aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--drivers/net/dsa/mv88e6xxx/chip.c2
-rw-r--r--drivers/net/ethernet/intel/ice/ice_txrx.c2
-rw-r--r--drivers/net/ethernet/renesas/rswitch.c2
-rw-r--r--drivers/net/ethernet/sfc/tc.c27
-rw-r--r--drivers/net/ipa/ipa_endpoint.c2
-rw-r--r--drivers/net/phy/mxl-gpy.c16
-rw-r--r--include/net/tcp.h1
-rw-r--r--net/core/rtnetlink.c54
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv4/tcp_timer.c16
-rw-r--r--net/mptcp/protocol.c140
-rw-r--r--net/mptcp/protocol.h15
-rw-r--r--net/mptcp/subflow.c28
-rw-r--r--net/sched/cls_flower.c3
14 files changed, 163 insertions, 147 deletions
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 64a2f2f83735..08a46ffd53af 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -7170,7 +7170,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
goto out;
}
if (chip->reset)
- usleep_range(1000, 2000);
+ usleep_range(10000, 20000);
/* Detect if the device is configured in single chip addressing mode,
* otherwise continue with address specific smi init/detection.
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 059bd911c51d..52d0a126eb61 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1152,11 +1152,11 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
unsigned int offset = rx_ring->rx_offset;
struct xdp_buff *xdp = &rx_ring->xdp;
+ u32 cached_ntc = rx_ring->first_desc;
struct ice_tx_ring *xdp_ring = NULL;
struct bpf_prog *xdp_prog = NULL;
u32 ntc = rx_ring->next_to_clean;
u32 cnt = rx_ring->count;
- u32 cached_ntc = ntc;
u32 xdp_xmit = 0;
u32 cached_ntu;
bool failure;
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 29afaddb598d..aace87139cea 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -1485,7 +1485,7 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd
if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - 1) {
netif_stop_subqueue(ndev, 0);
- return ret;
+ return NETDEV_TX_BUSY;
}
if (skb_put_padto(skb, ETH_ZLEN))
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 0327639a628a..c004443c1d58 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -624,13 +624,12 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
if (!found) { /* We don't care. */
netif_dbg(efx, drv, efx->net_dev,
"Ignoring foreign filter that doesn't egdev us\n");
- rc = -EOPNOTSUPP;
- goto release;
+ return -EOPNOTSUPP;
}
rc = efx_mae_match_check_caps(efx, &match.mask, NULL);
if (rc)
- goto release;
+ return rc;
if (efx_tc_match_is_encap(&match.mask)) {
enum efx_encap_type type;
@@ -639,8 +638,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
if (type == EFX_ENCAP_TYPE_NONE) {
NL_SET_ERR_MSG_MOD(extack,
"Egress encap match on unsupported tunnel device");
- rc = -EOPNOTSUPP;
- goto release;
+ return -EOPNOTSUPP;
}
rc = efx_mae_check_encap_type_supported(efx, type);
@@ -648,25 +646,24 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
NL_SET_ERR_MSG_FMT_MOD(extack,
"Firmware reports no support for %s encap match",
efx_tc_encap_type_name(type));
- goto release;
+ return rc;
}
rc = efx_tc_flower_record_encap_match(efx, &match, type,
extack);
if (rc)
- goto release;
+ return rc;
} else {
/* This is not a tunnel decap rule, ignore it */
netif_dbg(efx, drv, efx->net_dev,
"Ignoring foreign filter without encap match\n");
- rc = -EOPNOTSUPP;
- goto release;
+ return -EOPNOTSUPP;
}
rule = kzalloc(sizeof(*rule), GFP_USER);
if (!rule) {
rc = -ENOMEM;
- goto release;
+ goto out_free;
}
INIT_LIST_HEAD(&rule->acts.list);
rule->cookie = tc->cookie;
@@ -678,7 +675,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
"Ignoring already-offloaded rule (cookie %lx)\n",
tc->cookie);
rc = -EEXIST;
- goto release;
+ goto out_free;
}
act = kzalloc(sizeof(*act), GFP_USER);
@@ -843,6 +840,7 @@ release:
efx_tc_match_action_ht_params);
efx_tc_free_action_set_list(efx, &rule->acts, false);
}
+out_free:
kfree(rule);
if (match.encap)
efx_tc_flower_release_encap_match(efx, match.encap);
@@ -899,8 +897,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
return rc;
if (efx_tc_match_is_encap(&match.mask)) {
NL_SET_ERR_MSG_MOD(extack, "Ingress enc_key matches not supported");
- rc = -EOPNOTSUPP;
- goto release;
+ return -EOPNOTSUPP;
}
