summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/bridge/br_netlink.c51
-rw-r--r--net/bridge/br_netlink_tunnel.c14
-rw-r--r--net/bridge/br_private.h14
-rw-r--r--net/bridge/br_private_tunnel.h3
-rw-r--r--net/bridge/br_vlan.c78
-rw-r--r--net/dsa/dsa.c39
-rw-r--r--net/dsa/dsa2.c8
-rw-r--r--net/dsa/dsa_priv.h5
-rw-r--r--net/dsa/legacy.c4
-rw-r--r--net/dsa/port.c47
-rw-r--r--net/ipv4/syncookies.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c184
-rw-r--r--net/ipv4/tcp.c6
-rw-r--r--net/ipv4/tcp_input.c39
-rw-r--r--net/ipv4/tcp_ipv4.c16
-rw-r--r--net/ipv4/tcp_metrics.c4
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/tcp_output.c31
-rw-r--r--net/ipv6/exthdrs.c5
-rw-r--r--net/ipv6/syncookies.c2
-rw-r--r--net/l2tp/l2tp_core.c21
-rw-r--r--net/l2tp/l2tp_core.h3
-rw-r--r--net/l2tp/l2tp_eth.c99
-rw-r--r--net/l2tp/l2tp_ppp.c238
24 files changed, 539 insertions, 376 deletions
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index fb61b6c79235..e732403669c6 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -506,8 +506,9 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
}
static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
- int cmd, struct bridge_vlan_info *vinfo)
+ int cmd, struct bridge_vlan_info *vinfo, bool *changed)
{
+ bool curr_change;
int err = 0;
switch (cmd) {
@@ -516,22 +517,27 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
/* if the MASTER flag is set this will act on the global
* per-VLAN entry as well
*/
- err = nbp_vlan_add(p, vinfo->vid, vinfo->flags);
- if (err)
- break;
+ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags,
+ &curr_change);
} else {
vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY;
- err = br_vlan_add(br, vinfo->vid, vinfo->flags);
+ err = br_vlan_add(br, vinfo->vid, vinfo->flags,
+ &curr_change);
}
+ if (curr_change)
+ *changed = true;
break;
case RTM_DELLINK:
if (p) {
- nbp_vlan_delete(p, vinfo->vid);
- if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
- br_vlan_delete(p->br, vinfo->vid);
- } else {
- br_vlan_delete(br, vinfo->vid);
+ if (!nbp_vlan_delete(p, vinfo->vid))
+ *changed = true;
+
+ if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) &&
+ !br_vlan_delete(p->br, vinfo->vid))
+ *changed = true;
+ } else if (!br_vlan_delete(br, vinfo->vid)) {
+ *changed = true;
}
break;
}
@@ -542,7 +548,8 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
static int br_process_vlan_info(struct net_bridge *br,
struct net_bridge_port *p, int cmd,
struct bridge_vlan_info *vinfo_curr,
- struct bridge_vlan_info **vinfo_last)
+ struct bridge_vlan_info **vinfo_last,
+ bool *changed)
{
if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK)
return -EINVAL;
@@ -572,7 +579,7 @@ static int br_process_vlan_info(struct net_bridge *br,
sizeof(struct bridge_vlan_info));
for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) {
tmp_vinfo.vid = v;
- err = br_vlan_info(br, p, cmd, &tmp_vinfo);
+ err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed);
if (err)
break;
}
@@ -581,13 +588,13 @@ static int br_process_vlan_info(struct net_bridge *br,
return err;
}
- return br_vlan_info(br, p, cmd, vinfo_curr);
+ return br_vlan_info(br, p, cmd, vinfo_curr, changed);
}
static int br_afspec(struct net_bridge *br,
struct net_bridge_port *p,
struct nlattr *af_spec,
- int cmd)
+ int cmd, bool *changed)
{
struct bridge_vlan_info *vinfo_curr = NULL;
struct bridge_vlan_info *vinfo_last = NULL;
@@ -607,7 +614,8 @@ static int br_afspec(struct net_bridge *br,
return err;
err = br_process_vlan_tunnel_info(br, p, cmd,
&tinfo_curr,
- &tinfo_last);
+ &tinfo_last,
+ changed);
if (err)
return err;
break;
@@ -616,7 +624,7 @@ static int br_afspec(struct net_bridge *br,
return -EINVAL;
vinfo_curr = nla_data(attr);
err = br_process_vlan_info(br, p, cmd, vinfo_curr,
- &vinfo_last);
+ &vinfo_last, changed);
if (err)
return err;
break;
@@ -804,6 +812,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
struct nlattr *afspec;
struct net_bridge_port *p;
struct nlattr *tb[IFLA_BRPORT_MAX + 1];
+ bool changed = false;
int err = 0;
protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO);
@@ -839,14 +848,15 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
}
if (err)
goto out;
+ changed = true;
}
if (afspec) {
err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
- afspec, RTM_SETLINK);
+ afspec, RTM_SETLINK, &changed);
}
- if (err == 0)
+ if (changed)
br_ifinfo_notify(RTM_NEWLINK, p);
out:
return err;
@@ -857,6 +867,7 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
{
struct nlattr *afspec;
struct net_bridge_port *p;
+ bool changed = false;
int err = 0;
afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
@@ -869,8 +880,8 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
return -EINVAL;
err = br_afspec((struct net_bridge *)netdev_priv(dev), p,
- afspec, RTM_DELLINK);
- if (err == 0)
+ afspec, RTM_DELLINK, &changed);
+ if (changed)
/* Send RTM_NEWLINK because userspace
* expects RTM_NEWLINK for vlan dels
*/
diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c
index 3712c7f0e00c..da8cb99fd259 100644
--- a/net/bridge/br_netlink_tunnel.c
+++ b/net/bridge/br_netlink_tunnel.c
@@ -198,7 +198,7 @@ static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX +
};
static int br_vlan_tunnel_info(struct net_bridge_port *p, int cmd,
- u16 vid, u32 tun_id)
+ u16 vid, u32 tun_id, bool *changed)
{
int err = 0;
@@ -208,9 +208,12 @@ static int br_vlan_tunnel_info(struct net_bridge_port *p, int cmd,
switch (cmd) {
case RTM_SETLINK:
err = nbp_vlan_tunnel_info_add(p, vid, tun_id);
+ if (!err)
+ *changed = true;
break;
case RTM_DELLINK:
- nbp_vlan_tunnel_info_delete(p, vid);
+ if (!nbp_vlan_tunnel_info_delete(p, vid))
+ *changed = true;
break;
}
@@ -254,7 +257,8 @@ int br_parse_vlan_tunnel_info(struct nlattr *attr,
int br_process_vlan_tunnel_info(struct net_bridge *br,
struct net_bridge_port *p, int cmd,
struct vtunnel_info *tinfo_curr,
- struct vtunnel_info *tinfo_last)
+ struct vtunnel_info *tinfo_last,
+ bool *changed)
{
int err;
@@ -272,7 +276,7 @@ int br_process_vlan_tunnel_info(struct net_bridge *br,
return -EINVAL;
t = tinfo_last->tunid;
for (v = tinfo_last->vid; v <= tinfo_curr->vid; v++) {
- err = br_vlan_tunnel_info(p, cmd, v, t);
+ err = br_vlan_tunnel_info(p, cmd, v, t, changed);
if (err)
return err;
t++;
@@ -283,7 +287,7 @@ int br_process_vlan_tunnel_info(struct net_bridge *br,
if (tinfo_last->flags)
return -EINVAL;
err = br_vlan_tunnel_info(p, cmd, tinfo_curr->vid,
- tinfo_curr->tunid);
+ tinfo_curr->tunid, changed);
if (err)
return err;
memset(tinfo_last, 0, sizeof(struct vtunnel_info));
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index fa0039f44818..860e4afaf71a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -803,7 +803,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
