aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/can/af_can.c34
-rw-r--r--net/can/j1939/main.c22
-rw-r--r--net/can/j1939/socket.c13
-rw-r--r--net/can/proc.c19
-rw-r--r--net/ceph/ceph_common.c17
-rw-r--r--net/dsa/Kconfig1
-rw-r--r--net/hsr/hsr_framereg.c9
-rw-r--r--net/hsr/hsr_framereg.h1
-rw-r--r--net/hsr/hsr_main.h1
-rw-r--r--net/ipv4/icmp.c5
-rw-r--r--net/ipv6/icmp.c18
-rw-r--r--net/ipv6/ip6_icmp.c12
-rw-r--r--net/mptcp/options.c23
-rw-r--r--net/mptcp/protocol.c64
-rw-r--r--net/mptcp/subflow.c6
-rw-r--r--net/psample/psample.c4
-rw-r--r--net/qrtr/tun.c12
-rw-r--r--net/sched/cls_flower.c15
-rw-r--r--net/socket.c6
-rw-r--r--net/sunrpc/rpc_pipe.c1
-rw-r--r--net/sunrpc/svcsock.c35
-rw-r--r--net/sunrpc/xprtrdma/backchannel.c4
-rw-r--r--net/sunrpc/xprtrdma/frwr_ops.c12
-rw-r--r--net/sunrpc/xprtrdma/rpc_rdma.c67
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_backchannel.c4
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c6
-rw-r--r--net/sunrpc/xprtrdma/xprt_rdma.h15
-rw-r--r--net/sunrpc/xprtsock.c17
-rw-r--r--net/unix/af_unix.c5
29 files changed, 236 insertions, 212 deletions
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 837bb8af0ec3..cce2af10eb3e 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -304,8 +304,8 @@ static struct can_dev_rcv_lists *can_dev_rcv_lists_find(struct net *net,
struct net_device *dev)
{
if (dev) {
- struct can_ml_priv *ml_priv = dev->ml_priv;
- return &ml_priv->dev_rcv_lists;
+ struct can_ml_priv *can_ml = can_get_ml_priv(dev);
+ return &can_ml->dev_rcv_lists;
} else {
return net->can.rx_alldev_list;
}
@@ -790,25 +790,6 @@ void can_proto_unregister(const struct can_proto *cp)
}
EXPORT_SYMBOL(can_proto_unregister);
-/* af_can notifier to create/remove CAN netdevice specific structs */
-static int can_notifier(struct notifier_block *nb, unsigned long msg,
- void *ptr)
-{
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-
- if (dev->type != ARPHRD_CAN)
- return NOTIFY_DONE;
-
- switch (msg) {
- case NETDEV_REGISTER:
- WARN(!dev->ml_priv,
- "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n");
- break;
- }
-
- return NOTIFY_DONE;
-}
-
static int can_pernet_init(struct net *net)
{
spin_lock_init(&net->can.rcvlists_lock);
@@ -876,11 +857,6 @@ static const struct net_proto_family can_family_ops = {
.owner = THIS_MODULE,
};
-/* notifier block for netdevice event */
-static struct notifier_block can_netdev_notifier __read_mostly = {
- .notifier_call = can_notifier,
-};
-
static struct pernet_operations can_pernet_ops __read_mostly = {
.init = can_pernet_init,
.exit = can_pernet_exit,
@@ -911,17 +887,12 @@ static __init int can_init(void)
err = sock_register(&can_family_ops);
if (err)
goto out_sock;
- err = register_netdevice_notifier(&can_netdev_notifier);
- if (err)
- goto out_notifier;
dev_add_pack(&can_packet);
dev_add_pack(&canfd_packet);
return 0;
-out_notifier:
- sock_unregister(PF_CAN);
out_sock:
unregister_pernet_subsys(&can_pernet_ops);
out_pernet:
@@ -935,7 +906,6 @@ static __exit void can_exit(void)
/* protocol unregister */
dev_remove_pack(&canfd_packet);
dev_remove_pack(&can_packet);
- unregister_netdevice_notifier(&can_netdev_notifier);
sock_unregister(PF_CAN);
unregister_pernet_subsys(&can_pernet_ops);
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index bb914d8b4216..da3a7a7bcff2 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -140,9 +140,9 @@ static struct j1939_priv *j1939_priv_create(struct net_device *ndev)
static inline void j1939_priv_set(struct net_device *ndev,
struct j1939_priv *priv)
{
- struct can_ml_priv *can_ml_priv = ndev->ml_priv;
+ struct can_ml_priv *can_ml = can_get_ml_priv(ndev);
- can_ml_priv->j1939_priv = priv;
+ can_ml->j1939_priv = priv;
}
static void __j1939_priv_release(struct kref *kref)
@@ -211,12 +211,9 @@ static void __j1939_rx_release(struct kref *kref)
/* get pointer to priv without increasing ref counter */
static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev)
{
- struct can_ml_priv *can_ml_priv = ndev->ml_priv;
+ struct can_ml_priv *can_ml = can_get_ml_priv(ndev);
- if (!can_ml_priv)
- return NULL;
-
- return can_ml_priv->j1939_priv;
+ return can_ml->j1939_priv;
}
static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev)
@@ -225,9 +222,6 @@ static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev)
lockdep_assert_held(&j1939_netdev_lock);
- if (ndev->type != ARPHRD_CAN)
- return NULL;
-
priv = j1939_ndev_to_priv(ndev);
if (priv)
j1939_priv_get(priv);
@@ -348,15 +342,16 @@ static int j1939_netdev_notify(struct notifier_block *nb,
unsigned long msg, void *data)
{
struct net_device *ndev = netdev_notifier_info_to_dev(data);
+ struct can_ml_priv *can_ml = can_get_ml_priv(ndev);
struct j1939_priv *priv;
+ if (!can_ml)
+ goto notify_done;
+
priv = j1939_priv_get_by_ndev(ndev);
if (!priv)
goto notify_done;
- if (ndev->type != ARPHRD_CAN)
- goto notify_put;
-
switch (msg) {
case NETDEV_DOWN:
j1939_cancel_active_session(priv, NULL);
@@ -365,7 +360,6 @@ static int j1939_netdev_notify(struct notifier_block *nb,
break;
}
-notify_put:
j1939_priv_put(priv);
notify_done:
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index f23966526a88..56aa66147d5a 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -12,6 +12,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/can/can-ml.h>
