summaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/ctrl.c34
-rw-r--r--net/mptcp/diag.c2
-rw-r--r--net/mptcp/fastopen.c4
-rw-r--r--net/mptcp/mib.c2
-rw-r--r--net/mptcp/mib.h4
-rw-r--r--net/mptcp/options.c56
-rw-r--r--net/mptcp/pm.c57
-rw-r--r--net/mptcp/pm_netlink.c324
-rw-r--r--net/mptcp/pm_userspace.c19
-rw-r--r--net/mptcp/protocol.c131
-rw-r--r--net/mptcp/protocol.h70
-rw-r--r--net/mptcp/sched.c26
-rw-r--r--net/mptcp/sockopt.c92
-rw-r--r--net/mptcp/subflow.c171
14 files changed, 699 insertions, 293 deletions
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 2963ba84e2ee..99382c317ebb 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -92,7 +92,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
pernet->allow_join_initial_addr_port = 1;
pernet->stale_loss_cnt = 4;
pernet->pm_type = MPTCP_PM_TYPE_KERNEL;
- strcpy(pernet->scheduler, "default");
+ strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler));
}
#ifdef CONFIG_SYSCTL
@@ -113,7 +113,7 @@ static int mptcp_set_scheduler(const struct net *net, const char *name)
return ret;
}
-static int proc_scheduler(struct ctl_table *ctl, int write,
+static int proc_scheduler(const struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
const struct net *net = current->nsproxy->net_ns;
@@ -133,6 +133,24 @@ static int proc_scheduler(struct ctl_table *ctl, int write,
return ret;
}
+static int proc_available_schedulers(const struct ctl_table *ctl,
+ int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table tbl = { .maxlen = MPTCP_SCHED_BUF_MAX, };
+ int ret;
+
+ tbl.data = kmalloc(tbl.maxlen, GFP_USER);
+ if (!tbl.data)
+ return -ENOMEM;
+
+ mptcp_get_available_schedulers(tbl.data, MPTCP_SCHED_BUF_MAX);
+ ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+ kfree(tbl.data);
+
+ return ret;
+}
+
static struct ctl_table mptcp_sysctl_table[] = {
{
.procname = "enabled",
@@ -188,12 +206,17 @@ static struct ctl_table mptcp_sysctl_table[] = {
.proc_handler = proc_scheduler,
},
{
+ .procname = "available_schedulers",
+ .maxlen = MPTCP_SCHED_BUF_MAX,
+ .mode = 0644,
+ .proc_handler = proc_available_schedulers,
+ },
+ {
.procname = "close_timeout",
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- {}
};
static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -215,7 +238,8 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
table[4].data = &pernet->stale_loss_cnt;
table[5].data = &pernet->pm_type;
table[6].data = &pernet->scheduler;
- table[7].data = &pernet->close_timeout;
+ /* table[7] is for available_schedulers which is read-only info */
+ table[8].data = &pernet->close_timeout;
hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
ARRAY_SIZE(mptcp_sysctl_table));
@@ -235,7 +259,7 @@ err_alloc:
static void mptcp_pernet_del_table(struct mptcp_pernet *pernet)
{
- struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg;
+ const struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg;
unregister_net_sysctl_table(pernet->ctl_table_hdr);
diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
index 3ae46b545d2c..2d3efb405437 100644
--- a/net/mptcp/diag.c
+++ b/net/mptcp/diag.c
@@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk)
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */
nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */
- nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
+ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */
nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */
diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index ad28da655f8b..a29ff901df75 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -68,12 +68,12 @@ void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflo
skb = skb_peek_tail(&sk->sk_receive_queue);
if (skb) {
WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
- pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx", sk,
+ pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx\n", sk,
MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq,
MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq);
MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq;
MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq;
}
- pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);
+ pr_debug("msk=%p ack_seq=%llx\n", msk, msk->ack_seq);
}
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index c30405e76833..7884217f33eb 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX),
+ SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX),
SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX),
+ SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX),
SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index dd7fd1f246b5..66aa67f49d03 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -1,5 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
+#include <net/inet_common.h>
+
enum linux_mptcp_mib_field {
MPTCP_MIB_NUM = 0,
MPTCP_MIB_MPCAPABLEPASSIVE, /* Received SYN with MP_CAPABLE */
@@ -12,7 +14,9 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */
MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */
MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */
+ MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */
MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */
+ MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */
MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */
MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */
MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 27ca42c77b02..370c3836b771 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -117,7 +117,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
ptr += 2;
}
- pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u",
+ pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u\n",
version, flags, opsize, mp_opt->sndr_key,
mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum);
break;
@@ -131,7 +131,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 4;
mp_opt->nonce = get_unaligned_be32(ptr);
ptr += 4;
- pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u",
+ pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u\n",
mp_opt->backup, mp_opt->join_id,
mp_opt->token, mp_opt->nonce);
} else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) {
@@ -142,19 +142,19 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 8;
mp_opt->nonce = get_unaligned_be32(ptr);
ptr += 4;
- pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u",
+ pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u\n",
mp_opt->backup, mp_opt->join_id,
mp_opt->thmac, mp_opt->nonce);
} else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) {
mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK;
ptr += 2;
memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
- pr_debug("MP_JOIN hmac");
+ pr_debug("MP_JOIN hmac\n");
}
break;
case MPTCPOPT_DSS:
- pr_debug("DSS");
+ pr_debug("DSS\n");
ptr++;
/* we must clear 'mpc_map' be able to detect MP_CAPABLE
@@ -169,7 +169,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
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",
+ 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);
@@ -207,7 +207,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 4;
}
- pr_debug("data_ack=%llu", mp_opt->data_ack);
+ pr_debug("data_ack=%llu\n", mp_opt->data_ack);
}
if (mp_opt->use_map) {
@@ -231,7 +231,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 2;
}
- pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
+ pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n",
mp_opt->data_seq, mp_opt->subflow_seq,
mp_opt->data_len, !!(mp_opt->suboptions & OPTION_MPTCP_CSUMREQD),
mp_opt->csum);
@@ -293,7 +293,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->ahmac = get_unaligned_be64(ptr);
ptr += 8;
}
- pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d",
+ pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d\n",
(mp_opt->addr.family == AF_INET6) ? "6" : "",
mp_opt->addr.id, mp_opt->ahmac, mp_opt->echo, ntohs(mp_opt->addr.port));
break;
@@ -309,7 +309,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE;
for (i = 0; i < mp_opt->rm_list.nr; i++)
mp_opt->rm_list.ids[i] = *ptr++;
- pr_debug("RM_ADDR: rm_list_nr=%d", mp_opt->rm_list.nr);
+ pr_debug("RM_ADDR: rm_list_nr=%d\n", mp_opt->rm_list.nr);
break;
case MPTCPOPT_MP_PRIO:
@@ -318,7 +318,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->suboptions |= OPTION_MPTCP_PRIO;
mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP;
- pr_debug("MP_PRIO: prio=%d", mp_opt->backup);
+ pr_debug("MP_PRIO: prio=%d\n", mp_opt->backup);
break;
case MPTCPOPT_MP_FASTCLOSE:
@@ -329,7 +329,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
mp_opt->rcvr_key = get_unaligned_be64(ptr);
ptr += 8;
mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE;
- pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key);
+ pr_debug("MP_FASTCLOSE: recv_key=%llu\n", mp_opt->rcvr_key);
break;
case MPTCPOPT_RST:
@@ -343,7 +343,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
flags = *ptr++;
mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT;
mp_opt->reset_reason = *ptr;
- pr_debug("MP_RST: transient=%u reason=%u",
+ pr_debug("MP_RST: transient=%u reason=%u\n",
mp_opt->reset_transient, mp_opt->reset_reason);
break;
@@ -354,7 +354,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
ptr += 2;
mp_opt->suboptions |= OPTION_MPTCP_FAIL;
mp_opt->fail_seq = get_unaligned_be64(ptr);
- pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq);
+ pr_debug("MP_FAIL: data_seq=%llu\n", mp_opt->fail_seq);
break;
default:
@@ -417,7 +417,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
*size = TCPOLEN_MPTCP_MPC_SYN;
return true;
} else if (subflow->request_join) {
- pr_debug("remote_token=%u, nonce=%u", subflow->remote_token,
+ pr_debug("remote_token=%u, nonce=%u\n", subflow->remote_token,
subflow->local_nonce);
opts->suboptions = OPTION_MPTCP_MPJ_SYN;
opts->join_id = subflow->local_id;
@@ -500,7 +500,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
*size = TCPOLEN_MPTCP_MPC_ACK;
}
- pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d",
+ pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d\n",
subflow, subflow->local_key, subflow->remote_key,
data_len);
@@ -509,7 +509,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
opts->suboptions = OPTION_MPTCP_MPJ_ACK;
memcpy(opts->hmac, subflow->hmac, MPTCPOPT_HMAC_LEN);
*size = TCPOLEN_MPTCP_MPJ_ACK;
- pr_debug("subflow=%p", subflow);
+ pr_debug("subflow=%p\n", subflow);
/* we can use the full delegate action helper only from BH context
* If we are in process context - sk is flushing the backlog at
@@ -675,7 +675,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
*size = len;
if (drop_other_suboptions) {
- pr_debug("drop other suboptions");
+ pr_debug("drop other suboptions\n");
opts->suboptions = 0;
/* note that e.g. DSS could have written into the memory
@@ -695,7 +695,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
} else {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX);
}
- pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
+ pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n",
opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port));
return true;
@@ -726,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk,
opts->rm_list = rm_list;
for (i = 0; i < opts->rm_list.nr; i++)
- pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]);
+ pr_debug("rm_list_ids[%d]=%d\n", i, opts->rm_list.ids[i]);
MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr);
return true;
}
@@ -752,7 +752,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk,
opts->suboptions |= OPTION_MPTCP_PRIO;
opts->backup = subflow->request_bkup;
- pr_debug("prio=%d", opts->backup);
+ pr_debug("prio=%d\n", opts->backup);
return true;
}
@@ -794,7 +794,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk,
opts->suboptions |= OPTION_MPTCP_FASTCLOSE;
opts->rcvr_key = READ_ONCE(msk->remote_key);
- pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);
+ pr_debug("FASTCLOSE key=%llu\n", opts->rcvr_key);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
return true;
}
@@ -816,7 +816,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk,
opts->suboptions |= OPTION_MPTCP_FAIL;
opts->fail_seq = subflow->map_seq;
- pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);
+ pr_debug("MP_FAIL fail_seq=%llu\n", opts->fail_seq);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
return true;
@@ -904,16 +904,16 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
opts->csum_reqd = subflow_req->csum_reqd;
opts->allow_join_id0 = subflow_req->allow_join_id0;
*size = TCPOLEN_MPTCP_MPC_SYNACK;
- pr_debug("subflow_req=%p, local_key=%llu",
+ pr_debug("subflow_req=%p, local_key=%llu\n",
subflow_req, subflow_req->local_key);
return true;
} else if (subflow_req->mp_join) {
opts->suboptions = OPTION_MPTCP_MPJ_SYNACK;
- opts->backup = subflow_req->backup;
+ opts->backup = subflow_req->request_bkup;
opts->join_id = subflow_req->local_id;
opts->thmac = subflow_req->thmac;
opts->nonce = subflow_req->local_nonce;
- pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u",
+ pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u\n",
subflow_req, opts->backup, opts->join_id,
opts->thmac, opts->nonce);
*size = TCPOLEN_MPTCP_MPJ_SYNACK;
@@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
if (subflow->remote_key_valid &&
(((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) ||
- ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) {
+ ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) &&
+ (!mp_opt->echo || subflow->mp_join)))) {
/* subflows are fully established as soon as we get any
* additional ack, including ADD_ADDR.
