* [PATCH net-next 1/3] net: core: Add a UID field to struct sock.
From: Lorenzo Colitti @ 2016-10-27 17:20 UTC (permalink / raw)
To: netdev; +Cc: davem, ek, eric.dumazet, zenczykowski, Lorenzo Colitti
In-Reply-To: <1477588841-140767-1-git-send-email-lorenzo@google.com>
Protocol sockets (struct sock) don't have UIDs, but most of the
time, they map 1:1 to userspace sockets (struct socket) which do.
Various operations such as the iptables xt_owner match need
access to the "UID of a socket", and do so by following the
backpointer to the struct socket. This involves taking
sk_callback_lock and doesn't work when there is no socket
because userspace has already called close().
Simplify this by adding a sk_uid field to struct sock whose value
matches the UID of the corresponding struct socket. The semantics
are as follows:
1. Whenever sk_socket is non-null: sk_uid is the same as the UID
in sk_socket, i.e., matches the return value of sock_i_uid.
Specifically, the UID is set when userspace calls socket(),
fchown(), or accept().
2. When sk_socket is null, sk_uid is defined as follows:
- For a socket that no longer has a sk_socket because
userspace has called close(): the previous UID.
- For a cloned socket (e.g., an incoming connection that is
established but on which userspace has not yet called
accept): the UID of the socket it was cloned from.
- For a socket that has never had an sk_socket (e.g., a kernel
ICMP socket): UID 0 inside the user namespace corresponding
to the network namespace the socket belongs to. This is
arguably better than GLOBAL_ROOT_UID because it allows
"--owner-uid 0" to match kernel-originated packets in
non-root namespaces.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
---
include/net/sock.h | 7 +++++++
net/core/sock.c | 6 +++++-
net/socket.c | 14 ++++++++++++++
3 files changed, 26 insertions(+), 1 deletion(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index 2764895..2086922 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -417,6 +417,7 @@ struct sock {
u32 sk_max_ack_backlog;
__u32 sk_priority;
__u32 sk_mark;
+ kuid_t sk_uid;
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
long sk_rcvtimeo;
@@ -1651,6 +1652,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
sk->sk_wq = parent->wq;
parent->sk = sk;
sk_set_socket(sk, parent);
+ sk->sk_uid = SOCK_INODE(parent)->i_uid;
security_sock_graft(sk, parent);
write_unlock_bh(&sk->sk_callback_lock);
}
@@ -1658,6 +1660,11 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
kuid_t sock_i_uid(struct sock *sk);
unsigned long sock_i_ino(struct sock *sk);
+static inline kuid_t sock_net_uid(struct net *net, const struct sock *sk)
+{
+ return sk ? sk->sk_uid : make_kuid(net->user_ns, 0);
+}
+
static inline u32 net_tx_rndhash(void)
{
u32 v = prandom_u32();
diff --git a/net/core/sock.c b/net/core/sock.c
index d8e4532e..831e4e8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1570,6 +1570,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
*/
sk_refcnt_debug_inc(newsk);
sk_set_socket(newsk, NULL);
+ newsk->sk_uid = sk->sk_uid;
newsk->sk_wq = NULL;
if (newsk->sk_prot->sockets_allocated)
@@ -2460,8 +2461,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_type = sock->type;
sk->sk_wq = sock->wq;
sock->sk = sk;
- } else
+ sk->sk_uid = SOCK_INODE(sock)->i_uid;
+ } else {
sk->sk_wq = NULL;
+ sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0);
+ }
rwlock_init(&sk->sk_callback_lock);
lockdep_set_class_and_name(&sk->sk_callback_lock,
diff --git a/net/socket.c b/net/socket.c
index 5a9bf5e..5a4747e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -518,8 +518,22 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
return used;
}
+int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+ int err = simple_setattr(dentry, iattr);
+
+ if (!err) {
+ struct socket *sock = SOCKET_I(d_inode(dentry));
+
+ sock->sk->sk_uid = iattr->ia_uid;
+ }
+
+ return err;
+}
+
static const struct inode_operations sockfs_inode_ops = {
.listxattr = sockfs_listxattr,
+ .setattr = sockfs_setattr,
};
/**
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH net-next 2/3] net: core: add UID to flows, rules, and routes
From: Lorenzo Colitti @ 2016-10-27 17:20 UTC (permalink / raw)
To: netdev; +Cc: davem, ek, eric.dumazet, zenczykowski, Lorenzo Colitti
In-Reply-To: <1477588841-140767-1-git-send-email-lorenzo@google.com>
- Define a new FIB rule attributes, FRA_UID_RANGE, to describe a
range of UIDs.
- Define a RTA_UID attribute for per-UID route lookups and dumps.
- Support passing these attributes to and from userspace via
rtnetlink. The value INVALID_UID indicates no UID was
specified.
- Add a UID field to the flow structures.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
---
include/net/fib_rules.h | 9 ++++-
include/net/flow.h | 5 +++
include/uapi/linux/fib_rules.h | 6 ++++
include/uapi/linux/rtnetlink.h | 1 +
net/core/fib_rules.c | 74 ++++++++++++++++++++++++++++++++++++++++--
net/ipv4/fib_frontend.c | 1 +
net/ipv4/route.c | 11 +++++++
net/ipv6/route.c | 7 ++++
8 files changed, 111 insertions(+), 3 deletions(-)
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 456e4a6..8dbfdf7 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -8,6 +8,11 @@
#include <net/flow.h>
#include <net/rtnetlink.h>
+struct fib_kuid_range {
+ kuid_t start;
+ kuid_t end;
+};
+
struct fib_rule {
struct list_head list;
int iifindex;
@@ -30,6 +35,7 @@ struct fib_rule {
int suppress_prefixlen;
char iifname[IFNAMSIZ];
char oifname[IFNAMSIZ];
+ struct fib_kuid_range uid_range;
struct rcu_head rcu;
};
@@ -92,7 +98,8 @@ struct fib_rules_ops {
[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
[FRA_GOTO] = { .type = NLA_U32 }, \
- [FRA_L3MDEV] = { .type = NLA_U8 }
+ [FRA_L3MDEV] = { .type = NLA_U8 }, \
+ [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }
static inline void fib_rule_get(struct fib_rule *rule)
{
diff --git a/include/net/flow.h b/include/net/flow.h
index 035aa77..51373f3 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -11,6 +11,7 @@
#include <linux/in6.h>
#include <linux/atomic.h>
#include <net/flow_dissector.h>
+#include <linux/uidgid.h>
/*
* ifindex generation is per-net namespace, and loopback is
@@ -37,6 +38,7 @@ struct flowi_common {
#define FLOWI_FLAG_SKIP_NH_OIF 0x04
__u32 flowic_secid;
struct flowi_tunnel flowic_tun_key;
+ kuid_t flowic_uid;
};
union flowi_uli {
@@ -74,6 +76,7 @@ struct flowi4 {
#define flowi4_flags __fl_common.flowic_flags
#define flowi4_secid __fl_common.flowic_secid
#define flowi4_tun_key __fl_common.flowic_tun_key
+#define flowi4_uid __fl_common.flowic_uid
/* (saddr,daddr) must be grouped, same order as in IP header */
__be32 saddr;
@@ -131,6 +134,7 @@ struct flowi6 {
#define flowi6_flags __fl_common.flowic_flags
#define flowi6_secid __fl_common.flowic_secid
#define flowi6_tun_key __fl_common.flowic_tun_key
+#define flowi6_uid __fl_common.flowic_uid
struct in6_addr daddr;
struct in6_addr saddr;
/* Note: flowi6_tos is encoded in flowlabel, too. */
@@ -176,6 +180,7 @@ struct flowi {
#define flowi_flags u.__fl_common.flowic_flags
#define flowi_secid u.__fl_common.flowic_secid
#define flowi_tun_key u.__fl_common.flowic_tun_key
+#define flowi_uid u.__fl_common.flowic_uid
