summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2024-02-16 01:01:43 +0300
committerJakub Kicinski <kuba@kernel.org>2024-02-16 03:20:04 +0300
commit73be9a3aabdd976123e7f05dd20dbcf131347e84 (patch)
tree7b9575df90cae451b7640d53d5e3b3858900a275 /net
parentdfe7f12788f5428d8bc16e86eedcfa889a3e3b29 (diff)
parent4f5e5092fdbf5cec6bedc19fbe69cce4f5f08372 (diff)
downloadlinux-73be9a3aabdd976123e7f05dd20dbcf131347e84.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR. No conflicts. Adjacent changes: net/core/dev.c 9f30831390ed ("net: add rcu safety to rtnl_prop_list_size()") 723de3ebef03 ("net: free altname using an RCU callback") net/unix/garbage.c 11498715f266 ("af_unix: Remove io_uring code for GC.") 25236c91b5ab ("af_unix: Fix task hung while purging oob_skb in GC.") drivers/net/ethernet/renesas/ravb_main.c ed4adc07207d ("net: ravb: Count packets instead of descriptors in GbEth RX path" ) c2da9408579d ("ravb: Add Rx checksum offload support for GbEth") net/mptcp/protocol.c bdd70eb68913 ("mptcp: drop the push_pending field") 28e5c1380506 ("mptcp: annotate lockless accesses around read-mostly fields") Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
-rw-r--r--net/6lowpan/core.c1
-rw-r--r--net/atm/mpc.c1
-rw-r--r--net/can/j1939/j1939-priv.h3
-rw-r--r--net/can/j1939/main.c2
-rw-r--r--net/can/j1939/socket.c46
-rw-r--r--net/ceph/messenger_v1.c33
-rw-r--r--net/ceph/messenger_v2.c4
-rw-r--r--net/ceph/osd_client.c27
-rw-r--r--net/core/dev.c5
-rw-r--r--net/core/rtnetlink.c15
-rw-r--r--net/handshake/handshake-test.c5
-rw-r--r--net/ipv4/ah4.c1
-rw-r--r--net/ipv4/esp4.c1
-rw-r--r--net/ipv4/ip_gre.c1
-rw-r--r--net/ipv4/ip_output.c13
-rw-r--r--net/ipv4/ip_tunnel.c1
-rw-r--r--net/ipv4/ip_vti.c1
-rw-r--r--net/ipv4/ipip.c1
-rw-r--r--net/ipv4/tcp.c3
-rw-r--r--net/ipv4/tunnel4.c1
-rw-r--r--net/ipv4/udp_tunnel_core.c1
-rw-r--r--net/ipv4/xfrm4_tunnel.c1
-rw-r--r--net/ipv6/ah6.c1
-rw-r--r--net/ipv6/esp6.c1
-rw-r--r--net/ipv6/ip6_output.c13
-rw-r--r--net/ipv6/ip6_udp_tunnel.c1
-rw-r--r--net/ipv6/mip6.c1
-rw-r--r--net/ipv6/sit.c1
-rw-r--r--net/ipv6/tunnel6.c1
-rw-r--r--net/ipv6/xfrm6_tunnel.c1
-rw-r--r--net/key/af_key.c1
-rw-r--r--net/mac80211/tx.c5
-rw-r--r--net/mptcp/fastopen.c6
-rw-r--r--net/mptcp/options.c9
-rw-r--r--net/mptcp/pm_userspace.c13
-rw-r--r--net/mptcp/protocol.c31
-rw-r--r--net/mptcp/protocol.h16
-rw-r--r--net/mptcp/subflow.c71
-rw-r--r--net/netfilter/nf_nat_core.c5
-rw-r--r--net/netfilter/nft_flow_offload.c1
-rw-r--r--net/netfilter/nft_set_pipapo.h4
-rw-r--r--net/netfilter/nft_set_pipapo_avx2.c2
-rw-r--r--net/openvswitch/flow_netlink.c49
-rw-r--r--net/rds/recv.c13
-rw-r--r--net/sched/act_mirred.c2
-rw-r--r--net/sched/em_canid.c1
-rw-r--r--net/sched/em_cmp.c1
-rw-r--r--net/sched/em_meta.c1
-rw-r--r--net/sched/em_nbyte.c1
-rw-r--r--net/sched/em_text.c1
-rw-r--r--net/sched/em_u32.c1
-rw-r--r--net/sctp/inqueue.c14
-rw-r--r--net/smc/af_smc.c1
-rw-r--r--net/tls/tls_sw.c135
-rw-r--r--net/unix/garbage.c7
-rw-r--r--net/xfrm/xfrm_algo.c1
-rw-r--r--net/xfrm/xfrm_user.c1
57 files changed, 352 insertions, 228 deletions
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c
index 7b3341cef926..850d4a185f55 100644
--- a/net/6lowpan/core.c
+++ b/net/6lowpan/core.c
@@ -179,4 +179,5 @@ static void __exit lowpan_module_exit(void)
module_init(lowpan_module_init);
module_exit(lowpan_module_exit);
+MODULE_DESCRIPTION("IPv6 over Low-Power Wireless Personal Area Network core module");
MODULE_LICENSE("GPL");
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 033871e718a3..324e3ab96bb3 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -1532,4 +1532,5 @@ static void __exit atm_mpoa_cleanup(void)
module_init(atm_mpoa_init);
module_exit(atm_mpoa_cleanup);
+MODULE_DESCRIPTION("Multi-Protocol Over ATM (MPOA) driver");
MODULE_LICENSE("GPL");
diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index 16af1a7f80f6..31a93cae5111 100644
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -86,7 +86,7 @@ struct j1939_priv {
unsigned int tp_max_packet_size;
/* lock for j1939_socks list */
- spinlock_t j1939_socks_lock;
+ rwlock_t j1939_socks_lock;
struct list_head j1939_socks;
struct kref rx_kref;
@@ -301,6 +301,7 @@ struct j1939_sock {
int ifindex;
struct j1939_addr addr;
+ spinlock_t filters_lock;
struct j1939_filter *filters;
int nfilters;
pgn_t pgn_rx_filter;
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index ecff1c947d68..a6fb89fa6278 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev)
return ERR_PTR(-ENOMEM);
j1939_tp_init(priv);
- spin_lock_init(&priv->j1939_socks_lock);
+ rwlock_init(&priv->j1939_socks_lock);
INIT_LIST_HEAD(&priv->j1939_socks);
mutex_lock(&j1939_netdev_lock);
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 14c431663233..305dd72c844c 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk)
jsk->state |= J1939_SOCK_BOUND;
j1939_priv_get(priv);
- spin_lock_bh(&priv->j1939_socks_lock);
+ write_lock_bh(&priv->j1939_socks_lock);
list_add_tail(&jsk->list, &priv->j1939_socks);
- spin_unlock_bh(&priv->j1939_socks_lock);
+ write_unlock_bh(&priv->j1939_socks_lock);
}
static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk)
{
- spin_lock_bh(&priv->j1939_socks_lock);
+ write_lock_bh(&priv->j1939_socks_lock);
list_del_init(&jsk->list);
- spin_unlock_bh(&priv->j1939_socks_lock);
+ write_unlock_bh(&priv->j1939_socks_lock);
j1939_priv_put(priv);
jsk->state &= ~J1939_SOCK_BOUND;
@@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk,
static bool j1939_sk_match_filter(struct j1939_sock *jsk,
const struct j1939_sk_buff_cb *skcb)
{
- const struct j1939_filter *f = jsk->filters;
- int nfilter = jsk->nfilters;
+ const struct j1939_filter *f;
+ int nfilter;
+
+ spin_lock_bh(&jsk->filters_lock);
+
+ f = jsk->filters;
+ nfilter = jsk->nfilters;
if (!nfilter)
/* receive all when no filters are assigned */
- return true;
+ goto filter_match_found;
for (; nfilter; ++f, --nfilter) {
if ((skcb->addr.pgn & f->pgn_mask) != f->pgn)
@@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk,
continue;