*/
@@ -1068,6 +1069,7 @@ static void ack_update_msk(struct mptcp_sock *msk,
__mptcp_snd_una_update(msk, new_snd_una);
__mptcp_data_acked(sk);
}
+ msk->last_ack_recv = tcp_jiffies32;
mptcp_data_unlock(sk);
trace_ack_update_msk(mp_opt->data_ack,
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 55406720c607..37f6dbcd8434 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -19,7 +19,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
{
u8 add_addr = READ_ONCE(msk->pm.addr_signal);
- pr_debug("msk=%p, local_id=%d, echo=%d", msk, addr->id, echo);
+ pr_debug("msk=%p, local_id=%d, echo=%d\n", msk, addr->id, echo);
lockdep_assert_held(&msk->pm.lock);
@@ -45,7 +45,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
{
u8 rm_addr = READ_ONCE(msk->pm.addr_signal);
- pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
+ pr_debug("msk=%p, rm_list_nr=%d\n", msk, rm_list->nr);
if (rm_addr) {
MPTCP_ADD_STATS(sock_net((struct sock *)msk),
@@ -60,23 +60,13 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
return 0;
}
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list)
-{
- pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
-
- spin_lock_bh(&msk->pm.lock);
- mptcp_pm_nl_rm_subflow_received(msk, rm_list);
- spin_unlock_bh(&msk->pm.lock);
- return 0;
-}
-
/* path manager event handlers */
void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side)
{
struct mptcp_pm_data *pm = &msk->pm;
- pr_debug("msk=%p, token=%u side=%d", msk, READ_ONCE(msk->token), server_side);
+ pr_debug("msk=%p, token=%u side=%d\n", msk, READ_ONCE(msk->token), server_side);
WRITE_ONCE(pm->server_side, server_side);
mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC);
@@ -100,7 +90,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
subflows_max = mptcp_pm_get_subflows_max(msk);
- pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows,
+ pr_debug("msk=%p subflows=%d max=%d allow=%d\n", msk, pm->subflows,
subflows_max, READ_ONCE(pm->accept_subflow));
/* try to avoid acquiring the lock below */
@@ -124,7 +114,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
static bool mptcp_pm_schedule_work(struct mptcp_sock *msk,
enum mptcp_pm_status new_status)
{
- pr_debug("msk=%p status=%x new=%lx", msk, msk->pm.status,
+ pr_debug("msk=%p status=%x new=%lx\n", msk, msk->pm.status,
BIT(new_status));
if (msk->pm.status & BIT(new_status))
return false;
@@ -139,7 +129,7 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
struct mptcp_pm_data *pm = &msk->pm;
bool announce = false;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
spin_lock_bh(&pm->lock);
@@ -163,14 +153,14 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
void mptcp_pm_connection_closed(struct mptcp_sock *msk)
{
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
}
void mptcp_pm_subflow_established(struct mptcp_sock *msk)
{
struct mptcp_pm_data *pm = &msk->pm;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
if (!READ_ONCE(pm->work_pending))
return;
@@ -222,7 +212,7 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct mptcp_pm_data *pm = &msk->pm;
- pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id,
+ pr_debug("msk=%p remote_id=%d accept=%d\n", msk, addr->id,
READ_ONCE(pm->accept_addr));
mptcp_event_addr_announced(ssk, addr);
@@ -236,7 +226,9 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
} else {
__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP);
}
- } else if (!READ_ONCE(pm->accept_addr)) {
+ /* id0 should not have a different address */
+ } else if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) ||
+ (addr->id > 0 && !READ_ONCE(pm->accept_addr))) {
mptcp_pm_announce_addr(msk, addr, true);
mptcp_pm_add_addr_send_ack(msk);
} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
@@ -253,7 +245,7 @@ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
{
struct mptcp_pm_data *pm = &msk->pm;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
spin_lock_bh(&pm->lock);
@@ -277,7 +269,7 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
struct mptcp_pm_data *pm = &msk->pm;
u8 i;
- pr_debug("msk=%p remote_ids_nr=%d", msk, rm_list->nr);
+ pr_debug("msk=%p remote_ids_nr=%d\n", msk, rm_list->nr);
for (i = 0; i < rm_list->nr; i++)
mptcp_event_addr_removed(msk, rm_list->ids[i]);
@@ -309,19 +301,19 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
- pr_debug("fail_seq=%llu", fail_seq);
+ pr_debug("fail_seq=%llu\n", fail_seq);
if (!READ_ONCE(msk->allow_infinite_fallback))
return;
if (!subflow->fail_tout) {
- pr_debug("send MP_FAIL response and infinite map");
+ pr_debug("send MP_FAIL response and infinite map\n");
subflow->send_mp_fail = 1;
subflow->send_infinite_map = 1;
tcp_send_ack(sk);
} else {
- pr_debug("MP_FAIL response received");
+ pr_debug("MP_FAIL response received\n");
WRITE_ONCE(subflow->fail_tout, 0);
}
}
@@ -426,15 +418,24 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
return mptcp_pm_nl_get_local_id(msk, &skc_local);
}
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
+{
+ struct mptcp_addr_info skc_local;
+
+ mptcp_local_address((struct sock_common *)skc, &skc_local);
+
+ if (mptcp_pm_is_userspace(msk))
+ return mptcp_userspace_pm_is_backup(msk, &skc_local);
+
+ return mptcp_pm_nl_is_backup(msk, &skc_local);
+}
+
int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
u8 *flags, int *ifindex)
{
*flags = 0;
*ifindex = 0;
- if (!id)
- return 0;
-
if (mptcp_pm_is_userspace(msk))
return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 5c17d39146ea..f891bc714668 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -14,6 +14,7 @@
#include "protocol.h"
#include "mib.h"
+#include "mptcp_pm_gen.h"
static int pm_nl_pernet_id;
@@ -129,12 +130,15 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
{
struct mptcp_subflow_context *subflow;
struct mptcp_addr_info cur;
- struct sock_common *skc;
list_for_each_entry(subflow, list, node) {
- skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- remote_address(skc, &cur);
+ if (!((1 << inet_sk_state_load(ssk)) &
+ (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV)))
+ continue;
+
+ remote_address((struct sock_common *)ssk, &cur);
if (mptcp_addresses_equal(&cur, daddr, daddr->port))
return true;
}
@@ -142,11 +146,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
return false;
}
-static struct mptcp_pm_addr_entry *
+static bool
select_local_address(const struct pm_nl_pernet *pernet,
- const struct mptcp_sock *msk)
+ const struct mptcp_sock *msk,
+ struct mptcp_pm_addr_entry *new_entry)
{
- struct mptcp_pm_addr_entry *entry, *ret = NULL;
+ struct mptcp_pm_addr_entry *entry;
+ bool found = false;
msk_owned_by_me(msk);
@@ -158,17 +164,21 @@ select_local_address(const struct pm_nl_pernet *pernet,
if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
continue;
- ret = entry;
+ *new_entry = *entry;
+ found = true;
break;
}
rcu_read_unlock();
- return ret;
+
+ return found;
}
-static struct mptcp_pm_addr_entry *
-select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
+static bool
+select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
+ struct mptcp_pm_addr_entry *new_entry)
{
- struct mptcp_pm_addr_entry *entry, *ret = NULL;
+ struct mptcp_pm_addr_entry *entry;
+ bool found = false;
rcu_read_lock();
/* do not keep any additional per socket state, just signal
@@ -183,11 +193,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
continue;
- ret = entry;
+ *new_entry = *entry;
+ found = true;
break;
}
rcu_read_unlock();
- return ret;
+
+ return found;
}
unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
@@ -278,7 +290,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
struct mptcp_sock *msk = entry->sock;
struct sock *sk = (struct sock *)msk;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
if (!msk)
return;
@@ -297,7 +309,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
spin_lock_bh(&msk->pm.lock);
if (!mptcp_pm_should_add_signal_addr(msk)) {
- pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
+ 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);
entry->retrans_times++;
@@ -347,7 +359,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
if (add_entry) {
- if (mptcp_pm_is_kernel(msk))
+ if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk)))
return false;
sk_reset_timer(sk, &add_entry->add_timer,