if (tc->common.chain_index) {
@@ -924,9 +921,9 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
if (old) {
netif_dbg(efx, drv, efx->net_dev,
"Already offloaded rule (cookie %lx)\n", tc->cookie);
- rc = -EEXIST;
NL_SET_ERR_MSG_MOD(extack, "Rule already offloaded");
- goto release;
+ kfree(rule);
+ return -EEXIST;
}
/* Parse actions */
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index 2ee80ed140b7..afa1d56d9095 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -119,7 +119,7 @@ enum ipa_status_field_id {
};
/* Size in bytes of an IPA packet status structure */
-#define IPA_STATUS_SIZE sizeof(__le32[4])
+#define IPA_STATUS_SIZE sizeof(__le32[8])
/* IPA status structure decoder; looks up field values for a structure */
static u32 ipa_status_extract(struct ipa *ipa, const void *data,
diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c
index 6301a9abfb95..ea1073adc5a1 100644
--- a/drivers/net/phy/mxl-gpy.c
+++ b/drivers/net/phy/mxl-gpy.c
@@ -274,13 +274,6 @@ static int gpy_config_init(struct phy_device *phydev)
return ret < 0 ? ret : 0;
}
-static bool gpy_has_broken_mdint(struct phy_device *phydev)
-{
- /* At least these PHYs are known to have broken interrupt handling */
- return phydev->drv->phy_id == PHY_ID_GPY215B ||
- phydev->drv->phy_id == PHY_ID_GPY215C;
-}
-
static int gpy_probe(struct phy_device *phydev)
{
struct device *dev = &phydev->mdio.dev;
@@ -300,8 +293,7 @@ static int gpy_probe(struct phy_device *phydev)
phydev->priv = priv;
mutex_init(&priv->mbox_lock);
- if (gpy_has_broken_mdint(phydev) &&
- !device_property_present(dev, "maxlinear,use-broken-interrupts"))
+ if (!device_property_present(dev, "maxlinear,use-broken-interrupts"))
phydev->dev_flags |= PHY_F_NO_IRQ;
fw_version = phy_read(phydev, PHY_FWV);
@@ -659,11 +651,9 @@ static irqreturn_t gpy_handle_interrupt(struct phy_device *phydev)
* frame. Therefore, polling is the best we can do and won't do any more
* harm.
* It was observed that this bug happens on link state and link speed
- * changes on a GPY215B and GYP215C independent of the firmware version
- * (which doesn't mean that this list is exhaustive).
+ * changes independent of the firmware version.
*/
- if (gpy_has_broken_mdint(phydev) &&
- (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC))) {
+ if (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC)) {
reg = gpy_mbox_read(phydev, REG_GPIO0_OUT);
if (reg < 0) {
phy_error(phydev);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 18a038d16434..5066e4586cf0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -632,6 +632,7 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb);
void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);
void tcp_fin(struct sock *sk);
void tcp_check_space(struct sock *sk);
+void tcp_sack_compress_send_ack(struct sock *sk);
/* tcp_timer.c */
void tcp_init_xmit_timers(struct sock *);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 653901a1bf75..41de3a2f29e1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2385,6 +2385,37 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
if (tb[IFLA_BROADCAST] &&
nla_len(tb[IFLA_BROADCAST]) < dev->addr_len)
return -EINVAL;
+
+ if (tb[IFLA_GSO_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) {
+ NL_SET_ERR_MSG(extack, "too big gso_max_size");
+ return -EINVAL;
+ }
+
+ if (tb[IFLA_GSO_MAX_SEGS] &&
+ (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS ||
+ nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) {
+ NL_SET_ERR_MSG(extack, "too big gso_max_segs");
+ return -EINVAL;
+ }
+
+ if (tb[IFLA_GRO_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) {
+ NL_SET_ERR_MSG(extack, "too big gro_max_size");
+ return -EINVAL;
+ }
+
+ if (tb[IFLA_GSO_IPV4_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) {
+ NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size");
+ return -EINVAL;
+ }
+
+ if (tb[IFLA_GRO_IPV4_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) {
+ NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size");
+ return -EINVAL;
+ }
}
if (tb[IFLA_AF_SPEC]) {
@@ -2858,11 +2889,6 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_GSO_MAX_SIZE]) {
u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]);