if ((skcb->addr.src_name & f->name_mask) != f->name)
continue;
- return true;
+ goto filter_match_found;
}
+
+ spin_unlock_bh(&jsk->filters_lock);
return false;
+
+filter_match_found:
+ spin_unlock_bh(&jsk->filters_lock);
+ return true;
}
static bool j1939_sk_recv_match_one(struct j1939_sock *jsk,
@@ -329,13 +340,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb)
struct j1939_sock *jsk;
bool match = false;
- spin_lock_bh(&priv->j1939_socks_lock);
+ read_lock_bh(&priv->j1939_socks_lock);
list_for_each_entry(jsk, &priv->j1939_socks, list) {
match = j1939_sk_recv_match_one(jsk, skcb);
if (match)
break;
}
- spin_unlock_bh(&priv->j1939_socks_lock);
+ read_unlock_bh(&priv->j1939_socks_lock);
return match;
}
@@ -344,11 +355,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb)
{
struct j1939_sock *jsk;
- spin_lock_bh(&priv->j1939_socks_lock);
+ read_lock_bh(&priv->j1939_socks_lock);
list_for_each_entry(jsk, &priv->j1939_socks, list) {
j1939_sk_recv_one(jsk, skb);
}
- spin_unlock_bh(&priv->j1939_socks_lock);
+ read_unlock_bh(&priv->j1939_socks_lock);
}
static void j1939_sk_sock_destruct(struct sock *sk)
@@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk)
atomic_set(&jsk->skb_pending, 0);
spin_lock_init(&jsk->sk_session_queue_lock);
INIT_LIST_HEAD(&jsk->sk_session_queue);
+ spin_lock_init(&jsk->filters_lock);
/* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */
sock_set_flag(sk, SOCK_RCU_FREE);
@@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname,
}
lock_sock(&jsk->sk);
+ spin_lock_bh(&jsk->filters_lock);
ofilters = jsk->filters;
jsk->filters = filters;
jsk->nfilters = count;
+ spin_unlock_bh(&jsk->filters_lock);
release_sock(&jsk->sk);
kfree(ofilters);
return 0;
@@ -1080,12 +1094,12 @@ void j1939_sk_errqueue(struct j1939_session *session,
}
/* spread RX notifications to all sockets subscribed to this session */
- spin_lock_bh(&priv->j1939_socks_lock);
+ read_lock_bh(&priv->j1939_socks_lock);
list_for_each_entry(jsk, &priv->j1939_socks, list) {
if (j1939_sk_recv_match_one(jsk, &session->skcb))
__j1939_sk_errqueue(session, &jsk->sk, type);
}
- spin_unlock_bh(&priv->j1939_socks_lock);
+ read_unlock_bh(&priv->j1939_socks_lock);
};
void j1939_sk_send_loop_abort(struct sock *sk, int err)
@@ -1273,7 +1287,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
struct j1939_sock *jsk;
int error_code = ENETDOWN;
- spin_lock_bh(&priv->j1939_socks_lock);
+ read_lock_bh(&priv->j1939_socks_lock);
list_for_each_entry(jsk, &priv->j1939_socks, list) {
jsk->sk.sk_err = error_code;
if (!sock_flag(&jsk->sk, SOCK_DEAD))
@@ -1281,7 +1295,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
j1939_sk_queue_drop_all(priv, jsk, error_code);
}
- spin_unlock_bh(&priv->j1939_socks_lock);
+ read_unlock_bh(&priv->j1939_socks_lock);
}
static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd,
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index f9a50d7f0d20..0cb61c76b9b8 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -160,8 +160,9 @@ static size_t sizeof_footer(struct ceph_connection *con)
static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
{
/* Initialize data cursor if it's not a sparse read */
- if (!msg->sparse_read)
- ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
+ u64 len = msg->sparse_read_total ? : data_len;
+
+ ceph_msg_data_cursor_init(&msg->cursor, msg, len);
}
/*
@@ -991,7 +992,7 @@ static inline int read_partial_message_section(struct ceph_connection *con,
return read_partial_message_chunk(con, section, sec_len, crc);
}
-static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
+static int read_partial_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
{
struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
bool do_bounce = ceph_test_opt(from_msgr(con->msgr), RXBOUNCE);
@@ -1026,7 +1027,7 @@ static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
return 1;
}
-static int read_sparse_msg_data(struct ceph_connection *con)
+static int read_partial_sparse_msg_data(struct ceph_connection *con)
{
struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
@@ -1036,31 +1037,31 @@ static int read_sparse_msg_data(struct ceph_connection *con)
if (do_datacrc)
crc = con->in_data_crc;
- do {
+ while (cursor->total_resid) {
if (con->v1.in_sr_kvec.iov_base)
ret = read_partial_message_chunk(con,
&con->v1.in_sr_kvec,
con->v1.in_sr_len,
&crc);
else if (cursor->sr_resid > 0)
- ret = read_sparse_msg_extent(con, &crc);
-
- if (ret <= 0) {
- if (do_datacrc)
- con->in_data_crc = crc;
- return ret;
- }
+ ret = read_partial_sparse_msg_extent(con, &crc);
+ if (ret <= 0)
+ break;
memset(&con->v1.in_sr_kvec, 0, sizeof(con->v1.in_sr_kvec));
ret = con->ops->sparse_read(con, cursor,
(char **)&con->v1.in_sr_kvec.iov_base);
+ if (ret <= 0) {
+ ret = ret ? ret : 1; /* must return > 0 to indicate success */
+ break;
+ }
con->v1.in_sr_len = ret;
- } while (ret > 0);
+ }
if (do_datacrc)
con->in_data_crc = crc;
- return ret < 0 ? ret : 1; /* must return > 0 to indicate success */
+ return ret;
}
static int read_partial_msg_data(struct ceph_connection *con)
@@ -1253,8 +1254,8 @@ static int read_partial_message(struct ceph_connection *con)
if (!m->num_data_items)
return -EIO;
- if (m->sparse_read)
- ret = read_sparse_msg_data(con);
+ if (m->sparse_read_total)
+ ret = read_partial_sparse_msg_data(con);
else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
ret = read_partial_msg_data_bounce(con);
else
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index f8ec60e1aba3..a0ca5414b333 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1128,7 +1128,7 @@ static int decrypt_tail(struct ceph_connection *con)
struct sg_table enc_sgt = {};
struct sg_table sgt = {};
struct page **pages = NULL;
- bool sparse = con->in_msg->sparse_read;
+ bool sparse = !!con->in_msg->sparse_read_total;
int dpos = 0;
int tail_len;
int ret;
@@ -2060,7 +2060,7 @@ static int prepare_read_tail_plain(struct ceph_connection *con)
}
if (data_len(msg)) {
- if (msg->sparse_read)
+ if (msg->sparse_read_total)
con->v2.in_state = IN_S_PREPARE_SPARSE_DATA;