@@ -378,7 +390,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
struct sock *sk = (struct sock *)msk;
LIST_HEAD(free_list);
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
spin_lock_bh(&msk->pm.lock);
list_splice_init(&msk->pm.anno_list, &free_list);
@@ -464,13 +476,12 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow;
- pr_debug("send ack for %s",
+ pr_debug("send ack for %s\n",
prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr"));
slow = lock_sock_fast(ssk);
if (prio) {
subflow->send_mp_prio = 1;
- subflow->backup = backup;
subflow->request_bkup = backup;
}
@@ -513,8 +524,9 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
{
struct sock *sk = (struct sock *)msk;
- struct mptcp_pm_addr_entry *local;
+ struct mptcp_pm_addr_entry local;
unsigned int add_addr_signal_max;
+ bool signal_and_subflow = false;
unsigned int local_addr_max;
struct pm_nl_pernet *pernet;
unsigned int subflows_max;
@@ -555,8 +567,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
/* check first for announce */
if (msk->pm.add_addr_signaled < add_addr_signal_max) {
- local = select_signal_address(pernet, msk);
-
/* 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
@@ -567,16 +577,30 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
return;
- if (local) {
- if (mptcp_pm_alloc_anno_list(msk, &local->addr)) {
- __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
- msk->pm.add_addr_signaled++;
- mptcp_pm_announce_addr(msk, &local->addr, false);
- mptcp_pm_nl_addr_send_ack(msk);
- }
- }
+ if (!select_signal_address(pernet, msk, &local))
+ goto subflow;
+
+ /* 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))
+ return;
+
+ __clear_bit(local.addr.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_nl_addr_send_ack(msk);
+
+ if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+ signal_and_subflow = true;
}
+subflow:
/* check if should create a new subflow */
while (msk->pm.local_addr_used < local_addr_max &&
msk->pm.subflows < subflows_max) {
@@ -584,21 +608,28 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
bool fullmesh;
int i, nr;
- local = select_local_address(pernet, msk);
- if (!local)
+ if (signal_and_subflow)
+ signal_and_subflow = false;
+ else if (!select_local_address(pernet, msk, &local))
break;
- fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
+ fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
- msk->pm.local_addr_used++;
- __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
- nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs);
+ __clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+
+ /* Special case for ID0: set the correct ID */
+ if (local.addr.id == msk->mpc_endpoint_id)
+ local.addr.id = 0;
+ 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);
if (nr == 0)
continue;
spin_unlock_bh(&msk->pm.lock);
for (i = 0; i < nr; i++)
- __mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
+ __mptcp_subflow_connect(sk, &local.addr, &addrs[i]);
spin_lock_bh(&msk->pm.lock);
}
mptcp_pm_nl_check_work_pending(msk);
@@ -623,6 +654,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
{
struct sock *sk = (struct sock *)msk;
struct mptcp_pm_addr_entry *entry;
+ struct mptcp_addr_info mpc_addr;
struct pm_nl_pernet *pernet;
unsigned int subflows_max;
int i = 0;
@@ -630,6 +662,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
pernet = pm_nl_get_pernet_from_msk(msk);
subflows_max = mptcp_pm_get_subflows_max(msk);
+ mptcp_local_address((struct sock_common *)msk, &mpc_addr);
+
rcu_read_lock();
list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
@@ -640,7 +674,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
if (msk->pm.subflows < subflows_max) {
msk->pm.subflows++;
- addrs[i++] = entry->addr;
+ addrs[i] = entry->addr;
+
+ /* Special case for ID0: set the correct ID */
+ if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port))
+ addrs[i].id = 0;
+
+ i++;
}
}
rcu_read_unlock();
@@ -676,12 +716,13 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
unsigned int add_addr_accept_max;
struct mptcp_addr_info remote;
unsigned int subflows_max;
+ bool sf_created = false;
int i, nr;
add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
subflows_max = mptcp_pm_get_subflows_max(msk);
- pr_debug("accepted %d:%d remote family %d",
+ pr_debug("accepted %d:%d remote family %d\n",
msk->pm.add_addr_accepted, add_addr_accept_max,
msk->pm.remote.family);
@@ -703,15 +744,29 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
if (nr == 0)
return;
- msk->pm.add_addr_accepted++;
- if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
- msk->pm.subflows >= subflows_max)
- WRITE_ONCE(msk->pm.accept_addr, false);
-
spin_unlock_bh(&msk->pm.lock);
for (i = 0; i < nr; i++)
- __mptcp_subflow_connect(sk, &addrs[i], &remote);
+ if (__mptcp_subflow_connect(sk, &addrs[i], &remote) == 0)
+ sf_created = true;
spin_lock_bh(&msk->pm.lock);
+
+ if (sf_created) {
+ /* add_addr_accepted is not decr for ID 0 */
+ if (remote.id)
+ msk->pm.add_addr_accepted++;
+ if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
+ msk->pm.subflows >= subflows_max)
+ WRITE_ONCE(msk->pm.accept_addr, false);
+ }
+}
+
+bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *remote)
+{
+ struct mptcp_addr_info mpc_remote;
+
+ remote_address((struct sock_common *)msk, &mpc_remote);
+ return mptcp_addresses_equal(&mpc_remote, remote, remote->port);
}
void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
@@ -725,9 +780,12 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
!mptcp_pm_should_rm_signal(msk))
return;
- subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
- if (subflow)
- mptcp_pm_send_ack(msk, subflow, false, false);
+ mptcp_for_each_subflow(msk, subflow) {
+ if (__mptcp_subflow_active(subflow)) {
+ mptcp_pm_send_ack(msk, subflow, false, false);
+ break;
+ }
+ }
}
int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
@@ -737,7 +795,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
{
struct mptcp_subflow_context *subflow;
- pr_debug("bkup=%d", bkup);
+ pr_debug("bkup=%d\n", bkup);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -760,11 +818,6 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
return -EINVAL;
}
-static bool mptcp_local_id_match(const struct mptcp_sock *msk, u8 local_id, u8 id)
-{
- return local_id == id || (!local_id && msk->mpc_endpoint_id == id);
-}
-
static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list,
enum linux_mptcp_mib_field rm_type)
@@ -773,7 +826,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
struct sock *sk = (struct sock *)msk;
u8 i;
- pr_debug("%s rm_list_nr %d",
+ pr_debug("%s rm_list_nr %d\n",
rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr);
msk_owned_by_me(msk);
@@ -797,12 +850,14 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
u8 id = subflow_get_local_id(subflow);
+ if (inet_sk_state_load(ssk) == TCP_CLOSE)
+ continue;
if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
continue;
- if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
+ if (rm_type == MPTCP_MIB_RMSUBFLOW && id != rm_id)
continue;
- pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
+ pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u\n",
rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
i, rm_id, id, remote_id, msk->mpc_endpoint_id);
spin_unlock_bh(&msk->pm.lock);
@@ -812,22 +867,27 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
mptcp_close_ssk(sk, ssk, subflow);
spin_lock_bh(&msk->pm.lock);
- removed = true;
- __MPTCP_INC_STATS(sock_net(sk), rm_type);
+ removed |= subflow->request_join;
+ if (rm_type == MPTCP_MIB_RMSUBFLOW)
+ __MPTCP_INC_STATS(sock_net(sk), rm_type);
}
- if (rm_type == MPTCP_MIB_RMSUBFLOW)
- __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap);
+
+ if (rm_type == MPTCP_MIB_RMADDR)
+ __MPTCP_INC_STATS(sock_net(sk), rm_type);
+
if (!removed)
continue;
if (!mptcp_pm_is_kernel(msk))
continue;
- if (rm_type == MPTCP_MIB_RMADDR) {
- msk->pm.add_addr_accepted--;
- WRITE_ONCE(msk->pm.accept_addr, true);
- } else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
- msk->pm.local_addr_used--;
+ if (rm_type == MPTCP_MIB_RMADDR && rm_id &&
+ !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
+ /* Note: if the subflow has been closed before, this
+ * add_addr_accepted counter will not be decremented.
