aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--drivers/net/ethernet/cadence/macb_main.c2
-rw-r--r--drivers/net/ipa/gsi.c6
-rw-r--r--drivers/net/ipa/ipa_endpoint.c13
-rw-r--r--drivers/net/ipa/ipa_qmi.c2
-rw-r--r--include/net/inet_timewait_sock.h3
-rw-r--r--net/dccp/ipv4.c6
-rw-r--r--net/dccp/ipv6.c6
-rw-r--r--net/ipv4/inet_timewait_sock.c58
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv6/tcp_ipv6.c6
-rw-r--r--net/mptcp/pm.c5
-rw-r--r--net/mptcp/protocol.h14
-rw-r--r--net/mptcp/subflow.c12
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh48
14 files changed, 156 insertions, 27 deletions
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index e475be29845c..61284baa0496 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1219,7 +1219,6 @@ static void gem_rx_refill(struct macb_queue *queue)
/* Make hw descriptor updates visible to CPU */
rmb();
- queue->rx_prepared_head++;
desc = macb_rx_desc(queue, entry);
if (!queue->rx_skbuff[entry]) {
@@ -1258,6 +1257,7 @@ static void gem_rx_refill(struct macb_queue *queue)
dma_wmb();
desc->addr &= ~MACB_BIT(RX_USED);
}
+ queue->rx_prepared_head++;
}
/* Make descriptor updates visible to hardware */
diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c
index bc981043cc80..a701178a1d13 100644
--- a/drivers/net/ipa/gsi.c
+++ b/drivers/net/ipa/gsi.c
@@ -1367,9 +1367,10 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index)
struct gsi_event *event_done;
struct gsi_event *event;
struct gsi_trans *trans;
+ u32 trans_count = 0;
u32 byte_count = 0;
- u32 old_index;
u32 event_avail;
+ u32 old_index;
trans_info = &channel->trans_info;
@@ -1390,6 +1391,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index)
do {
trans->len = __le16_to_cpu(event->len);
byte_count += trans->len;
+ trans_count++;
/* Move on to the next event and transaction */
if (--event_avail)
@@ -1401,7 +1403,7 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index)
/* We record RX bytes when they are received */
channel->byte_count += byte_count;
- channel->trans_count++;
+ channel->trans_count += trans_count;
}
/* Initialize a ring, including allocating DMA memory for its entries */
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index 888e94278a84..cea7b2e2ce96 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -1150,13 +1150,12 @@ static void ipa_endpoint_skb_copy(struct ipa_endpoint *endpoint,
return;
skb = __dev_alloc_skb(len, GFP_ATOMIC);
- if (!skb)
- return;
-
- /* Copy the data into the socket buffer and receive it */
- skb_put(skb, len);
- memcpy(skb->data, data, len);
- skb->truesize += extra;
+ if (skb) {
+ /* Copy the data into the socket buffer and receive it */
+ skb_put(skb, len);
+ memcpy(skb->data, data, len);
+ skb->truesize += extra;
+ }
ipa_modem_skb_rx(endpoint->netdev, skb);
}
diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c
index 90f3aec55b36..ec010cf2e816 100644
--- a/drivers/net/ipa/ipa_qmi.c
+++ b/drivers/net/ipa/ipa_qmi.c
@@ -125,7 +125,7 @@ static void ipa_qmi_indication(struct ipa_qmi *ipa_qmi)
*/
static void ipa_qmi_ready(struct ipa_qmi *ipa_qmi)
{
- struct ipa *ipa = container_of(ipa_qmi, struct ipa, qmi);
+ struct ipa *ipa;
int ret;
/* We aren't ready until the modem and microcontroller are */
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 463ae5d33eb0..5b47545f22d3 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -71,7 +71,6 @@ struct inet_timewait_sock {
tw_tos : 8;
u32 tw_txhash;
u32 tw_priority;
- u32 tw_bslot; /* bind bucket slot */
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
};
@@ -110,6 +109,8 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo
void inet_twsk_deschedule_put(struct inet_timewait_sock *tw);
+void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family);
+
static inline
struct net *twsk_net(const struct inet_timewait_sock *twsk)
{
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ae662567a6cb..0ea29270d7e5 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -1030,9 +1030,15 @@ static void __net_exit dccp_v4_exit_net(struct net *net)
inet_ctl_sock_destroy(pn->v4_ctl_sk);
}
+static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list)
+{
+ inet_twsk_purge(&dccp_hashinfo, AF_INET);
+}
+
static struct pernet_operations dccp_v4_ops = {
.init = dccp_v4_init_net,
.exit = dccp_v4_exit_net,
+ .exit_batch = dccp_v4_exit_batch,
.id = &dccp_v4_pernet_id,
.size = sizeof(struct dccp_v4_pernet),
};