else
con->v2.in_state = IN_S_PREPARE_READ_DATA;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 625622016f57..9d078b37fe0b 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5510,7 +5510,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
}
m = ceph_msg_get(req->r_reply);
- m->sparse_read = (bool)srlen;
+ m->sparse_read_total = srlen;
dout("get_reply tid %lld %p\n", tid, m);
@@ -5777,11 +5777,8 @@ static int prep_next_sparse_read(struct ceph_connection *con,
}
if (o->o_sparse_op_idx < 0) {
- u64 srlen = sparse_data_requested(req);
-
- dout("%s: [%d] starting new sparse read req. srlen=0x%llx\n",
- __func__, o->o_osd, srlen);
- ceph_msg_data_cursor_init(cursor, con->in_msg, srlen);
+ dout("%s: [%d] starting new sparse read req\n",
+ __func__, o->o_osd);
} else {
u64 end;
@@ -5857,8 +5854,8 @@ static int osd_sparse_read(struct ceph_connection *con,
struct ceph_osd *o = con->private;
struct ceph_sparse_read *sr = &o->o_sparse_read;
u32 count = sr->sr_count;
- u64 eoff, elen;
- int ret;
+ u64 eoff, elen, len = 0;
+ int i, ret;
switch (sr->sr_state) {
case CEPH_SPARSE_READ_HDR:
@@ -5903,8 +5900,20 @@ next_op:
convert_extent_map(sr);
ret = sizeof(sr->sr_datalen);
*pbuf = (char *)&sr->sr_datalen;
- sr->sr_state = CEPH_SPARSE_READ_DATA;
+ sr->sr_state = CEPH_SPARSE_READ_DATA_PRE;
break;
+ case CEPH_SPARSE_READ_DATA_PRE:
+ /* Convert sr_datalen to host-endian */
+ sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen);
+ for (i = 0; i < count; i++)
+ len += sr->sr_extent[i].len;
+ if (sr->sr_datalen != len) {
+ pr_warn_ratelimited("data len %u != extent len %llu\n",
+ sr->sr_datalen, len);
+ return -EREMOTEIO;
+ }
+ sr->sr_state = CEPH_SPARSE_READ_DATA;
+ fallthrough;
case CEPH_SPARSE_READ_DATA:
if (sr->sr_index >= count) {
sr->sr_state = CEPH_SPARSE_READ_HDR;
diff --git a/net/core/dev.c b/net/core/dev.c
index d8dd293a7a27..cc9c2eda65ac 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -316,7 +316,7 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name)
return -ENOMEM;
netdev_name_node_add(net, name_node);
/* The node that holds dev->name acts as a head of per-device list. */
- list_add_tail(&name_node->list, &dev->name_node->list);
+ list_add_tail_rcu(&name_node->list, &dev->name_node->list);
return 0;
}
@@ -11695,11 +11695,12 @@ static void __init net_dev_struct_check(void)
CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
/* TXRX read-mostly hotpath */
+ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
- CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30);
+ CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38);
/* RX read-mostly hotpath */
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 39e66bf3e238..c54dbe05c4c5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1019,14 +1019,17 @@ static size_t rtnl_xdp_size(void)
static size_t rtnl_prop_list_size(const struct net_device *dev)
{
struct netdev_name_node *name_node;
- size_t size;
+ unsigned int cnt = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(name_node, &dev->name_node->list, list)
+ cnt++;
+ rcu_read_unlock();
- if (list_empty(&dev->name_node->list))
+ if (!cnt)
return 0;
- size = nla_total_size(0);
- list_for_each_entry(name_node, &dev->name_node->list, list)
- size += nla_total_size(ALTIFNAMSIZ);
- return size;
+
+ return nla_total_size(0) + cnt * nla_total_size(ALTIFNAMSIZ);
}
static size_t rtnl_proto_down_size(const struct net_device *dev)
diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c
index 16ed7bfd29e4..34fd1d9b2db8 100644
--- a/net/handshake/handshake-test.c
+++ b/net/handshake/handshake-test.c
@@ -471,7 +471,10 @@ static void handshake_req_destroy_test1(struct kunit *test)
handshake_req_cancel(sock->sk);
/* Act */
- fput(filp);
+ /* Ensure the close/release/put process has run to
+ * completion before checking the result.
+ */
+ __fput_sync(filp);
/* Assert */
KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req);
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a2e6e1fdf82b..64aec3dff8ec 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -597,5 +597,6 @@ static void __exit ah4_fini(void)
module_init(ah4_init);
module_exit(ah4_fini);
+MODULE_DESCRIPTION("IPv4 AH transformation library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4ccfc104f13a..4dd9e5040672 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -1247,5 +1247,6 @@ static void __exit esp4_fini(void)
module_init(esp4_init);
module_exit(esp4_fini);
+MODULE_DESCRIPTION("IPv4 ESP transformation library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index aad5125b7a65..7b16c211b904 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1799,6 +1799,7 @@ static void __exit ipgre_fini(void)
module_init(ipgre_init);
module_exit(ipgre_fini);
+MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("gre");
MODULE_ALIAS_RTNL_LINK("gretap");
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5b5a0adb927f..1fe794967211 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -972,8 +972,8 @@ static int __ip_append_data(struct sock *sk,
unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
int csummode = CHECKSUM_NONE;
struct rtable *rt = (struct rtable *)cork->dst;
+ bool paged, hold_tskey, extra_uref = false;
unsigned int wmem_alloc_delta = 0;
- bool paged, extra_uref = false;
u32 tskey = 0;
skb = skb_peek_tail(queue);
@@ -982,10 +982,6 @@ static int __ip_append_data(struct sock *sk,
mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
paged = !!cork->gso_size;
- if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
- READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
- tskey = atomic_inc_return(&sk->sk_tskey) - 1;
-
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
@@ -1052,6 +1048,11 @@ static int __ip_append_data(struct sock *sk,
cork->length += length;
+ hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
+ READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
+ if (hold_tskey)
+ tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+
/* So, what's going on in the loop below?