+ */
+ if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
+ WRITE_ONCE(msk->pm.accept_addr, true);
}
}
}
@@ -837,8 +897,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
}
-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
- const struct mptcp_rm_list *rm_list)
+static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
+ const struct mptcp_rm_list *rm_list)
{
mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
}
@@ -854,7 +914,7 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk)
spin_lock_bh(&msk->pm.lock);
- pr_debug("msk=%p status=%x", msk, pm->status);
+ pr_debug("msk=%p status=%x\n", msk, pm->status);
if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) {
pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
mptcp_pm_nl_add_addr_received(msk);
@@ -1094,6 +1154,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
return ret;
}
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+{
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+ struct mptcp_pm_addr_entry *entry;
+ bool backup = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+ if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) {
+ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return backup;
+}
+
#define MPTCP_PM_CMD_GRP_OFFSET 0
#define MPTCP_PM_EV_GRP_OFFSET 1
@@ -1254,20 +1332,27 @@ static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info)
return pm_nl_get_pernet(genl_info_net(info));
}
-static int mptcp_nl_add_subflow_or_signal_addr(struct net *net)
+static int mptcp_nl_add_subflow_or_signal_addr(struct net *net,
+ struct mptcp_addr_info *addr)
{
struct mptcp_sock *msk;
long s_slot = 0, s_num = 0;
while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
struct sock *sk = (struct sock *)msk;
+ struct mptcp_addr_info mpc_addr;
if (!READ_ONCE(msk->fully_established) ||
mptcp_pm_is_userspace(msk))
goto next;
+ /* if the endp linked to the init sf is re-added with a != ID */
+ mptcp_local_address((struct sock_common *)msk, &mpc_addr);
+
lock_sock(sk);
spin_lock_bh(&msk->pm.lock);
+ if (mptcp_addresses_equal(addr, &mpc_addr, addr->port))
+ msk->mpc_endpoint_id = addr->id;
mptcp_pm_create_subflow_or_signal_addr(msk);
spin_unlock_bh(&msk->pm.lock);
release_sock(sk);
@@ -1303,8 +1388,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
if (ret < 0)
return ret;
- if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
- GENL_SET_ERR_MSG(info, "flags must have signal when using port");
+ if (addr.addr.port && !address_use_port(&addr)) {
+ GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port");
return -EINVAL;
}
@@ -1340,7 +1425,7 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
goto out_free;
}
- mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk));
+ mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr);
return 0;
out_free:
@@ -1355,6 +1440,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int
struct sock *sk = (struct sock *)msk;
struct net *net = sock_net(sk);
+ /* No entries with ID 0 */
+ if (id == 0)
+ return 0;
+
rcu_read_lock();
entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
if (entry) {
@@ -1381,6 +1470,12 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
return false;
}
+static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr)
+{
+ return msk->mpc_endpoint_id == addr->id ? 0 : addr->id;
+}
+
static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr,
bool force)
@@ -1388,28 +1483,38 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
struct mptcp_rm_list list = { .nr = 0 };
bool ret;
- list.ids[list.nr++] = addr->id;
+ list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
ret = remove_anno_list_by_saddr(msk, addr);
if (ret || force) {
spin_lock_bh(&msk->pm.lock);
+ if (ret) {
+ __set_bit(addr->id, msk->pm.id_avail_bitmap);
+ msk->pm.add_addr_signaled--;
+ }
mptcp_pm_remove_addr(msk, &list);
spin_unlock_bh(&msk->pm.lock);
}
return ret;
}
+static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id)
+{
+ /* If it was marked as used, and not ID 0, decrement local_addr_used */
+ if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) &&
+ id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0))
+ msk->pm.local_addr_used--;
+}
+
static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
const struct mptcp_pm_addr_entry *entry)
{
const struct mptcp_addr_info *addr = &entry->addr;
- struct mptcp_rm_list list = { .nr = 0 };
+ struct mptcp_rm_list list = { .nr = 1 };
long s_slot = 0, s_num = 0;
struct mptcp_sock *msk;
- pr_debug("remove_id=%d", addr->id);
-
- list.ids[list.nr++] = addr->id;
+ pr_debug("remove_id=%d\n", addr->id);
while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
struct sock *sk = (struct sock *)msk;
@@ -1427,8 +1532,22 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
!(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
- if (remove_subflow)
- mptcp_pm_remove_subflow(msk, &list);
+
+ list.ids[0] = mptcp_endp_get_local_id(msk, addr);
+ if (remove_subflow) {
+ spin_lock_bh(&msk->pm.lock);
+ mptcp_pm_nl_rm_subflow_received(msk, &list);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+
+ if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+ spin_lock_bh(&msk->pm.lock);
+ __mark_subflow_endp_available(msk, list.ids[0]);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+
+ if (msk->mpc_endpoint_id == entry->addr.id)
+ msk->mpc_endpoint_id = 0;
release_sock(sk);
next:
@@ -1463,6 +1582,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
spin_lock_bh(&msk->pm.lock);
mptcp_pm_remove_addr(msk, &list);
mptcp_pm_nl_rm_subflow_received(msk, &list);
+ __mark_subflow_endp_available(msk, 0);
spin_unlock_bh(&msk->pm.lock);
release_sock(sk);
@@ -1522,25 +1642,36 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
return ret;
}
+/* Called from the userspace PM only */
void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
{
struct mptcp_rm_list alist = { .nr = 0 };
struct mptcp_pm_addr_entry *entry;
+ int anno_nr = 0;
list_for_each_entry(entry, rm_list, list) {
- if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
- lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
- alist.nr < MPTCP_RM_IDS_MAX)
- alist.ids[alist.nr++] = entry->addr.id;
+ if (alist.nr >= MPTCP_RM_IDS_MAX)
+ break;
+
+ /* only delete if either announced or matching a subflow */
+ if (remove_anno_list_by_saddr(msk, &entry->addr))
+ anno_nr++;
+ else if (!lookup_subflow_by_saddr(&msk->conn_list,
+ &entry->addr))
+ continue;
+
+ alist.ids[alist.nr++] = entry->addr.id;
}
if (alist.nr) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= anno_nr;
mptcp_pm_remove_addr(msk, &alist);
spin_unlock_bh(&msk->pm.lock);
}
}
+/* Called from the in-kernel PM only */
static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
struct list_head *rm_list)
{
@@ -1548,22 +1679,26 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
struct mptcp_pm_addr_entry *entry;
list_for_each_entry(entry, rm_list, list) {
- if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
- slist.nr < MPTCP_RM_IDS_MAX)
- slist.ids[slist.nr++] = entry->addr.id;
+ if (slist.nr < MPTCP_RM_IDS_MAX &&
+ lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
+ slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
- if (remove_anno_list_by_saddr(msk, &entry->addr) &&
- alist.nr < MPTCP_RM_IDS_MAX)
- alist.ids[alist.nr++] = entry->addr.id;
+ if (alist.nr < MPTCP_RM_IDS_MAX &&
+ remove_anno_list_by_saddr(msk, &entry->addr))
+ alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
}
+ spin_lock_bh(&msk->pm.lock);
if (alist.nr) {
- spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= alist.nr;
mptcp_pm_remove_addr(msk, &alist);
- spin_unlock_bh(&msk->pm.lock);
}
if (slist.nr)
- mptcp_pm_remove_subflow(msk, &slist);
+ mptcp_pm_nl_rm_subflow_received(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;
+ spin_unlock_bh(&msk->pm.lock);
}
static void mptcp_nl_remove_addrs_list(struct net *net,
@@ -1847,10 +1982,11 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
{
struct mptcp_rm_list list = { .nr = 0 };
- list.ids[list.nr++] = addr->id;
+ list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
spin_lock_bh(&msk->pm.lock);
mptcp_pm_nl_rm_subflow_received(msk, &list);
+ __mark_subflow_endp_available(msk, list.ids[0]);
mptcp_pm_create_subflow_or_signal_addr(msk);
spin_unlock_bh(&msk->pm.lock);
}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 9f5d422d5ef6..8eaa9fbe3e34 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -6,6 +6,7 @@
#include "protocol.h"
#include "mib.h"
+#include "mptcp_pm_gen.h"
void mptcp_free_local_addr_list(struct mptcp_sock *msk)
{
@@ -164,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
}
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
+ struct mptcp_addr_info *skc)
+{
+ struct mptcp_pm_addr_entry *entry;
+ bool backup = false;
+
+ spin_lock_bh(&msk->pm.lock);
+ list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (mptcp_addresses_equal(&entry->addr, skc, false)) {
+ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ break;
+ }
+ }
+ spin_unlock_bh(&msk->pm.lock);
+
+ return backup;
+}
+
int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 965eb69dc5de..37ebcb7640eb 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -20,6 +20,7 @@
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
+#include <net/hotdata.h>
#include <net/xfrm.h>
#include <asm/ioctls.h>
#include "protocol.h"
@@ -138,7 +139,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
!skb_try_coalesce(to, from, &fragstolen, &delta))
return false;
- pr_debug("colesced seq %llx into %llx new len %d new end seq %llx",
+ pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n",
MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
to->len, MPTCP_SKB_CB(from)->end_seq);
MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
@@ -216,7 +217,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
end_seq = MPTCP_SKB_CB(skb)->end_seq;
max_seq = atomic64_read(&msk->rcv_wnd_sent);
- pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
+ pr_debug("msk=%p seq=%llx limit=%llx empty=%d\n", msk, seq, max_seq,
RB_EMPTY_ROOT(&msk->out_of_order_queue));
if (after64(end_seq, max_seq)) {
/* out of window */
@@ -349,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
skb_orphan(skb);
/* try to fetch required memory from subflow */
- if (!mptcp_rmem_schedule(sk, ssk, skb->truesize))
+ if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
goto drop;
+ }
has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
@@ -640,7 +643,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
}
}
- pr_debug("msk=%p ssk=%p", msk, ssk);
+ pr_debug("msk=%p ssk=%p\n", msk, ssk);
tp = tcp_sk(ssk);
do {
u32 map_remaining, offset;
@@ -706,6 +709,8 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
}
} while (more_data_avail);
+ if (moved > 0)
+ msk->last_data_recv = tcp_jiffies32;
*bytes += moved;
return done;
}
@@ -719,7 +724,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
u64 end_seq;
p = rb_first(&msk->out_of_order_queue);
- pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
+ pr_debug("msk=%p empty=%d\n", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
while (p) {
skb = rb_to_skb(p);
if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq))