const struct net_bridge_port *port,
struct net_bridge_vlan_group *vg,
struct sk_buff *skb);
-int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
+int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags,
+ bool *changed);
int br_vlan_delete(struct net_bridge *br, u16 vid);
void br_vlan_flush(struct net_bridge *br);
struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid);
@@ -816,7 +817,8 @@ int br_vlan_set_stats(struct net_bridge *br, unsigned long val);
int br_vlan_init(struct net_bridge *br);
int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val);
int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid);
-int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
+int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
+ bool *changed);
int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
void nbp_vlan_flush(struct net_bridge_port *port);
int nbp_vlan_init(struct net_bridge_port *port);
@@ -903,8 +905,10 @@ static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
return skb;
}
-static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
+static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags,
+ bool *changed)
{
+ *changed = false;
return -EOPNOTSUPP;
}
@@ -926,8 +930,10 @@ static inline int br_vlan_init(struct net_bridge *br)
return 0;
}
-static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
+static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
+ bool *changed)
{
+ *changed = false;
return -EOPNOTSUPP;
}
diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h
index 4a447a378ab3..a259471bfd78 100644
--- a/net/bridge/br_private_tunnel.h
+++ b/net/bridge/br_private_tunnel.h
@@ -26,7 +26,8 @@ int br_process_vlan_tunnel_info(struct net_bridge *br,
struct net_bridge_port *p,
int cmd,
struct vtunnel_info *tinfo_curr,
- struct vtunnel_info *tinfo_last);
+ struct vtunnel_info *tinfo_last,
+ bool *changed);
int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg);
int br_fill_vlan_tunnel_info(struct sk_buff *skb,
struct net_bridge_vlan_group *vg);
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 233a30040c91..51935270c651 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -32,27 +32,34 @@ static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid)
return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params);
}
-static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid)
+static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid)
{
if (vg->pvid == vid)
- return;
+ return false;
smp_wmb();
vg->pvid = vid;
+
+ return true;
}
-static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid)
+static bool __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid)
{
if (vg->pvid != vid)
- return;
+ return false;
smp_wmb();
vg->pvid = 0;
+
+ return true;
}
-static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
+/* return true if anything changed, false otherwise */
+static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
{
struct net_bridge_vlan_group *vg;
+ u16 old_flags = v->flags;
+ bool ret;
if (br_vlan_is_master(v))
vg = br_vlan_group(v->br);
@@ -60,14 +67,16 @@ static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
vg = nbp_vlan_group(v->port);
if (flags & BRIDGE_VLAN_INFO_PVID)
- __vlan_add_pvid(vg, v->vid);
+ ret = __vlan_add_pvid(vg, v->vid);
else
- __vlan_delete_pvid(vg, v->vid);
+ ret = __vlan_delete_pvid(vg, v->vid);
if (flags & BRIDGE_VLAN_INFO_UNTAGGED)
v->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
else
v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED;
+
+ return ret || !!(old_flags ^ v->flags);
}
static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br,
@@ -151,8 +160,10 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid
vg = br_vlan_group(br);
masterv = br_vlan_find(vg, vid);
if (!masterv) {
+ bool changed;
+
/* missing global ctx, create it now */
- if (br_vlan_add(br, vid, 0))
+ if (br_vlan_add(br, vid, 0, &changed))
return NULL;
masterv = br_vlan_find(vg, vid);
if (WARN_ON(!masterv))
@@ -232,8 +243,11 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
/* need to work on the master vlan too */
if (flags & BRIDGE_VLAN_INFO_MASTER) {
- err = br_vlan_add(br, v->vid, flags |
- BRIDGE_VLAN_INFO_BRENTRY);
+ bool changed;
+
+ err = br_vlan_add(br, v->vid,
+ flags | BRIDGE_VLAN_INFO_BRENTRY,
+ &changed);
if (err)
goto out_filt;
}
@@ -550,8 +564,9 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
+ * changed must be true only if the vlan was created or updated
*/
-int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
+int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed)
{
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *vlan;
@@ -559,6 +574,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
ASSERT_RTNL();
+ *changed = false;
vg = br_vlan_group(br);
vlan = br_vlan_find(vg, vid);
if (vlan) {
@@ -576,8 +592,11 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
refcount_inc(&vlan->refcnt);
vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY;
vg->num_vlans++;
+ *changed = true;
}
- __vlan_add_flags(vlan, flags);
+ if (__vlan_add_flags(vlan, flags))
+ *changed = true;
+
return 0;
}
@@ -600,6 +619,8 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
if (ret) {
free_percpu(vlan->stats);
kfree(vlan);
+ } else {
+ *changed = true;
}
return ret;
@@ -824,9 +845,10 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
const struct net_bridge_vlan *pvent;
struct net_bridge_vlan_group *vg;
struct net_bridge_port *p;
+ unsigned long *changed;
+ bool vlchange;
u16 old_pvid;
int err = 0;
- unsigned long *changed;
if (!pvid) {
br_vlan_disable_default_pvid(br);
@@ -850,7 +872,8 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
err = br_vlan_add(br, pvid,
BRIDGE_VLAN_INFO_PVID |
BRIDGE_VLAN_INFO_UNTAGGED |
- BRIDGE_VLAN_INFO_BRENTRY);
+ BRIDGE_VLAN_INFO_BRENTRY,
+ &vlchange);
if (err)
goto out;
br_vlan_delete(br, old_pvid);
@@ -869,7 +892,8 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
err = nbp_vlan_add(p, pvid,
BRIDGE_VLAN_INFO_PVID |
- BRIDGE_VLAN_INFO_UNTAGGED);
+ BRIDGE_VLAN_INFO_UNTAGGED,
+ &vlchange);
if (err)
goto err_port;
nbp_vlan_delete(p, old_pvid);
@@ -890,7 +914,8 @@ err_port:
if (old_pvid)
nbp_vlan_add(p, old_pvid,
BRIDGE_VLAN_INFO_PVID |
- BRIDGE_VLAN_INFO_UNTAGGED);
+ BRIDGE_VLAN_INFO_UNTAGGED,
+ &vlchange);
nbp_vlan_delete(p, pvid);
}
@@ -899,7 +924,8 @@ err_port:
br_vlan_add(br, old_pvid,
BRIDGE_VLAN_INFO_PVID |
BRIDGE_VLAN_INFO_UNTAGGED |
- BRIDGE_VLAN_INFO_BRENTRY);
+ BRIDGE_VLAN_INFO_BRENTRY,
+ &vlchange);
br_vlan_delete(br, pvid);
}
goto out;
@@ -931,6 +957,7 @@ int br_vlan_init(struct net_bridge *br)
{
struct net_bridge_vlan_group *vg;
int ret = -ENOMEM;
+ bool changed;