*
* We use calculated fragment length to generate chained skb,
@@ -1274,6 +1275,8 @@ error:
cork->length -= length;
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+ if (hold_tskey)
+ atomic_dec(&sk->sk_tskey);
return err;
}
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 9f44c49a61de..756f8b923883 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1296,4 +1296,5 @@ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id)
}
EXPORT_SYMBOL_GPL(ip_tunnel_setup);
+MODULE_DESCRIPTION("IPv4 tunnel implementation library");
MODULE_LICENSE("GPL");
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index fb1f52d21311..ee587adb169f 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -723,6 +723,7 @@ static void __exit vti_fini(void)
module_init(vti_init);
module_exit(vti_fini);
+MODULE_DESCRIPTION("Virtual (secure) IP tunneling library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("vti");
MODULE_ALIAS_NETDEV("ip_vti0");
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 0151eea06cc5..f2696eaadbe6 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -660,6 +660,7 @@ static void __exit ipip_fini(void)
module_init(ipip_init);
module_exit(ipip_fini);
+MODULE_DESCRIPTION("IP/IP protocol decoder library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("ipip");
MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7e2481b9eae1..c82dc42f57c6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4615,7 +4615,8 @@ static void __init tcp_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out);
- CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio);
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32);
/* RX read-mostly hotpath cache lines */
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq);
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index 5048c47c79b2..4c1f836aae38 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -294,4 +294,5 @@ static void __exit tunnel4_fini(void)
module_init(tunnel4_init);
module_exit(tunnel4_fini);
+MODULE_DESCRIPTION("IPv4 XFRM tunnel library");
MODULE_LICENSE("GPL");
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index a87defb2b167..860aff5f8599 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -253,4 +253,5 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb,
}
EXPORT_SYMBOL_GPL(udp_tunnel_dst_lookup);
+MODULE_DESCRIPTION("IPv4 Foo over UDP tunnel driver");
MODULE_LICENSE("GPL");
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index 8489fa106583..8cb266af1393 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -114,5 +114,6 @@ static void __exit ipip_fini(void)
module_init(ipip_init);
module_exit(ipip_fini);
+MODULE_DESCRIPTION("IPv4 XFRM tunnel driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_IPIP);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 2016e90e6e1d..eb474f0987ae 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -800,5 +800,6 @@ static void __exit ah6_fini(void)
module_init(ah6_init);
module_exit(ah6_fini);
+MODULE_DESCRIPTION("IPv6 AH transformation helpers");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_AH);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 2cc1a45742d8..6e6efe026cdc 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -1301,5 +1301,6 @@ static void __exit esp6_fini(void)
module_init(esp6_init);
module_exit(esp6_fini);
+MODULE_DESCRIPTION("IPv6 ESP transformation helpers");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ESP);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a722a43dd668..31b86fe661aa 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1424,11 +1424,11 @@ static int __ip6_append_data(struct sock *sk,
bool zc = false;
u32 tskey = 0;
struct rt6_info *rt = (struct rt6_info *)cork->dst;
+ bool paged, hold_tskey, extra_uref = false;
struct ipv6_txoptions *opt = v6_cork->opt;
int csummode = CHECKSUM_NONE;
unsigned int maxnonfragsize, headersize;
unsigned int wmem_alloc_delta = 0;
- bool paged, extra_uref = false;
skb = skb_peek_tail(queue);
if (!skb) {
@@ -1440,10 +1440,6 @@ static int __ip6_append_data(struct sock *sk,
mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
orig_mtu = mtu;
- if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
- READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
- tskey = atomic_inc_return(&sk->sk_tskey) - 1;
-
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
@@ -1538,6 +1534,11 @@ emsgsize:
flags &= ~MSG_SPLICE_PAGES;
}
+ hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
+ READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
+ if (hold_tskey)
+ tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
@@ -1794,6 +1795,8 @@ error:
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+ if (hold_tskey)
+ atomic_dec(&sk->sk_tskey);
return err;
}
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index a7bf0327b380..c99053189ea8 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -182,4 +182,5 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb,
}
EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup);
+MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver");
MODULE_LICENSE("GPL");
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 83d2a8be263f..6a16a5bd0d91 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -405,6 +405,7 @@ static void __exit mip6_fini(void)
module_init(mip6_init);
module_exit(mip6_fini);
+MODULE_DESCRIPTION("IPv6 Mobility driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_DSTOPTS);
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ROUTING);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b2da1f1b5fec..ed3a44aa1e9d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1954,6 +1954,7 @@ xfrm_tunnel_failed:
module_init(sit_init);
module_exit(sit_cleanup);
+MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("sit");
MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index 00e8d8b1c9a7..dc4ea9b11794 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -302,4 +302,5 @@ static void __exit tunnel6_fini(void)
module_init(tunnel6_init);
module_exit(tunnel6_fini);
+MODULE_DESCRIPTION("IP-in-IPv6 tunnel driver");
MODULE_LICENSE("GPL");
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 1323f2f6928e..f6cb94f82cc3 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -401,5 +401,6 @@ static void __exit xfrm6_tunnel_fini(void)
module_init(xfrm6_tunnel_init);
module_exit(xfrm6_tunnel_fini);
+MODULE_DESCRIPTION("IPv6 XFRM tunnel driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_IPV6);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index d68d01804dc7..f79fb99271ed 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3924,5 +3924,6 @@ out_unregister_key_proto:
module_init(ipsec_pfkey_init);
module_exit(ipsec_pfkey_exit);
+MODULE_DESCRIPTION("PF_KEY socket helpers");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NETPROTO(PF_KEY);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index e448ab338448..6fbb15b65902 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5,7 +5,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
*
* Transmit and frame generation functions.
*/
@@ -3927,6 +3927,7 @@ begin:
goto begin;
skb = __skb_dequeue(&tx.skbs);
+ info = IEEE80211_SKB_CB(skb);
if (!skb_queue_empty(&tx.skbs)) {
spin_lock_bh(&fq->lock);
@@ -3971,7 +3972,7 @@ begin:
}
encap_out:
- IEEE80211_SKB_CB(skb)->control.vif = vif;
+ info->control.vif = vif;
if (tx.sta &&
wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) {
diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index 74698582a285..ad28da655f8b 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
mptcp_data_unlock(sk);
}
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt)
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt)
{
struct sock *sk = (struct sock *)msk;
struct sk_buff *skb;
- mptcp_data_lock(sk);
skb = skb_peek_tail(&sk->sk_receive_queue);
if (skb) {
WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
@@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_
}
pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);
- mptcp_data_unlock(sk);
}
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 801a3525230d..23e317ffc901 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
/* subflows are fully established as soon as we get any
* additional ack, including ADD_ADDR.
*/
- subflow->fully_established = 1;
- WRITE_ONCE(msk->fully_established, true);
- goto check_notify;
+ goto set_fully_established;
}
/* If the first established packet does not contain MP_CAPABLE + data
@@ -986,7 +984,10 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
set_fully_established:
if (unlikely(!READ_ONCE(msk->pm.server_side)))
pr_warn_once("bogus mpc option on established client sk");
- mptcp_subflow_fully_established(subflow, mp_opt);
+
+ mptcp_data_lock((struct sock *)msk);
+ __mptcp_subflow_fully_established(msk, subflow, mp_opt);
+ mptcp_data_unlock((struct sock *)msk);
check_notify:
/* if the subflow is not already linked into the conn_list, we can't