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index eab3bd1ee9a0..fa663518fa0e 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1115,9 +1115,15 @@ static void __net_exit dccp_v6_exit_net(struct net *net)
inet_ctl_sock_destroy(pn->v6_ctl_sk);
}
+static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list)
+{
+ inet_twsk_purge(&dccp_hashinfo, AF_INET6);
+}
+
static struct pernet_operations dccp_v6_ops = {
.init = dccp_v6_init_net,
.exit = dccp_v6_exit_net,
+ .exit_batch = dccp_v6_exit_batch,
.id = &dccp_v6_pernet_id,
.size = sizeof(struct dccp_v6_pernet),
};
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 9e0bbd026560..0ec501845cb3 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -52,7 +52,8 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw)
spin_unlock(lock);
/* Disassociate with bind bucket. */
- bhead = &hashinfo->bhash[tw->tw_bslot];
+ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
+ hashinfo->bhash_size)];
spin_lock(&bhead->lock);
inet_twsk_bind_unhash(tw, hashinfo);
@@ -111,12 +112,8 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
Note, that any socket with inet->num != 0 MUST be bound in
binding cache, even if it is closed.
*/
- /* Cache inet_bhashfn(), because 'struct net' might be no longer
- * available later in inet_twsk_kill().
- */
- tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num,
- hashinfo->bhash_size);
- bhead = &hashinfo->bhash[tw->tw_bslot];
+ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
+ hashinfo->bhash_size)];
spin_lock(&bhead->lock);
tw->tw_tb = icsk->icsk_bind_hash;
WARN_ON(!icsk->icsk_bind_hash);
@@ -257,3 +254,50 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
}
}
EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
+
+void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
+{
+ struct inet_timewait_sock *tw;
+ struct sock *sk;
+ struct hlist_nulls_node *node;
+ unsigned int slot;
+
+ for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
+ struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
+restart_rcu:
+ cond_resched();
+ rcu_read_lock();
+restart:
+ sk_nulls_for_each_rcu(sk, node, &head->chain) {
+ if (sk->sk_state != TCP_TIME_WAIT)
+ continue;
+ tw = inet_twsk(sk);
+ if ((tw->tw_family != family) ||
+ refcount_read(&twsk_net(tw)->ns.count))
+ continue;
+
+ if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
+ continue;
+
+ if (unlikely((tw->tw_family != family) ||
+ refcount_read(&twsk_net(tw)->ns.count))) {
+ inet_twsk_put(tw);
+ goto restart;
+ }
+
+ rcu_read_unlock();
+ local_bh_disable();
+ inet_twsk_deschedule_put(tw);
+ local_bh_enable();
+ goto restart_rcu;
+ }
+ /* If the nulls value we got at the end of this lookup is
+ * not the expected one, we must restart lookup.
+ * We probably met an item that was moved to another chain.
+ */
+ if (get_nulls_value(node) != slot)
+ goto restart;
+ rcu_read_unlock();
+ }
+}
+EXPORT_SYMBOL_GPL(inet_twsk_purge);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f9cec624068d..457f5b5d5d4a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3173,6 +3173,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
struct net *net;
+ inet_twsk_purge(&tcp_hashinfo, AF_INET);
+
list_for_each_entry(net, net_exit_list, exit_list)
tcp_fastopen_ctx_destroy(net);
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 13678d3908fa..faaddaf43c90 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2207,9 +2207,15 @@ static void __net_exit tcpv6_net_exit(struct net *net)
inet_ctl_sock_destroy(net->ipv6.tcp_sk);
}
+static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list)
+{
+ inet_twsk_purge(&tcp_hashinfo, AF_INET6);
+}
+
static struct pernet_operations tcpv6_net_ops = {
.init = tcpv6_net_init,
.exit = tcpv6_net_exit,
+ .exit_batch = tcpv6_net_exit_batch,
};
int __init tcpv6_init(void)
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 01809eef29b4..aa51b100e033 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -178,14 +178,13 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
struct mptcp_pm_data *pm = &msk->pm;
bool update_subflows;
- update_subflows = (ssk->sk_state == TCP_CLOSE) &&
- (subflow->request_join || subflow->mp_join);
+ update_subflows = subflow->request_join || subflow->mp_join;
if (!READ_ONCE(pm->work_pending) && !update_subflows)
return;
spin_lock_bh(&pm->lock);
if (update_subflows)
- pm->subflows--;
+ __mptcp_pm_close_subflow(msk);
/* Even if this subflow is not really established, tell the PM to try
* to pick the next ones, if possible.