- if (max_size > dev->tso_max_size) {
- err = -EINVAL;
- goto errout;
- }
-
if (dev->gso_max_size ^ max_size) {
netif_set_gso_max_size(dev, max_size);
status |= DO_SETLINK_MODIFIED;
@@ -2872,11 +2898,6 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_GSO_MAX_SEGS]) {
u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]);
- if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) {
- err = -EINVAL;
- goto errout;
- }
-
if (dev->gso_max_segs ^ max_segs) {
netif_set_gso_max_segs(dev, max_segs);
status |= DO_SETLINK_MODIFIED;
@@ -2895,11 +2916,6 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_GSO_IPV4_MAX_SIZE]) {
u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]);
- if (max_size > dev->tso_max_size) {
- err = -EINVAL;
- goto errout;
- }
-
if (dev->gso_ipv4_max_size ^ max_size) {
netif_set_gso_ipv4_max_size(dev, max_size);
status |= DO_SETLINK_MODIFIED;
@@ -3285,6 +3301,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
struct net_device *dev;
unsigned int num_tx_queues = 1;
unsigned int num_rx_queues = 1;
+ int err;
if (tb[IFLA_NUM_TX_QUEUES])
num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]);
@@ -3320,13 +3337,18 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
if (!dev)
return ERR_PTR(-ENOMEM);
+ err = validate_linkmsg(dev, tb, extack);
+ if (err < 0) {
+ free_netdev(dev);
+ return ERR_PTR(err);
+ }
+
dev_net_set(dev, net);
dev->rtnl_link_ops = ops;
dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
if (tb[IFLA_MTU]) {
u32 mtu = nla_get_u32(tb[IFLA_MTU]);
- int err;
err = dev_validate_mtu(dev, mtu, extack);
if (err) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 61b6710f337a..bf8b22218dd4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
}
}
-static void tcp_sack_compress_send_ack(struct sock *sk)
+void tcp_sack_compress_send_ack(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b839c2f91292..39eb947fe392 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk)
void tcp_delack_timer_handler(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
- if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
- !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+ if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+ return;
+
+ /* Handling the sack compression case */
+ if (tp->compressed_ack) {
+ tcp_mstamp_refresh(tp);
+ tcp_sack_compress_send_ack(sk);
+ return;
+ }
+
+ if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
return;
if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk)
inet_csk_exit_pingpong_mode(sk);
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
- tcp_mstamp_refresh(tcp_sk(sk));
+ tcp_mstamp_refresh(tp);
tcp_send_ack(sk);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 08dc53f56bc2..67311e7d5b21 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -90,8 +90,8 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
if (err)
return err;
- msk->first = ssock->sk;
- msk->subflow = ssock;
+ WRITE_ONCE(msk->first, ssock->sk);
+ WRITE_ONCE(msk->subflow, ssock);
subflow = mptcp_subflow_ctx(ssock->sk);
list_add(&subflow->node, &msk->conn_list);
sock_hold(ssock->sk);
@@ -603,7 +603,7 @@ static bool mptcp_check_data_fin(struct sock *sk)
WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
WRITE_ONCE(msk->rcv_data_fin, 0);
- sk->sk_shutdown |= RCV_SHUTDOWN;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
switch (sk->sk_state) {
@@ -825,6 +825,13 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
mptcp_data_unlock(sk);
}
+static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk)
+{
+ mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq);
+ WRITE_ONCE(msk->allow_infinite_fallback, false);
+ mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
+}
+
static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
{
struct sock *sk = (struct sock *)msk;
@@ -839,6 +846,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
mptcp_sock_graft(ssk, sk->sk_socket);
mptcp_sockopt_sync_locked(msk, ssk);
+ mptcp_subflow_joined(msk, ssk);
return true;
}
@@ -910,7 +918,7 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
/* hopefully temporary hack: propagate shutdown status
* to msk, when all subflows agree on it
*/