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index efecbe3cf415..4f3901d5b8ef 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -130,10 +130,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
struct mptcp_addr_info *skc)
{
- struct mptcp_pm_addr_entry new_entry;
+ struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry;
__be16 msk_sport = ((struct inet_sock *)
inet_sk((struct sock *)msk))->inet_sport;
+ spin_lock_bh(&msk->pm.lock);
+ list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (mptcp_addresses_equal(&e->addr, skc, false)) {
+ entry = e;
+ break;
+ }
+ }
+ spin_unlock_bh(&msk->pm.lock);
+ if (entry)
+ return entry->addr.id;
+
memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry));
new_entry.addr = *skc;
new_entry.addr.id = 0;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ad39f54b3a81..c7af62c057bc 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1510,8 +1510,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
void mptcp_check_and_set_pending(struct sock *sk)
{
- if (mptcp_send_head(sk))
- mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
+ if (mptcp_send_head(sk)) {
+ mptcp_data_lock(sk);
+ mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING);
+ mptcp_data_unlock(sk);
+ }
}
static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
@@ -1965,6 +1968,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
if (copied <= 0)
return;
+ if (!msk->rcvspace_init)
+ mptcp_rcv_space_init(msk, msk->first);
+
msk->rcvq_space.copied += copied;
mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC);
@@ -3147,7 +3153,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
WRITE_ONCE(msk->flags, 0);
msk->cb_flags = 0;
- msk->push_pending = 0;
msk->recovery = false;
WRITE_ONCE(msk->can_ack, false);
WRITE_ONCE(msk->fully_established, false);
@@ -3163,6 +3168,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
msk->bytes_received = 0;
msk->bytes_sent = 0;
msk->bytes_retrans = 0;
+ msk->rcvspace_init = 0;
WRITE_ONCE(sk->sk_shutdown, 0);
sk_error_report(sk);
@@ -3185,6 +3191,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk;
if (!nsk)
@@ -3225,7 +3232,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
/* The msk maintain a ref to each subflow in the connections list */
WRITE_ONCE(msk->first, ssk);
- list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list);
+ subflow = mptcp_subflow_ctx(ssk);
+ list_add(&subflow->node, &msk->conn_list);
sock_hold(ssk);
/* new mpc subflow takes ownership of the newly
@@ -3240,6 +3248,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
__mptcp_propagate_sndbuf(nsk, ssk);
mptcp_rcv_space_init(msk, ssk);
+
+ if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)
+ __mptcp_subflow_fully_established(msk, subflow, mp_opt);
bh_unlock_sock(nsk);
/* note: the newly allocated socket refcount is 2 now */
@@ -3250,6 +3261,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
{
const struct tcp_sock *tp = tcp_sk(ssk);
+ msk->rcvspace_init = 1;
msk->rcvq_space.copied = 0;
msk->rcvq_space.rtt_us = 0;
@@ -3260,8 +3272,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
TCP_INIT_CWND * tp->advmss);
if (msk->rcvq_space.space == 0)
msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
-
- WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
}
void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
@@ -3332,8 +3342,7 @@ static void mptcp_release_cb(struct sock *sk)
struct mptcp_sock *msk = mptcp_sk(sk);
for (;;) {
- unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
- msk->push_pending;
+ unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED);
struct list_head join_list;
if (!flags)
@@ -3349,7 +3358,6 @@ static void mptcp_release_cb(struct sock *sk)
* datapath acquires the msk socket spinlock while helding
* the subflow socket lock
*/
- msk->push_pending = 0;
msk->cb_flags &= ~flags;
spin_unlock_bh(&sk->sk_lock.slock);
@@ -3477,13 +3485,8 @@ void mptcp_finish_connect(struct sock *ssk)
* accessing the field below
*/
WRITE_ONCE(msk->local_key, subflow->local_key);
- WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
- WRITE_ONCE(msk->snd_nxt, msk->write_seq);
- WRITE_ONCE(msk->snd_una, msk->write_seq);
mptcp_pm_new_connection(msk, ssk, 0);
-
- mptcp_rcv_space_init(msk, ssk);
}
void mptcp_sock_graft(struct sock *sk, struct socket *parent)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 421dede93e2b..c5ec056040eb 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -288,7 +288,6 @@ struct mptcp_sock {
int rmem_released;
unsigned long flags;
unsigned long cb_flags;
- unsigned long push_pending;
bool recovery; /* closing subflow write queue reinjected */
bool can_ack;
bool fully_established;
@@ -307,7 +306,8 @@ struct mptcp_sock {
nodelay:1,
fastopening:1,
in_accept_queue:1,
- free_first:1;
+ free_first:1,
+ rcvspace_init:1;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
@@ -624,8 +624,9 @@ 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_subflow_fully_established(struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt);
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+ struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt);
bool __mptcp_retransmit_pending_data(struct sock *sk);
void mptcp_check_and_set_pending(struct sock *sk);
void __mptcp_push_pending(struct sock *sk, unsigned int flags);
@@ -954,8 +955,8 @@ void mptcp_event_pm_listener(const struct sock *ssk,
enum mptcp_event_type event);
bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt);
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt);
void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,
struct request_sock *req);
@@ -1130,7 +1131,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) &&
+ return (1 << sk->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) &&
is_active_ssk(subflow) &&
!subflow->conn_finished;
}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index d60b83511302..02dab0669cfc 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -422,29 +422,26 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
void __mptcp_sync_state(struct sock *sk, int state)
{
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
+ struct sock *ssk = msk->first;
+
+ subflow = mptcp_subflow_ctx(ssk);
+ __mptcp_propagate_sndbuf(sk, ssk);
+ if (!msk->rcvspace_init)
+ mptcp_rcv_space_init(msk, ssk);
- __mptcp_propagate_sndbuf(sk, msk->first);
if (sk->sk_state == TCP_SYN_SENT) {
+ /* subflow->idsn is always available is TCP_SYN_SENT state,
+ * even for the FASTOPEN scenarios
+ */
+ WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
mptcp_set_state(sk, state);
sk->sk_state_change(sk);
}
}
-static void mptcp_propagate_state(struct sock *sk, struct sock *ssk)
-{
- struct mptcp_sock *msk = mptcp_sk(sk);
-
- mptcp_data_lock(sk);
- if (!sock_owned_by_user(sk)) {
- __mptcp_sync_state(sk, ssk->sk_state);
- } else {
- msk->pending_state = ssk->sk_state;
- __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
- }
- mptcp_data_unlock(sk);
-}
-
static void subflow_set_remote_key(struct mptcp_sock *msk,
struct mptcp_subflow_context *subflow,
const struct mptcp_options_received *mp_opt)
@@ -466,6 +463,31 @@ static void subflow_set_remote_key(struct mptcp_sock *msk,
atomic64_set(&msk->rcv_wnd_sent, subflow->iasn);
}
+static void mptcp_propagate_state(struct sock *sk, struct sock *ssk,
+ struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ mptcp_data_lock(sk);
+ if (mp_opt) {
+ /* Options are available only in the non fallback cases
+ * avoid updating rx path fields otherwise
+ */
+ WRITE_ONCE(msk->snd_una, subflow->idsn + 1);
+ WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd);
+ subflow_set_remote_key(msk, subflow, mp_opt);
+ }
+
+ if (!sock_owned_by_user(sk)) {
+ __mptcp_sync_state(sk, ssk->sk_state);
+ } else {
+ msk->pending_state = ssk->sk_state;
+ __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
+ }
+ mptcp_data_unlock(sk);
+}
+
static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -500,10 +522,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
if (mp_opt.deny_join_id0)
WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
subflow->mp_capable = 1;
- subflow_set_remote_key(msk, subflow, &mp_opt);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
mptcp_finish_connect(sk);
- mptcp_propagate_state(parent, sk);
+ mptcp_propagate_state(parent, sk, subflow, &mp_opt);
} else if (subflow->request_join) {
u8 hmac[SHA256_DIGEST_SIZE];
@@ -546,8 +567,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
}
} else if (mptcp_check_fallback(sk)) {
fallback:
- mptcp_rcv_space_init(msk, sk);
- mptcp_propagate_state(parent, sk);
+ mptcp_propagate_state(parent, sk, subflow, NULL);
}
return;
@@ -733,17 +753,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk)
kfree_rcu(ctx, rcu);
}
-void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt)
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+ struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt)
{
- struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-
subflow_set_remote_key(msk, subflow, mp_opt);