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 14404b3..bbf02a6 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -29,6 +29,11 @@ struct fib_rule_hdr {
__u32 flags;
};
+struct fib_rule_uid_range {
+ __u32 start;
+ __u32 end;
+};
+
enum {
FRA_UNSPEC,
FRA_DST, /* destination address */
@@ -51,6 +56,7 @@ enum {
FRA_OIFNAME,
FRA_PAD,
FRA_L3MDEV, /* iif or oif is l3mdev goto its table */
+ FRA_UID_RANGE, /* UID range */
__FRA_MAX
};
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 262f037..bb85e78 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -318,6 +318,7 @@ enum rtattr_type_t {
RTA_ENCAP,
RTA_EXPIRES,
RTA_PAD,
+ RTA_UID,
__RTA_MAX
};
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index be4629c..5de436a 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -18,6 +18,11 @@
#include <net/fib_rules.h>
#include <net/ip_tunnels.h>
+static const struct fib_kuid_range fib_kuid_range_unset = {
+ KUIDT_INIT(0),
+ KUIDT_INIT(~0),
+};
+
int fib_default_rule_add(struct fib_rules_ops *ops,
u32 pref, u32 table, u32 flags)
{
@@ -33,6 +38,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
r->table = table;
r->flags = flags;
r->fr_net = ops->fro_net;
+ r->uid_range = fib_kuid_range_unset;
r->suppress_prefixlen = -1;
r->suppress_ifgroup = -1;
@@ -172,6 +178,34 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
}
EXPORT_SYMBOL_GPL(fib_rules_unregister);
+static int uid_range_set(struct fib_kuid_range *range)
+{
+ return uid_valid(range->start) && uid_valid(range->end);
+}
+
+static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb)
+{
+ struct fib_rule_uid_range *in;
+ struct fib_kuid_range out;
+
+ in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]);
+
+ out.start = make_kuid(current_user_ns(), in->start);
+ out.end = make_kuid(current_user_ns(), in->end);
+
+ return out;
+}
+
+static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range)
+{
+ struct fib_rule_uid_range out = {
+ from_kuid_munged(current_user_ns(), range->start),
+ from_kuid_munged(current_user_ns(), range->end)
+ };
+
+ return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out);
+}
+
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
struct flowi *fl, int flags,
struct fib_lookup_arg *arg)
@@ -193,6 +227,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg))
goto out;
+ if (uid_lt(fl->flowi_uid, rule->uid_range.start) ||
+ uid_gt(fl->flowi_uid, rule->uid_range.end))
+ goto out;
+
ret = ops->match(rule, fl, flags);
out:
return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -429,6 +467,21 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
if (rule->l3mdev && rule->table)
goto errout_free;
+ if (tb[FRA_UID_RANGE]) {
+ if (current_user_ns() != net->user_ns) {
+ err = -EPERM;
+ goto errout_free;
+ }
+
+ rule->uid_range = nla_get_kuid_range(tb);
+
+ if (!uid_range_set(&rule->uid_range) ||
+ !uid_lte(rule->uid_range.start, rule->uid_range.end))
+ goto errout_free;
+ } else {
+ rule->uid_range = fib_kuid_range_unset;
+ }
+
if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
rule_exists(ops, frh, tb, rule)) {
err = -EEXIST;
@@ -497,6 +550,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
struct fib_rules_ops *ops = NULL;
struct fib_rule *rule, *tmp;
struct nlattr *tb[FRA_MAX+1];
+ struct fib_kuid_range range;
int err = -EINVAL;
if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
@@ -516,6 +570,14 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
if (err < 0)
goto errout;
+ if (tb[FRA_UID_RANGE]) {
+ range = nla_get_kuid_range(tb);
+ if (!uid_range_set(&range))
+ goto errout;
+ } else {
+ range = fib_kuid_range_unset;
+ }
+
list_for_each_entry(rule, &ops->rules_list, list) {
if (frh->action && (frh->action != rule->action))
continue;
@@ -552,6 +614,11 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
(rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV])))
continue;
+ if (uid_range_set(&range) &&
+ (!uid_eq(rule->uid_range.start, range.start) ||
+ !uid_eq(rule->uid_range.end, range.end)))
+ continue;
+
if (!ops->compare(rule, frh, tb))
continue;
@@ -619,7 +686,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
+ nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
+ nla_total_size(4) /* FRA_FWMARK */
+ nla_total_size(4) /* FRA_FWMASK */
- + nla_total_size_64bit(8); /* FRA_TUN_ID */
+ + nla_total_size_64bit(8) /* FRA_TUN_ID */
+ + nla_total_size(sizeof(struct fib_kuid_range));
if (ops->nlmsg_payload)
payload += ops->nlmsg_payload(rule);
@@ -679,7 +747,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
(rule->tun_id &&
nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) ||
(rule->l3mdev &&
- nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)))
+ nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) ||
+ (uid_range_set(&rule->uid_range) &&
+ nla_put_uid_range(skb, &rule->uid_range)))
goto nla_put_failure;
if (rule->suppress_ifgroup != -1) {
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c3b8047..d93eea8 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -610,6 +610,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
[RTA_FLOW] = { .type = NLA_U32 },
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 62d4d90..0a42dc0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2493,6 +2493,11 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
+ if (!uid_eq(fl4->flowi4_uid, INVALID_UID) &&
+ nla_put_u32(skb, RTA_UID,
+ from_kuid_munged(current_user_ns(), fl4->flowi4_uid)))
+ goto nla_put_failure;
+
error = rt->dst.error;
if (rt_is_input_route(rt)) {
@@ -2545,6 +2550,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
int mark;
struct sk_buff *skb;
u32 table_id = RT_TABLE_MAIN;
+ kuid_t uid;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
@@ -2572,6 +2578,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+ if (tb[RTA_UID])
+ uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID]));
+ else
+ uid = (iif ? INVALID_UID : current_uid());
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = dst;
@@ -2579,6 +2589,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
fl4.flowi4_tos = rtm->rtm_tos;
fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = uid;
if (iif) {
struct net_device *dev;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bdbc38e..cd84ded 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2767,6 +2767,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
[RTA_EXPIRES] = { .type = NLA_U32 },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -3341,6 +3342,12 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
if (tb[RTA_MARK])
fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+ if (tb[RTA_UID])
+ fl6.flowi6_uid = make_kuid(current_user_ns(),
+ nla_get_u32(tb[RTA_UID]));
+ else
+ fl6.flowi6_uid = iif ? INVALID_UID : current_uid();
+
if (iif) {
struct net_device *dev;
int flags = 0;
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH net-next 3/3] net: inet: Support UID-based routing in IP protocols.
From: Lorenzo Colitti @ 2016-10-27 17:20 UTC (permalink / raw)
To: netdev; +Cc: davem, ek, eric.dumazet, zenczykowski, Lorenzo Colitti
In-Reply-To: <1477588841-140767-1-git-send-email-lorenzo@google.com>
- Use the UID in routing lookups made by protocol connect() and
sendmsg() functions.
- Make sure that routing lookups triggered by incoming packets
(e.g., Path MTU discovery) take the UID of the socket into
account.