vg = kzalloc(sizeof(*vg), GFP_KERNEL);
if (!vg)
@@ -947,7 +974,7 @@ int br_vlan_init(struct net_bridge *br)
rcu_assign_pointer(br->vlgrp, vg);
ret = br_vlan_add(br, 1,
BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED |
- BRIDGE_VLAN_INFO_BRENTRY);
+ BRIDGE_VLAN_INFO_BRENTRY, &changed);
if (ret)
goto err_vlan_add;
@@ -992,9 +1019,12 @@ int nbp_vlan_init(struct net_bridge_port *p)
INIT_LIST_HEAD(&vg->vlan_list);
rcu_assign_pointer(p->vlgrp, vg);
if (p->br->default_pvid) {
+ bool changed;
+
ret = nbp_vlan_add(p, p->br->default_pvid,
BRIDGE_VLAN_INFO_PVID |
- BRIDGE_VLAN_INFO_UNTAGGED);
+ BRIDGE_VLAN_INFO_UNTAGGED,
+ &changed);
if (ret)
goto err_vlan_add;
}
@@ -1016,8 +1046,10 @@ err_vlan_enabled:
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
+ * changed must be true only if the vlan was created or updated
*/
-int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
+int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags,
+ bool *changed)
{
struct switchdev_obj_port_vlan v = {
.obj.orig_dev = port->dev,
@@ -1031,13 +1063,15 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
ASSERT_RTNL();
+ *changed = false;
vlan = br_vlan_find(nbp_vlan_group(port), vid);
if (vlan) {
/* Pass the flags to the hardware bridge */
ret = switchdev_port_obj_add(port->dev, &v.obj);
if (ret && ret != -EOPNOTSUPP)
return ret;
- __vlan_add_flags(vlan, flags);
+ *changed = __vlan_add_flags(vlan, flags);
+
return 0;
}
@@ -1050,6 +1084,8 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
ret = __vlan_add(vlan, flags);
if (ret)
kfree(vlan);
+ else
+ *changed = true;
return ret;
}
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index fe0081730305..b8f2d9f7c3ed 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -68,37 +68,6 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
[DSA_TAG_PROTO_NONE] = &none_ops,
};
-int dsa_cpu_dsa_setup(struct dsa_port *port)
-{
- struct device_node *port_dn = port->dn;
- struct dsa_switch *ds = port->ds;
- struct phy_device *phydev;
- int ret, mode;
-
- if (of_phy_is_fixed_link(port_dn)) {
- ret = of_phy_register_fixed_link(port_dn);
- if (ret) {
- dev_err(ds->dev, "failed to register fixed PHY\n");
- return ret;
- }
- phydev = of_phy_find_device(port_dn);
-
- mode = of_get_phy_mode(port_dn);
- if (mode < 0)
- mode = PHY_INTERFACE_MODE_NA;
- phydev->interface = mode;
-
- genphy_config_init(phydev);
- genphy_read_status(phydev);
- if (ds->ops->adjust_link)
- ds->ops->adjust_link(ds, port->index, phydev);
-
- put_device(&phydev->mdio.dev);
- }
-
- return 0;
-}
-
const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
{
const struct dsa_device_ops *ops;
@@ -113,14 +82,6 @@ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
return ops;
}
-void dsa_cpu_dsa_destroy(struct dsa_port *port)
-{
- struct device_node *port_dn = port->dn;
-
- if (of_phy_is_fixed_link(port_dn))
- of_phy_deregister_fixed_link(port_dn);
-}
-
static int dev_is_class(struct device *dev, void *class)
{
if (dev->class != NULL && !strcmp(dev->class->name, class))
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index ec58654a71cd..de91c48b6806 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -219,7 +219,7 @@ static int dsa_dsa_port_apply(struct dsa_port *port)
struct dsa_switch *ds = port->ds;
int err;
- err = dsa_cpu_dsa_setup(port);
+ err = dsa_port_fixed_link_register_of(port);
if (err) {
dev_warn(ds->dev, "Failed to setup dsa port %d: %d\n",
port->index, err);
@@ -235,7 +235,7 @@ static int dsa_dsa_port_apply(struct dsa_port *port)
static void dsa_dsa_port_unapply(struct dsa_port *port)
{
devlink_port_unregister(&port->devlink_port);
- dsa_cpu_dsa_destroy(port);
+ dsa_port_fixed_link_unregister_of(port);
}
static int dsa_cpu_port_apply(struct dsa_port *port)
@@ -243,7 +243,7 @@ static int dsa_cpu_port_apply(struct dsa_port *port)
struct dsa_switch *ds = port->ds;
int err;
- err = dsa_cpu_dsa_setup(port);
+ err = dsa_port_fixed_link_register_of(port);
if (err) {
dev_warn(ds->dev, "Failed to setup cpu port %d: %d\n",
port->index, err);
@@ -259,7 +259,7 @@ static int dsa_cpu_port_apply(struct dsa_port *port)
static void dsa_cpu_port_unapply(struct dsa_port *port)
{
devlink_port_unregister(&port->devlink_port);
- dsa_cpu_dsa_destroy(port);
+ dsa_port_fixed_link_unregister_of(port);
}
static int dsa_user_port_apply(struct dsa_port *port)
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 1e9914062d0b..1e65afd6989e 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -93,8 +93,6 @@ struct dsa_slave_priv {
};
/* dsa.c */
-int dsa_cpu_dsa_setup(struct dsa_port *port);
-void dsa_cpu_dsa_destroy(struct dsa_port *dport);
const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol);
bool dsa_schedule_work(struct work_struct *work);
@@ -159,6 +157,9 @@ int dsa_port_vlan_add(struct dsa_port *dp,
struct switchdev_trans *trans);
int dsa_port_vlan_del(struct dsa_port *dp,
const struct switchdev_obj_port_vlan *vlan);
+int dsa_port_fixed_link_register_of(struct dsa_port *dp);
+void dsa_port_fixed_link_unregister_of(struct dsa_port *dp);
+
/* slave.c */
extern const struct dsa_device_ops notag_netdev_ops;
void dsa_slave_mii_bus_init(struct dsa_switch *ds);
diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c
index 93e1b116ef83..ed7aae342fca 100644
--- a/net/dsa/legacy.c
+++ b/net/dsa/legacy.c
@@ -86,7 +86,7 @@ static int dsa_cpu_dsa_setups(struct dsa_switch *ds)
if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
continue;
- ret = dsa_cpu_dsa_setup(&ds->ports[port]);
+ ret = dsa_port_fixed_link_register_of(&ds->ports[port]);
if (ret)
return ret;
}
@@ -274,7 +274,7 @@ static void dsa_switch_destroy(struct dsa_switch *ds)
for (port = 0; port < ds->num_ports; port++) {
if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
continue;
- dsa_cpu_dsa_destroy(&ds->ports[port]);
+ dsa_port_fixed_link_unregister_of(&ds->ports[port]);
}
if (ds->slave_mii_bus && ds->ops->phy_read)
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 72c8dbd3d3f2..bb30b1a7de3a 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -12,6 +12,8 @@
#include <linux/if_bridge.h>
#include <linux/notifier.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
#include "dsa_priv.h"
@@ -264,3 +266,48 @@ int dsa_port_vlan_del(struct dsa_port *dp,
return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info);
}
+
+int dsa_port_fixed_link_register_of(struct dsa_port *dp)
+{
+ struct device_node *dn = dp->dn;
+ struct dsa_switch *ds = dp->ds;
+ struct phy_device *phydev;
+ int port = dp->index;
+ int mode;
+ int err;
+
+ if (of_phy_is_fixed_link(dn)) {
+ err = of_phy_register_fixed_link(dn);
+ if (err) {
+ dev_err(ds->dev,
+ "failed to register the fixed PHY of port %d\n",
+ port);
+ return err;
+ }
+
+ phydev = of_phy_find_device(dn);
+