subflow->fully_established = 1;
WRITE_ONCE(msk->fully_established, true);
if (subflow->is_mptfo)
- mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
+ __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
}
static struct sock *subflow_syn_recv_sock(const struct sock *sk,
@@ -836,7 +855,6 @@ create_child:
* mpc option
*/
if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) {
- mptcp_subflow_fully_established(ctx, &mp_opt);
mptcp_pm_fully_established(owner, child);
ctx->pm_notified = 1;
}
@@ -1746,10 +1764,9 @@ static void subflow_state_change(struct sock *sk)
msk = mptcp_sk(parent);
if (subflow_simultaneous_connect(sk)) {
mptcp_do_fallback(sk);
- mptcp_rcv_space_init(msk, sk);
pr_fallback(msk);
subflow->conn_finished = 1;
- mptcp_propagate_state(parent, sk);
+ mptcp_propagate_state(parent, sk, subflow, NULL);
}
/* as recvmsg() does not acquire the subflow socket for ssk selection
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index c3d7ecbc777c..016c816d91cb 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -551,8 +551,11 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
find_free_id:
if (range->flags & NF_NAT_RANGE_PROTO_OFFSET)
off = (ntohs(*keyptr) - ntohs(range->base_proto.all));
- else
+ else if ((range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL) ||
+ maniptype != NF_NAT_MANIP_DST)
off = get_random_u16();
+ else
+ off = 0;
attempts = range_size;
if (attempts > NF_NAT_MAX_ATTEMPTS)
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 397351fa4d5f..ab9576098701 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -361,6 +361,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
}
+ __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags);
ret = flow_offload_add(flowtable, flow);
if (ret < 0)
goto err_flow_add;
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index f59a0cd81105..3842c7341a9f 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -144,10 +144,10 @@ struct nft_pipapo_scratch {
/**
* struct nft_pipapo_match - Data used for lookup and matching
- * @field_count Amount of fields in set
+ * @field_count: Amount of fields in set
* @scratch: Preallocated per-CPU maps for partial matching results
* @bsize_max: Maximum lookup table bucket size of all fields, in longs
- * @rcu Matching data is swapped on commits
+ * @rcu: Matching data is swapped on commits
* @f: Fields, with lookup and mapping tables
*/
struct nft_pipapo_match {
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 90e275bb3e5d..a3a8ddca9918 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -57,7 +57,7 @@
/* Jump to label if @reg is zero */
#define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label) \
- asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \
+ asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \
"je %l[" #label "]" : : : : label)
/* Store 256 bits from YMM register into memory. Contrary to bucket load
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 88965e2068ac..ebc5728aab4e 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -48,6 +48,7 @@ struct ovs_len_tbl {
#define OVS_ATTR_NESTED -1
#define OVS_ATTR_VARIABLE -2
+#define OVS_COPY_ACTIONS_MAX_DEPTH 16
static bool actions_may_change_flow(const struct nlattr *actions)
{
@@ -2545,13 +2546,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log);
+ u32 mpls_label_count, bool log,
+ u32 depth);
static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log, bool last)
+ u32 mpls_label_count, bool log, bool last,
+ u32 depth)
{
const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
const struct nlattr *probability, *actions;
@@ -2602,7 +2605,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
return err;
err = __ovs_nla_copy_actions(net, actions, key, sfa,
- eth_type, vlan_tci, mpls_label_count, log);
+ eth_type, vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -2617,7 +2621,8 @@ static int validate_and_copy_dec_ttl(struct net *net,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log)
+ u32 mpls_label_count, bool log,
+ u32 depth)
{
const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1];
int start, action_start, err, rem;
@@ -2660,7 +2665,8 @@ static int validate_and_copy_dec_ttl(struct net *net,
return action_start;
err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type,
- vlan_tci, mpls_label_count, log);
+ vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -2674,7 +2680,8 @@ static int validate_and_copy_clone(struct net *net,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log, bool last)
+ u32 mpls_label_count, bool log, bool last,
+ u32 depth)
{
int start, err;
u32 exec;
@@ -2694,7 +2701,8 @@ static int validate_and_copy_clone(struct net *net,
return err;
err = __ovs_nla_copy_actions(net, attr, key, sfa,
- eth_type, vlan_tci, mpls_label_count, log);
+ eth_type, vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -3063,7 +3071,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
u32 mpls_label_count,
- bool log, bool last)
+ bool log, bool last, u32 depth)
{
const struct nlattr *acts_if_greater, *acts_if_lesser_eq;
struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1];
@@ -3111,7 +3119,8 @@ static int validate_and_copy_check_pkt_len(struct net *net,
return nested_acts_start;
err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa,
- eth_type, vlan_tci, mpls_label_count, log);
+ eth_type, vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -3124,7 +3133,8 @@ static int validate_and_copy_check_pkt_len(struct net *net,
return nested_acts_start;
err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa,
- eth_type, vlan_tci, mpls_label_count, log);
+ eth_type, vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -3152,12 +3162,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log)
+ u32 mpls_label_count, bool log,
+ u32 depth)
{
u8 mac_proto = ovs_key_mac_proto(key);
const struct nlattr *a;
int rem, err;
+ if (depth > OVS_COPY_ACTIONS_MAX_DEPTH)
+ return -EOVERFLOW;
+
nla_for_each_nested(a, attr, rem) {
/* Expected argument lengths, (u32)-1 for variable length. */
static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
@@ -3355,7 +3369,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
err = validate_and_copy_sample(net, a, key, sfa,
eth_type, vlan_tci,
mpls_label_count,
- log, last);
+ log, last, depth);
if (err)
return err;
skip_copy = true;
@@ -3426,7 +3440,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
err = validate_and_copy_clone(net, a, key, sfa,
eth_type, vlan_tci,
mpls_label_count,
- log, last);
+ log, last, depth);
if (err)
return err;
skip_copy = true;
@@ -3440,7 +3454,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
eth_type,
vlan_tci,
mpls_label_count,
- log, last);
+ log, last,
+ depth);
if (err)
return err;
skip_copy = true;
@@ -3450,7 +3465,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
case OVS_ACTION_ATTR_DEC_TTL:
err = validate_and_copy_dec_ttl(net, a, key, sfa,
eth_type, vlan_tci,
- mpls_label_count, log);
+ mpls_label_count, log,
+ depth);
if (err)
return err;
skip_copy = true;
@@ -3495,7 +3511,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
(*sfa)->orig_len = nla_len(attr);
err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
- key->eth.vlan.tci, mpls_label_count, log);
+ key->eth.vlan.tci, mpls_label_count, log,
+ 0);
if (err)
ovs_nla_free_flow_actions(*sfa);
diff --git a/net/rds/recv.c b/net/rds/recv.c
index c71b923764fd..5627f80013f8 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -425,6 +425,7 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
struct sock *sk = rds_rs_to_sk(rs);
int ret = 0;
unsigned long flags;
+ struct rds_incoming *to_drop = NULL;
write_lock_irqsave(&rs->rs_recv_lock, flags);
if (!list_empty(&inc->i_item)) {
@@ -435,11 +436,14 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
-be32_to_cpu(inc->i_hdr.h_len),
inc->i_hdr.h_dport);
list_del_init(&inc->i_item);
- rds_inc_put(inc);
+ to_drop = inc;
}
}
write_unlock_irqrestore(&rs->rs_recv_lock, flags);
+ if (to_drop)
+ rds_inc_put(to_drop);
+
rdsdebug("inc %p rs %p still %d dropped %d\n", inc, rs, ret, drop);
return ret;
}
@@ -758,16 +762,21 @@ void rds_clear_recv_queue(struct rds_sock *rs)
struct sock *sk = rds_rs_to_sk(rs);
struct rds_incoming *inc, *tmp;
unsigned long flags;
+ LIST_HEAD(to_drop);
write_lock_irqsave(&rs->rs_recv_lock, flags);
list_for_each_entry_safe(inc, tmp, &rs->rs_recv_queue, i_item) {
rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong,
-be32_to_cpu(inc->i_hdr.h_len),
inc->i_hdr.h_dport);
+ list_move(&inc->i_item, &to_drop);
+ }
+ write_unlock_irqrestore(&rs->rs_recv_lock, flags);
+
+ list_for_each_entry_safe(inc, tmp, &to_drop, i_item) {
list_del_init(&inc->i_item);
rds_inc_put(inc);
}
- write_unlock_irqrestore(&rs->rs_recv_lock, flags);
}
/*
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 93a96e9d8d90..6f4bb1c8ce7b 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -533,8 +533,6 @@ static int mirred_device_event(struct notifier_block *unused,
* net_device are already rcu protected.