#include <linux/can/core.h>
#include <linux/can/skb.h>
#include <linux/errqueue.h>
@@ -453,6 +454,7 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len)
j1939_jsk_del(priv, jsk);
j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa);
} else {
+ struct can_ml_priv *can_ml;
struct net_device *ndev;
ndev = dev_get_by_index(net, addr->can_ifindex);
@@ -461,15 +463,8 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len)
goto out_release_sock;
}
- if (ndev->type != ARPHRD_CAN) {
- dev_put(ndev);
- ret = -ENODEV;
- goto out_release_sock;
- }
-
- if (!ndev->ml_priv) {
- netdev_warn_once(ndev,
- "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n");
+ can_ml = can_get_ml_priv(ndev);
+ if (!can_ml) {
dev_put(ndev);
ret = -ENODEV;
goto out_release_sock;
diff --git a/net/can/proc.c b/net/can/proc.c
index 5ea8695f507e..b15760b5c1cc 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -322,8 +322,11 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v)
/* receive list for registered CAN devices */
for_each_netdev_rcu(net, dev) {
- if (dev->type == ARPHRD_CAN && dev->ml_priv)
- can_rcvlist_proc_show_one(m, idx, dev, dev->ml_priv);
+ struct can_ml_priv *can_ml = can_get_ml_priv(dev);
+
+ if (can_ml)
+ can_rcvlist_proc_show_one(m, idx, dev,
+ &can_ml->dev_rcv_lists);
}
rcu_read_unlock();
@@ -375,8 +378,10 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
/* sff receive list for registered CAN devices */
for_each_netdev_rcu(net, dev) {
- if (dev->type == ARPHRD_CAN && dev->ml_priv) {
- dev_rcv_lists = dev->ml_priv;
+ struct can_ml_priv *can_ml = can_get_ml_priv(dev);
+
+ if (can_ml) {
+ dev_rcv_lists = &can_ml->dev_rcv_lists;
can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_sff,
ARRAY_SIZE(dev_rcv_lists->rx_sff));
}
@@ -406,8 +411,10 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
/* eff receive list for registered CAN devices */
for_each_netdev_rcu(net, dev) {
- if (dev->type == ARPHRD_CAN && dev->ml_priv) {
- dev_rcv_lists = dev->ml_priv;
+ struct can_ml_priv *can_ml = can_get_ml_priv(dev);
+
+ if (can_ml) {
+ dev_rcv_lists = &can_ml->dev_rcv_lists;
can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_eff,
ARRAY_SIZE(dev_rcv_lists->rx_eff));
}
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 271287c5ec12..97d6ea763e32 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -252,7 +252,6 @@ static int parse_fsid(const char *str, struct ceph_fsid *fsid)
* ceph options
*/
enum {
- Opt_osdtimeout,
Opt_osdkeepalivetimeout,
Opt_mount_timeout,
Opt_osd_idle_ttl,
@@ -307,7 +306,8 @@ static const struct constant_table ceph_param_ms_mode[] = {
static const struct fs_parameter_spec ceph_parameters[] = {
fsparam_flag ("abort_on_full", Opt_abort_on_full),
- fsparam_flag_no ("cephx_require_signatures", Opt_cephx_require_signatures),
+ __fsparam (NULL, "cephx_require_signatures", Opt_cephx_require_signatures,
+ fs_param_neg_with_no|fs_param_deprecated, NULL),
fsparam_flag_no ("cephx_sign_messages", Opt_cephx_sign_messages),
fsparam_flag_no ("crc", Opt_crc),
fsparam_string ("crush_location", Opt_crush_location),
@@ -319,8 +319,6 @@ static const struct fs_parameter_spec ceph_parameters[] = {
fsparam_u32 ("osd_idle_ttl", Opt_osd_idle_ttl),
fsparam_u32 ("osd_request_timeout", Opt_osd_request_timeout),
fsparam_u32 ("osdkeepalive", Opt_osdkeepalivetimeout),
- __fsparam (fs_param_is_s32, "osdtimeout", Opt_osdtimeout,
- fs_param_deprecated, NULL),
fsparam_enum ("read_from_replica", Opt_read_from_replica,
ceph_param_read_from_replica),
fsparam_enum ("ms_mode", Opt_ms_mode,
@@ -552,9 +550,6 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
}
break;
- case Opt_osdtimeout:
- warn_plog(&log, "Ignoring osdtimeout");
- break;
case Opt_osdkeepalivetimeout:
/* 0 isn't well defined right now, reject it */
if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000)
@@ -596,9 +591,9 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
break;
case Opt_cephx_require_signatures:
if (!result.negated)
- opt->flags &= ~CEPH_OPT_NOMSGAUTH;
+ warn_plog(&log, "Ignoring cephx_require_signatures");
else
- opt->flags |= CEPH_OPT_NOMSGAUTH;
+ warn_plog(&log, "Ignoring nocephx_require_signatures, use nocephx_sign_messages");
break;
case Opt_cephx_sign_messages:
if (!result.negated)
@@ -686,8 +681,6 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client,
seq_puts(m, "noshare,");
if (opt->flags & CEPH_OPT_NOCRC)
seq_puts(m, "nocrc,");
- if (opt->flags & CEPH_OPT_NOMSGAUTH)
- seq_puts(m, "nocephx_require_signatures,");
if (opt->flags & CEPH_OPT_NOMSGSIGN)
seq_puts(m, "nocephx_sign_messages,");
if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0)
@@ -756,7 +749,7 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private)
client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT;
client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT;
- if (!ceph_test_opt(client, NOMSGAUTH))
+ if (!ceph_test_opt(client, NOMSGSIGN))
client->required_features |= CEPH_FEATURE_MSG_AUTH;
/* msgr */
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index a45572cfb71a..3589224c8da9 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -9,6 +9,7 @@ menuconfig NET_DSA