@@ -741,7 +746,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
/* skip overlapping data, if any */
- pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d",
+ pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n",
MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
delta);
MPTCP_SKB_CB(skb)->offset += delta;
@@ -841,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
sk_rbuf = ssk_rbuf;
/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
- if (__mptcp_rmem(sk) > sk_rbuf) {
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+ if (__mptcp_rmem(sk) > sk_rbuf)
return;
- }
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
@@ -1237,7 +1240,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
size_t copy;
int i;
- pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u",
+ pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u\n",
msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
if (WARN_ON_ONCE(info->sent > info->limit ||
@@ -1270,7 +1273,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
i = skb_shinfo(skb)->nr_frags;
can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset);
- if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
+ if (!can_coalesce && i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) {
tcp_mark_push(tcp_sk(ssk), skb);
goto alloc_skb;
}
@@ -1338,7 +1341,7 @@ alloc_skb:
mpext->use_map = 1;
mpext->dsn64 = 1;
- pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d",
+ pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d\n",
mpext->data_seq, mpext->subflow_seq, mpext->data_len,
mpext->dsn64);
@@ -1419,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
}
mptcp_for_each_subflow(msk, subflow) {
+ bool backup = subflow->backup || subflow->request_bkup;
+
trace_mptcp_subflow_get_send(subflow);
ssk = mptcp_subflow_tcp_sock(subflow);
if (!mptcp_subflow_active(subflow))
continue;
tout = max(tout, mptcp_timeout_from_subflow(subflow));
- nr_active += !subflow->backup;
+ nr_active += !backup;
pace = subflow->avg_pacing_rate;
if (unlikely(!pace)) {
/* init pacing rate from socket */
@@ -1436,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
}
linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
- if (linger_time < send_info[subflow->backup].linger_time) {
- send_info[subflow->backup].ssk = ssk;
- send_info[subflow->backup].linger_time = linger_time;
+ if (linger_time < send_info[backup].linger_time) {
+ send_info[backup].ssk = ssk;
+ send_info[backup].linger_time = linger_time;
}
}
__mptcp_set_timeout(sk, tout);
@@ -1556,6 +1561,8 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
err = copied;
out:
+ if (err > 0)
+ msk->last_data_sent = tcp_jiffies32;
return err;
}
@@ -1885,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!msk->first_pending)
WRITE_ONCE(msk->first_pending, dfrag);
}
- pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk,
+ pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk,
dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
!dfrag_collapsed);
@@ -2035,13 +2042,13 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
do_div(grow, msk->rcvq_space.space);
rcvwin += (grow << 1);
- rcvbuf = min_t(u64, __tcp_space_from_win(scaling_ratio, rcvwin),
+ rcvbuf = min_t(u64, mptcp_space_from_win(sk, rcvwin),
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
if (rcvbuf > sk->sk_rcvbuf) {
u32 window_clamp;
- window_clamp = __tcp_win_from_space(scaling_ratio, rcvbuf);
+ window_clamp = mptcp_win_from_space(sk, rcvbuf);
WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
/* Make subflows follow along. If we do not do this, we
@@ -2056,7 +2063,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
ssk = mptcp_subflow_tcp_sock(subflow);
slow = lock_sock_fast(ssk);
WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf);
- tcp_sk(ssk)->window_clamp = window_clamp;
+ WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp);
tcp_cleanup_rbuf(ssk, 1);
unlock_sock_fast(ssk, slow);
}
@@ -2197,7 +2204,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk))
continue;
- /* only the master socket status is relevant here. The exit
+ /* only the MPTCP socket status is relevant here. The exit
* conditions mirror closely tcp_recvmsg()
*/
if (copied >= target)
@@ -2241,7 +2248,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
}
}
- pr_debug("block timeout %ld", timeo);
+ pr_debug("block timeout %ld\n", timeo);
sk_wait_data(sk, &timeo, NULL);
}
@@ -2257,7 +2264,7 @@ out_err:
}
}
- pr_debug("msk=%p rx queue empty=%d:%d copied=%d",
+ pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n",
msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
skb_queue_empty(&msk->receive_queue), copied);
if (!(flags & MSG_PEEK))
@@ -2319,7 +2326,7 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
continue;
}
- if (subflow->backup) {
+ if (subflow->backup || subflow->request_bkup) {
if (!backup)
backup = ssk;
continue;
@@ -2501,6 +2508,12 @@ out:
void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow)
{
+ /* The first subflow can already be closed and still in the list */
+ if (subflow->close_event_done)
+ return;
+
+ subflow->close_event_done = true;
+
if (sk->sk_state == TCP_ESTABLISHED)
mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL);
@@ -2526,8 +2539,11 @@ static void __mptcp_close_subflow(struct sock *sk)
mptcp_for_each_subflow_safe(msk, subflow, tmp) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ int ssk_state = inet_sk_state_load(ssk);
- if (inet_sk_state_load(ssk) != TCP_CLOSE)
+ if (ssk_state != TCP_CLOSE &&
+ (ssk_state != TCP_CLOSE_WAIT ||
+ inet_sk_state_load(sk) != TCP_ESTABLISHED))
continue;
/* 'subflow_data_ready' will re-sched once rx queue is empty */
@@ -2565,7 +2581,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
slow = lock_sock_fast(tcp_sk);
if (tcp_sk->sk_state != TCP_CLOSE) {
- tcp_send_active_reset(tcp_sk, GFP_ATOMIC);
+ mptcp_send_active_reset_reason(tcp_sk);
tcp_set_state(tcp_sk, TCP_CLOSE);
}
unlock_sock_fast(tcp_sk, slow);
@@ -2707,7 +2723,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
if (!ssk)
return;
- pr_debug("MP_FAIL doesn't respond, reset the subflow");
+ pr_debug("MP_FAIL doesn't respond, reset the subflow\n");
slow = lock_sock_fast(ssk);
mptcp_subflow_reset(ssk);
@@ -2793,6 +2809,9 @@ static void __mptcp_init_sock(struct sock *sk)
WRITE_ONCE(msk->allow_infinite_fallback, true);
msk->recovery = false;
msk->subflow_id = 1;
+ msk->last_data_sent = tcp_jiffies32;
+ msk->last_data_recv = tcp_jiffies32;
+ msk->last_ack_recv = tcp_jiffies32;
mptcp_pm_data_init(msk);
@@ -2806,7 +2825,8 @@ static void mptcp_ca_reset(struct sock *sk)
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_assign_congestion_control(sk);
- strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name);
+ strscpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name,
+ sizeof(mptcp_sk(sk)->ca_name));
/* no need to keep a reference to the ops, the name will suffice */
tcp_cleanup_congestion_control(sk);
@@ -2877,7 +2897,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
break;
default:
if (__mptcp_check_fallback(mptcp_sk(sk))) {
- pr_debug("Fallback");
+ pr_debug("Fallback\n");
ssk->sk_shutdown |= how;
tcp_shutdown(ssk, how);
@@ -2887,7 +2907,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt);
mptcp_schedule_work(sk);
} else {
- pr_debug("Sending DATA_FIN on subflow %p", ssk);
+ pr_debug("Sending DATA_FIN on subflow %p\n", ssk);
tcp_send_ack(ssk);
if (!mptcp_rtx_timer_pending(sk))
mptcp_reset_rtx_timer(sk);
@@ -2907,9 +2927,14 @@ void mptcp_set_state(struct sock *sk, int state)
if (oldstate != TCP_ESTABLISHED)
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
break;
-
+ case TCP_CLOSE_WAIT:
+ /* Unlike TCP, MPTCP sk would not have the TCP_SYN_RECV state:
+ * MPTCP "accepted" sockets will be created later on. So no
+ * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT.
+ */
+ break;
default:
- if (oldstate == TCP_ESTABLISHED)
+ if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT)
MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB);
}
@@ -2948,7 +2973,7 @@ static void mptcp_check_send_data_fin(struct sock *sk)
struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
- pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
+ pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu\n",
msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
msk->snd_nxt, msk->write_seq);
@@ -2972,7 +2997,7 @@ static void __mptcp_wr_shutdown(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
+ pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d\n",
msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
!!mptcp_send_head(sk));
@@ -2987,7 +3012,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
might_sleep();
@@ -3095,7 +3120,7 @@ cleanup:
mptcp_set_state(sk, TCP_CLOSE);
sock_hold(sk);
- pr_debug("msk=%p state=%d", sk, sk->sk_state);
+ pr_debug("msk=%p state=%d\n", sk, sk->sk_state);
if (msk->token)
mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
@@ -3512,7 +3537,7 @@ void mptcp_subflow_process_delegated(struct sock *ssk, long status)
static int mptcp_hash(struct sock *sk)
{
/* should never be called,
- * we hash the TCP subflows not the master socket
+ * we hash the TCP subflows not the MPTCP socket
*/
WARN_ON_ONCE(1);
return 0;
@@ -3527,7 +3552,7 @@ static int mptcp_get_port(struct sock *sk, unsigned short snum)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- pr_debug("msk=%p, ssk=%p", msk, msk->first);
+ pr_debug("msk=%p, ssk=%p\n", msk, msk->first);
if (WARN_ON_ONCE(!msk->first))
return -EINVAL;
@@ -3544,7 +3569,7 @@ void mptcp_finish_connect(struct sock *ssk)
sk = subflow->conn;
msk = mptcp_sk(sk);
- pr_debug("msk=%p, token=%u", sk, subflow->token);
+ pr_debug("msk=%p, token=%u\n", sk, subflow->token);
subflow->map_seq = subflow->iasn;
subflow->map_subflow_seq = 1;
@@ -3573,7 +3598,7 @@ bool mptcp_finish_join(struct sock *ssk)
struct sock *parent = (void *)msk;
bool ret = true;
- pr_debug("msk=%p, subflow=%p", msk, subflow);
+ pr_debug("msk=%p, subflow=%p\n", msk, subflow);
/* mptcp socket already closing? */
if (!mptcp_is_fully_established(parent)) {
@@ -3619,7 +3644,7 @@ err_prohibited:
static void mptcp_shutdown(struct sock *sk, int how)
{
- pr_debug("sk=%p, how=%d", sk, how);
+ pr_debug("sk=%p, how=%d\n", sk, how);
if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
__mptcp_wr_shutdown(sk);
@@ -3726,6 +3751,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
WRITE_ONCE(msk->write_seq, subflow->idsn);
WRITE_ONCE(msk->snd_nxt, subflow->idsn);
+ WRITE_ONCE(msk->snd_una, subflow->idsn);
if (likely(!__mptcp_check_fallback(msk)))
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE);
@@ -3839,7 +3865,7 @@ static int mptcp_listen(struct socket *sock, int backlog)
struct sock *ssk;
int err;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
lock_sock(sk);
@@ -3873,13 +3899,12 @@ unlock:
}
static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
- int flags, bool kern)
+ struct proto_accept_arg *arg)
{
struct mptcp_sock *msk = mptcp_sk(sock->sk);
struct sock *ssk, *newsk;
- int err;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
/* Buggy applications can call accept on socket states other then LISTEN
* but no need to allocate the first subflow just to error out.