Tested: compiles allnoconfig, allyesconfig, allmodconfig
Tested: https://android-review.googlesource.com/253302
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
---
include/net/flow.h | 4 +++-
include/net/ip.h | 1 +
include/net/ip6_route.h | 2 +-
include/net/route.h | 5 +++--
net/ipv4/icmp.c | 9 ++++++---
net/ipv4/inet_connection_sock.c | 4 ++--
net/ipv4/ip_output.c | 3 ++-
net/ipv4/ping.c | 3 ++-
net/ipv4/raw.c | 2 +-
net/ipv4/route.c | 31 +++++++++++++++++--------------
net/ipv4/syncookies.c | 2 +-
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/udp.c | 3 ++-
net/ipv6/af_inet6.c | 1 +
net/ipv6/ah6.c | 2 +-
net/ipv6/datagram.c | 1 +
net/ipv6/esp6.c | 2 +-
net/ipv6/icmp.c | 4 +++-
net/ipv6/inet6_connection_sock.c | 2 ++
net/ipv6/ip6_gre.c | 4 ++++
net/ipv6/ip6_tunnel.c | 4 ++++
net/ipv6/ip6_vti.c | 3 ++-
net/ipv6/ipcomp6.c | 2 +-
net/ipv6/netfilter.c | 1 +
net/ipv6/ping.c | 1 +
net/ipv6/raw.c | 1 +
net/ipv6/route.c | 7 +++++--
net/ipv6/syncookies.c | 1 +
net/ipv6/tcp_ipv6.c | 2 ++
net/ipv6/udp.c | 1 +
net/l2tp/l2tp_ip6.c | 1 +
31 files changed, 75 insertions(+), 35 deletions(-)
diff --git a/include/net/flow.h b/include/net/flow.h
index 51373f3..6bbbca8 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -96,7 +96,8 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
__u32 mark, __u8 tos, __u8 scope,
__u8 proto, __u8 flags,
__be32 daddr, __be32 saddr,
- __be16 dport, __be16 sport)
+ __be16 dport, __be16 sport,
+ kuid_t uid)
{
fl4->flowi4_oif = oif;
fl4->flowi4_iif = LOOPBACK_IFINDEX;
@@ -107,6 +108,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
fl4->flowi4_flags = flags;
fl4->flowi4_secid = 0;
fl4->flowi4_tun_key.tun_id = 0;
+ fl4->flowi4_uid = uid;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->fl4_dport = dport;
diff --git a/include/net/ip.h b/include/net/ip.h
index bc43c0f..f4182b1 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -173,6 +173,7 @@ struct ip_reply_arg {
/* -1 if not needed */
int bound_dev_if;
u8 tos;
+ kuid_t uid;
};
#define IP_REPLY_ARG_NOSRCCHECK 1
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index e0cd318..8498e19 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -139,7 +139,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr);
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif,
- u32 mark);
+ u32 mark, kuid_t uid);
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu);
void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark);
void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
diff --git a/include/net/route.h b/include/net/route.h
index 0429d47..c0874c8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -153,7 +153,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
RT_SCOPE_UNIVERSE, proto,
sk ? inet_sk_flowi_flags(sk) : 0,
- daddr, saddr, dport, sport);
+ daddr, saddr, dport, sport, sock_net_uid(net, sk));
if (sk)
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
return ip_route_output_flow(net, fl4, sk);
@@ -269,7 +269,8 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
flow_flags |= FLOWI_FLAG_ANYSRC;
flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
- protocol, flow_flags, dst, src, dport, sport);
+ protocol, flow_flags, dst, src, dport, sport,
+ sk->sk_uid);
}
static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 38abe70..7455987 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -425,6 +425,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
fl4.daddr = daddr;
fl4.saddr = saddr;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = sk->sk_uid;
fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
fl4.flowi4_proto = IPPROTO_ICMP;
fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
@@ -460,7 +461,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
struct flowi4 *fl4,
struct sk_buff *skb_in,
const struct iphdr *iph,
- __be32 saddr, u8 tos, u32 mark,
+ __be32 saddr, u8 tos,
+ const struct sock *sk,
int type, int code,
struct icmp_bxm *param)
{
@@ -472,7 +474,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->daddr = (param->replyopts.opt.opt.srr ?
param->replyopts.opt.opt.faddr : iph->saddr);
fl4->saddr = saddr;
- fl4->flowi4_mark = mark;
+ fl4->flowi4_mark = sk->sk_mark;
+ fl4->flowi4_uid = sk->sk_uid;
fl4->flowi4_tos = RT_TOS(tos);
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
@@ -701,7 +704,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
ipc.ttl = 0;
ipc.tos = -1;
- rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
+ rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, sk,
type, code, icmp_param);
if (IS_ERR(rt))
goto out_unlock;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 61a9dee..d5d3ead 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -415,7 +415,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
- htons(ireq->ir_num));
+ htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
@@ -452,7 +452,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
- htons(ireq->ir_num));
+ htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 05d1058..37f0138 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1590,7 +1590,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
ip_reply_arg_flowi_flags(arg),
daddr, saddr,
- tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+ tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
+ arg->uid);
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7cf7d6e..146be157 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -789,7 +789,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
- inet_sk_flowi_flags(sk), faddr, saddr, 0, 0);
+ inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
+ sk->sk_uid);
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 03618ed..3a7bc93 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -606,7 +606,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
- daddr, saddr, 0, 0);
+ daddr, saddr, 0, 0, sk->sk_uid);
if (!inet->hdrincl) {
rfv.msg = msg;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0a42dc0..b0f2a21 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -507,7 +507,8 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
}
EXPORT_SYMBOL(__ip_select_ident);
-static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void __build_flow_key(struct net *net, struct flowi4 *fl4,
+ struct sock *sk,
const struct iphdr *iph,
int oif, u8 tos,
u8 prot, u32 mark, int flow_flags)
@@ -523,11 +524,11 @@ static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
flowi4_init_output(fl4, oif, mark, tos,
RT_SCOPE_UNIVERSE, prot,
flow_flags,
- iph->daddr, iph->saddr, 0, 0);
+ iph->daddr, iph->saddr, 0, 0, sk->sk_uid);
}
static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
- const struct sock *sk)
+ struct sock *sk)
{
const struct iphdr *iph = ip_hdr(skb);
int oif = skb->dev->ifindex;
@@ -535,10 +536,10 @@ static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
u8 prot = iph->protocol;
u32 mark = skb->mark;
- __build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
+ __build_flow_key(sock_net(sk), fl4, sk, iph, oif, tos, prot, mark, 0);
}
-static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
+static void build_sk_flow_key(struct flowi4 *fl4, struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
@@ -552,11 +553,11 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk),
- daddr, inet->inet_saddr, 0, 0);
+ daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
rcu_read_unlock();
}
-static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void ip_rt_build_flow_key(struct flowi4 *fl4, struct sock *sk,
const struct sk_buff *skb)
{
if (skb)
@@ -800,7 +801,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
rt = (struct rtable *) dst;
- __build_flow_key(&fl4, sk, iph, oif, tos, prot, mark, 0);
+ __build_flow_key(sock_net(sk), &fl4, sk, iph, oif, tos, prot, mark, 0);
__ip_do_redirect(rt, skb, &fl4, true);
}
@@ -1018,7 +1019,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
if (!mark)
mark = IP4_REPLY_MARK(net, skb->mark);
- __build_flow_key(&fl4, NULL, iph, oif,
+ __build_flow_key(net, &fl4, NULL, iph, oif,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
@@ -1034,7 +1035,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
struct flowi4 fl4;
struct rtable *rt;
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+ __build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0);
if (!fl4.flowi4_mark)
fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark);
@@ -1053,6 +1054,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
struct rtable *rt;
struct dst_entry *odst = NULL;
bool new = false;
+ struct net *net = sock_net(sk);
bh_lock_sock(sk);
@@ -1066,7 +1068,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
goto out;
}
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+ __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
rt = (struct rtable *)odst;
if (odst->obsolete && !odst->ops->check(odst, 0)) {
@@ -1106,7 +1108,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net,
struct flowi4 fl4;
struct rtable *rt;
- __build_flow_key(&fl4, NULL, iph, oif,
+ __build_flow_key(net, &fl4, NULL, iph, oif,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
@@ -1121,9 +1123,10 @@ void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
+ struct net *net = sock_net(sk);
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
- rt = __ip_route_output_key(sock_net(sk), &fl4);
+ __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
+ rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_do_redirect(rt, skb, &fl4, false);
ip_rt_put(rt);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index e3c4043..0dc6286 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -372,7 +372,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
opt->srr ? opt->faddr : ireq->ir_rmt_addr,
- ireq->ir_loc_addr, th->source, th->dest);
+ ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