tristate "Distributed Switch Architecture"
depends on HAVE_NET_DSA
depends on BRIDGE || BRIDGE=n
+ depends on HSR || HSR=n
select GRO_CELLS
select NET_SWITCHDEV
select PHYLINK
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index f9a8cc82ae2e..bb1351c38397 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -164,8 +164,10 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr,
* as initialization. (0 could trigger an spurious ring error warning).
*/
now = jiffies;
- for (i = 0; i < HSR_PT_PORTS; i++)
+ for (i = 0; i < HSR_PT_PORTS; i++) {
new_node->time_in[i] = now;
+ new_node->time_out[i] = now;
+ }
for (i = 0; i < HSR_PT_PORTS; i++)
new_node->seq_out[i] = seq_out;
@@ -413,9 +415,12 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port,
int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node,
u16 sequence_nr)
{
- if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type]))
+ if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type]) &&
+ time_is_after_jiffies(node->time_out[port->type] +
+ msecs_to_jiffies(HSR_ENTRY_FORGET_TIME)))
return 1;
+ node->time_out[port->type] = jiffies;
node->seq_out[port->type] = sequence_nr;
return 0;
}
diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h
index 86b43f539f2c..d9628e7a5f05 100644
--- a/net/hsr/hsr_framereg.h
+++ b/net/hsr/hsr_framereg.h
@@ -75,6 +75,7 @@ struct hsr_node {
enum hsr_port_type addr_B_port;
unsigned long time_in[HSR_PT_PORTS];
bool time_in_stale[HSR_PT_PORTS];
+ unsigned long time_out[HSR_PT_PORTS];
/* if the node is a SAN */
bool san_a;
bool san_b;
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index a169808ee78a..8f264672b70b 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -22,6 +22,7 @@
#define HSR_LIFE_CHECK_INTERVAL 2000 /* ms */
#define HSR_NODE_FORGET_TIME 60000 /* ms */
#define HSR_ANNOUNCE_INTERVAL 100 /* ms */
+#define HSR_ENTRY_FORGET_TIME 400 /* ms */
/* By how much may slave1 and slave2 timestamps of latest received frame from
* each node differ before we notify of communication problem?
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 396b492c804f..616e2dc1c8fa 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -775,13 +775,14 @@ EXPORT_SYMBOL(__icmp_send);
void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
{
struct sk_buff *cloned_skb = NULL;
+ struct ip_options opts = { 0 };
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
__be32 orig_ip;
ct = nf_ct_get(skb_in, &ctinfo);
if (!ct || !(ct->status & IPS_SRC_NAT)) {
- icmp_send(skb_in, type, code, info);
+ __icmp_send(skb_in, type, code, info, &opts);
return;
}
@@ -796,7 +797,7 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
orig_ip = ip_hdr(skb_in)->saddr;
ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip;
- icmp_send(skb_in, type, code, info);
+ __icmp_send(skb_in, type, code, info, &opts);
ip_hdr(skb_in)->saddr = orig_ip;
out:
consume_skb(cloned_skb);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index f3d05866692e..fd1f896115c1 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -331,10 +331,9 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st
}
#if IS_ENABLED(CONFIG_IPV6_MIP6)
-static void mip6_addr_swap(struct sk_buff *skb)
+static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
- struct inet6_skb_parm *opt = IP6CB(skb);
struct ipv6_destopt_hao *hao;
struct in6_addr tmp;
int off;
@@ -351,7 +350,7 @@ static void mip6_addr_swap(struct sk_buff *skb)
}
}
#else
-static inline void mip6_addr_swap(struct sk_buff *skb) {}
+static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {}
#endif
static struct dst_entry *icmpv6_route_lookup(struct net *net,
@@ -446,7 +445,8 @@ static int icmp6_iif(const struct sk_buff *skb)
* Send an ICMP message in response to a packet in error
*/
void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
- const struct in6_addr *force_saddr)
+ const struct in6_addr *force_saddr,
+ const struct inet6_skb_parm *parm)
{
struct inet6_dev *idev = NULL;
struct ipv6hdr *hdr = ipv6_hdr(skb);
@@ -542,7 +542,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type))
goto out_bh_enable;
- mip6_addr_swap(skb);
+ mip6_addr_swap(skb, parm);
sk = icmpv6_xmit_lock(net);
if (!sk)
@@ -559,7 +559,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
/* select a more meaningful saddr from input if */
struct net_device *in_netdev;
- in_netdev = dev_get_by_index(net, IP6CB(skb)->iif);
+ in_netdev = dev_get_by_index(net, parm->iif);
if (in_netdev) {
ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr,
inet6_sk(sk)->srcprefs,
@@ -640,7 +640,7 @@ EXPORT_SYMBOL(icmp6_send);
*/
void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
{
- icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL);
+ icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb));
kfree_skb(skb);
}
@@ -697,10 +697,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
}
if (type == ICMP_TIME_EXCEEDED)
icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
- info, &temp_saddr);
+ info, &temp_saddr, IP6CB(skb2));
else
icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
- info, &temp_saddr);
+ info, &temp_saddr, IP6CB(skb2));
if (rt)
ip6_rt_put(rt);
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 70c8c2f36c98..9e3574880cb0 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -33,23 +33,25 @@ int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn)