@@ -3888,12 +3913,12 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
if (!ssk)
return -EINVAL;
- pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
- newsk = inet_csk_accept(ssk, flags, &err, kern);
+ pr_debug("ssk=%p, listener=%p\n", ssk, mptcp_subflow_ctx(ssk));
+ newsk = inet_csk_accept(ssk, arg);
if (!newsk)
- return err;
+ return arg->err;
- pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
+ pr_debug("newsk=%p, subflow is mptcp=%d\n", newsk, sk_is_mptcp(newsk));
if (sk_is_mptcp(newsk)) {
struct mptcp_subflow_context *subflow;
struct sock *new_mptcp_sock;
@@ -3912,7 +3937,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
newsk = new_mptcp_sock;
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
- newsk->sk_kern_sock = kern;
+ newsk->sk_kern_sock = arg->kern;
lock_sock(newsk);
__inet_accept(sock, newsock, newsk);
@@ -3941,7 +3966,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
}
} else {
tcpfallback:
- newsk->sk_kern_sock = kern;
+ newsk->sk_kern_sock = arg->kern;
lock_sock(newsk);
__inet_accept(sock, newsock, newsk);
/* we are being invoked after accepting a non-mp-capable
@@ -3986,7 +4011,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
sock_poll_wait(file, sock, wait);
state = inet_sk_state_load(sk);
- pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
+ pr_debug("msk=%p state=%d flags=%lx\n", msk, state, msk->flags);
if (state == TCP_LISTEN) {
struct sock *ssk = READ_ONCE(msk->first);
@@ -4161,7 +4186,7 @@ int __init mptcp_proto_v6_init(void)
int err;
mptcp_v6_prot = mptcp_prot;
- strcpy(mptcp_v6_prot.name, "MPTCPv6");
+ strscpy(mptcp_v6_prot.name, "MPTCPv6", sizeof(mptcp_v6_prot.name));
mptcp_v6_prot.slab = NULL;
mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock);
mptcp_v6_prot.ipv6_pinfo_offset = offsetof(struct mptcp6_sock, np);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a10ebf3ee10a..3b22313d1b86 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -12,8 +12,7 @@
#include <net/inet_connection_sock.h>
#include <uapi/linux/mptcp.h>
#include <net/genetlink.h>
-
-#include "mptcp_pm_gen.h"
+#include <net/rstreason.h>
#define MPTCP_SUPPORTED_VERSION 1
@@ -282,6 +281,9 @@ struct mptcp_sock {
u64 bytes_acked;
u64 snd_una;
u64 wnd_end;
+ u32 last_data_sent;
+ u32 last_data_recv;
+ u32 last_ack_recv;
unsigned long timer_ival;
u32 token;
int rmem_released;
@@ -308,6 +310,9 @@ struct mptcp_sock {
free_first:1,
rcvspace_init:1;
u32 notsent_lowat;
+ int keepalive_cnt;
+ int keepalive_idle;
+ int keepalive_intvl;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
@@ -381,6 +386,11 @@ static inline int mptcp_win_from_space(const struct sock *sk, int space)
return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space);
}
+static inline int mptcp_space_from_win(const struct sock *sk, int win)
+{
+ return __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, win);
+}
+
static inline int __mptcp_space(const struct sock *sk)
{
return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
@@ -438,6 +448,7 @@ struct mptcp_subflow_request_sock {
u16 mp_capable : 1,
mp_join : 1,
backup : 1,
+ request_bkup : 1,
csum_reqd : 1,
allow_join_id0 : 1;
u8 local_id;
@@ -513,7 +524,8 @@ struct mptcp_subflow_context {
stale : 1, /* unable to snd/rcv data, do not use for xmit */
valid_csum_seen : 1, /* at least one csum validated */
is_mptfo : 1, /* subflow is doing TFO */
- __unused : 10;
+ close_event_done : 1, /* has done the post-closed part */
+ __unused : 9;
bool data_avail;
bool scheduled;
u32 remote_nonce;
@@ -558,7 +570,7 @@ struct mptcp_subflow_context {
static inline struct mptcp_subflow_context *
mptcp_subflow_ctx(const struct sock *sk)
{
- struct inet_connection_sock *icsk = inet_csk(sk);
+ const struct inet_connection_sock *icsk = inet_csk(sk);
/* Use RCU on icsk_ulp_data only for sock diag code */
return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
@@ -578,6 +590,43 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow)
WRITE_ONCE(subflow->local_id, -1);
}
+/* Convert reset reasons in MPTCP to enum sk_rst_reason type */
+static inline enum sk_rst_reason
+sk_rst_convert_mptcp_reason(u32 reason)
+{
+ switch (reason) {
+ case MPTCP_RST_EUNSPEC:
+ return SK_RST_REASON_MPTCP_RST_EUNSPEC;
+ case MPTCP_RST_EMPTCP:
+ return SK_RST_REASON_MPTCP_RST_EMPTCP;
+ case MPTCP_RST_ERESOURCE:
+ return SK_RST_REASON_MPTCP_RST_ERESOURCE;
+ case MPTCP_RST_EPROHIBIT:
+ return SK_RST_REASON_MPTCP_RST_EPROHIBIT;
+ case MPTCP_RST_EWQ2BIG:
+ return SK_RST_REASON_MPTCP_RST_EWQ2BIG;
+ case MPTCP_RST_EBADPERF:
+ return SK_RST_REASON_MPTCP_RST_EBADPERF;
+ case MPTCP_RST_EMIDDLEBOX:
+ return SK_RST_REASON_MPTCP_RST_EMIDDLEBOX;
+ default:
+ /* It should not happen, or else errors may occur
+ * in MPTCP layer
+ */
+ return SK_RST_REASON_ERROR;
+ }
+}
+
+static inline void
+mptcp_send_active_reset_reason(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ enum sk_rst_reason reason;
+
+ reason = sk_rst_convert_mptcp_reason(subflow->reset_reason);
+ tcp_send_active_reset(sk, GFP_ATOMIC, reason);
+}
+
static inline u64
mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow)
{
@@ -642,6 +691,7 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net);
unsigned int mptcp_close_timeout(const struct sock *sk);
int mptcp_get_pm_type(const struct net *net);
const char *mptcp_get_scheduler(const struct net *net);
+void mptcp_get_available_schedulers(char *buf, size_t maxlen);
void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
struct mptcp_subflow_context *subflow,
const struct mptcp_options_received *mp_opt);
@@ -943,6 +993,8 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
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);
+bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *remote);
void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk);
void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list);
@@ -977,7 +1029,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr,
bool echo);
int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list);
void mptcp_free_local_addr_list(struct mptcp_sock *msk);
@@ -1060,6 +1111,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
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_addr_info *skc);
int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb);
int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
struct netlink_callback *cb);
@@ -1081,8 +1135,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
void __init mptcp_pm_nl_init(void);
void mptcp_pm_nl_work(struct mptcp_sock *msk);
-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
- const struct mptcp_rm_list *rm_list);
unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);
@@ -1128,7 +1180,7 @@ static inline bool mptcp_check_fallback(const struct sock *sk)
static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
{
if (__mptcp_check_fallback(msk)) {
- pr_debug("TCP fallback already done (msk=%p)", msk);
+ pr_debug("TCP fallback already done (msk=%p)\n", msk);
return;
}
set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
@@ -1164,7 +1216,7 @@ static inline void mptcp_do_fallback(struct sock *ssk)
}
}
-#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
+#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)\n", __func__, a)
static inline bool mptcp_check_infinite_map(struct sk_buff *skb)
{
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 4ab0693c069c..78ed508ebc1b 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -51,6 +51,28 @@ struct mptcp_sched_ops *mptcp_sched_find(const char *name)
return ret;
}
+/* Build string with list of available scheduler values.