+ mode = of_get_phy_mode(dn);
+ if (mode < 0)
+ mode = PHY_INTERFACE_MODE_NA;
+ phydev->interface = mode;
+
+ genphy_config_init(phydev);
+ genphy_read_status(phydev);
+
+ if (ds->ops->adjust_link)
+ ds->ops->adjust_link(ds, port, phydev);
+
+ put_device(&phydev->mdio.dev);
+ }
+
+ return 0;
+}
+
+void dsa_port_fixed_link_unregister_of(struct dsa_port *dp)
+{
+ struct device_node *dn = dp->dn;
+
+ if (of_phy_is_fixed_link(dn))
+ of_phy_deregister_fixed_link(dn);
+}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 77cf32a80952..fda37f2862c9 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -385,7 +385,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
/* Try to redo what tcp_v4_send_synack did. */
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
- tcp_select_initial_window(tcp_full_space(sk), req->mss,
+ tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index f1bcb9b7e082..4602af6d5358 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -438,13 +438,6 @@ static struct ctl_table ipv4_table[] = {
.extra1 = &one,
},
{
- .procname = "tcp_min_rtt_wlen",
- .data = &sysctl_tcp_min_rtt_wlen,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_low_latency",
.data = &sysctl_tcp_low_latency,
.maxlen = sizeof(int),
@@ -452,53 +445,11 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "tcp_no_metrics_save",
- .data = &sysctl_tcp_nometrics_save,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "tcp_moderate_rcvbuf",
- .data = &sysctl_tcp_moderate_rcvbuf,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "tcp_tso_win_divisor",
- .data = &sysctl_tcp_tso_win_divisor,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
.procname = "tcp_congestion_control",
.mode = 0644,
.maxlen = TCP_CA_NAME_MAX,
.proc_handler = proc_tcp_congestion_control,
},
- {
- .procname = "tcp_workaround_signed_windows",
- .data = &sysctl_tcp_workaround_signed_windows,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_limit_output_bytes",
- .data = &sysctl_tcp_limit_output_bytes,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_challenge_ack_limit",
- .data = &sysctl_tcp_challenge_ack_limit,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
#ifdef CONFIG_NETLABEL
{
.procname = "cipso_cache_enable",
@@ -542,49 +493,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_allowed_congestion_control,
},
{
- .procname = "tcp_min_tso_segs",
- .data = &sysctl_tcp_min_tso_segs,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
- .extra2 = &gso_max_segs,
- },
- {
- .procname = "tcp_pacing_ss_ratio",
- .data = &sysctl_tcp_pacing_ss_ratio,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &thousand,
- },
- {
- .procname = "tcp_pacing_ca_ratio",
- .data = &sysctl_tcp_pacing_ca_ratio,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &thousand,
- },
- {
- .procname = "tcp_autocorking",
- .data = &sysctl_tcp_autocorking,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &one,
- },
- {
- .procname = "tcp_invalid_ratelimit",
- .data = &sysctl_tcp_invalid_ratelimit,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_ms_jiffies,
- },
- {
.procname = "tcp_available_ulp",
.maxlen = TCP_ULP_BUF_MAX,
.mode = 0444,
@@ -1145,6 +1053,98 @@ static struct ctl_table ipv4_net_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "tcp_no_metrics_save",
+ .data = &init_net.ipv4.sysctl_tcp_nometrics_save,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_moderate_rcvbuf",
+ .data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_tso_win_divisor",
+ .data = &init_net.ipv4.sysctl_tcp_tso_win_divisor,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_workaround_signed_windows",
+ .data = &init_net.ipv4.sysctl_tcp_workaround_signed_windows,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_limit_output_bytes",
+ .data = &init_net.ipv4.sysctl_tcp_limit_output_bytes,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_challenge_ack_limit",
+ .data = &init_net.ipv4.sysctl_tcp_challenge_ack_limit,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_min_tso_segs",
+ .data = &init_net.ipv4.sysctl_tcp_min_tso_segs,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ .extra2 = &gso_max_segs,
+ },
+ {
+ .procname = "tcp_min_rtt_wlen",
+ .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_autocorking",
+ .data = &init_net.ipv4.sysctl_tcp_autocorking,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
+ .procname = "tcp_invalid_ratelimit",
+ .data = &init_net.ipv4.sysctl_tcp_invalid_ratelimit,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_ms_jiffies,
+ },
+ {
+ .procname = "tcp_pacing_ss_ratio",
+ .data = &init_net.ipv4.sysctl_tcp_pacing_ss_ratio,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &thousand,
+ },
+ {
+ .procname = "tcp_pacing_ca_ratio",
+ .data = &init_net.ipv4.sysctl_tcp_pacing_ca_ratio,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &thousand,
+ },
{ }
};
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c7c983f0f817..a7a0f316eb86 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -285,10 +285,6 @@
#include <trace/events/tcp.h>
-int sysctl_tcp_min_tso_segs __read_mostly = 2;
-
-int sysctl_tcp_autocorking __read_mostly = 1;
-
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
@@ -699,7 +695,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
int size_goal)
{
return skb->len < size_goal &&
- sysctl_tcp_autocorking &&
+ sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
skb != tcp_write_queue_head(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 90d76f1c8f96..b62a7d1707ae 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -76,16 +76,9 @@
#include <asm/unaligned.h>
#include <linux/errqueue.h>
#include <trace/events/tcp.h>
-#include <linux/unaligned/access_ok.h>
#include <linux/static_key.h>
-/* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 1000;
-
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
-int sysctl_tcp_min_rtt_wlen __read_mostly = 300;
-int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
-int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
@@ -411,7 +404,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
/* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
* Allow enough cushion so that sender is not limited by our window
*/
- if (sysctl_tcp_moderate_rcvbuf)
+ if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)
rcvmem <<= 2;
if (sk->sk_rcvbuf < rcvmem)
@@ -602,7 +595,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (sysctl_tcp_moderate_rcvbuf &&
+ if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvwin, rcvmem, rcvbuf;
@@ -773,15 +766,6 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
tp->srtt_us = max(1U, srtt);
}
-/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
- * Note: TCP stack does not yet implement pacing.