*/
RCU_INIT_POINTER(m->tcfm_dev, NULL);
- } else if (m->tcfm_blockid) {
- m->tcfm_blockid = 0;
}
spin_unlock_bh(&m->tcf_lock);
}
diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c
index 5ea84decec19..5337bc462755 100644
--- a/net/sched/em_canid.c
+++ b/net/sched/em_canid.c
@@ -222,6 +222,7 @@ static void __exit exit_em_canid(void)
tcf_em_unregister(&em_canid_ops);
}
+MODULE_DESCRIPTION("ematch classifier to match CAN IDs embedded in skb CAN frames");
MODULE_LICENSE("GPL");
module_init(init_em_canid);
diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c
index f17b049ea530..c90ad7ea26b4 100644
--- a/net/sched/em_cmp.c
+++ b/net/sched/em_cmp.c
@@ -87,6 +87,7 @@ static void __exit exit_em_cmp(void)
tcf_em_unregister(&em_cmp_ops);
}
+MODULE_DESCRIPTION("ematch classifier for basic data types(8/16/32 bit) against skb data");
MODULE_LICENSE("GPL");
module_init(init_em_cmp);
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 09d8afd04a2a..8996c73c9779 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -1006,6 +1006,7 @@ static void __exit exit_em_meta(void)
tcf_em_unregister(&em_meta_ops);
}
+MODULE_DESCRIPTION("ematch classifier for various internal kernel metadata, skb metadata and sk metadata");
MODULE_LICENSE("GPL");
module_init(init_em_meta);
diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c
index a83b237cbeb0..4f9f21a05d5e 100644
--- a/net/sched/em_nbyte.c
+++ b/net/sched/em_nbyte.c
@@ -68,6 +68,7 @@ static void __exit exit_em_nbyte(void)
tcf_em_unregister(&em_nbyte_ops);
}
+MODULE_DESCRIPTION("ematch classifier for arbitrary skb multi-bytes");
MODULE_LICENSE("GPL");
module_init(init_em_nbyte);
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
index f176afb70559..420c66203b17 100644
--- a/net/sched/em_text.c
+++ b/net/sched/em_text.c
@@ -147,6 +147,7 @@ static void __exit exit_em_text(void)
tcf_em_unregister(&em_text_ops);
}
+MODULE_DESCRIPTION("ematch classifier for embedded text in skbs");
MODULE_LICENSE("GPL");
module_init(init_em_text);
diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c
index 71b070da0437..fdec4db5ec89 100644
--- a/net/sched/em_u32.c
+++ b/net/sched/em_u32.c
@@ -52,6 +52,7 @@ static void __exit exit_em_u32(void)
tcf_em_unregister(&em_u32_ops);
}
+MODULE_DESCRIPTION("ematch skb classifier using 32 bit chunks of data");
MODULE_LICENSE("GPL");
module_init(init_em_u32);
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 7182c5a450fb..5c1652181805 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -38,6 +38,14 @@ void sctp_inq_init(struct sctp_inq *queue)
INIT_WORK(&queue->immediate, NULL);
}
+/* Properly release the chunk which is being worked on. */
+static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk)
+{
+ if (chunk->head_skb)
+ chunk->skb = chunk->head_skb;
+ sctp_chunk_free(chunk);
+}
+
/* Release the memory associated with an SCTP inqueue. */
void sctp_inq_free(struct sctp_inq *queue)
{
@@ -53,7 +61,7 @@ void sctp_inq_free(struct sctp_inq *queue)
* free it as well.
*/
if (queue->in_progress) {
- sctp_chunk_free(queue->in_progress);
+ sctp_inq_chunk_free(queue->in_progress);
queue->in_progress = NULL;
}
}
@@ -130,9 +138,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
goto new_skb;
}
- if (chunk->head_skb)
- chunk->skb = chunk->head_skb;
- sctp_chunk_free(chunk);
+ sctp_inq_chunk_free(chunk);
chunk = queue->in_progress = NULL;
} else {
/* Nothing to do. Next chunk in the packet, please. */
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 66763c74ab76..4b52b3b159c0 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -924,6 +924,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
smc->clcsock->file->private_data = smc->clcsock;
smc->clcsock->wq.fasync_list =
smc->sk.sk_socket->wq.fasync_list;
+ smc->sk.sk_socket->wq.fasync_list = NULL;
/* There might be some wait entries remaining
* in smc sk->sk_wq and they should be woken up
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 31e8a94dfc11..9fbc70200cd0 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -63,6 +63,7 @@ struct tls_decrypt_ctx {
u8 iv[TLS_MAX_IV_SIZE];
u8 aad[TLS_MAX_AAD_SIZE];
u8 tail;
+ bool free_sgout;
struct scatterlist sg[];
};
@@ -187,7 +188,6 @@ static void tls_decrypt_done(void *data, int err)
struct aead_request *aead_req = data;
struct crypto_aead *aead = crypto_aead_reqtfm(aead_req);
struct scatterlist *sgout = aead_req->dst;
- struct scatterlist *sgin = aead_req->src;
struct tls_sw_context_rx *ctx;
struct tls_decrypt_ctx *dctx;
struct tls_context *tls_ctx;
@@ -196,6 +196,17 @@ static void tls_decrypt_done(void *data, int err)
struct sock *sk;
int aead_size;
+ /* If requests get too backlogged crypto API returns -EBUSY and calls
+ * ->complete(-EINPROGRESS) immediately followed by ->complete(0)
+ * to make waiting for backlog to flush with crypto_wait_req() easier.
+ * First wait converts -EBUSY -> -EINPROGRESS, and the second one
+ * -EINPROGRESS -> 0.
+ * We have a single struct crypto_async_request per direction, this
+ * scheme doesn't help us, so just ignore the first ->complete().
+ */
+ if (err == -EINPROGRESS)
+ return;
+
aead_size = sizeof(*aead_req) + crypto_aead_reqsize(aead);
aead_size = ALIGN(aead_size, __alignof__(*dctx));
dctx = (void *)((u8 *)aead_req + aead_size);
@@ -213,7 +224,7 @@ static void tls_decrypt_done(void *data, int err)
}
/* Free the destination pages if skb was not decrypted inplace */
- if (sgout != sgin) {
+ if (dctx->free_sgout) {
/* Skip the first S/G entry as it points to AAD */
for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) {
if (!sg)
@@ -224,10 +235,17 @@ static void tls_decrypt_done(void *data, int err)
kfree(aead_req);
- spin_lock_bh(&ctx->decrypt_compl_lock);
- if (!atomic_dec_return(&ctx->decrypt_pending))
+ if (atomic_dec_and_test(&ctx->decrypt_pending))
complete(&ctx->async_wait.completion);
- spin_unlock_bh(&ctx->decrypt_compl_lock);
+}
+
+static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx)
+{
+ if (!atomic_dec_and_test(&ctx->decrypt_pending))
+ crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ atomic_inc(&ctx->decrypt_pending);
+
+ return ctx->async_wait.err;
}
static int tls_do_decryption(struct sock *sk,
@@ -253,6 +271,7 @@ static int tls_do_decryption(struct sock *sk,
aead_request_set_callback(aead_req,
CRYPTO_TFM_REQ_MAY_BACKLOG,
tls_decrypt_done, aead_req);
+ DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->decrypt_pending) < 1);
atomic_inc(&ctx->decrypt_pending);
} else {
aead_request_set_callback(aead_req,
@@ -261,6 +280,10 @@ static int tls_do_decryption(struct sock *sk,
}
ret = crypto_aead_decrypt(aead_req);
+ if (ret == -EBUSY) {
+ ret = tls_decrypt_async_wait(ctx);
+ ret = ret ?: -EINPROGRESS;
+ }
if (ret == -EINPROGRESS) {
if (darg->async)
return 0;
@@ -439,9 +462,10 @@ static void tls_encrypt_done(void *data, int err)
struct tls_rec *rec = data;
struct scatterlist *sge;
struct sk_msg *msg_en;
- bool ready = false;
struct sock *sk;
- int pending;
+