if (IS_ERR(rt)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 83b3d0b..a5da319 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -692,6 +692,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
offsetof(struct inet_timewait_sock, tw_bound_dev_if));
arg.tos = ip_hdr(skb)->tos;
+ arg.uid = sock_net_uid(net, sk);
local_bh_disable();
ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
skb, &TCP_SKB_CB(skb)->header.h4.opt,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c833271..36dae6a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1019,7 +1019,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
flow_flags,
- faddr, saddr, dport, inet->inet_sport);
+ faddr, saddr, dport, inet->inet_sport,
+ sk->sk_uid);
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 46ad699..c86911b 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -678,6 +678,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
rcu_read_lock();
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 0630a4d5..466d624 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -664,7 +664,7 @@ static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 37874e2..6d8a66a 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -54,6 +54,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
fl6->fl6_dport = inet->inet_dport;
fl6->fl6_sport = inet->inet_sport;
fl6->flowlabel = np->flow_label;
+ fl6->flowi6_uid = sk->sk_uid;
if (!fl6->flowi6_oif)
fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 060a60b..ad360ee 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -476,7 +476,7 @@ static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index bd59c34..db01af2 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -92,7 +92,7 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
struct net *net = dev_net(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
else if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0);
@@ -507,6 +507,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
ipc6.tclass = np->tclass;
fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+ fl6.flowi6_uid = sk->sk_uid;
dst = icmpv6_route_lookup(net, skb, sk, &fl6);
if (IS_ERR(dst))
@@ -670,6 +671,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl6.flowi6_oif = np->mcast_oif;
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
err = ip6_dst_lookup(net, sk, &dst, &fl6);
if (err)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 532c3ef..1c86c47 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -88,6 +88,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
fl6->flowi6_mark = ireq->ir_mark;
fl6->fl6_dport = ireq->ir_rmt_port;
fl6->fl6_sport = htons(ireq->ir_num);
+ fl6->flowi6_uid = sk->sk_uid;
security_req_classify_flow(req, flowi6_to_flowi(fl6));
dst = ip6_dst_lookup_flow(sk, fl6, final_p);
@@ -136,6 +137,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_sport = inet->inet_sport;
fl6->fl6_dport = inet->inet_dport;
+ fl6->flowi6_uid = sk->sk_uid;
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
rcu_read_lock();
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d7d6d3a..710bc79 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -548,6 +548,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM));
if (err)
return -1;
@@ -602,6 +604,8 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)))
return -1;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3a70567..ae23a5c 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1237,6 +1237,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
fl6.flowi6_mark = skb->mark;
}
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
@@ -1315,6 +1317,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
fl6.flowi6_mark = skb->mark;
}
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 35c5b2d..79ec327 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -610,7 +610,8 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0,
+ sock_net_uid(net, skb->sk));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 1b9316e..313ef6b 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -76,7 +76,7 @@ static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0);
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d11c468..39970e2 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -26,6 +26,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
struct flowi6 fl6 = {
.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.flowi6_mark = skb->mark,
+ .flowi6_uid = sock_net_uid(net, skb->sk),
.daddr = iph->daddr,
.saddr = iph->saddr,
};
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 0e983b6..f196779 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -113,6 +113,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.daddr = *daddr;
fl6.flowi6_oif = oif;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index d7e8b95..16e4123 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -776,6 +776,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
ipc6.hlimit = -1;
ipc6.tclass = -1;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index cd84ded..0582a8b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1401,7 +1401,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
}
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
- int oif, u32 mark)
+ int oif, u32 mark, kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
@@ -1413,6 +1413,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
@@ -1426,7 +1427,7 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
struct dst_entry *dst;
ip6_update_pmtu(skb, sock_net(sk), mtu,
- sk->sk_bound_dev_if, sk->sk_mark);
+ sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
@@ -1531,6 +1532,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr);
rt6_do_redirect(dst, NULL, skb);
@@ -1552,6 +1554,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
fl6.flowi6_mark = mark;
fl6.daddr = msg->dest;
fl6.saddr = iph->daddr;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
dst = ip6_route_redirect(net, &fl6, &iph->saddr);
rt6_do_redirect(dst, NULL, skb);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 59c4839..97830a6 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -227,6 +227,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
fl6.flowi6_mark = ireq->ir_mark;
fl6.fl6_dport = ireq->ir_rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5a27ab4..8a544eb 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -233,6 +233,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
@@ -824,6 +825,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
+ fl6.flowi6_uid = sock_net_uid(net, (struct sock *)sk);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
/* Pass a socket to ip6_dst_lookup either it is for RST
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 71963b2..b05f722 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1137,6 +1137,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
sockc.tsflags = sk->sk_tsflags;
if (msg->msg_controllen) {
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index ea2ae66..a244439 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -519,6 +519,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
ipc6.hlimit = -1;
ipc6.tclass = -1;
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH net-next] tcp_bbr: add a state transition diagram and accompanying comment
From: Neal Cardwell @ 2016-10-27 17:26 UTC (permalink / raw)
To: David Miller
Cc: netdev, Neal Cardwell, Yuchung Cheng, Eric Dumazet,
Soheil Hassas Yeganeh
Document the possible state transitions for a BBR flow, and also add a
prose summary of the state machine, covering the life of a typical BBR
flow.
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
---
net/ipv4/tcp_bbr.c | 32 +++++++++++++++++++++++++++++++-
1 file changed, 31 insertions(+), 1 deletion(-)
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 0ea66c2..b89bce4 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -14,6 +14,36 @@
* observed, or adjust the sending rate if it estimates there is a
* traffic policer, in order to keep the drop rate reasonable.
*
+ * Here is a state transition diagram for BBR:
+ *
+ * |
+ * V
+ * +---> STARTUP ----+
+ * | | |
+ * | V |
+ * | DRAIN ----+
+ * | | |
+ * | V |
+ * +---> PROBE_BW ----+
+ * | ^ | |
+ * | | | |
+ * | +----+ |
+ * | |
+ * +---- PROBE_RTT <--+
+ *
+ * A BBR flow starts in STARTUP, and ramps up its sending rate quickly.
+ * When it estimates the pipe is full, it enters DRAIN to drain the queue.
+ * In steady state a BBR flow only uses PROBE_BW and PROBE_RTT.
+ * A long-lived BBR flow spends the vast majority of its time remaining
+ * (repeatedly) in PROBE_BW, fully probing and utilizing the pipe's bandwidth
+ * in a fair manner, with a small, bounded queue. *If* a flow has been
+ * continuously sending for the entire min_rtt window, and hasn't seen an RTT
+ * sample that matches or decreases its min_rtt estimate for 10 seconds, then
+ * it briefly enters PROBE_RTT to cut inflight to a minimum value to re-probe
+ * the path's two-way propagation delay (min_rtt). When exiting PROBE_RTT, if
+ * we estimated that we reached the full bw of the pipe then we enter PROBE_BW;
+ * otherwise we enter STARTUP to try to fill the pipe.
+ *
* BBR is described in detail in:
* "BBR: Congestion-Based Congestion Control",
* Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh,
@@ -51,7 +81,7 @@ enum bbr_mode {
BBR_STARTUP, /* ramp up sending rate rapidly to fill pipe */
BBR_DRAIN, /* drain any queue created during startup */
BBR_PROBE_BW, /* discover, share bw: pace around estimated bw */
- BBR_PROBE_RTT, /* cut cwnd to min to probe min_rtt */
+ BBR_PROBE_RTT, /* cut inflight to min to probe min_rtt */
};
/* BBR congestion control block */
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* [PATCH net v2 1/2] ibmvnic: Fix releasing of sub-CRQ IRQs in interrupt context
From: Thomas Falcon @ 2016-10-27 17:28 UTC (permalink / raw)
To: netdev
Schedule these XPORT event tasks in the shared workqueue
so that IRQs are not freed in an interrupt context when
sub-CRQs are released.
Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
---
v2: correct warnings by kbuild bot
---
drivers/net/ethernet/ibm/ibmvnic.c | 35 ++++++++++++++++++++++++-----------
drivers/net/ethernet/ibm/ibmvnic.h | 1 +
2 files changed, 25 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 213162d..a922fb9 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -3232,6 +3232,27 @@ static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
spin_unlock_irqrestore(&adapter->inflight_lock, flags);
}
+static void ibmvnic_xport_event(struct work_struct *work)
+{
+ struct ibmvnic_adapter *adapter = container_of(work,
+ struct ibmvnic_adapter,
+ ibmvnic_xport);
+ struct device *dev = &adapter->vdev->dev;
+ long rc;
+
+ ibmvnic_free_inflight(adapter);
+ release_sub_crqs(adapter);
+ if (adapter->migrated) {
+ rc = ibmvnic_reenable_crq_queue(adapter);
+ if (rc)
+ dev_err(dev, "Error after enable rc=%ld\n", rc);
+ adapter->migrated = false;
+ rc = ibmvnic_send_crq_init(adapter);
+ if (rc)
+ dev_err(dev, "Error sending init rc=%ld\n", rc);
+ }
+}
+
static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
struct ibmvnic_adapter *adapter)
{
@@ -3267,15 +3288,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
if (gen_crq->cmd == IBMVNIC_PARTITION_MIGRATED) {
dev_info(dev, "Re-enabling adapter\n");
adapter->migrated = true;
- ibmvnic_free_inflight(adapter);
- release_sub_crqs(adapter);
- rc = ibmvnic_reenable_crq_queue(adapter);
- if (rc)
- dev_err(dev, "Error after enable rc=%ld\n", rc);
- adapter->migrated = false;
- rc = ibmvnic_send_crq_init(adapter);
- if (rc)
- dev_err(dev, "Error sending init rc=%ld\n", rc);
+ schedule_work(&adapter->ibmvnic_xport);
} else if (gen_crq->cmd == IBMVNIC_DEVICE_FAILOVER) {
dev_info(dev, "Backing device failover detected\n");
netif_carrier_off(netdev);
@@ -3284,8 +3297,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
/* The adapter lost the connection */
dev_err(dev, "Virtual Adapter failed (rc=%d)\n",
gen_crq->cmd);
- ibmvnic_free_inflight(adapter);
- release_sub_crqs(adapter);
+ schedule_work(&adapter->ibmvnic_xport);
}
return;
case IBMVNIC_CRQ_CMD_RSP:
@@ -3726,6 +3738,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
SET_NETDEV_DEV(netdev, &dev->dev);
INIT_WORK(&adapter->vnic_crq_init, handle_crq_init_rsp);
+ INIT_WORK(&adapter->ibmvnic_xport, ibmvnic_xport_event);
spin_lock_init(&adapter->stats_lock);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 878e2c0..dd775d9 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -1048,5 +1048,6 @@ struct ibmvnic_adapter {
u8 map_id;
struct work_struct vnic_crq_init;
+ struct work_struct ibmvnic_xport;
bool failover;
};
--
2.7.4
^ permalink raw reply related
* [PATCH net v1 2/2] ibmvnic: Fix missing brackets in init_sub_crq_irqs
From: Thomas Falcon @ 2016-10-27 17:28 UTC (permalink / raw)
To: netdev
In-Reply-To: <1477589332-513-1-git-send-email-tlfalcon@linux.vnet.ibm.com>
Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
---
v1: caught by kbuild bot with -Wmisleading-indentation after
after submitting previous patch
---
drivers/net/ethernet/ibm/ibmvnic.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index a922fb9..5f44c55 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1461,14 +1461,16 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter)
return rc;
req_rx_irq_failed:
- for (j = 0; j < i; j++)
+ for (j = 0; j < i; j++) {
free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]);
irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+ }
i = adapter->req_tx_queues;
req_tx_irq_failed:
- for (j = 0; j < i; j++)
+ for (j = 0; j < i; j++) {
free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+ }
release_sub_crqs_no_irqs(adapter);
return rc;
}
--
2.7.4
^ permalink raw reply related
* Re: [PATCH net-next 1/3] net: core: Add a UID field to struct sock.
From: Eric Dumazet @ 2016-10-27 17:36 UTC (permalink / raw)
To: Lorenzo Colitti; +Cc: netdev, davem, ek, zenczykowski
In-Reply-To: <1477588841-140767-2-git-send-email-lorenzo@google.com>
On Fri, 2016-10-28 at 02:20 +0900, Lorenzo Colitti wrote:
> diff --git a/net/core/sock.c b/net/core/sock.c
> index d8e4532e..831e4e8 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -1570,6 +1570,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
> */
> sk_refcnt_debug_inc(newsk);
> sk_set_socket(newsk, NULL);
> + newsk->sk_uid = sk->sk_uid;
Not sure why this is needed ?
sk_clone_lock() already copies sk to newsk, using sock_copy(newsk, sk);
> newsk->sk_wq = NULL;
>
> if (newsk->sk_prot->sockets_allocated)
> @@ -2460,8 +2461,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
^ permalink raw reply
* Re: [PATCH] net: smsc911x: Synchronize the runtime PM status during system suspend
From: Ulf Hansson @ 2016-10-27 17:47 UTC (permalink / raw)
To: Geert Uytterhoeven, Rafael J. Wysocki
Cc: Alan Stern, Linux PM list, netdev@vger.kernel.org, Len Brown,
Pavel Machek, Kevin Hilman, Lina Iyer, Jon Hunter,
Marek Szyprowski, Linus Walleij, Steve Glendinning
In-Reply-To: <CAMuHMdV_aybcUGu+g-8uNj5k1MtoyJ5s8CfujC+iJrxs7h5eAA@mail.gmail.com>
On 27 October 2016 at 13:54, Geert Uytterhoeven <geert@linux-m68k.org> wrote:
> Hi Ulf,
>
> On Thu, Oct 27, 2016 at 1:53 PM, Ulf Hansson <ulf.hansson@linaro.org> wrote:
>> On 27 October 2016 at 13:41, Geert Uytterhoeven <geert@linux-m68k.org> wrote:
>>> On Thu, Oct 27, 2016 at 1:23 PM, Ulf Hansson <ulf.hansson@linaro.org> wrote:
>>>> The smsc911c driver puts its device into low power state when entering
>>>> system suspend. Although it doesn't update the device's runtime PM status
>>>> to RPM_SUSPENDED, which causes problems for a parent device.
>>>>
>>>> In particular, when the runtime PM status of the parent is requested to be
>>>> updated to RPM_SUSPENDED, the runtime PM core prevent this, because it's
>>>> forbidden to runtime suspend a device, which has an active child.
>>>>
>>>> Fix this by updating the runtime PM status of the smsc911x device to
>>>> RPM_SUSPENDED during system suspend. In system resume, let's reverse that
>>>> action by runtime resuming the device and thus also the parent.
>>>
>>> Thanks for your patch!
>>>
>>> The changelog sounds quite innocent, but this does fix a system crash
>>> during resume from s2ram.
>>>
>>>> Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
>>>> Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
>>>> Cc: Steve Glendinning <steve.glendinning@shawell.net>
>>>> Fixes: 8b1107b85efd ("PM / Runtime: Don't allow to suspend a device with an active child")
>>>
>>> While the abovementioned commit made the problem visible, the root cause
>>> was present before, right?
>>
>> Yes.
>>
>>>> ---
>>>>
>>>> Note that the commit this change fixes is currently queued for 4.10 via
>>>> Rafael's linux-pm tree. So this fix should go via that tree as well.
>>>
>>> Alternatively, this could go in in v4.9 to avoid the problem from ever
>>> appearing in upstream?
>>
>> Makes perfect sense! In that case we should remove the fixes tag.
>>
>> Rafael, can you pick this up for 4.9 rc[n]?
>
> Actually I was thinking about DaveM and the network tree instead.
Well, that would work as well.
Although, perhaps it becomes easier if Rafael deals with this, as it
gives him better control of when below change also can go in.
https://patchwork.kernel.org/patch/9375061
Rafael, please tell what you prefer?