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3c1a3036550f..f4ce28bb0fdc 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -833,6 +833,20 @@ 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);
unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk);
+/* called under PM lock */
+static inline void __mptcp_pm_close_subflow(struct mptcp_sock *msk)
+{
+ if (--msk->pm.subflows < mptcp_pm_get_subflows_max(msk))
+ WRITE_ONCE(msk->pm.accept_subflow, true);
+}
+
+static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk)
+{
+ spin_lock_bh(&msk->pm.lock);
+ __mptcp_pm_close_subflow(msk);
+ spin_unlock_bh(&msk->pm.lock);
+}
+
void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);
void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index aba260f547da..8c37087f0d84 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1422,20 +1422,20 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
struct sockaddr_storage addr;
int remote_id = remote->id;
int local_id = loc->id;
+ int err = -ENOTCONN;
struct socket *sf;
struct sock *ssk;
u32 remote_token;
int addrlen;
int ifindex;
u8 flags;
- int err;
if (!mptcp_is_fully_established(sk))
- return -ENOTCONN;
+ goto err_out;
err = mptcp_subflow_create_socket(sk, &sf);
if (err)
- return err;
+ goto err_out;
ssk = sf->sk;
subflow = mptcp_subflow_ctx(ssk);
@@ -1492,6 +1492,12 @@ failed_unlink:
failed:
subflow->disposable = 1;
sock_release(sf);
+
+err_out:
+ /* we account subflows before the creation, and this failures will not
+ * be caught by sk_state_change()
+ */
+ mptcp_pm_close_subflow(msk);
return err;
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 7314257d248a..48ef112f42c2 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -1444,6 +1444,33 @@ chk_prio_nr()
[ "${dump_stats}" = 1 ] && dump_stats
}
+chk_subflow_nr()
+{
+ local need_title="$1"
+ local msg="$2"
+ local subflow_nr=$3
+ local cnt1
+ local cnt2
+
+ if [ -n "${need_title}" ]; then
+ printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}"
+ else
+ printf "%-${nr_blank}s %s" " " "${msg}"
+ fi
+
+ cnt1=$(ss -N $ns1 -tOni | grep -c token)
+ cnt2=$(ss -N $ns2 -tOni | grep -c token)
+ if [ "$cnt1" != "$subflow_nr" -o "$cnt2" != "$subflow_nr" ]; then
+ echo "[fail] got $cnt1:$cnt2 subflows expected $subflow_nr"
+ fail_test
+ dump_stats=1
+ else
+ echo "[ ok ]"
+ fi
+
+ [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint )
+}
+
chk_link_usage()
{
local ns=$1
@@ -2556,7 +2583,7 @@ fastclose_tests()
fi
}
-implicit_tests()
+endpoint_tests()
{
# userspace pm type prevents add_addr
if reset "implicit EP"; then
@@ -2578,6 +2605,23 @@ implicit_tests()
$ns2 10.0.2.2 id 1 flags signal
wait
fi
+
+ if reset "delete and re-add"; then
+ pm_nl_set_limits $ns1 1 1
+ pm_nl_set_limits $ns2 1 1
+ pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
+ run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow &
+
+ wait_mpj $ns2
+ pm_nl_del_endpoint $ns2 2 10.0.2.2
+ sleep 0.5
+ chk_subflow_nr needtitle "after delete" 1
+
+ pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
+ wait_mpj $ns2
+ chk_subflow_nr "" "after re-add" 2
+ wait
+ fi
}
# [$1: error message]
@@ -2624,7 +2668,7 @@ all_tests_sorted=(
d@deny_join_id0_tests
m@fullmesh_tests
z@fastclose_tests
- I@implicit_tests
+ I@endpoint_tests
)
all_tests_args=""
Powered by cgit, Gruvboxed by Blaster4385.