}
EXPORT_SYMBOL(inet6_unregister_icmp_sender);
-void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
+void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+ const struct inet6_skb_parm *parm)
{
ip6_icmp_send_t *send;
rcu_read_lock();
send = rcu_dereference(ip6_icmp_send);
if (send)
- send(skb, type, code, info, NULL);
+ send(skb, type, code, info, NULL, parm);
rcu_read_unlock();
}
-EXPORT_SYMBOL(icmpv6_send);
+EXPORT_SYMBOL(__icmpv6_send);
#endif
#if IS_ENABLED(CONFIG_NF_NAT)
#include <net/netfilter/nf_conntrack.h>
void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
{
+ struct inet6_skb_parm parm = { 0 };
struct sk_buff *cloned_skb = NULL;
enum ip_conntrack_info ctinfo;
struct in6_addr orig_ip;
@@ -57,7 +59,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
ct = nf_ct_get(skb_in, &ctinfo);
if (!ct || !(ct->status & IPS_SRC_NAT)) {
- icmpv6_send(skb_in, type, code, info);
+ __icmpv6_send(skb_in, type, code, info, &parm);
return;
}
@@ -72,7 +74,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
orig_ip = ipv6_hdr(skb_in)->saddr;
ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6;
- icmpv6_send(skb_in, type, code, info);
+ __icmpv6_send(skb_in, type, code, info, &parm);
ipv6_hdr(skb_in)->saddr = orig_ip;
out:
consume_skb(cloned_skb);
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index b63574d6b812..444a38681e93 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -411,6 +411,7 @@ static void clear_3rdack_retransmission(struct sock *sk)
}
static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
+ bool snd_data_fin_enable,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
@@ -428,9 +429,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
if (!skb)
return false;
- /* MPC/MPJ needed only on 3rd ack packet */
- if (subflow->fully_established ||
- subflow->snd_isn != TCP_SKB_CB(skb)->seq)
+ /* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */
+ if (subflow->fully_established || snd_data_fin_enable ||
+ subflow->snd_isn != TCP_SKB_CB(skb)->seq ||
+ sk->sk_state != TCP_ESTABLISHED)
return false;
if (subflow->mp_capable) {
@@ -502,20 +504,20 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
}
static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
+ bool snd_data_fin_enable,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
- u64 snd_data_fin_enable, ack_seq;
unsigned int dss_size = 0;
struct mptcp_ext *mpext;
unsigned int ack_size;
bool ret = false;
+ u64 ack_seq;
mpext = skb ? mptcp_get_ext(skb) : NULL;
- snd_data_fin_enable = mptcp_data_fin_enabled(msk);
if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
unsigned int map_size;
@@ -717,12 +719,15 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
unsigned int *size, unsigned int remaining,
struct mptcp_out_options *opts)
{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_sock *msk = mptcp_sk(subflow->conn);
unsigned int opt_size = 0;
+ bool snd_data_fin;
bool ret = false;
opts->suboptions = 0;
- if (unlikely(mptcp_check_fallback(sk)))
+ if (unlikely(__mptcp_check_fallback(msk)))
return false;
/* prevent adding of any MPTCP related options on reset packet
@@ -731,10 +736,10 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST))
return false;
- if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts))
+ snd_data_fin = mptcp_data_fin_enabled(msk);
+ if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts))
ret = true;
- else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining,
- opts))
+ else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts))
ret = true;
/* we reserved enough space for the above options, and exceeding the
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a57f3eab7b6a..c5d5e68940ea 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -11,6 +11,7 @@
#include <linux/netdevice.h>
#include <linux/sched/signal.h>
#include <linux/atomic.h>
+#include <linux/igmp.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
@@ -19,6 +20,7 @@
#include <net/tcp_states.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
#include <net/transp_v6.h>
+#include <net/addrconf.h>
#endif
#include <net/mptcp.h>
#include <net/xfrm.h>
@@ -2264,13 +2266,12 @@ static void mptcp_worker(struct work_struct *work)
__mptcp_check_send_data_fin(sk);
mptcp_check_data_fin(sk);
- /* if the msk data is completely acked, or the socket timedout,
- * there is no point in keeping around an orphaned sk
+ /* There is no point in keeping around an orphaned sk timedout or
+ * closed, but we need the msk around to reply to incoming DATA_FIN,
+ * even if it is orphaned and in FIN_WAIT2 state
*/
if (sock_flag(sk, SOCK_DEAD) &&
- (mptcp_check_close_timeout(sk) ||
- (state != sk->sk_state &&
- ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) {
+ (mptcp_check_close_timeout(sk) || sk->sk_state == TCP_CLOSE)) {
inet_sk_state_store(sk, TCP_CLOSE);
__mptcp_destroy_sock(sk);
goto unlock;
@@ -3375,10 +3376,34 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
return mask;
}
+static int mptcp_release(struct socket *sock)
+{
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = sock->sk;
+ struct mptcp_sock *msk;
+
+ if (!sk)
+ return 0;
+