Kind regards
Uffe
^ permalink raw reply
* Re: [PATCH net-next] ibmveth: v1 calculate correct gso_size and set gso_type
From: Thomas Falcon @ 2016-10-27 17:54 UTC (permalink / raw)
To: Eric Dumazet, Jon Maxwell
Cc: jmaxwell, hofrat, linux-kernel, jarod, netdev, paulus, tom,
mleitner, linuxppc-dev, davem
In-Reply-To: <1477582016.7065.212.camel@edumazet-glaptop3.roam.corp.google.com>
On 10/27/2016 10:26 AM, Eric Dumazet wrote:
> On Wed, 2016-10-26 at 11:09 +1100, Jon Maxwell wrote:
>> We recently encountered a bug where a few customers using ibmveth on the
>> same LPAR hit an issue where a TCP session hung when large receive was
>> enabled. Closer analysis revealed that the session was stuck because the
>> one side was advertising a zero window repeatedly.
>>
>> We narrowed this down to the fact the ibmveth driver did not set gso_size
>> which is translated by TCP into the MSS later up the stack. The MSS is
>> used to calculate the TCP window size and as that was abnormally large,
>> it was calculating a zero window, even although the sockets receive buffer
>> was completely empty.
>>
>> We were able to reproduce this and worked with IBM to fix this. Thanks Tom
>> and Marcelo for all your help and review on this.
>>
>> The patch fixes both our internal reproduction tests and our customers tests.
>>
>> Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
>> ---
>> drivers/net/ethernet/ibm/ibmveth.c | 20 ++++++++++++++++++++
>> 1 file changed, 20 insertions(+)
>>
>> diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
>> index 29c05d0..c51717e 100644
>> --- a/drivers/net/ethernet/ibm/ibmveth.c
>> +++ b/drivers/net/ethernet/ibm/ibmveth.c
>> @@ -1182,6 +1182,8 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
>> int frames_processed = 0;
>> unsigned long lpar_rc;
>> struct iphdr *iph;
>> + bool large_packet = 0;
>> + u16 hdr_len = ETH_HLEN + sizeof(struct tcphdr);
>>
>> restart_poll:
>> while (frames_processed < budget) {
>> @@ -1236,10 +1238,28 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
>> iph->check = 0;
>> iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
>> adapter->rx_large_packets++;
>> + large_packet = 1;
>> }
>> }
>> }
>>
>> + if (skb->len > netdev->mtu) {
>> + iph = (struct iphdr *)skb->data;
>> + if (be16_to_cpu(skb->protocol) == ETH_P_IP &&
>> + iph->protocol == IPPROTO_TCP) {
>> + hdr_len += sizeof(struct iphdr);
>> + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
>> + skb_shinfo(skb)->gso_size = netdev->mtu - hdr_len;
>> + } else if (be16_to_cpu(skb->protocol) == ETH_P_IPV6 &&
>> + iph->protocol == IPPROTO_TCP) {
>> + hdr_len += sizeof(struct ipv6hdr);
>> + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
>> + skb_shinfo(skb)->gso_size = netdev->mtu - hdr_len;
>> + }
>> + if (!large_packet)
>> + adapter->rx_large_packets++;
>> + }
>> +
>>
> This might break forwarding and PMTU discovery.
>
> You force gso_size to device mtu, regardless of real MSS used by the TCP
> sender.
>
> Don't you have the MSS provided in RX descriptor, instead of guessing
> the value ?
>
>
>
The MSS is not always available unfortunately, so this is the best solution there is at the moment.
^ permalink raw reply
* Re: [PATCH net-next] ibmveth: v1 calculate correct gso_size and set gso_type
From: Eric Dumazet @ 2016-10-27 18:08 UTC (permalink / raw)
To: Thomas Falcon
Cc: Jon Maxwell, jmaxwell, hofrat, linux-kernel, jarod, netdev,
paulus, tom, mleitner, linuxppc-dev, davem
In-Reply-To: <7b97bb2a-63ed-7dde-9a2f-e390c67de382@linux.vnet.ibm.com>
On Thu, 2016-10-27 at 12:54 -0500, Thomas Falcon wrote:
> On 10/27/2016 10:26 AM, Eric Dumazet wrote:
> > On Wed, 2016-10-26 at 11:09 +1100, Jon Maxwell wrote:
> >> We recently encountered a bug where a few customers using ibmveth on the
> >> same LPAR hit an issue where a TCP session hung when large receive was
> >> enabled. Closer analysis revealed that the session was stuck because the
> >> one side was advertising a zero window repeatedly.
> >>
> >> We narrowed this down to the fact the ibmveth driver did not set gso_size
> >> which is translated by TCP into the MSS later up the stack. The MSS is
> >> used to calculate the TCP window size and as that was abnormally large,
> >> it was calculating a zero window, even although the sockets receive buffer
> >> was completely empty.
> >>
> >> We were able to reproduce this and worked with IBM to fix this. Thanks Tom
> >> and Marcelo for all your help and review on this.
> >>
> >> The patch fixes both our internal reproduction tests and our customers tests.
> >>
> >> Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
> >> ---
> >> drivers/net/ethernet/ibm/ibmveth.c | 20 ++++++++++++++++++++
> >> 1 file changed, 20 insertions(+)
> >>
> >> diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
> >> index 29c05d0..c51717e 100644
> >> --- a/drivers/net/ethernet/ibm/ibmveth.c
> >> +++ b/drivers/net/ethernet/ibm/ibmveth.c
> >> @@ -1182,6 +1182,8 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
> >> int frames_processed = 0;
> >> unsigned long lpar_rc;
> >> struct iphdr *iph;
> >> + bool large_packet = 0;
> >> + u16 hdr_len = ETH_HLEN + sizeof(struct tcphdr);
> >>
> >> restart_poll:
> >> while (frames_processed < budget) {
> >> @@ -1236,10 +1238,28 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
> >> iph->check = 0;
> >> iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
> >> adapter->rx_large_packets++;
> >> + large_packet = 1;
> >> }
> >> }
> >> }
> >>
> >> + if (skb->len > netdev->mtu) {
> >> + iph = (struct iphdr *)skb->data;
> >> + if (be16_to_cpu(skb->protocol) == ETH_P_IP &&
> >> + iph->protocol == IPPROTO_TCP) {
> >> + hdr_len += sizeof(struct iphdr);
> >> + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
> >> + skb_shinfo(skb)->gso_size = netdev->mtu - hdr_len;
> >> + } else if (be16_to_cpu(skb->protocol) == ETH_P_IPV6 &&
> >> + iph->protocol == IPPROTO_TCP) {
> >> + hdr_len += sizeof(struct ipv6hdr);
> >> + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
> >> + skb_shinfo(skb)->gso_size = netdev->mtu - hdr_len;
> >> + }
> >> + if (!large_packet)
> >> + adapter->rx_large_packets++;
> >> + }
> >> +
> >>
> > This might break forwarding and PMTU discovery.
> >
> > You force gso_size to device mtu, regardless of real MSS used by the TCP
> > sender.
> >
> > Don't you have the MSS provided in RX descriptor, instead of guessing
> > the value ?
> >
> >
> >
> The MSS is not always available unfortunately, so this is the best solution there is at the moment.
Hmm... then what about skb_shinfo(skb)->gso_segs ?
ip_rcv() for example has :
__IP_ADD_STATS(net,
IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
Also prefer : (skb->protocol == htons(ETH_P_IP)) tests
And the ipv6 test is wrong :
} else if (be16_to_cpu(skb->protocol) == ETH_P_IPV6 &&
iph->protocol == IPPROTO_TCP) {
Since iph is a pointer to ipv4 iphdr .
^ permalink raw reply
* Re: Pure polling mode for netdevices
From: Zach Brown @ 2016-10-27 18:29 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev, linux-kernel, linux-rt-users
In-Reply-To: <1477075306.7065.86.camel@edumazet-glaptop3.roam.corp.google.com>
On Fri, Oct 21, 2016 at 11:41:46AM -0700, Eric Dumazet wrote:
> On Fri, 2016-10-21 at 13:03 -0500, Zach Brown wrote:
> > Is there a way to get NAPI to poll all the time?