- * FQ packet scheduler can be used to implement cheap but effective
- * TCP pacing, to smooth the burst on large writes when packets
- * in flight is significantly lower than cwnd (or rwin)
- */
-int sysctl_tcp_pacing_ss_ratio __read_mostly = 200;
-int sysctl_tcp_pacing_ca_ratio __read_mostly = 120;
-
static void tcp_update_pacing_rate(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
@@ -799,9 +783,9 @@ static void tcp_update_pacing_rate(struct sock *sk)
* end of slow start and should slow down.
*/
if (tp->snd_cwnd < tp->snd_ssthresh / 2)
- rate *= sysctl_tcp_pacing_ss_ratio;
+ rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
else
- rate *= sysctl_tcp_pacing_ca_ratio;
+ rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;
rate *= max(tp->snd_cwnd, tp->packets_out);
@@ -2919,8 +2903,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
{
+ u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
struct tcp_sock *tp = tcp_sk(sk);
- u32 wlen = sysctl_tcp_min_rtt_wlen * HZ;
minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32,
rtt_us ? : jiffies_to_usecs(1));
@@ -3408,7 +3392,7 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
if (*last_oow_ack_time) {
s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
- if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+ if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
NET_INC_STATS(net, mib_idx);
return true; /* rate-limited: don't send yet! */
}
@@ -3444,10 +3428,11 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
static u32 challenge_timestamp;
static unsigned int challenge_count;
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
u32 count, now;
/* First check our per-socket dupack rate limit. */
- if (__tcp_oow_rate_limited(sock_net(sk),
+ if (__tcp_oow_rate_limited(net,
LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
&tp->last_oow_ack_time))
return;
@@ -3455,16 +3440,16 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
/* Then check host-wide RFC 5961 rate limit. */
now = jiffies / HZ;
if (now != challenge_timestamp) {
- u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+ u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+ u32 half = (ack_limit + 1) >> 1;
challenge_timestamp = now;
- WRITE_ONCE(challenge_count, half +
- prandom_u32_max(sysctl_tcp_challenge_ack_limit));
+ WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
}
count = READ_ONCE(challenge_count);
if (count > 0) {
WRITE_ONCE(challenge_count, count - 1);
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
+ NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK);
tcp_send_ack(sk);
}
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 49757c758211..7c1dae6493c3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2493,6 +2493,22 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_app_win = 31;
net->ipv4.sysctl_tcp_adv_win_scale = 1;
net->ipv4.sysctl_tcp_frto = 2;
+ net->ipv4.sysctl_tcp_moderate_rcvbuf = 1;
+ /* This limits the percentage of the congestion window which we
+ * will allow a single TSO frame to consume. Building TSO frames
+ * which are too large can cause TCP streams to be bursty.
+ */
+ net->ipv4.sysctl_tcp_tso_win_divisor = 3;
+ /* Default TSQ limit of four TSO segments */
+ net->ipv4.sysctl_tcp_limit_output_bytes = 262144;
+ /* rfc5961 challenge ack rate limiting */
+ net->ipv4.sysctl_tcp_challenge_ack_limit = 1000;
+ net->ipv4.sysctl_tcp_min_tso_segs = 2;
+ net->ipv4.sysctl_tcp_min_rtt_wlen = 300;
+ net->ipv4.sysctl_tcp_autocorking = 1;
+ net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2;
+ net->ipv4.sysctl_tcp_pacing_ss_ratio = 200;
+ net->ipv4.sysctl_tcp_pacing_ca_ratio = 120;
net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 0ab78abc811b..0507b56b6d4b 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -20,8 +20,6 @@
#include <net/tcp.h>
#include <net/genetlink.h>
-int sysctl_tcp_nometrics_save __read_mostly;
-
static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *saddr,
const struct inetpeer_addr *daddr,
struct net *net, unsigned int hash);
@@ -330,7 +328,7 @@ void tcp_update_metrics(struct sock *sk)
int m;
sk_dst_confirm(sk);
- if (sysctl_tcp_nometrics_save || !dst)
+ if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
return;
rcu_read_lock();
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 3270ab8416ce..3c65c1a3f944 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -369,7 +369,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
full_space = rcv_wnd * mss;
/* tcp_full_space because it is guaranteed to be the first packet */
- tcp_select_initial_window(full_space,
+ tcp_select_initial_window(sk_listener, full_space,
mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
&req->rsk_rcv_wnd,
&req->rsk_window_clamp,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 55a0aa4b96df..aab6e7145013 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -45,20 +45,6 @@
#include <trace/events/tcp.h>
-/* People can turn this on to work with those rare, broken TCPs that
- * interpret the window field as a signed quantity.
- */
-int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
-
-/* Default TSQ limit of four TSO segments */
-int sysctl_tcp_limit_output_bytes __read_mostly = 262144;
-
-/* This limits the percentage of the congestion window which we
- * will allow a single TSO frame to consume. Building TSO frames
- * which are too large can cause TCP streams to be bursty.
- */
-int sysctl_tcp_tso_win_divisor __read_mostly = 3;
-
static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
int push_one, gfp_t gfp);
@@ -202,7 +188,7 @@ u32 tcp_default_init_rwnd(u32 mss)
* be a multiple of mss if possible. We assume here that mss >= 1.
* This MUST be enforced by all callers.
*/
-void tcp_select_initial_window(int __space, __u32 mss,
+void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
__u32 *rcv_wnd, __u32 *window_clamp,
int wscale_ok, __u8 *rcv_wscale,
__u32 init_rcv_wnd)
@@ -226,7 +212,7 @@ void tcp_select_initial_window(int __space, __u32 mss,
* which we interpret as a sign the remote TCP is not
* misinterpreting the window field as a signed quantity.
*/
- if (sysctl_tcp_workaround_signed_windows)
+ if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
else
(*rcv_wnd) = space;
@@ -286,7 +272,8 @@ static u16 tcp_select_window(struct sock *sk)
/* Make sure we do not exceed the maximum possible
* scaled window.