+ * Similar to tcp_get_available_congestion_control()
+ */
+void mptcp_get_available_schedulers(char *buf, size_t maxlen)
+{
+ struct mptcp_sched_ops *sched;
+ size_t offs = 0;
+
+ rcu_read_lock();
+ spin_lock(&mptcp_sched_list_lock);
+ list_for_each_entry_rcu(sched, &mptcp_sched_list, list) {
+ offs += snprintf(buf + offs, maxlen - offs,
+ "%s%s",
+ offs == 0 ? "" : " ", sched->name);
+
+ if (WARN_ON_ONCE(offs >= maxlen))
+ break;
+ }
+ spin_unlock(&mptcp_sched_list_lock);
+ rcu_read_unlock();
+}
+
int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
{
if (!sched->get_subflow)
@@ -64,7 +86,7 @@ int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
list_add_tail_rcu(&sched->list, &mptcp_sched_list);
spin_unlock(&mptcp_sched_list_lock);
- pr_debug("%s registered", sched->name);
+ pr_debug("%s registered\n", sched->name);
return 0;
}
@@ -96,7 +118,7 @@ int mptcp_init_sched(struct mptcp_sock *msk,
if (msk->sched->init)
msk->sched->init(msk);
- pr_debug("sched=%s", msk->sched->name);
+ pr_debug("sched=%s\n", msk->sched->name);
return 0;
}
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 73fdf423de44..505445a9598f 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -181,8 +181,6 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
switch (optname) {
case SO_KEEPALIVE:
- mptcp_sol_socket_sync_intval(msk, optname, val);
- return 0;
case SO_DEBUG:
case SO_MARK:
case SO_PRIORITY:
@@ -618,12 +616,37 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
}
if (ret == 0)
- strcpy(msk->ca_name, name);
+ strscpy(msk->ca_name, name, sizeof(msk->ca_name));
release_sock(sk);
return ret;
}
+static int __mptcp_setsockopt_set_val(struct mptcp_sock *msk, int max,
+ int (*set_val)(struct sock *, int),
+ int *msk_val, int val)
+{
+ struct mptcp_subflow_context *subflow;
+ int err = 0;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ int ret;
+
+ lock_sock(ssk);
+ ret = set_val(ssk, val);
+ err = err ? : ret;
+ release_sock(ssk);
+ }
+
+ if (!err) {
+ *msk_val = val;
+ sockopt_seq_inc(msk);
+ }
+
+ return err;
+}
+
static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val)
{
struct mptcp_subflow_context *subflow;
@@ -820,6 +843,22 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
case TCP_NODELAY:
ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val);
break;
+ case TCP_KEEPIDLE:
+ ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPIDLE,
+ &tcp_sock_set_keepidle_locked,
+ &msk->keepalive_idle, val);
+ break;
+ case TCP_KEEPINTVL:
+ ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPINTVL,
+ &tcp_sock_set_keepintvl,
+ &msk->keepalive_intvl, val);
+ break;
+ case TCP_KEEPCNT:
+ ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPCNT,
+ &tcp_sock_set_keepcnt,
+ &msk->keepalive_cnt,
+ val);
+ break;
default:
ret = -ENOPROTOOPT;
}
@@ -834,7 +873,7 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,
struct mptcp_sock *msk = mptcp_sk(sk);
struct sock *ssk;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
if (level == SOL_SOCKET)
return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
@@ -898,6 +937,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
struct sock *sk = (struct sock *)msk;
u32 flags = 0;
bool slow;
+ u32 now;
memset(info, 0, sizeof(*info));
@@ -926,11 +966,6 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
if (READ_ONCE(msk->can_ack))
flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED;
info->mptcpi_flags = flags;
- mptcp_data_lock(sk);
- info->mptcpi_snd_una = msk->snd_una;
- info->mptcpi_rcv_nxt = msk->ack_seq;
- info->mptcpi_bytes_acked = msk->bytes_acked;
- mptcp_data_unlock(sk);
slow = lock_sock_fast(sk);
info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
@@ -942,7 +977,17 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
info->mptcpi_bytes_retrans = msk->bytes_retrans;
info->mptcpi_subflows_total = info->mptcpi_subflows +
__mptcp_has_initial_subflow(msk);
+ now = tcp_jiffies32;
+ info->mptcpi_last_data_sent = jiffies_to_msecs(now - msk->last_data_sent);
+ info->mptcpi_last_data_recv = jiffies_to_msecs(now - msk->last_data_recv);
unlock_sock_fast(sk, slow);
+
+ mptcp_data_lock(sk);
+ info->mptcpi_last_ack_recv = jiffies_to_msecs(now - msk->last_ack_recv);
+ info->mptcpi_snd_una = msk->snd_una;
+ info->mptcpi_rcv_nxt = msk->ack_seq;
+ info->mptcpi_bytes_acked = msk->bytes_acked;
+ mptcp_data_unlock(sk);
}
EXPORT_SYMBOL_GPL(mptcp_diag_fill_info);
@@ -954,6 +999,10 @@ static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, in
if (get_user(len, optlen))
return -EFAULT;
+ /* When used only to check if a fallback to TCP happened. */
+ if (len == 0)
+ return 0;
+
len = min_t(unsigned int, len, sizeof(struct mptcp_info));
mptcp_diag_fill_info(msk, &m_info);
@@ -1322,6 +1371,8 @@ static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval,
static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
char __user *optval, int __user *optlen)
{
+ struct sock *sk = (void *)msk;
+
switch (optname) {
case TCP_ULP:
case TCP_CONGESTION:
@@ -1340,8 +1391,22 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
return mptcp_put_int_option(msk, optval, optlen, msk->cork);
case TCP_NODELAY:
return mptcp_put_int_option(msk, optval, optlen, msk->nodelay);
+ case TCP_KEEPIDLE:
+ return mptcp_put_int_option(msk, optval, optlen,
+ msk->keepalive_idle ? :
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_time) / HZ);
+ case TCP_KEEPINTVL:
+ return mptcp_put_int_option(msk, optval, optlen,
+ msk->keepalive_intvl ? :
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_intvl) / HZ);
+ case TCP_KEEPCNT:
+ return mptcp_put_int_option(msk, optval, optlen,
+ msk->keepalive_cnt ? :
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_probes));
case TCP_NOTSENT_LOWAT:
return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat);
+ case TCP_IS_MPTCP:
+ return mptcp_put_int_option(msk, optval, optlen, 1);
}
return -EOPNOTSUPP;
}
@@ -1388,7 +1453,7 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname,
struct mptcp_sock *msk = mptcp_sk(sk);
struct sock *ssk;
- pr_debug("msk=%p", msk);
+ pr_debug("msk=%p\n", msk);
/* @@ the meaning of setsockopt() when the socket is connected and
* there are multiple subflows is not yet defined. It is up to the
@@ -1457,6 +1522,9 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
tcp_set_congestion_control(ssk, msk->ca_name, false, true);
__tcp_sock_set_cork(ssk, !!msk->cork);
__tcp_sock_set_nodelay(ssk, !!msk->nodelay);
+ tcp_sock_set_keepidle_locked(ssk, msk->keepalive_idle);
+ tcp_sock_set_keepintvl(ssk, msk->keepalive_intvl);
+ tcp_sock_set_keepcnt(ssk, msk->keepalive_cnt);
inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk));
inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
@@ -1511,7 +1579,7 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
return 0;
- space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val);
+ space = mptcp_space_from_win(sk, val);
if (space <= sk->sk_rcvbuf)
return 0;
@@ -1523,7 +1591,7 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)
slow = lock_sock_fast(ssk);
WRITE_ONCE(ssk->sk_rcvbuf, space);
- tcp_sk(ssk)->window_clamp = val;
+ WRITE_ONCE(tcp_sk(ssk)->window_clamp, val);
unlock_sock_fast(ssk, slow);
}
return 0;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 6042a47da61b..064ab3235893 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -20,6 +20,7 @@
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
+
#include "protocol.h"
#include "mib.h"
@@ -38,7 +39,7 @@ static void subflow_req_destructor(struct request_sock *req)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
- pr_debug("subflow_req=%p", subflow_req);
+ pr_debug("subflow_req=%p\n", subflow_req);
if (subflow_req->msk)
sock_put((struct sock *)subflow_req->msk);
@@ -99,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
return NULL;
}
subflow_req->local_id = local_id;
+ subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req);
return msk;
}
@@ -144,14 +146,16 @@ static int subflow_check_req(struct request_sock *req,
struct mptcp_options_received mp_opt;
bool opt_mp_capable, opt_mp_join;
- pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
+ pr_debug("subflow_req=%p, listener=%p\n", subflow_req, listener);
#ifdef CONFIG_TCP_MD5SIG
/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
* TCP option space.
*/
- if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info))
+ if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) {
+ subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
return -EINVAL;
+ }
#endif
mptcp_get_options(skb, &mp_opt);
@@ -165,6 +169,9 @@ static int subflow_check_req(struct request_sock *req,
return 0;
} else if (opt_mp_join) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
+
+ if (mp_opt.backup)
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
}
if (opt_mp_capable && listener->request_mptcp) {
@@ -214,11 +221,12 @@ again:
}
if (subflow_use_different_sport(subflow_req->msk, sk_listener)) {
- pr_debug("syn inet_sport=%d %d",
+ 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)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
+ subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
return -EPERM;
}
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX);
@@ -227,13 +235,15 @@ again:
subflow_req_create_thmac(subflow_req);
if (unlikely(req->syncookie)) {
- if (mptcp_can_accept_new_subflow(subflow_req->msk))
- subflow_init_req_cookie_join_save(subflow_req, skb);
- else
+ if (!mptcp_can_accept_new_subflow(subflow_req->msk)) {
+ subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
return -EPERM;
+ }
+
+ subflow_init_req_cookie_join_save(subflow_req, skb);
}
- pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
+ pr_debug("token=%u, remote_nonce=%u msk=%p\n", subflow_req->token,
subflow_req->remote_nonce, subflow_req->msk);
}
@@ -281,10 +291,21 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
}
EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req);
+static enum sk_rst_reason mptcp_get_rst_reason(const struct sk_buff *skb)
+{
+ const struct mptcp_ext *mpext = mptcp_get_ext(skb);
+
+ if (!mpext)
+ return SK_RST_REASON_NOT_SPECIFIED;
+
+ return sk_rst_convert_mptcp_reason(mpext->reset_reason);
+}
+
static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
struct sk_buff *skb,
struct flowi *fl,
- struct request_sock *req)
+ struct request_sock *req,
+ u32 tw_isn)
{
struct dst_entry *dst;
int err;
@@ -292,7 +313,7 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
tcp_rsk(req)->is_mptcp = 1;
subflow_init_req(req, sk);
- dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req);
+ dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req, tw_isn);
if (!dst)
return NULL;
@@ -302,7 +323,8 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
dst_release(dst);
if (!req->syncookie)
- tcp_request_sock_ops.send_reset(sk, skb);
+ tcp_request_sock_ops.send_reset(sk, skb,
+ mptcp_get_rst_reason(skb));
return NULL;
}
@@ -351,7 +373,8 @@ static int subflow_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
struct sk_buff *skb,
struct flowi *fl,
- struct request_sock *req)
+ struct request_sock *req,
+ u32 tw_isn)
{
struct dst_entry *dst;
int err;
@@ -359,7 +382,7 @@ static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
tcp_rsk(req)->is_mptcp = 1;
subflow_init_req(req, sk);
- dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req);
+ dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req, tw_isn);
if (!dst)
return NULL;
@@ -369,7 +392,8 @@ static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
dst_release(dst);
if (!req->syncookie)