> > Or just any way to get netdevices to use only polling and no interrupts?
> >
> > We have some rt targets where the jitter can be improved by disabling
> > interrupts and using just polling. In these cases we're okay with the
> > performance downsides that come with polling.
> >
> > In particular we already have an implementation for the cadence macb driver
> > that does only polling mode and have verified that it improves the
> > jitter.
> >
> > We're hoping for a more general existing solution or at the very least a
> > solution that would be accepted upstream. Any thoughts?
>
> This is not yet done, although you could use busy poll infrastructure to
> get this without a kernel change.
>
> Open as many TCP flows are necessary to traverse all the queues you care
> about, then loop on recvmsg() to trigger NAPI polling.
>
>
I looked into the busy poll infrastructure and I don't think it meets our
needs. We're not interested in minimizing the latency of the ethernet device,
but rather diminishing if not eliminating the system jitter cause by ethernet
interrupts. Not to mention that some interfaces like macb don't provide a lot
of the config options to make busy polling really work well. For example,
interrupt coalescing configuration.
I was thinking more along the lines of an extenstion to the NAPI interface that
drivers can opt into that allows them to enter NAPI polling mode and never
leave when configured to do so.
^ permalink raw reply
* [patch net-next] rocker: set physical device for port netdevice
From: Jiri Pirko @ 2016-10-27 12:31 UTC (permalink / raw)
To: netdev; +Cc: davem
From: Jiri Pirko <jiri@mellanox.com>
Do this so the sysfs has "device" link correctly set.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
drivers/net/ethernet/rocker/rocker_main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 2e81b70..6d96a0c 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2542,6 +2542,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
dev = alloc_etherdev(sizeof(struct rocker_port));
if (!dev)
return -ENOMEM;
+ SET_NETDEV_DEV(dev, &pdev->dev);
rocker_port = netdev_priv(dev);
rocker_port->dev = dev;
rocker_port->rocker = rocker;
--
2.5.5
^ permalink raw reply related
* RE: [bnx2] [Regression 4.8] Driver loading fails without firmware
From: Mody, Rasesh @ 2016-10-27 18:16 UTC (permalink / raw)
To: Paul Menzel, Baoquan He
Cc: dvteam@molgen.mpg.de, Dept-HSGLinuxNICDev@qlogic.com,
David S. Miller, netdev@vger.kernel.org
In-Reply-To: <f055c961-58ca-ea81-46d8-610fa055cce8@molgen.mpg.de>
> From: dept_hsg_linux_nic_dev-bounces@qlclistserver.qlogic.com
> [mailto:dept_hsg_linux_nic_dev-bounces@qlclistserver.qlogic.com] On
> Behalf Of Paul Menzel
>
> Dear Baoquan,
>
>
> On 10/26/16 14:00, Baoquan He wrote:
>
> > On 10/26/16 at 12:31pm, Paul Menzel wrote:
> >>>> dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | @@
> >>>> -8607,6 +8608,7 @@ bnx2_init_one(struct pci_dev *pdev, const struct
> >>>> pci_device_id *ent)
> >>>> return 0;
> >>>>
> >>>> error:
> >>>> + bnx2_release_firmware(bp);
> >>>> pci_iounmap(pdev, bp->regview);
> >>>> pci_release_regions(pdev);
> >>>> pci_disable_device(pdev);
> >>
> >> Baoquan, could you please fix this regression. My suggestion is, that
> >> you add the old code back, but check if the firmware has been loaded.
> >> If it hasn’t, load it again.
> >>
> >> That way, people can update their Linux kernel, and it continues
> >> working without changing the initramfs, or anything else.
> >
> > I saw your mail but I am also not familiar with bnx2 driver. As the
> > commit log says I just tried to make bnx2 driver reset itself earlier.
> >
> > So you did a git bisect and found this commit caused the regression,
> > right? If yes, and network developers have no action, I will look into
> > the code and see if I have idea to fix it.
>
> Well, I looked through the commits and found that one, which would explain
> the changed behavior.
>
> To be sure, and to follow your request, I took Linux 4.8.4 and reverted your
> commit (attached). Then I deleted the firmware again from the initramfs,
> and rebooted. The devices showed up just fine as before.
Thanks Paul!
Acked-by: Rasesh Mody <Rasesh.Mody@cavium.com>
> So to summarize, the commit is indeed the culprit.
>
> Thank you for looking into this.
>
>
> Kind regards,
>
> Paul
^ permalink raw reply
* [PATCH net 1/2] vxlan: avoid using stale vxlan socket.
From: Pravin B Shelar @ 2016-10-27 18:51 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar
When vxlan device is closed vxlan socket is freed. This
operation can race with vxlan-xmit function which
dereferences vxlan socket. Following patch uses RCU
mechanism to avoid this situation.
Signed-off-by: Pravin B Shelar <pshelar@ovn.org>
---
drivers/net/vxlan.c | 80 +++++++++++++++++++++++++++++++++--------------------
include/net/vxlan.h | 4 +--
2 files changed, 52 insertions(+), 32 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index c1639a3..0bc1dcc 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -943,17 +943,20 @@ static bool vxlan_snoop(struct net_device *dev,
static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
{
struct vxlan_dev *vxlan;
+ struct vxlan_sock *sock4;
+ struct vxlan_sock *sock6 = NULL;
unsigned short family = dev->default_dst.remote_ip.sa.sa_family;
+ sock4 = rtnl_dereference(dev->vn4_sock);
+
/* The vxlan_sock is only used by dev, leaving group has
* no effect on other vxlan devices.