*/
- if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows)
+ if (!tp->rx_opt.rcv_wscale &&
+ sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -1771,7 +1758,8 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0;
return tso_segs ? :
- tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs);
+ tcp_tso_autosize(sk, mss_now,
+ sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
}
/* Returns the portion of skb which can be sent right away */
@@ -1988,7 +1976,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
goto send_now;
- win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor);
+ win_divisor = ACCESS_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor);
if (win_divisor) {
u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
@@ -2225,7 +2213,8 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
unsigned int limit;
limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
- limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
+ limit = min_t(u32, limit,
+ sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
limit <<= factor;
if (refcount_read(&sk->sk_wmem_alloc) > limit) {
@@ -3355,7 +3344,7 @@ static void tcp_connect_init(struct sock *sk)
if (rcv_wnd == 0)
rcv_wnd = dst_metric(dst, RTAX_INITRWND);
- tcp_select_initial_window(tcp_full_space(sk),
+ tcp_select_initial_window(sk, tcp_full_space(sk),
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 7835dea930b4..9f918a770f87 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -187,7 +187,6 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
struct ipv6_destopt_hao *hao;
struct inet6_skb_parm *opt = IP6CB(skb);
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
- struct in6_addr tmp_addr;
int ret;
if (opt->dsthao) {
@@ -229,9 +228,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->ip_summed = CHECKSUM_NONE;
- tmp_addr = ipv6h->saddr;
- ipv6h->saddr = hao->addr;
- hao->addr = tmp_addr;
+ swap(ipv6h->saddr, hao->addr);
if (skb->tstamp == 0)
__net_timestamp(skb);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 4e7817abc0b9..e7a3a6b6cf56 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -244,7 +244,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
}
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
- tcp_select_initial_window(tcp_full_space(sk), req->mss,
+ tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(dst, RTAX_INITRWND));
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index af22aa8ae35b..a1d56e143fcd 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -322,8 +322,8 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
}
EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname);
-static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
- struct l2tp_session *session)
+int l2tp_session_register(struct l2tp_session *session,
+ struct l2tp_tunnel *tunnel)
{
struct l2tp_session *session_walk;
struct hlist_head *g_head;
@@ -371,6 +371,10 @@ static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
hlist_add_head(&session->hlist, head);
write_unlock_bh(&tunnel->hlist_lock);
+ /* Ignore management session in session count value */
+ if (session->session_id != 0)
+ atomic_inc(&l2tp_session_count);
+
return 0;
err_tlock_pnlock:
@@ -380,6 +384,7 @@ err_tlock:
return err;
}
+EXPORT_SYMBOL_GPL(l2tp_session_register);
/* Lookup a tunnel by id
*/
@@ -1788,7 +1793,6 @@ EXPORT_SYMBOL_GPL(l2tp_session_set_header_len);
struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
{
struct l2tp_session *session;
- int err;
session = kzalloc(sizeof(struct l2tp_session) + priv_size, GFP_KERNEL);
if (session != NULL) {
@@ -1846,17 +1850,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
refcount_set(&session->ref_count, 1);
- err = l2tp_session_add_to_tunnel(tunnel, session);
- if (err) {
- kfree(session);
-
- return ERR_PTR(err);
- }
-
- /* Ignore management session in session count value */
- if (session->session_id != 0)
- atomic_inc(&l2tp_session_count);
-
return session;
}
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 67c79d9b5c6c..77caa5966736 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -263,6 +263,9 @@ struct l2tp_session *l2tp_session_create(int priv_size,
struct l2tp_tunnel *tunnel,
u32 session_id, u32 peer_session_id,
struct l2tp_session_cfg *cfg);
+int l2tp_session_register(struct l2tp_session *session,
+ struct l2tp_tunnel *tunnel);
+
void __l2tp_session_unhash(struct l2tp_session *session);
int l2tp_session_delete(struct l2tp_session *session);
void l2tp_session_free(struct l2tp_session *session);
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 014a7bc2a872..d29bfee291cb 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -54,7 +54,7 @@ struct l2tp_eth {
/* via l2tp_session_priv() */
struct l2tp_eth_sess {
- struct net_device *dev;
+ struct net_device __rcu *dev;
};
@@ -72,7 +72,14 @@ static int l2tp_eth_dev_init(struct net_device *dev)
static void l2tp_eth_dev_uninit(struct net_device *dev)
{
- dev_put(dev);
+ struct l2tp_eth *priv = netdev_priv(dev);
+ struct l2tp_eth_sess *spriv;
+
+ spriv = l2tp_session_priv(priv->session);
+ RCU_INIT_POINTER(spriv->dev, NULL);
+ /* No need for synchronize_net() here. We're called by
+ * unregister_netdev*(), which does the synchronisation for us.
+ */
}
static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -130,8 +137,8 @@ static void l2tp_eth_dev_setup(struct net_device *dev)
static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
{
struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
- struct net_device *dev = spriv->dev;
- struct l2tp_eth *priv = netdev_priv(dev);
+ struct net_device *dev;
+ struct l2tp_eth *priv;
if (session->debug & L2TP_MSG_DATA) {
unsigned int length;
@@ -155,16 +162,25 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb,
skb_dst_drop(skb);
nf_reset(skb);
+ rcu_read_lock();
+ dev = rcu_dereference(spriv->dev);
+ if (!dev)
+ goto error_rcu;
+
+ priv = netdev_priv(dev);
if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) {
atomic_long_inc(&priv->rx_packets);
atomic_long_add(data_len, &priv->rx_bytes);
} else {
atomic_long_inc(&priv->rx_errors);
}
+ rcu_read_unlock();
+
return;
+error_rcu:
+ rcu_read_unlock();
error:
- atomic_long_inc(&priv->rx_errors);
kfree_skb(skb);
}
@@ -175,11 +191,15 @@ static void l2tp_eth_delete(struct l2tp_session *session)
if (session) {
spriv = l2tp_session_priv(session);
- dev = spriv->dev;
+
+ rtnl_lock();
+ dev = rtnl_dereference(spriv->dev);
if (dev) {
- unregister_netdev(dev);
- spriv->dev = NULL;
+ unregister_netdevice(dev);
+ rtnl_unlock();
module_put(THIS_MODULE);
+ } else {
+ rtnl_unlock();
}
}
}
@@ -189,9 +209,20 @@ static void l2tp_eth_show(struct seq_file *m, void *arg)
{
struct l2tp_session *session = arg;
struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
- struct net_device *dev = spriv->dev;
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = rcu_dereference(spriv->dev);
+ if (!dev) {
+ rcu_read_unlock();
+ return;
+ }
+ dev_hold(dev);
+ rcu_read_unlock();
seq_printf(m, " interface %s\n", dev->name);
+
+ dev_put(dev);
}
#endif
@@ -268,14 +299,14 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
peer_session_id, cfg);
if (IS_ERR(session)) {
rc = PTR_ERR(session);
- goto out;
+ goto err;
}
dev = alloc_netdev(sizeof(*priv), name, name_assign_type,
l2tp_eth_dev_setup);
if (!dev) {
rc = -ENOMEM;
- goto out_del_session;
+ goto err_sess;
}
dev_net_set(dev, net);
@@ -295,26 +326,48 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
#endif
spriv = l2tp_session_priv(session);
- spriv->dev = dev;
- rc = register_netdev(dev);
- if (rc < 0)
- goto out_del_dev;
+ l2tp_session_inc_refcount(session);
+
+ rtnl_lock();
+
+ /* Register both device and session while holding the rtnl lock. This
+ * ensures that l2tp_eth_delete() will see that there's a device to
+ * unregister, even if it happened to run before we assign spriv->dev.
+ */
+ rc = l2tp_session_register(session, tunnel);
+ if (rc < 0) {
+ rtnl_unlock();
+ goto err_sess_dev;
+ }
+
+ rc = register_netdevice(dev);
+ if (rc < 0) {
+ rtnl_unlock();
+ l2tp_session_delete(session);
+ l2tp_session_dec_refcount(session);
+ free_netdev(dev);
+
+ return rc;
+ }
- __module_get(THIS_MODULE);
- /* Must be done after register_netdev() */
strlcpy(session->ifname, dev->name, IFNAMSIZ);
+ rcu_assign_pointer(spriv->dev, dev);
- dev_hold(dev);
+ rtnl_unlock();
+
+ l2tp_session_dec_refcount(session);
+
+ __module_get(THIS_MODULE);
return 0;
-out_del_dev:
+err_sess_dev:
+ l2tp_session_dec_refcount(session);
free_netdev(dev);
- spriv->dev = NULL;
-out_del_session:
- l2tp_session_delete(session);
-out:
+err_sess:
+ kfree(session);
+err:
return rc;
}
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index f50452b919d5..845aba543dce 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -122,8 +122,11 @@
struct pppol2tp_session {
int owner; /* pid that opened the socket */
- struct sock *sock; /* Pointer to the session
+ struct mutex sk_lock; /* Protects .sk */
+ struct sock __rcu *sk; /* Pointer to the session
* PPPoX socket */
+ struct sock *__sk; /* Copy of .sk, for cleanup */
+ struct rcu_head rcu; /* For asynchronous release */
struct sock *tunnel_sock; /* Pointer to the tunnel UDP
* socket */
int flags; /* accessed by PPPIOCGFLAGS.
@@ -138,6 +141,24 @@ static const struct ppp_channel_ops pppol2tp_chan_ops = {
static const struct proto_ops pppol2tp_ops;
+/* Retrieves the pppol2tp socket associated to a session.
+ * A reference is held on the returned socket, so this function must be paired
+ * with sock_put().
+ */
+static struct sock *pppol2tp_session_get_sock(struct l2tp_session *session)
+{
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+ struct sock *sk;
+
+ rcu_read_lock();
+ sk = rcu_dereference(ps->sk);
+ if (sk)
+ sock_hold(sk);
+ rcu_read_unlock();
+
+ return sk;
+}
+
/* Helpers to obtain tunnel/session contexts from sockets.
*/
static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk)
@@ -224,7 +245,8 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
/* If the socket is bound, send it in to PPP's input queue. Otherwise
* queue it on the session socket.
*/
- sk = ps->sock;
+ rcu_read_lock();
+ sk = rcu_dereference(ps->sk);
if (sk == NULL)
goto no_sock;
@@ -247,30 +269,16 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
kfree_skb(skb);
}
}
+ rcu_read_unlock();
return;
no_sock:
+ rcu_read_unlock();
l2tp_info(session, L2TP_MSG_DATA, "%s: no socket\n", session->name);
kfree_skb(skb);
}
-static void pppol2tp_session_sock_hold(struct l2tp_session *session)
-{
- struct pppol2tp_session *ps = l2tp_session_priv(session);
-
- if (ps->sock)
- sock_hold(ps->sock);
-}
-
-static void pppol2tp_session_sock_put(struct l2tp_session *session)
-{
- struct pppol2tp_session *ps = l2tp_session_priv(session);
-
- if (ps->sock)
- sock_put(ps->sock);
-}
-
/************************************************************************
* Transmit handling
***********************************************************************/
@@ -431,17 +439,16 @@ abort:
*/
static void pppol2tp_session_close(struct l2tp_session *session)
{
- struct pppol2tp_session *ps = l2tp_session_priv(session);
- struct sock *sk = ps->sock;
- struct socket *sock = sk->sk_socket;
+ struct sock *sk;
BUG_ON(session->magic != L2TP_SESSION_MAGIC);
- if (sock)
- inet_shutdown(sock, SEND_SHUTDOWN);
-
- /* Don't let the session go away before our socket does */
- l2tp_session_inc_refcount(session);
+ sk = pppol2tp_session_get_sock(session);
+ if (sk) {
+ if (sk->sk_socket)
+ inet_shutdown(sk->sk_socket, SEND_SHUTDOWN);
+ sock_put(sk);
+ }
}
/* Really kill the session socket. (Called from sock_put() if
@@ -461,6 +468,14 @@ static void pppol2tp_session_destruct(struct sock *sk)
}
}
+static void pppol2tp_put_sk(struct rcu_head *head)
+{
+ struct pppol2tp_session *ps;
+
+ ps = container_of(head, typeof(*ps), rcu);
+ sock_put(ps->__sk);
+}
+
/* Called when the PPPoX socket (session) is closed.
*/
static int pppol2tp_release(struct socket *sock)
@@ -486,11 +501,23 @@ static int pppol2tp_release(struct socket *sock)
session = pppol2tp_sock_to_session(sk);
- /* Purge any queued data */
if (session != NULL) {
- __l2tp_session_unhash(session);
- l2tp_session_queue_purge(session);
- sock_put(sk);
+ struct pppol2tp_session *ps;
+
+ l2tp_session_delete(session);
+
+ ps = l2tp_session_priv(session);
+ mutex_lock(&ps->sk_lock);
+ ps->__sk = rcu_dereference_protected(ps->sk,
+ lockdep_is_held(&ps->sk_lock));
+ RCU_INIT_POINTER(ps->sk, NULL);
+ mutex_unlock(&ps->sk_lock);
+ call_rcu(&ps->rcu, pppol2tp_put_sk);
+
+ /* Rely on the sock_put() call at the end of the function for
+ * dropping the reference held by pppol2tp_sock_to_session().
+ * The last reference will be dropped by pppol2tp_put_sk().
+ */
}
release_sock(sk);
@@ -557,16 +584,47 @@ out:
static void pppol2tp_show(struct seq_file *m, void *arg)
{
struct l2tp_session *session = arg;
- struct pppol2tp_session *ps = l2tp_session_priv(session);
+ struct sock *sk;
+
+ sk = pppol2tp_session_get_sock(session);
+ if (sk) {
+ struct pppox_sock *po = pppox_sk(sk);
- if (ps) {
- struct pppox_sock *po = pppox_sk(ps->sock);
- if (po)
- seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan));
+ seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan));
+ sock_put(sk);
}
}
#endif
+static void pppol2tp_session_init(struct l2tp_session *session)
+{
+ struct pppol2tp_session *ps;
+ struct dst_entry *dst;
+
+ session->recv_skb = pppol2tp_recv;
+ session->session_close = pppol2tp_session_close;
+#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
+ session->show = pppol2tp_show;
+#endif
+
+ ps = l2tp_session_priv(session);
+ mutex_init(&ps->sk_lock);
+ ps->tunnel_sock = session->tunnel->sock;
+ ps->owner = current->pid;
+
+ /* If PMTU discovery was enabled, use the MTU that was discovered */
+ dst = sk_dst_get(session->tunnel->sock);
+ if (dst) {
+ u32 pmtu = dst_mtu(dst);
+
+ if (pmtu) {
+ session->mtu = pmtu - PPPOL2TP_HEADER_OVERHEAD;
+ session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD;
+ }
+ dst_release(dst);
+ }
+}
+
/* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
*/
static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
@@ -578,7 +636,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
struct l2tp_session *session = NULL;
struct l2tp_tunnel *tunnel;
struct pppol2tp_session *ps;
- struct dst_entry *dst;
struct l2tp_session_cfg cfg = { 0, };
int error = 0;
u32 tunnel_id, peer_tunnel_id;
@@ -693,13 +750,17 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
/* Using a pre-existing session is fine as long as it hasn't
* been connected yet.
*/
- if (ps->sock) {
+ mutex_lock(&ps->sk_lock);
+ if (rcu_dereference_protected(ps->sk,
+ lockdep_is_held(&ps->sk_lock))) {
+ mutex_unlock(&ps->sk_lock);
error = -EEXIST;
goto end;
}
/* consistency checks */
if (ps->tunnel_sock != tunnel->sock) {
+ mutex_unlock(&ps->sk_lock);
error = -EEXIST;
goto end;
}
@@ -715,35 +776,19 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
error = PTR_ERR(session);
goto end;
}
- }
-
- /* Associate session with its PPPoL2TP socket */
- ps = l2tp_session_priv(session);
- ps->owner = current->pid;
- ps->sock = sk;
- ps->tunnel_sock = tunnel->sock;
-
- session->recv_skb = pppol2tp_recv;
- session->session_close = pppol2tp_session_close;
-#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
- session->show = pppol2tp_show;
-#endif
-
- /* We need to know each time a skb is dropped from the reorder
- * queue.
- */
- session->ref = pppol2tp_session_sock_hold;
- session->deref = pppol2tp_session_sock_put;
- /* If PMTU discovery was enabled, use the MTU that was discovered */
- dst = sk_dst_get(tunnel->sock);
- if (dst != NULL) {
- u32 pmtu = dst_mtu(dst);
+ pppol2tp_session_init(session);
+ ps = l2tp_session_priv(session);
+ l2tp_session_inc_refcount(session);
- if (pmtu != 0)
- session->mtu = session->mru = pmtu -
- PPPOL2TP_HEADER_OVERHEAD;
- dst_release(dst);
+ mutex_lock(&ps->sk_lock);
+ error = l2tp_session_register(session, tunnel);
+ if (error < 0) {
+ mutex_unlock(&ps->sk_lock);
+ kfree(session);
+ goto end;
+ }
+ drop_refcnt = true;
}
/* Special case: if source & dest session_id == 0x0000, this
@@ -768,12 +813,23 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
po->chan.mtu = session->mtu;
error = ppp_register_net_channel(sock_net(sk), &po->chan);
- if (error)
+ if (error) {
+ mutex_unlock(&ps->sk_lock);
goto end;
+ }
out_no_ppp:
/* This is how we get the session context from the socket. */
sk->sk_user_data = session;
+ rcu_assign_pointer(ps->sk, sk);
+ mutex_unlock(&ps->sk_lock);
+
+ /* Keep the reference we've grabbed on the session: sk doesn't expect
+ * the session to disappear. pppol2tp_session_destruct() is responsible
+ * for dropping it.
+ */
+ drop_refcnt = false;
+
sk->sk_state = PPPOX_CONNECTED;
l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n",
session->name);
@@ -795,12 +851,11 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel,
{
int error;
struct l2tp_session *session;
- struct pppol2tp_session *ps;
/* Error if tunnel socket is not prepped */
if (!tunnel->sock) {
error = -ENOENT;
- goto out;
+ goto err;
}
/* Default MTU values. */
@@ -815,18 +870,20 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel,
peer_session_id, cfg);
if (IS_ERR(session)) {
error = PTR_ERR(session);
- goto out;
+ goto err;
}
- ps = l2tp_session_priv(session);
- ps->tunnel_sock = tunnel->sock;
+ pppol2tp_session_init(session);
- l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n",
- session->name);
+ error = l2tp_session_register(session, tunnel);
+ if (error < 0)
+ goto err_sess;
- error = 0;
+ return 0;
-out:
+err_sess:
+ kfree(session);
+err:
return error;
}
@@ -987,12 +1044,10 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
"%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n",
session->name, cmd, arg);
- sk = ps->sock;
+ sk = pppol2tp_session_get_sock(session);
if (!sk)
return -EBADR;
- sock_hold(sk);
-
switch (cmd) {
case SIOCGIFMTU:
err = -ENXIO;
@@ -1268,7 +1323,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
int optname, int val)
{
int err = 0;
- struct pppol2tp_session *ps = l2tp_session_priv(session);
switch (optname) {
case PPPOL2TP_SO_RECVSEQ:
@@ -1289,8 +1343,8 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
}
session->send_seq = !!val;
{
- struct sock *ssk = ps->sock;
- struct pppox_sock *po = pppox_sk(ssk);
+ struct pppox_sock *po = pppox_sk(sk);
+
po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
}
@@ -1629,8 +1683,9 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
{
struct l2tp_session *session = v;
struct l2tp_tunnel *tunnel = session->tunnel;
- struct pppol2tp_session *ps = l2tp_session_priv(session);
- struct pppox_sock *po = pppox_sk(ps->sock);
+ unsigned char state;
+ char user_data_ok;
+ struct sock *sk;
u32 ip = 0;
u16 port = 0;
@@ -1640,6 +1695,15 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
port = ntohs(inet->inet_sport);
}
+ sk = pppol2tp_session_get_sock(session);
+ if (sk) {
+ state = sk->sk_state;
+ user_data_ok = (session == sk->sk_user_data) ? 'Y' : 'N';
+ } else {
+ state = 0;
+ user_data_ok = 'N';
+ }
+
seq_printf(m, " SESSION '%s' %08X/%d %04X/%04X -> "
"%04X/%04X %d %c\n",
session->name, ip, port,
@@ -1647,9 +1711,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
session->session_id,
tunnel->peer_tunnel_id,
session->peer_session_id,
- ps->sock->sk_state,
- (session == ps->sock->sk_user_data) ?
- 'Y' : 'N');
+ state, user_data_ok);
seq_printf(m, " %d/%d/%c/%c/%s %08x %u\n",
session->mtu, session->mru,
session->recv_seq ? 'R' : '-',
@@ -1666,8 +1728,12 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
atomic_long_read(&session->stats.rx_bytes),
atomic_long_read(&session->stats.rx_errors));
- if (po)
+ if (sk) {
+ struct pppox_sock *po = pppox_sk(sk);
+
seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan));
+ sock_put(sk);
+ }
}
static int pppol2tp_seq_show(struct seq_file *m, void *v)