- sk->sk_shutdown |= RCV_SHUTDOWN;
+ WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
sk->sk_data_ready(sk);
@@ -1702,7 +1710,6 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
lock_sock(ssk);
msg->msg_flags |= MSG_DONTWAIT;
- msk->connect_flags = O_NONBLOCK;
msk->fastopening = 1;
ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
msk->fastopening = 0;
@@ -2283,7 +2290,7 @@ static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk)
{
if (msk->subflow) {
iput(SOCK_INODE(msk->subflow));
- msk->subflow = NULL;
+ WRITE_ONCE(msk->subflow, NULL);
}
}
@@ -2420,7 +2427,7 @@ out_release:
sock_put(ssk);
if (ssk == msk->first)
- msk->first = NULL;
+ WRITE_ONCE(msk->first, NULL);
out:
if (ssk == msk->last_snd)
@@ -2527,7 +2534,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
}
inet_sk_state_store(sk, TCP_CLOSE);
- sk->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
@@ -2721,7 +2728,7 @@ static int __mptcp_init_sock(struct sock *sk)
WRITE_ONCE(msk->rmem_released, 0);
msk->timer_ival = TCP_RTO_MIN;
- msk->first = NULL;
+ WRITE_ONCE(msk->first, NULL);
inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
WRITE_ONCE(msk->allow_infinite_fallback, true);
@@ -2959,7 +2966,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
bool do_cancel_work = false;
int subflows_alive = 0;
- sk->sk_shutdown = SHUTDOWN_MASK;
+ WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
mptcp_listen_inuse_dec(sk);
@@ -3039,7 +3046,7 @@ static void mptcp_close(struct sock *sk, long timeout)
sock_put(sk);
}
-void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
+static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
const struct ipv6_pinfo *ssk6 = inet6_sk(ssk);
@@ -3102,7 +3109,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
mptcp_pm_data_reset(msk);
mptcp_ca_reset(sk);
- sk->sk_shutdown = 0;
+ WRITE_ONCE(sk->sk_shutdown, 0);
sk_error_report(sk);
return 0;
}
@@ -3116,9 +3123,10 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
}
#endif
-struct sock *mptcp_sk_clone(const struct sock *sk,
- const struct mptcp_options_received *mp_opt,
- struct request_sock *req)
+struct sock *mptcp_sk_clone_init(const struct sock *sk,
+ const struct mptcp_options_received *mp_opt,
+ struct sock *ssk,
+ struct request_sock *req)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
@@ -3137,7 +3145,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
msk = mptcp_sk(nsk);
msk->local_key = subflow_req->local_key;
msk->token = subflow_req->token;
- msk->subflow = NULL;
+ WRITE_ONCE(msk->subflow, NULL);
msk->in_accept_queue = 1;
WRITE_ONCE(msk->fully_established, false);
if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD)
@@ -3150,10 +3158,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
sock_reset_flag(nsk, SOCK_RCU_FREE);
- /* will be fully established after successful MPC subflow creation */
- inet_sk_state_store(nsk, TCP_SYN_RECV);
-
security_inet_csk_clone(nsk, req);
+
+ /* this can't race with mptcp_close(), as the msk is
+ * not yet exposted to user-space
+ */
+ inet_sk_state_store(nsk, TCP_ESTABLISHED);
+
+ /* 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);
+ sock_hold(ssk);
+
+ /* new mpc subflow takes ownership of the newly
+ * created mptcp socket
+ */
+ mptcp_token_accept(subflow_req, msk);
+
+ /* set msk addresses early to ensure mptcp_pm_get_local_id()
+ * uses the correct data
+ */
+ mptcp_copy_inaddrs(nsk, ssk);
+ mptcp_propagate_sndbuf(nsk, ssk);
+
+ mptcp_rcv_space_init(msk, ssk);
bh_unlock_sock(nsk);
/* note: the newly allocated socket refcount is 2 now */
@@ -3185,7 +3213,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
struct socket *listener;
struct sock *newsk;
- listener = msk->subflow;
+ listener = READ_ONCE(msk->subflow);
if (WARN_ON_ONCE(!listener)) {
*err = -EINVAL;
return NULL;
@@ -3465,14 +3493,16 @@ bool mptcp_finish_join(struct sock *ssk)
return false;
}
- if (!list_empty(&subflow->node))
- goto out;
+ /* active subflow, already present inside the conn_list */
+ if (!list_empty(&subflow->node)) {
+ mptcp_subflow_joined(msk, ssk);
+ return true;
+ }
if (!mptcp_pm_allow_new_subflow(msk))
goto err_prohibited;
- /* active connections are already on conn_list.
- * If we can't acquire msk socket lock here, let the release callback
+ /* If we can't acquire msk socket lock here, let the release callback
* handle it
*/
mptcp_data_lock(parent);
@@ -3495,11 +3525,6 @@ err_prohibited:
return false;
}
- subflow->map_seq = READ_ONCE(msk->ack_seq);
- WRITE_ONCE(msk->allow_infinite_fallback, false);
-
-out:
- mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
return true;
}
@@ -3617,9 +3642,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
* acquired the subflow socket lock, too.
*/
if (msk->fastopening)
- err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
+ err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1);
else
- err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);
+ err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK);
inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect;
/* on successful connect, the msk state will be moved to established by
@@ -3632,12 +3657,10 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
mptcp_copy_inaddrs(sk, ssock->sk);
- /* unblocking connect, mptcp-level inet_stream_connect will error out
- * without changing the socket state, update it here.
+ /* silence EINPROGRESS and let the caller inet_stream_connect
+ * handle the connection in progress
*/
- if (err == -EINPROGRESS)
- sk->sk_socket->state = ssock->state;
- return err;
+ return 0;
}
static struct proto mptcp_prot = {
@@ -3696,18 +3719,6 @@ unlock:
return err;
}
-static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
- int addr_len, int flags)
-{
- int ret;
-
- lock_sock(sock->sk);
- mptcp_sk(sock->sk)->connect_flags = flags;
- ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0);
- release_sock(sock->sk);
- return ret;
-}
-
static int mptcp_listen(struct socket *sock, int backlog)
{
struct mptcp_sock *msk = mptcp_sk(sock->sk);
@@ -3751,10 +3762,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
pr_debug("msk=%p", msk);
- /* buggy applications can call accept on socket states other then LISTEN
+ /* Buggy applications can call accept on socket states other then LISTEN
* but no need to allocate the first subflow just to error out.
*/
- ssock = msk->subflow;
+ ssock = READ_ONCE(msk->subflow);
if (!ssock)
return -EINVAL;
@@ -3800,9 +3811,6 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
{
struct sock *sk = (struct sock *)msk;
- if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
- return EPOLLOUT | EPOLLWRNORM;
-
if (sk_stream_is_writeable(sk))
return EPOLLOUT | EPOLLWRNORM;
@@ -3820,6 +3828,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
struct sock *sk = sock->sk;
struct mptcp_sock *msk;
__poll_t mask = 0;
+ u8 shutdown;
int state;
msk = mptcp_sk(sk);
@@ -3828,23 +3837,30 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
state = inet_sk_state_load(sk);
pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
if (state == TCP_LISTEN) {
- if (WARN_ON_ONCE(!msk->subflow || !msk->subflow->sk))
+ struct socket *ssock = READ_ONCE(msk->subflow);
+
+ if (WARN_ON_ONCE(!ssock || !ssock->sk))
return 0;
- return inet_csk_listen_poll(msk->subflow->sk);
+ return inet_csk_listen_poll(ssock->sk);
}
+ shutdown = READ_ONCE(sk->sk_shutdown);
+ if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
+ mask |= EPOLLHUP;
+ if (shutdown & RCV_SHUTDOWN)
+ mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
+
if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
mask |= mptcp_check_readable(msk);
- mask |= mptcp_check_writeable(msk);
+ if (shutdown & SEND_SHUTDOWN)
+ mask |= EPOLLOUT | EPOLLWRNORM;
+ else
+ mask |= mptcp_check_writeable(msk);
} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
/* cf tcp_poll() note about TFO */
mask |= EPOLLOUT | EPOLLWRNORM;
}
- if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
- mask |= EPOLLHUP;
- if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
/* This barrier is coupled with smp_wmb() in __mptcp_error_report() */
smp_rmb();
@@ -3859,7 +3875,7 @@ static const struct proto_ops mptcp_stream_ops = {
.owner = THIS_MODULE,