+ lock_sock(sk);
+
+ msk = mptcp_sk(sk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ ip_mc_drop_socket(ssk);
+ }
+
+ release_sock(sk);
+
+ return inet_release(sock);
+}
+
static const struct proto_ops mptcp_stream_ops = {
.family = PF_INET,
.owner = THIS_MODULE,
- .release = inet_release,
+ .release = mptcp_release,
.bind = mptcp_bind,
.connect = mptcp_stream_connect,
.socketpair = sock_no_socketpair,
@@ -3470,10 +3495,35 @@ void __init mptcp_proto_init(void)
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static int mptcp6_release(struct socket *sock)
+{
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk;
+ struct sock *sk = sock->sk;
+
+ if (!sk)
+ return 0;
+
+ lock_sock(sk);
+
+ msk = mptcp_sk(sk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ ip_mc_drop_socket(ssk);
+ ipv6_sock_mc_close(ssk);
+ ipv6_sock_ac_close(ssk);
+ }
+
+ release_sock(sk);
+ return inet6_release(sock);
+}
+
static const struct proto_ops mptcp_v6_stream_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
- .release = inet6_release,
+ .release = mptcp6_release,
.bind = mptcp_bind,
.connect = mptcp_stream_connect,
.socketpair = sock_no_socketpair,
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 06e233410e0e..e1fbcab257e6 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1096,6 +1096,12 @@ static void subflow_data_ready(struct sock *sk)
msk = mptcp_sk(parent);
if (state & TCPF_LISTEN) {
+ /* MPJ subflow are removed from accept queue before reaching here,
+ * avoid stray wakeups
+ */
+ if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue))
+ return;
+
set_bit(MPTCP_DATA_READY, &msk->flags);
parent->sk_data_ready(parent);
return;
diff --git a/net/psample/psample.c b/net/psample/psample.c
index 33e238c965bd..482c07f2766b 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -309,10 +309,10 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info)
unsigned short tun_proto = ip_tunnel_info_af(tun_info);
const struct ip_tunnel_key *tun_key = &tun_info->key;
int tun_opts_len = tun_info->options_len;
- int sum = 0;
+ int sum = nla_total_size(0); /* PSAMPLE_ATTR_TUNNEL */
if (tun_key->tun_flags & TUNNEL_KEY)
- sum += nla_total_size(sizeof(u64));
+ sum += nla_total_size_64bit(sizeof(u64));
if (tun_info->mode & IP_TUNNEL_INFO_BRIDGE)
sum += nla_total_size(0);
diff --git a/net/qrtr/tun.c b/net/qrtr/tun.c
index b238c40a9984..304b41fea5ab 100644
--- a/net/qrtr/tun.c
+++ b/net/qrtr/tun.c
@@ -31,6 +31,7 @@ static int qrtr_tun_send(struct qrtr_endpoint *ep, struct sk_buff *skb)
static int qrtr_tun_open(struct inode *inode, struct file *filp)
{
struct qrtr_tun *tun;
+ int ret;
tun = kzalloc(sizeof(*tun), GFP_KERNEL);
if (!tun)
@@ -43,7 +44,16 @@ static int qrtr_tun_open(struct inode *inode, struct file *filp)
filp->private_data = tun;
- return qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO);
+ ret = qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO);
+ if (ret)
+ goto out;
+
+ return 0;
+
+out:
+ filp->private_data = NULL;
+ kfree(tun);
+ return ret;
}
static ssize_t qrtr_tun_read_iter(struct kiocb *iocb, struct iov_iter *to)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 2409e522c68f..d097b5c15faa 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1417,6 +1417,21 @@ static int fl_validate_ct_state(u16 state, struct nlattr *tb,
return -EINVAL;
}
+ if (state & TCA_FLOWER_KEY_CT_FLAGS_INVALID &&
+ state & ~(TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+ TCA_FLOWER_KEY_CT_FLAGS_INVALID)) {
+ NL_SET_ERR_MSG_ATTR(extack, tb,
+ "when inv is set, only trk may be set");
+ return -EINVAL;
+ }
+
+ if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW &&
+ state & TCA_FLOWER_KEY_CT_FLAGS_REPLY) {
+ NL_SET_ERR_MSG_ATTR(extack, tb,
+ "new and rpl are mutually exclusive");
+ return -EINVAL;
+ }
+
return 0;
}
diff --git a/net/socket.c b/net/socket.c
index 90a60899aae5..84a8049c2b09 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -334,6 +334,7 @@ static const struct xattr_handler sockfs_xattr_handler = {
};
static int sockfs_security_xattr_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
struct dentry *dentry, struct inode *inode,
const char *suffix, const void *value,
size_t size, int flags)
@@ -537,9 +538,10 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
return used;
}
-static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
+static int sockfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr)
{
- int err = simple_setattr(dentry, iattr);
+ int err = simple_setattr(&init_user_ns, dentry, iattr);
if (!err && (iattr->ia_valid & ATTR_UID)) {
struct socket *sock = SOCKET_I(d_inode(dentry));
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 8241f5a4a01c..09c000d490a1 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -478,6 +478,7 @@ rpc_get_inode(struct super_block *sb, umode_t mode)
inode->i_fop = &simple_dir_operations;
inode->i_op = &simple_dir_inode_operations;
inc_nlink(inode);
+ break;
default:
break;
}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 5a809c64dc7b..2e2f007dfc9f 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1078,9 +1078,8 @@ static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
* In addition, the logic assumes that * .bv_len is never larger
* than PAGE_SIZE.