+ if (err == -EINPROGRESS) /* see the comment in tls_decrypt_done() */
+ return;
msg_en = &rec->msg_encrypted;
@@ -476,23 +500,25 @@ static void tls_encrypt_done(void *data, int err)
/* If received record is at head of tx_list, schedule tx */
first_rec = list_first_entry(&ctx->tx_list,
struct tls_rec, list);
- if (rec == first_rec)
- ready = true;
+ if (rec == first_rec) {
+ /* Schedule the transmission */
+ if (!test_and_set_bit(BIT_TX_SCHEDULED,
+ &ctx->tx_bitmask))
+ schedule_delayed_work(&ctx->tx_work.work, 1);
+ }
}
- spin_lock_bh(&ctx->encrypt_compl_lock);
- pending = atomic_dec_return(&ctx->encrypt_pending);
-
- if (!pending && ctx->async_notify)
+ if (atomic_dec_and_test(&ctx->encrypt_pending))
complete(&ctx->async_wait.completion);
- spin_unlock_bh(&ctx->encrypt_compl_lock);
+}
- if (!ready)
- return;
+static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx)
+{
+ if (!atomic_dec_and_test(&ctx->encrypt_pending))
+ crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ atomic_inc(&ctx->encrypt_pending);
- /* Schedule the transmission */
- if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
- schedule_delayed_work(&ctx->tx_work.work, 1);
+ return ctx->async_wait.err;
}
static int tls_do_encryption(struct sock *sk,
@@ -541,9 +567,14 @@ static int tls_do_encryption(struct sock *sk,
/* Add the record in tx_list */
list_add_tail((struct list_head *)&rec->list, &ctx->tx_list);
+ DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->encrypt_pending) < 1);
atomic_inc(&ctx->encrypt_pending);
rc = crypto_aead_encrypt(aead_req);
+ if (rc == -EBUSY) {
+ rc = tls_encrypt_async_wait(ctx);
+ rc = rc ?: -EINPROGRESS;
+ }
if (!rc || rc != -EINPROGRESS) {
atomic_dec(&ctx->encrypt_pending);
sge->offset -= prot->prepend_size;
@@ -984,7 +1015,6 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
int num_zc = 0;
int orig_size;
int ret = 0;
- int pending;
if (!eor && (msg->msg_flags & MSG_EOR))
return -EINVAL;
@@ -1163,24 +1193,12 @@ trim_sgl:
if (!num_async) {
goto send_end;
} else if (num_zc) {
- /* Wait for pending encryptions to get completed */
- spin_lock_bh(&ctx->encrypt_compl_lock);
- ctx->async_notify = true;
-
- pending = atomic_read(&ctx->encrypt_pending);
- spin_unlock_bh(&ctx->encrypt_compl_lock);
- if (pending)
- crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
- else
- reinit_completion(&ctx->async_wait.completion);
-
- /* There can be no concurrent accesses, since we have no
- * pending encrypt operations
- */
- WRITE_ONCE(ctx->async_notify, false);
+ int err;
- if (ctx->async_wait.err) {
- ret = ctx->async_wait.err;
+ /* Wait for pending encryptions to get completed */
+ err = tls_encrypt_async_wait(ctx);
+ if (err) {
+ ret = err;
copied = 0;
}
}
@@ -1229,7 +1247,6 @@ void tls_sw_splice_eof(struct socket *sock)
ssize_t copied = 0;
bool retrying = false;
int ret = 0;
- int pending;
if (!ctx->open_rec)
return;
@@ -1264,22 +1281,7 @@ retry:
}
/* Wait for pending encryptions to get completed */
- spin_lock_bh(&ctx->encrypt_compl_lock);
- ctx->async_notify = true;
-
- pending = atomic_read(&ctx->encrypt_pending);
- spin_unlock_bh(&ctx->encrypt_compl_lock);
- if (pending)
- crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
- else
- reinit_completion(&ctx->async_wait.completion);
-
- /* There can be no concurrent accesses, since we have no pending
- * encrypt operations
- */
- WRITE_ONCE(ctx->async_notify, false);
-
- if (ctx->async_wait.err)
+ if (tls_encrypt_async_wait(ctx))
goto unlock;
/* Transmit if any encryptions have completed */
@@ -1581,6 +1583,7 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
} else if (out_sg) {
memcpy(sgout, out_sg, n_sgout * sizeof(*sgout));
}
+ dctx->free_sgout = !!pages;
/* Prepare and submit AEAD request */
err = tls_do_decryption(sk, sgin, sgout, dctx->iv,
@@ -2109,16 +2112,10 @@ put_on_rx_list:
recv_end:
if (async) {
- int ret, pending;
+ int ret;
/* Wait for all previously submitted records to be decrypted */
- spin_lock_bh(&ctx->decrypt_compl_lock);
- reinit_completion(&ctx->async_wait.completion);
- pending = atomic_read(&ctx->decrypt_pending);
- spin_unlock_bh(&ctx->decrypt_compl_lock);
- ret = 0;
- if (pending)
- ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ ret = tls_decrypt_async_wait(ctx);
__skb_queue_purge(&ctx->async_hold);
if (ret) {
@@ -2135,7 +2132,6 @@ recv_end:
else
err = process_rx_list(ctx, msg, &control, 0,
async_copy_bytes, is_peek);
- decrypted += max(err, 0);
}
copied += decrypted;
@@ -2435,16 +2431,9 @@ void tls_sw_release_resources_tx(struct sock *sk)
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec, *tmp;
- int pending;
/* Wait for any pending async encryptions to complete */
- spin_lock_bh(&ctx->encrypt_compl_lock);
- ctx->async_notify = true;
- pending = atomic_read(&ctx->encrypt_pending);
- spin_unlock_bh(&ctx->encrypt_compl_lock);
-
- if (pending)
- crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ tls_encrypt_async_wait(ctx);
tls_tx_records(sk, -1);
@@ -2607,7 +2596,7 @@ static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct soc
}
crypto_init_wait(&sw_ctx_tx->async_wait);
- spin_lock_init(&sw_ctx_tx->encrypt_compl_lock);
+ atomic_set(&sw_ctx_tx->encrypt_pending, 1);
INIT_LIST_HEAD(&sw_ctx_tx->tx_list);
INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler);
sw_ctx_tx->tx_work.sk = sk;
@@ -2628,7 +2617,7 @@ static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx)
}
crypto_init_wait(&sw_ctx_rx->async_wait);
- spin_lock_init(&sw_ctx_rx->decrypt_compl_lock);
+ atomic_set(&sw_ctx_rx->decrypt_pending, 1);
init_waitqueue_head(&sw_ctx_rx->wq);
skb_queue_head_init(&sw_ctx_rx->rx_list);
skb_queue_head_init(&sw_ctx_rx->async_hold);
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 3e4b986de94b..51acf795f096 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -340,10 +340,11 @@ static void __unix_gc(struct work_struct *work)
__skb_queue_purge(&hitlist);
#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
- list_for_each_entry_safe(u, next, &gc_candidates, link) {
- struct sk_buff *skb = u->oob_skb;
+ while (!list_empty(&gc_candidates)) {
+ u = list_entry(gc_candidates.next, struct unix_sock, link);
+ if (u->oob_skb) {
+ struct sk_buff *skb = u->oob_skb;
- if (skb) {
u->oob_skb = NULL;
kfree_skb(skb);
}
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index 41533c631431..e6da7e8495c9 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -858,4 +858,5 @@ int xfrm_count_pfkey_enc_supported(void)
}
EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported);
+MODULE_DESCRIPTION("XFRM Algorithm interface");
MODULE_LICENSE("GPL");
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index dc4f9b8d7cb0..a5232dcfea46 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3888,5 +3888,6 @@ static void __exit xfrm_user_exit(void)
module_init(xfrm_user_init);
module_exit(xfrm_user_exit);
+MODULE_DESCRIPTION("XFRM User interface");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM);