -12,6 +12,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
struct sock *sk, *ssk;
struct sk_buff *skb;
struct tcp_sock *tp;
+ bool has_rxtstamp;
/* on early fallback the subflow context is deleted by
* subflow_syn_recv_sock()
@@ -40,12 +41,13 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
*/
tp->copied_seq += skb->len;
subflow->ssn_offset += skb->len;
+ has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
/* Only the sequence delta is relevant */
MPTCP_SKB_CB(skb)->map_seq = -skb->len;
MPTCP_SKB_CB(skb)->end_seq = 0;
MPTCP_SKB_CB(skb)->offset = 0;
- MPTCP_SKB_CB(skb)->has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
+ MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;
MPTCP_SKB_CB(skb)->cant_coalesce = 1;
mptcp_data_lock(sk);
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 8a1c5698983c..c664023d37ba 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -157,17 +157,11 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr++;
flags = (*ptr++) & MPTCP_DSS_FLAG_MASK;
- mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0;
mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0;
mp_opt->use_map = (flags & MPTCP_DSS_HAS_MAP) != 0;
mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0;
mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK);
- pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d\n",
- mp_opt->data_fin, mp_opt->dsn64,
- mp_opt->use_map, mp_opt->ack64,
- mp_opt->use_ack);
-
expected_opsize = TCPOLEN_MPTCP_DSS_BASE;
if (mp_opt->use_ack) {
@@ -178,12 +172,18 @@ static void mptcp_parse_option(const struct sk_buff *skb,
}
if (mp_opt->use_map) {
+ mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0;
if (mp_opt->dsn64)
expected_opsize += TCPOLEN_MPTCP_DSS_MAP64;
else
expected_opsize += TCPOLEN_MPTCP_DSS_MAP32;
}
+ pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d\n",
+ mp_opt->data_fin, mp_opt->dsn64,
+ mp_opt->use_map, mp_opt->ack64,
+ mp_opt->use_ack);
+
/* Always parse any csum presence combination, we will enforce
* RFC 8684 Section 3.3.0 checks later in subflow_data_ready
*/
@@ -447,8 +447,7 @@ static void clear_3rdack_retransmission(struct sock *sk)
}
static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
- bool snd_data_fin_enable,
- unsigned int *size,
+ bool snd_data_fin_enable, int *size,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -560,18 +559,19 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
}
static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
- bool snd_data_fin_enable,
- unsigned int *size,
+ bool snd_data_fin_enable, int *size,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+ struct tcp_sock *tp = tcp_sk(sk);
unsigned int dss_size = 0;
struct mptcp_ext *mpext;
unsigned int ack_size;
bool ret = false;
- u64 ack_seq;
+ /* Zero `use_ack` and `use_map` flags with one shot. */
+ memset(&opts->ext_copy.flags, 0, sizeof(opts->ext_copy.flags));
opts->csum_reqd = READ_ONCE(msk->csum_enabled);
mpext = skb ? mptcp_get_ext(skb) : NULL;
@@ -595,20 +595,16 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
/* passive sockets msk will set the 'can_ack' after accept(), even
* if the first subflow may have the already the remote key handy
*/
- opts->ext_copy.use_ack = 0;
if (!READ_ONCE(msk->can_ack)) {
*size = ALIGN(dss_size, 4);
return ret;
}
- ack_seq = READ_ONCE(msk->ack_seq);
if (READ_ONCE(msk->use_64bit_ack)) {
ack_size = TCPOLEN_MPTCP_DSS_ACK64;
- opts->ext_copy.data_ack = ack_seq;
opts->ext_copy.ack64 = 1;
} else {
ack_size = TCPOLEN_MPTCP_DSS_ACK32;
- opts->ext_copy.data_ack32 = (uint32_t)ack_seq;
opts->ext_copy.ack64 = 0;
}
opts->ext_copy.use_ack = 1;
@@ -618,6 +614,12 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
if (dss_size == 0)
ack_size += TCPOLEN_MPTCP_DSS_BASE;
+ /* The caller is __tcp_transmit_skb(), and will compute the new rcv
+ * wnd soon: ensure that the window can shrink.
+ */
+ if (skb)
+ tp->rcv_wnd = tp->rcv_nxt - tp->rcv_wup;
+
dss_size += ack_size;
*size = ALIGN(dss_size, 4);
@@ -651,56 +653,32 @@ static u64 add_addr_generate_hmac(u64 key1, u64 key2,
return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
}
-static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *skb,
- unsigned int *size,
+static bool mptcp_established_options_add_addr(struct sock *sk,
+ struct sk_buff *skb, int *size,
unsigned int remaining,
+ bool has_ts,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
- bool drop_other_suboptions = false;
- unsigned int opt_size = *size;
struct mptcp_addr_info addr;
+ bool drop_ts = has_ts;
bool echo;
- int len;
/* add addr will strip the existing options, be sure to avoid breaking
* MPC/MPJ handshakes
*/
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, &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;
- else if (opts->suboptions & OPTION_MPTCP_DSS)
+ !skb || !skb_is_tcp_pure_ack(skb) ||
+ !mptcp_pm_add_addr_signal(msk, size, remaining, &addr, &echo,
+ &drop_ts))
return false;
- len = mptcp_add_addr_len(addr.family, echo, !!addr.port);
- if (remaining < len)
- return false;
-
- *size = len;
- if (drop_other_suboptions) {
- pr_debug("drop other suboptions\n");
- opts->suboptions = 0;
-
- /* note that e.g. DSS could have written into the memory
- * aliased by ahmac, we must reset the field here
- * to avoid appending the hmac even for ADD_ADDR echo
- * options
- */
- opts->ahmac = 0;
- *size -= opt_size;
- }
+ pr_debug("drop other suboptions\n");
+ opts->suboptions = OPTION_MPTCP_ADD_ADDR;
+ opts->drop_ts = drop_ts;
opts->addr = addr;
- opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
if (!echo) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX);
opts->ahmac = add_addr_generate_hmac(READ_ONCE(msk->local_key),
@@ -708,6 +686,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
&opts->addr);
} else {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX);
+ opts->ahmac = 0;
}
pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n",
opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port));
@@ -715,27 +694,19 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
return true;
}
-static bool mptcp_established_options_rm_addr(struct sock *sk,
- unsigned int *size,
+static bool mptcp_established_options_rm_addr(struct sock *sk, int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct mptcp_rm_list rm_list;
- int i, len;
+ int i;
if (!mptcp_pm_should_rm_signal(msk) ||
- !(mptcp_pm_rm_addr_signal(msk, remaining, &rm_list)))
+ !(mptcp_pm_rm_addr_signal(msk, remaining, &rm_list, size)))
return false;
- len = mptcp_rm_addr_len(&rm_list);
- if (len < 0)
- return false;
- if (remaining < len)
- return false;
-
- *size = len;
opts->suboptions |= OPTION_MPTCP_RM_ADDR;
opts->rm_list = rm_list;
@@ -745,8 +716,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk,
return true;
}
-static bool mptcp_established_options_mp_prio(struct sock *sk,
- unsigned int *size,
+static bool mptcp_established_options_mp_prio(struct sock *sk, int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
@@ -771,8 +741,8 @@ static bool mptcp_established_options_mp_prio(struct sock *sk,
return true;
}
-static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb,
- unsigned int *size,
+static noinline bool mptcp_established_options_rst(struct sock *sk,
+ int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
@@ -790,8 +760,7 @@ static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_bu
return true;
}
-static bool mptcp_established_options_fastclose(struct sock *sk,
- unsigned int *size,
+static bool mptcp_established_options_fastclose(struct sock *sk, int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
@@ -813,8 +782,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk,
return true;
}
-static bool mptcp_established_options_mp_fail(struct sock *sk,
- unsigned int *size,
+static bool mptcp_established_options_mp_fail(struct sock *sk, int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
@@ -836,15 +804,16 @@ static bool mptcp_established_options_mp_fail(struct sock *sk,
return true;
}
-bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
- unsigned int *size, unsigned int remaining,
- struct mptcp_out_options *opts)
+int mptcp_established_options(struct sock *sk, struct sk_buff *skb,
+ unsigned int remaining, bool has_ts,
+ struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
- unsigned int opt_size = 0;
+ int total_size = 0;
bool snd_data_fin;
bool ret = false;
+ int opt_size = 0;
opts->suboptions = 0;
@@ -852,34 +821,34 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
* option space.