*/
-static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg,
- struct xdr_buf *xdr, rpc_fraghdr marker,
- unsigned int *sentp)
+static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
+ rpc_fraghdr marker, unsigned int *sentp)
{
const struct kvec *head = xdr->head;
const struct kvec *tail = xdr->tail;
@@ -1088,21 +1087,22 @@ static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg,
.iov_base = &marker,
.iov_len = sizeof(marker),
};
- int flags, ret;
+ struct msghdr msg = {
+ .msg_flags = 0,
+ };
+ int ret;
*sentp = 0;
xdr_alloc_bvec(xdr, GFP_KERNEL);
- msg->msg_flags = MSG_MORE;
- ret = kernel_sendmsg(sock, msg, &rm, 1, rm.iov_len);
+ ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len);
if (ret < 0)
return ret;
*sentp += ret;
if (ret != rm.iov_len)
return -EAGAIN;
- flags = head->iov_len < xdr->len ? MSG_MORE | MSG_SENDPAGE_NOTLAST : 0;
- ret = svc_tcp_send_kvec(sock, head, flags);
+ ret = svc_tcp_send_kvec(sock, head, 0);
if (ret < 0)
return ret;
*sentp += ret;
@@ -1116,15 +1116,11 @@ static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg,
bvec = xdr->bvec + (xdr->page_base >> PAGE_SHIFT);
offset = offset_in_page(xdr->page_base);
remaining = xdr->page_len;
- flags = MSG_MORE | MSG_SENDPAGE_NOTLAST;
while (remaining > 0) {
- if (remaining <= PAGE_SIZE && tail->iov_len == 0)
- flags = 0;
-
len = min(remaining, bvec->bv_len - offset);
ret = kernel_sendpage(sock, bvec->bv_page,
bvec->bv_offset + offset,
- len, flags);
+ len, 0);
if (ret < 0)
return ret;
*sentp += ret;
@@ -1163,26 +1159,28 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
struct xdr_buf *xdr = &rqstp->rq_res;
rpc_fraghdr marker = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT |
(u32)xdr->len);
- struct msghdr msg = {
- .msg_flags = 0,
- };
unsigned int sent;
int err;
svc_tcp_release_rqst(rqstp);
+ atomic_inc(&svsk->sk_sendqlen);
mutex_lock(&xprt->xpt_mutex);
if (svc_xprt_is_dead(xprt))
goto out_notconn;
- err = svc_tcp_sendmsg(svsk->sk_sock, &msg, xdr, marker, &sent);
+ tcp_sock_set_cork(svsk->sk_sk, true);
+ err = svc_tcp_sendmsg(svsk->sk_sock, xdr, marker, &sent);
xdr_free_bvec(xdr);
trace_svcsock_tcp_send(xprt, err < 0 ? err : sent);
if (err < 0 || sent != (xdr->len + sizeof(marker)))
goto out_close;
+ if (atomic_dec_and_test(&svsk->sk_sendqlen))
+ tcp_sock_set_cork(svsk->sk_sk, false);
mutex_unlock(&xprt->xpt_mutex);
return sent;
out_notconn:
+ atomic_dec(&svsk->sk_sendqlen);
mutex_unlock(&xprt->xpt_mutex);
return -ENOTCONN;
out_close:
@@ -1192,6 +1190,7 @@ out_close:
(err < 0) ? err : sent, xdr->len);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
+ atomic_dec(&svsk->sk_sendqlen);
mutex_unlock(&xprt->xpt_mutex);
return -EAGAIN;
}
@@ -1261,7 +1260,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
svsk->sk_datalen = 0;
memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages));
- tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
+ tcp_sock_set_nodelay(sk);
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
switch (sk->sk_state) {
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index 946edf2db646..a249837d6a55 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -2,7 +2,7 @@
/*
* Copyright (c) 2015-2020, Oracle and/or its affiliates.
*
- * Support for backward direction RPCs on RPC/RDMA.
+ * Support for reverse-direction RPCs on RPC/RDMA.
*/
#include <linux/sunrpc/xprt.h>
@@ -208,7 +208,7 @@ create_req:
}
/**
- * rpcrdma_bc_receive_call - Handle a backward direction call
+ * rpcrdma_bc_receive_call - Handle a reverse-direction Call
* @r_xprt: transport receiving the call
* @rep: receive buffer containing the call
*
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index baca49fe83af..766a1048a48a 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -306,20 +306,14 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
if (nsegs > ep->re_max_fr_depth)
nsegs = ep->re_max_fr_depth;
for (i = 0; i < nsegs;) {
- if (seg->mr_page)
- sg_set_page(&mr->mr_sg[i],
- seg->mr_page,
- seg->mr_len,
- offset_in_page(seg->mr_offset));
- else
- sg_set_buf(&mr->mr_sg[i], seg->mr_offset,
- seg->mr_len);
+ sg_set_page(&mr->mr_sg[i], seg->mr_page,
+ seg->mr_len, seg->mr_offset);
++seg;
++i;
if (ep->re_mrtype == IB_MR_TYPE_SG_GAPS)
continue;
- if ((i < nsegs && offset_in_page(seg->mr_offset)) ||
+ if ((i < nsegs && seg->mr_offset) ||
offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
break;
}
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 8f5d0cb68360..292f066d006e 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -204,9 +204,7 @@ rpcrdma_alloc_sparse_pages(struct xdr_buf *buf)
return 0;
}
-/* Split @vec on page boundaries into SGEs. FMR registers pages, not
- * a byte range. Other modes coalesce these SGEs into a single MR
- * when they can.
+/* Convert @vec to a single SGL element.
*
* Returns pointer to next available SGE, and bumps the total number
* of SGEs consumed.
@@ -215,22 +213,11 @@ static struct rpcrdma_mr_seg *
rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg,
unsigned int *n)
{
- u32 remaining, page_offset;
- char *base;
-
- base = vec->iov_base;
- page_offset = offset_in_page(base);
- remaining = vec->iov_len;
- while (remaining) {
- seg->mr_page = NULL;
- seg->mr_offset = base;
- seg->mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining);
- remaining -= seg->mr_len;
- base += seg->mr_len;
- ++seg;
- ++(*n);
- page_offset = 0;
- }
+ seg->mr_page = virt_to_page(vec->iov_base);
+ seg->mr_offset = offset_in_page(vec->iov_base);
+ seg->mr_len = vec->iov_len;
+ ++seg;
+ ++(*n);
return seg;
}
@@ -259,7 +246,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
page_base = offset_in_page(xdrbuf->page_base);
while (len) {
seg->mr_page = *ppages;
- seg->mr_offset = (char *)page_base;
+ seg->mr_offset = page_base;
seg->mr_len = min_t(u32, PAGE_SIZE - page_base, len);
len -= seg->mr_len;
++ppages;
@@ -268,10 +255,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
page_base = 0;
}
- /* When encoding a Read chunk, the tail iovec contains an
- * XDR pad and may be omitted.
- */
- if (type == rpcrdma_readch && r_xprt->rx_ep->re_implicit_roundup)
+ if (type == rpcrdma_readch)
goto out;
/* When encoding a Write chunk, some servers need to see an
@@ -283,7 +267,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
goto out;
if (xdrbuf->tail[0].iov_len)
- seg = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n);
+ rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n);
out:
if (unlikely(n > RPCRDMA_MAX_SEGS))
@@ -644,9 +628,8 @@ out_mapping_err:
return false;
}
-/* The tail iovec may include an XDR pad for the page list,
- * as well as additional content, and may not reside in the
- * same page as the head iovec.
+/* The tail iovec might not reside in the same page as the
+ * head iovec.
*/
static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req,
struct xdr_buf *xdr,
@@ -764,27 +747,19 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt,
struct rpcrdma_req *req,
struct xdr_buf *xdr)
{
+ struct kvec *tail = &xdr->tail[0];
+
if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len))
return false;
- /* If there is a Read chunk, the page list is being handled
+ /* If there is a Read chunk, the page list is handled
* via explicit RDMA, and thus is skipped here.
*/
- /* Do not include the tail if it is only an XDR pad */
- if (xdr->tail[0].iov_len > 3) {
- unsigned int page_base, len;
-
- /* If the content in the page list is an odd length,
- * xdr_write_pages() adds a pad at the beginning of
- * the tail iovec. Force the tail's non-pad content to
- * land at the next XDR position in the Send message.
- */
- page_base = offset_in_page(xdr->tail[0].iov_base);
- len = xdr->tail[0].iov_len;
- page_base += len & 3;
- len -= len & 3;
- if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len))
+ if (tail->iov_len) {
+ if (!rpcrdma_prepare_tail_iov(req, xdr,
+ offset_in_page(tail->iov_base),
+ tail->iov_len))
return false;
kref_get(&req->rl_kref);
}
@@ -1164,14 +1139,10 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
*/
p = xdr_inline_decode(xdr, 3 * sizeof(*p));
if (unlikely(!p))
- goto out_short;
+ return true;
rpcrdma_bc_receive_call(r_xprt, rep);
return true;
-
-out_short:
- pr_warn("RPC/RDMA short backward direction call\n");
- return true;
}
#else /* CONFIG_SUNRPC_BACKCHANNEL */
{
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 63f8be974df2..4a1edbb4028e 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -2,7 +2,7 @@
/*
* Copyright (c) 2015-2018 Oracle. All rights reserved.
*
- * Support for backward direction RPCs on RPC/RDMA (server-side).
+ * Support for reverse-direction RPCs on RPC/RDMA (server-side).
*/
#include <linux/sunrpc/svc_rdma.h>
@@ -59,7 +59,7 @@ out_unlock:
spin_unlock(&xprt->queue_lock);
}
-/* Send a backwards direction RPC call.
+/* Send a reverse-direction RPC Call.
*
* Caller holds the connection's mutex and has already marshaled
* the RPC/RDMA request.
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index afba4e9d5425..c895f80df659 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -475,9 +475,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
if (!svc_rdma_post_recvs(newxprt))
goto errout;
- /* Swap out the handler */
- newxprt->sc_cm_id->event_handler = svc_rdma_cma_handler;
-
/* Construct RDMA-CM private message */
pmsg.cp_magic = rpcrdma_cmp_magic;
pmsg.cp_version = RPCRDMA_CMP_VERSION;
@@ -498,7 +495,10 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
}
conn_param.private_data = &pmsg;
conn_param.private_data_len = sizeof(pmsg);
+ rdma_lock_handler(newxprt->sc_cm_id);
+ newxprt->sc_cm_id->event_handler = svc_rdma_cma_handler;
ret = rdma_accept(newxprt->sc_cm_id, &conn_param);
+ rdma_unlock_handler(newxprt->sc_cm_id);
if (ret) {
trace_svcrdma_accept_err(newxprt, ret);
goto errout;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 94b28657aeeb..fe3be985e239 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -98,9 +98,9 @@ struct rpcrdma_ep {
atomic_t re_completion_ids;
};
-/* Pre-allocate extra Work Requests for handling backward receives
- * and sends. This is a fixed value because the Work Queues are
- * allocated when the forward channel is set up, long before the
+/* Pre-allocate extra Work Requests for handling reverse-direction
+ * Receives and Sends. This is a fixed value because the Work Queues
+ * are allocated when the forward channel is set up, long before the
* backchannel is provisioned. This value is two times
* NFS4_DEF_CB_SLOT_TABLE_SIZE.
*/
@@ -283,10 +283,11 @@ enum {
RPCRDMA_MAX_IOV_SEGS,
};
-struct rpcrdma_mr_seg { /* chunk descriptors */
- u32 mr_len; /* length of chunk or segment */
- struct page *mr_page; /* owning page, if any */
- char *mr_offset; /* kva if no page, else offset */
+/* Arguments for DMA mapping and registration */
+struct rpcrdma_mr_seg {
+ u32 mr_len; /* length of segment */
+ struct page *mr_page; /* underlying struct page */
+ u64 mr_offset; /* IN: page offset, OUT: iova */
};
/* The Send SGE array is provisioned to send a maximum size
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c56a66cdf4ac..e35760f238a4 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -829,7 +829,7 @@ xs_stream_record_marker(struct xdr_buf *xdr)
* EAGAIN: The socket was blocked, please call again later to
* complete the request
* ENOTCONN: Caller needs to invoke connect logic then call again
- * other: Some other error occured, the request was not sent
+ * other: Some other error occurred, the request was not sent
*/
static int xs_local_send_request(struct rpc_rqst *req)
{
@@ -1665,7 +1665,7 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock)
* This ensures that we can continue to establish TCP
* connections even when all local ephemeral ports are already
* a part of some TCP connection. This makes no difference
- * for UDP sockets, but also doens't harm them.
+ * for UDP sockets, but also doesn't harm them.
*
* If we're asking for any reserved port (i.e. port == 0 &&
* transport->xprt.resvport == 1) xs_get_srcport above will
@@ -1875,6 +1875,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
xprt->stat.connect_time += (long)jiffies -
xprt->stat.connect_start;
xprt_set_connected(xprt);
+ break;
case -ENOBUFS:
break;
case -ENOENT:
@@ -2276,10 +2277,8 @@ static void xs_tcp_setup_socket(struct work_struct *work)
case -EHOSTUNREACH:
case -EADDRINUSE:
case -ENOBUFS:
- /*
- * xs_tcp_force_close() wakes tasks with -EIO.
- * We need to wake them first to ensure the
- * correct error code.
+ /* xs_tcp_force_close() wakes tasks with a fixed error code.
+ * We need to wake them first to ensure the correct error code.
*/
xprt_wake_pending_tasks(xprt, status);
xs_tcp_force_close(xprt);
@@ -2380,7 +2379,7 @@ static void xs_error_handle(struct work_struct *work)
}
/**
- * xs_local_print_stats - display AF_LOCAL socket-specifc stats
+ * xs_local_print_stats - display AF_LOCAL socket-specific stats
* @xprt: rpc_xprt struct containing statistics
* @seq: output file
*
@@ -2409,7 +2408,7 @@ static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
}
/**
- * xs_udp_print_stats - display UDP socket-specifc stats
+ * xs_udp_print_stats - display UDP socket-specific stats
* @xprt: rpc_xprt struct containing statistics
* @seq: output file
*
@@ -2433,7 +2432,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
}
/**
- * xs_tcp_print_stats - display TCP socket-specifc stats
+ * xs_tcp_print_stats - display TCP socket-specific stats
* @xprt: rpc_xprt struct containing statistics
* @seq: output file
*
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 41c3303c3357..5a31307ceb76 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -936,7 +936,7 @@ static struct sock *unix_find_other(struct net *net,
if (err)
goto fail;
inode = d_backing_inode(path.dentry);
- err = inode_permission(inode, MAY_WRITE);
+ err = path_permission(&path, MAY_WRITE);
if (err)
goto put_fail;
@@ -996,7 +996,8 @@ static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
*/
err = security_path_mknod(&path, dentry, mode, 0);
if (!err) {
- err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
+ err = vfs_mknod(mnt_user_ns(path.mnt), d_inode(path.dentry),
+ dentry, mode, 0);
if (!err) {
res->mnt = mntget(path.mnt);
res->dentry = dget(dentry);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.