.release = inet_release,
.bind = mptcp_bind,
- .connect = mptcp_stream_connect,
+ .connect = inet_stream_connect,
.socketpair = sock_no_socketpair,
.accept = mptcp_stream_accept,
.getname = inet_getname,
@@ -3954,7 +3970,7 @@ static const struct proto_ops mptcp_v6_stream_ops = {
.owner = THIS_MODULE,
.release = inet6_release,
.bind = mptcp_bind,
- .connect = mptcp_stream_connect,
+ .connect = inet_stream_connect,
.socketpair = sock_no_socketpair,
.accept = mptcp_stream_accept,
.getname = inet6_getname,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 2d7b2c80a164..c5255258bfb3 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -297,7 +297,6 @@ struct mptcp_sock {
nodelay:1,
fastopening:1,
in_accept_queue:1;
- int connect_flags;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
@@ -306,7 +305,11 @@ struct mptcp_sock {
struct list_head rtx_queue;
struct mptcp_data_frag *first_pending;
struct list_head join_list;
- struct socket *subflow; /* outgoing connect/listener/!mp_capable */
+ struct socket *subflow; /* outgoing connect/listener/!mp_capable
+ * The mptcp ops can safely dereference, using suitable
+ * ONCE annotation, the subflow outside the socket
+ * lock as such sock is freed after close().
+ */
struct sock *first;
struct mptcp_pm_data pm;
struct {
@@ -613,7 +616,6 @@ int mptcp_is_checksum_enabled(const struct net *net);
int mptcp_allow_join_id0(const struct net *net);
unsigned int mptcp_stale_loss_cnt(const struct net *net);
int mptcp_get_pm_type(const struct net *net);
-void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk);
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
const struct mptcp_options_received *mp_opt);
bool __mptcp_retransmit_pending_data(struct sock *sk);
@@ -683,9 +685,10 @@ void __init mptcp_proto_init(void);
int __init mptcp_proto_v6_init(void);
#endif
-struct sock *mptcp_sk_clone(const struct sock *sk,
- const struct mptcp_options_received *mp_opt,
- struct request_sock *req);
+struct sock *mptcp_sk_clone_init(const struct sock *sk,
+ const struct mptcp_options_received *mp_opt,
+ struct sock *ssk,
+ struct request_sock *req);
void mptcp_get_options(const struct sk_buff *skb,
struct mptcp_options_received *mp_opt);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ba065b66551a..4688daa6b38b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -815,38 +815,12 @@ create_child:
ctx->setsockopt_seq = listener->setsockopt_seq;
if (ctx->mp_capable) {
- ctx->conn = mptcp_sk_clone(listener->conn, &mp_opt, req);
+ ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req);
if (!ctx->conn)
goto fallback;
owner = mptcp_sk(ctx->conn);
-
- /* this can't race with mptcp_close(), as the msk is
- * not yet exposted to user-space
- */
- inet_sk_state_store(ctx->conn, TCP_ESTABLISHED);
-
- /* record the newly created socket as the first msk
- * subflow, but don't link it yet into conn_list
- */
- WRITE_ONCE(owner->first, child);
-
- /* new mpc subflow takes ownership of the newly
- * created mptcp socket
- */
- owner->setsockopt_seq = ctx->setsockopt_seq;
mptcp_pm_new_connection(owner, child, 1);
- mptcp_token_accept(subflow_req, owner);
-
- /* set msk addresses early to ensure mptcp_pm_get_local_id()
- * uses the correct data
- */
- mptcp_copy_inaddrs(ctx->conn, child);
- mptcp_propagate_sndbuf(ctx->conn, child);
-
- mptcp_rcv_space_init(owner, child);
- list_add(&ctx->node, &owner->conn_list);
- sock_hold(child);
/* with OoO packets we can reach here without ingress
* mpc option
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 9dbc43388e57..815c3e416bc5 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1153,6 +1153,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key,
if (option_len > sizeof(struct geneve_opt))
data_len = option_len - sizeof(struct geneve_opt);
+ if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4)
+ return -ERANGE;
+
opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len];
memset(opt, 0xff, option_len);
opt->length = data_len / 4;
generated by cgit (git 2.34.1) at 2025-05-31 19:15:02 +0000