*/
if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb)))
- return true;
+ return 0;
if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) ||
mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {
- *size += opt_size;
+ total_size += opt_size;
remaining -= opt_size;
}
/* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */
- if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) {
- *size += opt_size;
+ if (mptcp_established_options_rst(sk, &opt_size, remaining, opts)) {
+ total_size += opt_size;
remaining -= opt_size;
}
- return true;
+ return total_size;
}
snd_data_fin = mptcp_data_fin_enabled(msk);
if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, opts))
ret = true;
else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, opts)) {
- unsigned int mp_fail_size;
+ int mp_fail_size;
ret = true;
if (mptcp_established_options_mp_fail(sk, &mp_fail_size,
remaining - opt_size, opts)) {
- *size += opt_size + mp_fail_size;
+ total_size += opt_size + mp_fail_size;
remaining -= opt_size - mp_fail_size;
- return true;
+ return total_size;
}
}
@@ -887,27 +856,28 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
* TCP option space would be fatal
*/
if (WARN_ON_ONCE(opt_size > remaining))
- return false;
+ return -1;
- *size += opt_size;
+ total_size += opt_size;
remaining -= opt_size;
- if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining, opts)) {
- *size += opt_size;
+ if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining,
+ has_ts, opts)) {
+ total_size += opt_size;
remaining -= opt_size;
ret = true;
} else if (mptcp_established_options_rm_addr(sk, &opt_size, remaining, opts)) {
- *size += opt_size;
+ total_size += opt_size;
remaining -= opt_size;
ret = true;
}
if (mptcp_established_options_mp_prio(sk, &opt_size, remaining, opts)) {
- *size += opt_size;
+ total_size += opt_size;
remaining -= opt_size;
ret = true;
}
- return ret;
+ return ret ? total_size : -1;
}
bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
@@ -1210,7 +1180,6 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
} else {
mptcp_pm_add_addr_echoed(msk, &mp_opt.addr);
- mptcp_pm_del_add_timer(msk, &mp_opt.addr, true);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD);
}
@@ -1297,19 +1266,14 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
return true;
}
-static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th)
+static u64 mptcp_set_rwin(struct mptcp_sock *msk, struct tcp_sock *tp,
+ struct tcphdr *th, u64 ack_seq)
{
const struct sock *ssk = (const struct sock *)tp;
- struct mptcp_subflow_context *subflow;
- u64 ack_seq, rcv_wnd_old, rcv_wnd_new;
- struct mptcp_sock *msk;
+ u64 rcv_wnd_old, rcv_wnd_new;
u32 new_win;
u64 win;
- subflow = mptcp_subflow_ctx(ssk);
- msk = mptcp_sk(subflow->conn);
-
- ack_seq = READ_ONCE(msk->ack_seq);
rcv_wnd_new = ack_seq + tp->rcv_wnd;
rcv_wnd_old = atomic64_read(&msk->rcv_wnd_sent);
@@ -1362,7 +1326,7 @@ raise_win:
update_wspace:
WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
- subflow->rcv_wnd_sent = rcv_wnd_new;
+ return rcv_wnd_new;
}
static void mptcp_track_rwin(struct tcp_sock *tp)
@@ -1474,13 +1438,25 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp,
*ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags);
if (mpext->use_ack) {
+ struct mptcp_sock *msk;
+ u64 ack_seq;
+
+ /* DSS option is set only by mptcp_established_options,
+ * the caller is __tcp_transmit_skb() and ssk is always
+ * not NULL.
+ */
+ subflow = mptcp_subflow_ctx(ssk);
+ msk = mptcp_sk(subflow->conn);
+ ack_seq = READ_ONCE(msk->ack_seq);
if (mpext->ack64) {
- put_unaligned_be64(mpext->data_ack, ptr);
+ put_unaligned_be64(ack_seq, ptr);
ptr += 2;
} else {
- put_unaligned_be32(mpext->data_ack32, ptr);
+ put_unaligned_be32(ack_seq, ptr);
ptr += 1;
}
+ subflow->rcv_wnd_sent = mptcp_set_rwin(msk, tp, th,
+ ack_seq);
}
if (mpext->use_map) {
@@ -1708,9 +1684,6 @@ mp_capable_done:
i += 4;
}
}
-
- if (tp)
- mptcp_set_rwin(tp, th);
}
__be32 mptcp_get_reset_option(const struct sk_buff *skb)
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 57a456690406..6afd39aea110 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -12,11 +12,12 @@
#define ADD_ADDR_RETRANS_MAX 3
-struct mptcp_pm_add_entry {
+struct mptcp_pm_add_addr {
struct list_head list;
struct mptcp_addr_info addr;
u8 retrans_times;
- struct timer_list add_timer;
+ bool timer_done;
+ struct timer_list timer;
struct mptcp_sock *sock;
struct rcu_head rcu;
};
@@ -114,14 +115,14 @@ static bool mptcp_pm_is_init_remote_addr(struct mptcp_sock *msk,
return mptcp_addresses_equal(&mpc_remote, remote, remote->port);
}
-bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
- const struct mptcp_addr_info *saddr)
+bool mptcp_pm_has_subflow_saddr(const struct mptcp_sock *msk,
+ const struct mptcp_addr_info *saddr)
{
struct mptcp_subflow_context *subflow;
struct mptcp_addr_info cur;
struct sock_common *skc;
- list_for_each_entry(subflow, list, node) {
+ mptcp_for_each_subflow(msk, subflow) {
skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
mptcp_local_address(skc, &cur);
@@ -132,11 +133,11 @@ bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
return false;
}
-static struct mptcp_pm_add_entry *
-mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
- const struct mptcp_addr_info *addr)
+static struct mptcp_pm_add_addr *
+mptcp_pm_announced_lookup(const struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr)
{
- struct mptcp_pm_add_entry *entry;
+ struct mptcp_pm_add_addr *entry;
lockdep_assert_held(&msk->pm.lock);
@@ -148,26 +149,60 @@ mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
return NULL;
}
-bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
- const struct mptcp_addr_info *addr)
+static struct mptcp_pm_add_addr *
+mptcp_pm_announced_del_timer(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr, bool check_id)
+{
+ struct sock *sk = (struct sock *)msk;
+ struct mptcp_pm_add_addr *entry;
+ bool stop_timer = false;
+
+ rcu_read_lock();
+
+ spin_lock_bh(&msk->pm.lock);
+ entry = mptcp_pm_announced_lookup(msk, addr);
+ if (entry && (!check_id || entry->addr.id == addr->id)) {
+ entry->retrans_times = ADD_ADDR_RETRANS_MAX;
+ stop_timer = true;
+ }
+ if (!check_id && entry)
+ list_del(&entry->list);
+ spin_unlock_bh(&msk->pm.lock);
+
+ /* Note: entry might have been removed by another thread.
+ * We hold rcu_read_lock() to ensure it is not freed under us.
+ */
+ if (stop_timer) {
+ if (check_id)
+ sk_stop_timer(sk, &entry->timer);
+ else
+ sk_stop_timer_sync(sk, &entry->timer);
+ }
+
+ rcu_read_unlock();
+ return entry;
+}
+
+bool mptcp_pm_announced_remove(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr)
{
- struct mptcp_pm_add_entry *entry;
+ struct mptcp_pm_add_addr *entry;
bool ret;
- entry = mptcp_pm_del_add_timer(msk, addr, false);
+ entry = mptcp_pm_announced_del_timer(msk, addr, false);
ret = entry;
kfree_rcu(entry, rcu);
return ret;
}
-bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk)
+bool mptcp_pm_announced_has_ssk(struct mptcp_sock *msk, const struct sock *ssk)
{
- struct mptcp_pm_add_entry *entry;
+ struct mptcp_pm_add_addr *entry;
struct mptcp_addr_info saddr;
bool ret = false;
- mptcp_local_address((struct sock_common *)sk, &saddr);
+ mptcp_local_address((struct sock_common *)ssk, &saddr);
spin_lock_bh(&msk->pm.lock);
list_for_each_entry(entry, &msk->pm.anno_list, list) {
@@ -225,6 +260,7 @@ static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow,
return false;
}
+static void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
static void
mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list)
@@ -283,6 +319,9 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
struct mptcp_addr_info local, remote;
+ if (!__mptcp_subflow_active(subflow))
+ continue;
+
mptcp_local_address((struct sock_common *)ssk, &local);
if (!mptcp_addresses_equal(&local, addr, addr->port))
continue;
@@ -305,53 +344,68 @@ static unsigned int mptcp_adjust_add_addr_timeout(struct mptcp_sock *msk)
const struct net *net = sock_net((struct sock *)msk);
unsigned int rto = mptcp_get_add_addr_timeout(net);
struct mptcp_subflow_context *subflow;
- unsigned int max = 0;
+ unsigned int max = 0, max_stale = 0;
+
+ if (!rto)
+ return 0;
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
struct inet_connection_sock *icsk = inet_csk(ssk);
- if (icsk->icsk_rto > max)
+ if (!__mptcp_subflow_active(subflow))
+ continue;
+
+ if (unlikely(subflow->stale)) {
+ if (icsk->icsk_rto > max_stale)
+ max_stale = icsk->icsk_rto;
+ } else if (icsk->icsk_rto > max) {
max = icsk->icsk_rto;
+ }
}
- if (max && max < rto)
- rto = max;
+ if (max)
+ return min(max, rto);
+
+ if (max_stale)
+ return min(max_stale, rto);
return rto;
}
-static void mptcp_pm_add_timer(struct timer_list *timer)
+static void mptcp_pm_add_addr_timer(struct timer_list *timer)
{
- struct mptcp_pm_add_entry *entry = timer_container_of(entry, timer,
- add_timer);
+ struct mptcp_pm_add_addr *entry = timer_container_of(entry, timer,
+ timer);
struct mptcp_sock *msk = entry->sock;
struct sock *sk = (struct sock *)msk;
- unsigned int timeout;
+ unsigned int timeout = 0;
pr_debug("msk=%p\n", msk);
- if (!msk)
- return;
-
- if (inet_sk_state_load(sk) == TCP_CLOSE)
- return;
-
- if (!entry->addr.id)
- return;
+ bh_lock_sock(sk);
+ if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
+ goto out;
- if (mptcp_pm_should_add_signal_addr(msk)) {
- sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8);
+ if (sock_owned_by_user(sk)) {
+ /* Try again later. */
+ timeout = HZ / 20;
goto out;
}
timeout = mptcp_adjust_add_addr_timeout(msk);
- if (!timeout)
+ if (!timeout || mptcp_pm_should_add_signal_addr(msk))
goto out;
spin_lock_bh(&msk->pm.lock);
- if (!mptcp_pm_should_add_signal_addr(msk)) {
+ /* The cancel path (mptcp_pm_announced_del_timer()) can race with this
+ * callback. Once cancel updates retrans_times to MAX, suppress further
+ * retransmissions here. If this callback acquires pm.lock first, one
+ * final transmit attempt is still possible.
+ */
+ if (entry->retrans_times < ADD_ADDR_RETRANS_MAX &&
+ !mptcp_pm_should_add_signal_addr(msk)) {
pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id);
mptcp_pm_announce_addr(msk, &entry->addr, false);
mptcp_pm_add_addr_send_ack(msk);
@@ -359,8 +413,9 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
}
if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
- sk_reset_timer(sk, timer,
- jiffies + (timeout << entry->retrans_times));
+ timeout <<= entry->retrans_times;
+ else
+ timeout = 0;
spin_unlock_bh(&msk->pm.lock);
@@ -368,50 +423,25 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
mptcp_pm_subflow_established(msk);
out:
- __sock_put(sk);
-}
-
-struct mptcp_pm_add_entry *
-mptcp_pm_del_add_timer(struct mptcp_sock *msk,
- const struct mptcp_addr_info *addr, bool check_id)
-{
- struct mptcp_pm_add_entry *entry;
- struct sock *sk = (struct sock *)msk;
- bool stop_timer = false;
-
- rcu_read_lock();
-
- spin_lock_bh(&msk->pm.lock);
- entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
- if (entry && (!check_id || entry->addr.id == addr->id)) {
- entry->retrans_times = ADD_ADDR_RETRANS_MAX;
- stop_timer = true;
- }
- if (!check_id && entry)
- list_del(&entry->list);
- spin_unlock_bh(&msk->pm.lock);
-
- /* Note: entry might have been removed by another thread.
- * We hold rcu_read_lock() to ensure it is not freed under us.
- */
- if (stop_timer)
- sk_stop_timer_sync(sk, &entry->add_timer);
-
- rcu_read_unlock();
- return entry;
+ if (timeout)
+ sk_reset_timer(sk, timer, jiffies + timeout);
+ else
+ /* if sock_put calls sk_free: avoid waiting for this timer */
+ entry->timer_done = true;
+ bh_unlock_sock(sk);
+ sock_put(sk);
}
-bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
+bool mptcp_pm_announced_alloc(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr)
{
- struct mptcp_pm_add_entry *add_entry = NULL;
+ struct mptcp_pm_add_addr *add_entry = NULL;
struct sock *sk = (struct sock *)msk;
unsigned int timeout;
lockdep_assert_held(&msk->pm.lock);
- add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
-
+ add_entry = mptcp_pm_announced_lookup(msk, addr);
if (add_entry) {
if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk)))
return false;
@@ -429,18 +459,19 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
add_entry->sock = msk;
add_entry->retrans_times = 0;
- timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
+ timer_setup(&add_entry->timer, mptcp_pm_add_addr_timer, 0);
reset_timer:
+ add_entry->timer_done = false;
timeout = mptcp_adjust_add_addr_timeout(msk);
if (timeout)
- sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout);
+ sk_reset_timer(sk, &add_entry->timer, jiffies + timeout);
return true;
}
-static void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
+static void mptcp_pm_free_announced_list(struct mptcp_sock *msk)
{
- struct mptcp_pm_add_entry *entry, *tmp;
+ struct mptcp_pm_add_addr *entry, *tmp;
struct sock *sk = (struct sock *)msk;
LIST_HEAD(free_list);
@@ -451,7 +482,8 @@ static void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
spin_unlock_bh(&msk->pm.lock);
list_for_each_entry_safe(entry, tmp, &free_list, list) {
- sk_stop_timer_sync(sk, &entry->add_timer);
+ if (!entry->timer_done)
+ sk_stop_timer_sync(sk, &entry->timer);
kfree_rcu(entry, rcu);
}
}
@@ -698,21 +730,25 @@ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr)
{
struct mptcp_pm_data *pm = &msk->pm;
+ struct mptcp_pm_add_addr *entry;
pr_debug("msk=%p\n", msk);
- if (!READ_ONCE(pm->work_pending))
+ entry = mptcp_pm_announced_del_timer(msk, addr, true);
+
+ if (!entry || !READ_ONCE(pm->work_pending))
return;
spin_lock_bh(&pm->lock);
- if (mptcp_lookup_anno_list_by_saddr(msk, addr) && READ_ONCE(pm->work_pending))
+ if (READ_ONCE(pm->work_pending))
mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED);
spin_unlock_bh(&pm->lock);
}
-void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk)
+/* To be called while pm->lock is held */
+static void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk)
{
if (!mptcp_pm_should_add_signal(msk))
return;
@@ -855,13 +891,29 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
}
}
-bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
- unsigned int opt_size, unsigned int remaining,
+static int mptcp_add_addr_len(int family, bool echo, bool port)
+{
+ int len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
+
+ if (family == AF_INET6)
+ len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
+ if (!echo)
+ len += MPTCPOPT_THMAC_LEN;
+ /* account for 2 trailing 'nop' options */
+ if (port)
+ len += TCPOLEN_MPTCP_PORT_LEN + TCPOLEN_MPTCP_PORT_ALIGN;
+
+ return len;
+}
+
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, int *size, int remaining,
struct mptcp_addr_info *addr, bool *echo,
- bool *drop_other_suboptions)
+ bool *drop_ts)
{
- int ret = false;
+ bool skip_add_addr = false;
+ bool ret = false;
u8 add_addr;
+ int len = 0;
u8 family;
bool port;
@@ -875,35 +927,74 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
* plain dup-ack from TCP perspective. The other MPTCP-relevant info,
* if any, will be carried by the 'original' TCP ack
*/
- if (skb && skb_is_tcp_pure_ack(skb)) {
- remaining += opt_size;
- *drop_other_suboptions = true;
- }
+ len -= *size;
*echo = mptcp_pm_should_add_signal_echo(msk);
- port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port);
-
- family = *echo ? msk->pm.remote.family : msk->pm.local.family;
- if (remaining < mptcp_add_addr_len(family, *echo, port))
- goto out_unlock;
-
if (*echo) {
*addr = msk->pm.remote;
add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_ECHO);
+ port = !!msk->pm.remote.port;
+ family = msk->pm.remote.family;
} else {
*addr = msk->pm.local;
add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_SIGNAL);
+ port = !!msk->pm.local.port;
+ family = msk->pm.local.family;
}
- WRITE_ONCE(msk->pm.addr_signal, add_addr);
+
+ len += mptcp_add_addr_len(family, *echo, port);
+ if (len > remaining) {
+ struct net *net = sock_net((struct sock *)msk);
+
+ if (*drop_ts && mptcp_add_addr_v6_port_drop_ts(net)) {
+ /* OK without TCP Timestamps? */
+ len -= TCPOLEN_TSTAMP_ALIGNED;
+ if (len <= remaining)
+ goto enough_space;
+ }
+
+ if (*echo) {
+ MPTCP_INC_STATS(net, MPTCP_MIB_ECHOADDTXDROP);
+ } else {
+ skip_add_addr = true;
+ MPTCP_INC_STATS(net, MPTCP_MIB_ADDADDRTXDROP);
+ }
+ goto drop_signal_mark;
+ }
+
+ *drop_ts = false;
+
+enough_space:
ret = true;
+ *size = len;
+
+drop_signal_mark:
+ WRITE_ONCE(msk->pm.addr_signal, add_addr);
out_unlock:
spin_unlock_bh(&msk->pm.lock);
+
+ /* On pure-ACK option-space exhaustion, stop retrying this ADD_ADDR:
+ * clear the signal bit, cancel the matching retransmission timer, and
+ * let the PM state machine progress.
+ */
+ if (skip_add_addr) {
+ mptcp_pm_announced_del_timer(msk, addr, true);
+ mptcp_pm_subflow_established(msk);
+ }
return ret;
}
+static int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list)
+{
+ if (rm_list->nr == 0 || rm_list->nr > MPTCP_RM_IDS_MAX)
+ return -EINVAL;
+
+ return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1;
+}
+
bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
- struct mptcp_rm_list *rm_list)
+ struct mptcp_rm_list *rm_list, int *size)
{
int ret = false, len;
u8 rm_addr;
@@ -923,6 +1014,7 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
if (remaining < len)
goto out_unlock;
+ *size = len;
*rm_list = msk->pm.rm_list_tx;
WRITE_ONCE(msk->pm.addr_signal, rm_addr);
ret = true;
@@ -1051,7 +1143,7 @@ void mptcp_pm_worker(struct mptcp_sock *msk)
void mptcp_pm_destroy(struct mptcp_sock *msk)
{
- mptcp_pm_free_anno_list(msk);
+ mptcp_pm_free_announced_list(msk);
if (mptcp_pm_is_userspace(msk))
mptcp_userspace_pm_free_local_addr_list(msk);
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index 0ebf43be9939..424f1a7f9248 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -30,6 +30,7 @@ struct pm_nl_pernet {
};
#define MPTCP_PM_ADDR_MAX 8
+#define MPTCP_PM_SUBFLOWS_MAX 64
static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net)
{
@@ -95,13 +96,13 @@ u8 mptcp_pm_get_limit_extra_subflows(const struct mptcp_sock *msk)
}
EXPORT_SYMBOL_GPL(mptcp_pm_get_limit_extra_subflows);
-static bool lookup_subflow_by_daddr(const struct list_head *list,
- const struct mptcp_addr_info *daddr)
+static bool has_subflow_daddr(const struct mptcp_sock *msk,
+ const struct mptcp_addr_info *daddr)
{
struct mptcp_subflow_context *subflow;
struct mptcp_addr_info cur;
- list_for_each_entry(subflow, list, node) {
+ mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
if (!((1 << inet_sk_state_load(ssk)) &
@@ -201,7 +202,8 @@ fill_remote_addr(struct mptcp_sock *msk, struct mptcp_addr_info *local,
static unsigned int
fill_remote_addresses_fullmesh(struct mptcp_sock *msk,
struct mptcp_addr_info *local,
- struct mptcp_addr_info *addrs)
+ struct mptcp_addr_info *addrs,
+ int addrs_size)
{
u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
@@ -236,7 +238,8 @@ fill_remote_addresses_fullmesh(struct mptcp_sock *msk,
msk->pm.extra_subflows++;
i++;
- if (msk->pm.extra_subflows >= limit_extra_subflows)
+ if (msk->pm.extra_subflows >= limit_extra_subflows ||
+ i == addrs_size)
break;
}
@@ -248,7 +251,8 @@ fill_remote_addresses_fullmesh(struct mptcp_sock *msk,
*/
static unsigned int
fill_remote_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *local,
- bool fullmesh, struct mptcp_addr_info *addrs)
+ bool fullmesh, struct mptcp_addr_info *addrs,
+ int addrs_size)
{
/* Non-fullmesh: fill in the single entry corresponding to the primary
* MPC subflow remote address, and return 1, corresponding to 1 entry.
@@ -257,7 +261,7 @@ fill_remote_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *local,
return fill_remote_addr(msk, local, addrs);
/* Fullmesh endpoint: fill all possible remote addresses */
- return fill_remote_addresses_fullmesh(msk, local, addrs);
+ return fill_remote_addresses_fullmesh(msk, local, addrs, addrs_size);
}
static struct mptcp_pm_addr_entry *
@@ -347,6 +351,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
/* check first for announce */
if (msk->pm.add_addr_signaled < endp_signal_max) {
+ u8 endp_id;
+
/* due to racing events on both ends we can reach here while
* previous add address is still running: if we invoke now
* mptcp_pm_announce_addr(), that will fail and the
@@ -360,19 +366,20 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
if (!select_signal_address(pernet, msk, &local))
goto subflow;
+ /* Special case for ID0: set the correct ID */
+ endp_id = local.addr.id;
+ if (endp_id == msk->mpc_endpoint_id)
+ local.addr.id = 0;
+
/* If the alloc fails, we are on memory pressure, not worth
* continuing, and trying to create subflows.
*/
- if (!mptcp_pm_alloc_anno_list(msk, &local.addr))
+ if (!mptcp_pm_announced_alloc(msk, &local.addr))
return;
- __clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+ __clear_bit(endp_id, msk->pm.id_avail_bitmap);
msk->pm.add_addr_signaled++;
- /* Special case for ID0: set the correct ID */
- if (local.addr.id == msk->mpc_endpoint_id)
- local.addr.id = 0;
-
mptcp_pm_announce_addr(msk, &local.addr, false);
mptcp_pm_addr_send_ack(msk);
@@ -407,7 +414,8 @@ subflow:
else /* local_addr_used is not decr for ID 0 */
msk->pm.local_addr_used++;
- nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs);
+ nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh,
+ addrs, ARRAY_SIZE(addrs));
if (nr == 0)
continue;
@@ -444,6 +452,7 @@ static unsigned int
fill_local_addresses_vec_fullmesh(struct mptcp_sock *msk,
struct mptcp_addr_info *remote,
struct mptcp_pm_local *locals,
+ int locals_size,
bool c_flag_case)
{
u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
@@ -485,7 +494,8 @@ fill_local_addresses_vec_fullmesh(struct mptcp_sock *msk,
msk->pm.extra_subflows++;
i++;
- if (msk->pm.extra_subflows >= limit_extra_subflows)
+ if (msk->pm.extra_subflows >= limit_extra_subflows ||
+ i == locals_size)
break;
}
rcu_read_unlock();
@@ -556,7 +566,8 @@ fill_local_laminar_endp(struct mptcp_sock *msk, struct mptcp_addr_info *remote,
static unsigned int
fill_local_addresses_vec_c_flag(struct mptcp_sock *msk,
struct mptcp_addr_info *remote,
- struct mptcp_pm_local *locals)
+ struct mptcp_pm_local *locals,
+ int locals_size)
{
u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk);
struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
@@ -583,7 +594,8 @@ fill_local_addresses_vec_c_flag(struct mptcp_sock *msk,
msk->pm.extra_subflows++;
i++;
- if (msk->pm.extra_subflows >= limit_extra_subflows)
+ if (msk->pm.extra_subflows >= limit_extra_subflows ||
+ i == locals_size)
break;
}
@@ -617,13 +629,14 @@ fill_local_address_any(struct mptcp_sock *msk, struct mptcp_addr_info *remote,
*/
static unsigned int
fill_local_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *remote,
- struct mptcp_pm_local *locals)
+ struct mptcp_pm_local *locals, int locals_size)
{
bool c_flag_case = remote->id && mptcp_pm_add_addr_c_flag_case(msk);
/* If there is at least one MPTCP endpoint with a fullmesh flag */
if (mptcp_pm_get_endp_fullmesh_max(msk))
return fill_local_addresses_vec_fullmesh(msk, remote, locals,
+ locals_size,
c_flag_case);
/* If there is at least one MPTCP endpoint with a laminar flag */
@@ -634,7 +647,8 @@ fill_local_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *remote,
* limits are used -- accepting no ADD_ADDR -- and use subflow endpoints
*/
if (c_flag_case)
- return fill_local_addresses_vec_c_flag(msk, remote, locals);
+ return fill_local_addresses_vec_c_flag(msk, remote, locals,
+ locals_size);
/* No special case: fill in the single 'IPADDRANY' local address */
return fill_local_address_any(msk, remote, &locals[0]);
@@ -659,7 +673,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
mptcp_pm_addr_send_ack(msk);
mptcp_mpc_endpoint_setup(msk);
- if (lookup_subflow_by_daddr(&msk->conn_list, &remote))
+ if (has_subflow_daddr(msk, &remote))
return;
/* pick id 0 port, if none is provided the remote address */
@@ -669,7 +683,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
/* connect to the specified remote address, using whatever
* local address the routing configuration will pick.
*/
- nr = fill_local_addresses_vec(msk, &remote, locals);
+ nr = fill_local_addresses_vec(msk, &remote, locals, ARRAY_SIZE(locals));
if (nr == 0)
return;
@@ -732,7 +746,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
*/
if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID)
pernet->next_id = 1;
- if (pernet->endpoints >= MPTCP_PM_ADDR_MAX) {
+ if (pernet->endpoints == MPTCP_PM_MAX_ADDR_ID) {
ret = -ERANGE;
goto out;
}
@@ -1039,7 +1053,7 @@ out_free:
return ret;
}
-static void mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
+static void mptcp_pm_remove_announced(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr,
bool force)
{
@@ -1048,7 +1062,7 @@ static void mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
- announced = mptcp_remove_anno_list_by_saddr(msk, addr);
+ announced = mptcp_pm_announced_remove(msk, addr);
if (announced || force) {
spin_lock_bh(&msk->pm.lock);
if (announced)
@@ -1084,8 +1098,8 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
goto next;
lock_sock(sk);
- remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr);
- mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
+ remove_subflow = mptcp_pm_has_subflow_saddr(msk, addr);
+ mptcp_pm_remove_announced(msk, addr, remove_subflow &&
!(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
list.ids[0] = mptcp_endp_get_local_id(msk, addr);
@@ -1209,19 +1223,30 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
}
static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk,
- struct list_head *rm_list)
+ struct list_head *rm_list,
+ struct mptcp_pm_addr_entry *entry)
{
- struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 };
- struct mptcp_pm_addr_entry *entry;
+ struct mptcp_rm_list alist, slist;
+ bool more;
- list_for_each_entry(entry, rm_list, list) {
- if (slist.nr < MPTCP_RM_IDS_MAX &&
- mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
+again:
+ alist.nr = 0;
+ slist.nr = 0;
+ more = false;
+
+ entry = list_prepare_entry(entry, rm_list, list);
+ list_for_each_entry_continue(entry, rm_list, list) {
+ if (mptcp_pm_has_subflow_saddr(msk, &entry->addr))
slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
- if (alist.nr < MPTCP_RM_IDS_MAX &&
- mptcp_remove_anno_list_by_saddr(msk, &entry->addr))
+ if (mptcp_pm_announced_remove(msk, &entry->addr))
alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
+
+ if (slist.nr == MPTCP_RM_IDS_MAX ||
+ alist.nr == MPTCP_RM_IDS_MAX) {
+ more = !list_is_last(&entry->list, rm_list);
+ break;
+ }
}
spin_lock_bh(&msk->pm.lock);
@@ -1232,9 +1257,14 @@ static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk,
if (slist.nr)
mptcp_pm_rm_subflow(msk, &slist);
/* Reset counters: maybe some subflows have been removed before */
- bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
- msk->pm.local_addr_used = 0;
+ if (!more) {
+ bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+ msk->pm.local_addr_used = 0;
+ }
spin_unlock_bh(&msk->pm.lock);
+
+ if (more)
+ goto again;
}
static void mptcp_nl_flush_addrs_list(struct net *net,
@@ -1251,7 +1281,7 @@ static void mptcp_nl_flush_addrs_list(struct net *net,
if (!mptcp_pm_is_userspace(msk)) {
lock_sock(sk);
- mptcp_pm_flush_addrs_and_subflows(msk, rm_list);
+ mptcp_pm_flush_addrs_and_subflows(msk, rm_list, NULL);
release_sock(sk);
}
@@ -1278,6 +1308,7 @@ static void __reset_counters(struct pm_nl_pernet *pernet)
WRITE_ONCE(pernet->endp_signal_max, 0);
WRITE_ONCE(pernet->endp_subflow_max, 0);
WRITE_ONCE(pernet->endp_laminar_max, 0);
+ WRITE_ONCE(pernet->endp_fullmesh_max, 0);
pernet->endpoints = 0;
}
@@ -1367,10 +1398,10 @@ static int parse_limit(struct genl_info *info, int id, unsigned int *limit)
return 0;
*limit = nla_get_u32(attr);
- if (*limit > MPTCP_PM_ADDR_MAX) {
+ if (*limit > MPTCP_PM_SUBFLOWS_MAX) {
NL_SET_ERR_MSG_ATTR_FMT(info->extack, attr,
"limit greater than maximum (%u)",
- MPTCP_PM_ADDR_MAX);
+ MPTCP_PM_SUBFLOWS_MAX);
return -EINVAL;
}
return 0;
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 8cbc1920afb4..945aa5afc2dd 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -132,12 +132,15 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
__be16 msk_sport = ((struct inet_sock *)
inet_sk((struct sock *)msk))->inet_sport;
struct mptcp_pm_addr_entry *entry;
+ int id;
spin_lock_bh(&msk->pm.lock);
entry = mptcp_userspace_pm_lookup_addr(msk, &skc->addr);
+ id = entry ? entry->addr.id : -1;
spin_unlock_bh(&msk->pm.lock);
- if (entry)
- return entry->addr.id;
+
+ if (id != -1)
+ return id;
if (skc->addr.port == msk_sport)
skc->addr.port = 0;
@@ -228,7 +231,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
lock_sock(sk);
spin_lock_bh(&msk->pm.lock);
- if (mptcp_pm_alloc_anno_list(msk, &addr_val.addr)) {
+ if (mptcp_pm_announced_alloc(msk, &addr_val.addr)) {
msk->pm.add_addr_signaled++;
mptcp_pm_announce_addr(msk, &addr_val.addr, false);
mptcp_pm_addr_send_ack(msk);
@@ -281,9 +284,9 @@ void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk,
int anno_nr = 0;
/* only delete if either announced or matching a subflow */
- if (mptcp_remove_anno_list_by_saddr(msk, &entry->addr))
+ if (mptcp_pm_announced_remove(msk, &entry->addr))
anno_nr++;
- else if (!mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
+ else if (!mptcp_pm_has_subflow_saddr(msk, &entry->addr))
return;
alist.ids[alist.nr++] = entry->addr.id;
@@ -408,19 +411,21 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
local.flags = entry.flags;
local.ifindex = entry.ifindex;
+ spin_lock_bh(&msk->pm.lock);
+ msk->pm.extra_subflows++;
+ spin_unlock_bh(&msk->pm.lock);
+
lock_sock(sk);
err = __mptcp_subflow_connect(sk, &local, &addr_r);
release_sock(sk);
- if (err)
+ if (err) {
GENL_SET_ERR_MSG_FMT(info, "connect error: %d", err);
- spin_lock_bh(&msk->pm.lock);
- if (err)
+ spin_lock_bh(&msk->pm.lock);
mptcp_userspace_pm_delete_local_addr(msk, &entry);
- else
- msk->pm.extra_subflows++;
- spin_unlock_bh(&msk->pm.lock);
+ spin_unlock_bh(&msk->pm.lock);
+ }
create_err:
sock_put(sk);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 718e910ff23f..ca644ec53eed 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -397,12 +397,26 @@ static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb)
return false;
}
- /* old data, keep it simple and drop the whole pkt, sender
- * will retransmit as needed, if needed.
+ /* Completely old data? */
+ if (!after64(MPTCP_SKB_CB(skb)->end_seq, msk->ack_seq)) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+ mptcp_drop(sk, skb);
+ return false;
+ }
+
+ /* Partial packet: map_seq < ack_seq < end_seq.
+ * Skip the already-acked bytes and enqueue the new data.
*/
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
- mptcp_drop(sk, skb);
- return false;
+ copy_len = MPTCP_SKB_CB(skb)->end_seq - msk->ack_seq;
+ MPTCP_SKB_CB(skb)->offset += msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
+ MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq -
+ MPTCP_SKB_CB(skb)->map_seq;
+ msk->bytes_received += copy_len;
+ WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len);
+
+ skb_set_owner_r(skb, sk);
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
+ return true;
}
static void mptcp_stop_rtx_timer(struct sock *sk)
@@ -2262,6 +2276,10 @@ static bool mptcp_move_skbs(struct sock *sk)
mptcp_backlog_spooled(sk, moved, &skbs);
}
mptcp_data_unlock(sk);
+
+ if (enqueued && mptcp_epollin_ready(sk))
+ sk->sk_data_ready(sk);
+
return enqueued;
}
@@ -2527,6 +2545,22 @@ static void __mptcp_subflow_disconnect(struct sock *ssk,
}
}
+static void mptcp_cleanup_ssk_backlog(struct sock *sk, struct sock *ssk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct sk_buff *skb;
+
+ mptcp_data_lock(sk);
+ list_for_each_entry(skb, &msk->backlog_list, list) {
+ if (skb->sk != ssk)
+ continue;
+
+ atomic_sub(skb->truesize, &skb->sk->sk_rmem_alloc);
+ skb->sk = NULL;
+ }
+ mptcp_data_unlock(sk);
+}
+
/* subflow sockets can be either outgoing (connect) or incoming
* (accept).
*
@@ -2550,6 +2584,9 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
subflow->closing = 1;
+ if (flags & MPTCP_CF_PUSH)
+ mptcp_cleanup_ssk_backlog(sk, ssk);
+
/* Borrow the fwd allocated page left-over; fwd memory for the subflow
* could be negative at this point, but will be reach zero soon - when
* the data allocated using such fragment will be freed.
@@ -2641,9 +2678,6 @@ out:
void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow)
{
- struct mptcp_sock *msk = mptcp_sk(sk);
- struct sk_buff *skb;
-
/* The first subflow can already be closed or disconnected */
if (subflow->close_event_done || READ_ONCE(subflow->local_id) < 0)
return;
@@ -2653,17 +2687,6 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
if (sk->sk_state == TCP_ESTABLISHED)
mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL);
- /* Remove any reference from the backlog to this ssk; backlog skbs consume
- * space in the msk receive queue, no need to touch sk->sk_rmem_alloc
- */
- list_for_each_entry(skb, &msk->backlog_list, list) {
- if (skb->sk != ssk)
- continue;
-
- atomic_sub(skb->truesize, &skb->sk->sk_rmem_alloc);
- skb->sk = NULL;
- }
-
/* subflow aborted before reaching the fully_established status
* attempt the creation of the next subflow
*/
@@ -2851,6 +2874,10 @@ static void __mptcp_retrans(struct sock *sk)
msk->bytes_retrans += len;
dfrag->already_sent = max(dfrag->already_sent, len);
+ /* With csum enabled retransmission can send new data. */
+ if (after64(dfrag->already_sent + dfrag->data_seq, msk->snd_nxt))
+ WRITE_ONCE(msk->snd_nxt, dfrag->already_sent + dfrag->data_seq);
+
reset_timer:
mptcp_check_and_set_pending(sk);
@@ -3302,7 +3329,8 @@ bool __mptcp_close(struct sock *sk, long timeout)
goto cleanup;
}
- if (mptcp_data_avail(msk) || timeout < 0) {
+ if (mptcp_data_avail(msk) || timeout < 0 ||
+ (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)) {
/* If the msk has read data, or the caller explicitly ask it,
* do the MPTCP equivalent of TCP reset, aka MPTCP fastclose
*/
@@ -3472,6 +3500,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
/* for fallback's sake */
WRITE_ONCE(msk->ack_seq, 0);
+ atomic64_set(&msk->rcv_wnd_sent, 0);
WRITE_ONCE(sk->sk_shutdown, 0);
sk_error_report(sk);
@@ -3883,6 +3912,7 @@ bool mptcp_finish_join(struct sock *ssk)
mptcp_data_unlock(parent);
if (!ret) {
+ mptcp_pm_close_subflow(msk);
err_prohibited:
subflow->reset_reason = MPTCP_RST_EPROHIBIT;
return false;
@@ -4404,6 +4434,8 @@ static int __mptcp_read_sock(struct sock *sk, read_descriptor_t *desc,
}
mptcp_eat_recv_skb(sk, skb);
+ if (!desc->count)
+ break;
}
if (noack)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index e4f5aba24da7..4a2d40cd7b13 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -798,6 +798,7 @@ unsigned int mptcp_close_timeout(const struct sock *sk);
int mptcp_get_pm_type(const struct net *net);
const char *mptcp_get_path_manager(const struct net *net);
const char *mptcp_get_scheduler(const struct net *net);
+unsigned int mptcp_add_addr_v6_port_drop_ts(const struct net *net);
void mptcp_active_disable(struct sock *sk);
bool mptcp_active_should_disable(struct sock *ssk);
@@ -1113,7 +1114,6 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
const struct mptcp_addr_info *addr);
void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr);
-void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
void mptcp_pm_send_ack(struct mptcp_sock *msk,
struct mptcp_subflow_context *subflow,
bool prio, bool backup);
@@ -1129,16 +1129,13 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
struct mptcp_addr_info *addr,
struct mptcp_addr_info *rem,
u8 bkup);
-bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
+bool mptcp_pm_announced_alloc(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr);
-bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
-struct mptcp_pm_add_entry *
-mptcp_pm_del_add_timer(struct mptcp_sock *msk,
- const struct mptcp_addr_info *addr, bool check_id);
-bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
- const struct mptcp_addr_info *saddr);
-bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
- const struct mptcp_addr_info *addr);
+bool mptcp_pm_announced_remove(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr);
+bool mptcp_pm_announced_has_ssk(struct mptcp_sock *msk, const struct sock *ssk);
+bool mptcp_pm_has_subflow_saddr(const struct mptcp_sock *msk,
+ const struct mptcp_addr_info *saddr);
int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
struct genl_info *info);
int mptcp_userspace_pm_set_flags(struct mptcp_pm_addr_entry *local,
@@ -1206,35 +1203,11 @@ static inline bool mptcp_pm_is_kernel(const struct mptcp_sock *msk)
return READ_ONCE(msk->pm.pm_type) == MPTCP_PM_TYPE_KERNEL;
}
-static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port)
-{
- u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
-
- if (family == AF_INET6)
- len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
- if (!echo)
- len += MPTCPOPT_THMAC_LEN;
- /* account for 2 trailing 'nop' options */
- if (port)
- len += TCPOLEN_MPTCP_PORT_LEN + TCPOLEN_MPTCP_PORT_ALIGN;
-
- return len;
-}
-
-static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list)
-{
- if (rm_list->nr == 0 || rm_list->nr > MPTCP_RM_IDS_MAX)
- return -EINVAL;
-
- return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1;
-}
-
-bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
- unsigned int opt_size, unsigned int remaining,
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, int *size, int remaining,
struct mptcp_addr_info *addr, bool *echo,
- bool *drop_other_suboptions);
+ bool *drop_ts);
bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
- struct mptcp_rm_list *rm_list);
+ struct mptcp_rm_list *rm_list, int *len);
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
struct mptcp_pm_addr_entry *skc);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index de90a2897d2d..fcf6feb2a9eb 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -67,6 +67,12 @@ static int mptcp_get_int_option(struct mptcp_sock *msk, sockptr_t optval,
return 0;
}
+static void __mptcp_subflow_set_rcvbuf(struct sock *ssk, int val)
+{
+ WRITE_ONCE(ssk->sk_rcvbuf, val);
+ tcp_set_rcvbuf(ssk, val);
+}
+
static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, int val)
{
struct mptcp_subflow_context *subflow;
@@ -100,7 +106,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in
case SO_RCVBUF:
case SO_RCVBUFFORCE:
ssk->sk_userlocks |= SOCK_RCVBUF_LOCK;
- WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf);
+ __mptcp_subflow_set_rcvbuf(ssk, sk->sk_rcvbuf);
break;
case SO_MARK:
if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) {
@@ -159,10 +165,10 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam
lock_sock(sk);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- bool slow = lock_sock_fast(ssk);
- sock_set_timestamp(sk, optname, !!val);
- unlock_sock_fast(ssk, slow);
+ lock_sock(ssk);
+ sock_set_timestamp(ssk, optname, !!val);
+ release_sock(ssk);
}
release_sock(sk);
@@ -235,15 +241,19 @@ static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk,
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- bool slow = lock_sock_fast(ssk);
+ int err;
- sock_set_timestamping(sk, optname, timestamping);
- unlock_sock_fast(ssk, slow);
+ lock_sock(ssk);
+ err = sock_set_timestamping(ssk, optname, timestamping);
+ release_sock(ssk);
+
+ if (err < 0 && ret == 0)
+ ret = err;
}
release_sock(sk);
- return 0;
+ return ret;
}
static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval,
@@ -807,11 +817,16 @@ static int mptcp_setsockopt_all_sf(struct mptcp_sock *msk, int level,
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ int err;
- ret = tcp_setsockopt(ssk, level, optname, optval, optlen);
- if (ret)
- break;
+ err = tcp_setsockopt(ssk, level, optname, optval, optlen);
+ if (err < 0 && ret == 0)
+ ret = err;
}
+
+ if (!ret)
+ sockopt_seq_inc(msk);
+
return ret;
}
@@ -1556,7 +1571,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf;
}
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
- WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf);
+ __mptcp_subflow_set_rcvbuf(ssk, sk->sk_rcvbuf);
}
if (sock_flag(sk, SOCK_LINGER)) {
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index e2cb9d23e4a0..8e386899ceb9 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -235,7 +235,7 @@ again:
pr_debug("syn inet_sport=%d %d\n",
ntohs(inet_sk(sk_listener)->inet_sport),
ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
- if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
+ if (!mptcp_pm_announced_has_ssk(subflow_req->msk, sk_listener)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
return -EPERM;
@@ -581,7 +581,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->backup);
if (!subflow_thmac_valid(subflow)) {
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC);
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKMAC);
subflow->reset_reason = MPTCP_RST_EMPTCP;
goto do_reset;
}
@@ -908,7 +908,7 @@ create_child:
if (!subflow_hmac_valid(subflow_req, &mp_opt)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
- subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
+ subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
goto dispose_child;
}
@@ -926,7 +926,7 @@ create_child:
pr_debug("ack inet_sport=%d %d\n",
ntohs(inet_sk(sk)->inet_sport),
ntohs(inet_sk((struct sock *)owner)->inet_sport));
- if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
+ if (!mptcp_pm_announced_has_ssk(owner, sk)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
goto dispose_child;
generated by cgit v1.2.3 (git 2.0.4) at 2026-07-29 04:50:36 +0000