- tcp6_request_sock_ops.send_reset(sk, skb);
+ tcp6_request_sock_ops.send_reset(sk, skb,
+ mptcp_get_rst_reason(skb));
return NULL;
}
#endif
@@ -405,7 +429,7 @@ void mptcp_subflow_reset(struct sock *ssk)
/* must hold: tcp_done() could drop last reference on parent */
sock_hold(sk);
- tcp_send_active_reset(ssk, GFP_ATOMIC);
+ mptcp_send_active_reset_reason(ssk);
tcp_done(ssk);
if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags))
mptcp_schedule_work(sk);
@@ -503,7 +527,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->rel_write_seq = 1;
subflow->conn_finished = 1;
subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
- pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
+ pr_debug("subflow=%p synack seq=%x\n", subflow, subflow->ssn_offset);
mptcp_get_options(skb, &mp_opt);
if (subflow->request_mptcp) {
@@ -535,7 +559,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->thmac = mp_opt.thmac;
subflow->remote_nonce = mp_opt.nonce;
WRITE_ONCE(subflow->remote_id, mp_opt.join_id);
- pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
+ pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d\n",
subflow, subflow->thmac, subflow->remote_nonce,
subflow->backup);
@@ -557,8 +581,11 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
subflow->mp_join = 1;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
+ if (subflow->backup)
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
+
if (subflow_use_different_dport(msk, sk)) {
- pr_debug("synack inet_dport=%d %d",
+ pr_debug("synack inet_dport=%d %d\n",
ntohs(inet_sk(sk)->inet_dport),
ntohs(inet_sk(parent)->inet_dport));
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX);
@@ -594,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk)
return err;
subflow_set_local_id(subflow, err);
+ subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk);
+
return 0;
}
@@ -626,7 +655,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- pr_debug("subflow=%p", subflow);
+ pr_debug("subflow=%p\n", subflow);
/* Never answer to SYNs sent to broadcast or multicast */
if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -657,7 +686,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- pr_debug("subflow=%p", subflow);
+ pr_debug("subflow=%p\n", subflow);
if (skb->protocol == htons(ETH_P_IP))
return subflow_v4_conn_request(sk, skb);
@@ -774,10 +803,11 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
struct mptcp_subflow_request_sock *subflow_req;
struct mptcp_options_received mp_opt;
bool fallback, fallback_is_fatal;
+ enum sk_rst_reason reason;
struct mptcp_sock *owner;
struct sock *child;
- pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
+ pr_debug("listener=%p, req=%p, conn=%p\n", listener, req, listener->conn);
/* After child creation we must look for MPC even when options
* are not parsed
@@ -868,18 +898,23 @@ create_child:
ctx->conn = (struct sock *)owner;
if (subflow_use_different_sport(owner, sk)) {
- pr_debug("ack inet_sport=%d %d",
+ 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)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
+ subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
goto dispose_child;
}
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX);
}
- if (!mptcp_finish_join(child))
+ if (!mptcp_finish_join(child)) {
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(child);
+
+ subflow_add_reset_reason(skb, subflow->reset_reason);
goto dispose_child;
+ }
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
tcp_rsk(req)->drop_req = true;
@@ -887,7 +922,7 @@ create_child:
}
/* check for expected invariant - should never trigger, just help
- * catching eariler subtle bugs
+ * catching earlier subtle bugs
*/
WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp &&
(!mptcp_subflow_ctx(child) ||
@@ -899,7 +934,8 @@ dispose_child:
tcp_rsk(req)->drop_req = true;
inet_csk_prepare_for_destroy_sock(child);
tcp_done(child);
- req->rsk_ops->send_reset(sk, skb);
+ reason = mptcp_get_rst_reason(skb);
+ req->rsk_ops->send_reset(sk, skb, reason);
/* The last child reference will be released by the caller */
return child;
@@ -925,7 +961,7 @@ enum mapping_status {
static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
{
- pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
+ pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d\n",
ssn, subflow->map_subflow_seq, subflow->map_data_len);
}
@@ -1085,17 +1121,19 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
data_len = mpext->data_len;
if (data_len == 0) {
- pr_debug("infinite mapping received");
+ pr_debug("infinite mapping received\n");
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
subflow->map_data_len = 0;
return MAPPING_INVALID;
}
if (mpext->data_fin == 1) {
+ u64 data_fin_seq;
+
if (data_len == 1) {
bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq,
mpext->dsn64);
- pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq);
+ pr_debug("DATA_FIN with no payload seq=%llu\n", mpext->data_seq);
if (subflow->map_valid) {
/* A DATA_FIN might arrive in a DSS
* option before the previous mapping
@@ -1104,26 +1142,26 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
*/
skb_ext_del(skb, SKB_EXT_MPTCP);
return MAPPING_OK;
- } else {
- if (updated)
- mptcp_schedule_work((struct sock *)msk);
-
- return MAPPING_DATA_FIN;
}
- } else {
- u64 data_fin_seq = mpext->data_seq + data_len - 1;
- /* If mpext->data_seq is a 32-bit value, data_fin_seq
- * must also be limited to 32 bits.
- */
- if (!mpext->dsn64)
- data_fin_seq &= GENMASK_ULL(31, 0);
+ if (updated)
+ mptcp_schedule_work((struct sock *)msk);
- mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
- pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
- data_fin_seq, mpext->dsn64);
+ return MAPPING_DATA_FIN;
}
+ data_fin_seq = mpext->data_seq + data_len - 1;
+
+ /* If mpext->data_seq is a 32-bit value, data_fin_seq must also
+ * be limited to 32 bits.
+ */
+ if (!mpext->dsn64)
+ data_fin_seq &= GENMASK_ULL(31, 0);
+
+ mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
+ pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d\n",
+ data_fin_seq, mpext->dsn64);
+
/* Adjust for DATA_FIN using 1 byte of sequence space */
data_len--;
}
@@ -1167,7 +1205,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
if (unlikely(subflow->map_csum_reqd != csum_reqd))
return MAPPING_INVALID;
- pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
+ pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n",
subflow->map_seq, subflow->map_subflow_seq,
subflow->map_data_len, subflow->map_csum_reqd,
subflow->map_data_csum);
@@ -1192,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
- u32 incr;
+ struct tcp_sock *tp = tcp_sk(ssk);
+ u32 offset, incr, avail_len;
+
+ offset = tp->copied_seq - TCP_SKB_CB(skb)->seq;
+ if (WARN_ON_ONCE(offset > skb->len))
+ goto out;
- incr = limit >= skb->len ? skb->len + fin : limit;
+ avail_len = skb->len - offset;
+ incr = limit >= avail_len ? avail_len + fin : limit;
- pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
- subflow->map_subflow_seq);
+ pr_debug("discarding=%d len=%d offset=%d seq=%d\n", incr, skb->len,
+ offset, subflow->map_subflow_seq);
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
tcp_sk(ssk)->copied_seq += incr;
+
+out:
if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
sk_eat_skb(ssk, skb);
if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
@@ -1209,12 +1255,16 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
/* sched mptcp worker to remove the subflow if no more data is pending */
static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
{
- if (likely(ssk->sk_state != TCP_CLOSE))
+ struct sock *sk = (struct sock *)msk;
+
+ if (likely(ssk->sk_state != TCP_CLOSE &&
+ (ssk->sk_state != TCP_CLOSE_WAIT ||
+ inet_sk_state_load(sk) != TCP_ESTABLISHED)))
return;
if (skb_queue_empty(&ssk->sk_receive_queue) &&
!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
- mptcp_schedule_work((struct sock *)msk);
+ mptcp_schedule_work(sk);
}
static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
@@ -1234,7 +1284,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
unsigned long fail_tout;
- /* greceful failure can happen only on the MPC subflow */
+ /* graceful failure can happen only on the MPC subflow */
if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first)))
return;
@@ -1291,7 +1341,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
old_ack = READ_ONCE(msk->ack_seq);
ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
- pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
+ pr_debug("msk ack_seq=%llx subflow ack_seq=%llx\n", old_ack,
ack_seq);
if (unlikely(before64(ack_seq, old_ack))) {
mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
@@ -1336,7 +1386,7 @@ reset:
tcp_set_state(ssk, TCP_CLOSE);
while ((skb = skb_peek(&ssk->sk_receive_queue)))
sk_eat_skb(ssk, skb);
- tcp_send_active_reset(ssk, GFP_ATOMIC);
+ mptcp_send_active_reset_reason(ssk);
WRITE_ONCE(subflow->data_avail, false);
return false;
}
@@ -1363,7 +1413,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
subflow->map_valid = 0;
WRITE_ONCE(subflow->data_avail, false);
- pr_debug("Done with mapping: seq=%u data_len=%u",
+ pr_debug("Done with mapping: seq=%u data_len=%u\n",
subflow->map_subflow_seq,
subflow->map_data_len);
}
@@ -1473,7 +1523,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk);
- pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d",
+ pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d\n",
subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped);
if (likely(icsk->icsk_af_ops == target))
@@ -1566,7 +1616,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
goto failed;
mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL);
- pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
+ pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d\n", msk,
remote_token, local_id, remote_id);
subflow->remote_token = remote_token;
WRITE_ONCE(subflow->remote_id, remote_id);
@@ -1690,7 +1740,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk);
release_sock(sf->sk);
- /* the newly created socket really belongs to the owning MPTCP master
+ /* the newly created socket really belongs to the owning MPTCP
* socket, even if for additional subflows the allocation is performed
* by a kernel workqueue. Adjust inode references, so that the
* procfs/diag interfaces really show this one belonging to the correct
@@ -1701,7 +1751,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid;
subflow = mptcp_subflow_ctx(sf->sk);
- pr_debug("subflow=%p", subflow);
+ pr_debug("subflow=%p\n", subflow);
*new_sock = sf;
sock_hold(sk);
@@ -1730,7 +1780,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
INIT_LIST_HEAD(&ctx->node);
INIT_LIST_HEAD(&ctx->delegated_node);
- pr_debug("subflow=%p", ctx);
+ pr_debug("subflow=%p\n", ctx);
ctx->tcp_sock = sk;
WRITE_ONCE(ctx->local_id, -1);
@@ -1881,7 +1931,7 @@ static int subflow_ulp_init(struct sock *sk)
goto out;
}
- pr_debug("subflow=%p, family=%d", ctx, sk->sk_family);
+ pr_debug("subflow=%p, family=%d\n", ctx, sk->sk_family);
tp->is_mptcp = 1;
ctx->icsk_af_ops = icsk->icsk_af_ops;
@@ -1976,6 +2026,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
new_ctx->fully_established = 1;
new_ctx->remote_key_valid = 1;
new_ctx->backup = subflow_req->backup;
+ new_ctx->request_bkup = subflow_req->request_bkup;
WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
new_ctx->token = subflow_req->token;
new_ctx->thmac = subflow_req->thmac;
generated by cgit v1.2.3-70-g09d2 (git 2.51.1) at 2025-11-02 03:39:50 +0000