*/
- if (family == AF_INET && dev->vn4_sock &&
- atomic_read(&dev->vn4_sock->refcnt) == 1)
+ if (family == AF_INET && sock4 && atomic_read(&sock4->refcnt) == 1)
return false;
#if IS_ENABLED(CONFIG_IPV6)
- if (family == AF_INET6 && dev->vn6_sock &&
- atomic_read(&dev->vn6_sock->refcnt) == 1)
+ sock6 = rtnl_dereference(dev->vn6_sock);
+ if (family == AF_INET6 && sock6 && atomic_read(&sock6->refcnt) == 1)
return false;
#endif
@@ -961,10 +964,12 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
if (!netif_running(vxlan->dev) || vxlan == dev)
continue;
- if (family == AF_INET && vxlan->vn4_sock != dev->vn4_sock)
+ if (family == AF_INET &&
+ rtnl_dereference(vxlan->vn4_sock) != sock4)
continue;
#if IS_ENABLED(CONFIG_IPV6)
- if (family == AF_INET6 && vxlan->vn6_sock != dev->vn6_sock)
+ if (family == AF_INET6 &&
+ rtnl_dereference(vxlan->vn6_sock) != sock6)
continue;
#endif
@@ -1005,22 +1010,25 @@ static bool __vxlan_sock_release_prep(struct vxlan_sock *vs)
static void vxlan_sock_release(struct vxlan_dev *vxlan)
{
- bool ipv4 = __vxlan_sock_release_prep(vxlan->vn4_sock);
+ struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
#if IS_ENABLED(CONFIG_IPV6)
- bool ipv6 = __vxlan_sock_release_prep(vxlan->vn6_sock);
+ struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);
+
+ rcu_assign_pointer(vxlan->vn6_sock, NULL);
#endif
+ rcu_assign_pointer(vxlan->vn4_sock, NULL);
synchronize_net();
- if (ipv4) {
- udp_tunnel_sock_release(vxlan->vn4_sock->sock);
- kfree(vxlan->vn4_sock);
+ if (__vxlan_sock_release_prep(sock4)) {
+ udp_tunnel_sock_release(sock4->sock);
+ kfree(sock4);
}
#if IS_ENABLED(CONFIG_IPV6)
- if (ipv6) {
- udp_tunnel_sock_release(vxlan->vn6_sock->sock);
- kfree(vxlan->vn6_sock);
+ if (__vxlan_sock_release_prep(sock6)) {
+ udp_tunnel_sock_release(sock6->sock);
+ kfree(sock6);
}
#endif
}
@@ -1036,18 +1044,21 @@ static int vxlan_igmp_join(struct vxlan_dev *vxlan)
int ret = -EINVAL;
if (ip->sa.sa_family == AF_INET) {
+ struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
.imr_ifindex = ifindex,
};
- sk = vxlan->vn4_sock->sock->sk;
+ sk = sock4->sock->sk;
lock_sock(sk);
ret = ip_mc_join_group(sk, &mreq);
release_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- sk = vxlan->vn6_sock->sock->sk;
+ struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);
+
+ sk = sock6->sock->sk;
lock_sock(sk);
ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
&ip->sin6.sin6_addr);
@@ -1067,18 +1078,21 @@ static int vxlan_igmp_leave(struct vxlan_dev *vxlan)
int ret = -EINVAL;
if (ip->sa.sa_family == AF_INET) {
+ struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
.imr_ifindex = ifindex,
};
- sk = vxlan->vn4_sock->sock->sk;
+ sk = sock4->sock->sk;
lock_sock(sk);
ret = ip_mc_leave_group(sk, &mreq);
release_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- sk = vxlan->vn6_sock->sock->sk;
+ struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);
+
+ sk = sock6->sock->sk;
lock_sock(sk);
ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
&ip->sin6.sin6_addr);
@@ -1828,11 +1842,15 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
struct dst_cache *dst_cache,
const struct ip_tunnel_info *info)
{
+ struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct dst_entry *ndst;
struct flowi6 fl6;
int err;
+ if (!sock6)
+ return ERR_PTR(-EIO);
+
if (tos && !info)
use_cache = false;
if (use_cache) {
@@ -1850,7 +1868,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
fl6.flowi6_proto = IPPROTO_UDP;
err = ipv6_stub->ipv6_dst_lookup(vxlan->net,
- vxlan->vn6_sock->sock->sk,
+ sock6->sock->sk,
&ndst, &fl6);
if (err < 0)
return ERR_PTR(err);
@@ -1995,9 +2013,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
}
if (dst->sa.sa_family == AF_INET) {
- if (!vxlan->vn4_sock)
+ struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
+
+ if (!sock4)
goto drop;
- sk = vxlan->vn4_sock->sock->sk;
+ sk = sock4->sock->sk;
rt = vxlan_get_route(vxlan, skb,
rdst ? rdst->remote_ifindex : 0, tos,
@@ -2050,12 +2070,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
src_port, dst_port, xnet, !udp_sum);
#if IS_ENABLED(CONFIG_IPV6)
} else {
+ struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
struct dst_entry *ndst;
u32 rt6i_flags;
- if (!vxlan->vn6_sock)
+ if (!sock6)
goto drop;
- sk = vxlan->vn6_sock->sock->sk;
+ sk = sock6->sock->sk;
ndst = vxlan6_get_route(vxlan, skb,
rdst ? rdst->remote_ifindex : 0, tos,
@@ -2415,9 +2436,10 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
dport = info->key.tp_dst ? : vxlan->cfg.dst_port;
if (ip_tunnel_info_af(info) == AF_INET) {
+ struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
struct rtable *rt;
- if (!vxlan->vn4_sock)
+ if (!sock4)
return -EINVAL;
rt = vxlan_get_route(vxlan, skb, 0, info->key.tos,
info->key.u.ipv4.dst,
@@ -2429,8 +2451,6 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
#if IS_ENABLED(CONFIG_IPV6)
struct dst_entry *ndst;
- if (!vxlan->vn6_sock)
- return -EINVAL;
ndst = vxlan6_get_route(vxlan, skb, 0, info->key.tos,
info->key.label, &info->key.u.ipv6.dst,
&info->key.u.ipv6.src, NULL, info);
@@ -2740,10 +2760,10 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
return PTR_ERR(vs);
#if IS_ENABLED(CONFIG_IPV6)
if (ipv6)
- vxlan->vn6_sock = vs;
+ rcu_assign_pointer(vxlan->vn6_sock, vs);
else
#endif
- vxlan->vn4_sock = vs;
+ rcu_assign_pointer(vxlan->vn4_sock, vs);
vxlan_vs_add_dev(vs, vxlan);
return 0;
}
@@ -2754,9 +2774,9 @@ static int vxlan_sock_add(struct vxlan_dev *vxlan)
bool metadata = vxlan->flags & VXLAN_F_COLLECT_METADATA;
int ret = 0;
- vxlan->vn4_sock = NULL;
+ rcu_assign_pointer(vxlan->vn4_sock, NULL);
#if IS_ENABLED(CONFIG_IPV6)
- vxlan->vn6_sock = NULL;
+ rcu_assign_pointer(vxlan->vn6_sock, NULL);
if (ipv6 || metadata)
ret = __vxlan_sock_add(vxlan, true);
#endif
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0255613..308adc4 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -225,9 +225,9 @@ struct vxlan_config {
struct vxlan_dev {
struct hlist_node hlist; /* vni hash table */
struct list_head next; /* vxlan's per namespace list */
- struct vxlan_sock *vn4_sock; /* listening socket for IPv4 */
+ struct vxlan_sock __rcu *vn4_sock; /* listening socket for IPv4 */
#if IS_ENABLED(CONFIG_IPV6)
- struct vxlan_sock *vn6_sock; /* listening socket for IPv6 */
+ struct vxlan_sock __rcu *vn6_sock; /* listening socket for IPv6 */
#endif
struct net_device *dev;
struct net *net; /* netns for packet i/o */
--
1.9.1
^ permalink raw reply related
* [PATCH net 2/2] geneve: avoid using stale geneve socket.
From: Pravin B Shelar @ 2016-10-27 18:51 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar
In-Reply-To: <1477594316-118234-1-git-send-email-pshelar@ovn.org>
This patch is similar to earlier vxlan patch.
Geneve device close operation frees geneve socket. This
operation can race with geneve-xmit function which
dereferences geneve socket. Following patch uses RCU
mechanism to avoid this situation.
Signed-off-by: Pravin B Shelar <pshelar@ovn.org>
---
drivers/net/geneve.c | 45 ++++++++++++++++++++++++++++++++++-----------
1 file changed, 34 insertions(+), 11 deletions(-)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 16af1ce..42edd7b 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -58,9 +58,9 @@ struct geneve_dev {
struct hlist_node hlist; /* vni hash table */
struct net *net; /* netns for packet i/o */
struct net_device *dev; /* netdev for geneve tunnel */
- struct geneve_sock *sock4; /* IPv4 socket used for geneve tunnel */
+ struct geneve_sock __rcu *sock4; /* IPv4 socket used for geneve tunnel */
#if IS_ENABLED(CONFIG_IPV6)
- struct geneve_sock *sock6; /* IPv6 socket used for geneve tunnel */
+ struct geneve_sock __rcu *sock6; /* IPv6 socket used for geneve tunnel */
#endif
u8 vni[3]; /* virtual network ID for tunnel */
u8 ttl; /* TTL override */
@@ -543,9 +543,19 @@ static void __geneve_sock_release(struct geneve_sock *gs)
static void geneve_sock_release(struct geneve_dev *geneve)
{
- __geneve_sock_release(geneve->sock4);
+ struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4);
#if IS_ENABLED(CONFIG_IPV6)
- __geneve_sock_release(geneve->sock6);
+ struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6);
+
+ rcu_assign_pointer(geneve->sock6, NULL);
+#endif
+
+ rcu_assign_pointer(geneve->sock4, NULL);
+ synchronize_net();
+
+ __geneve_sock_release(gs4);
+#if IS_ENABLED(CONFIG_IPV6)
+ __geneve_sock_release(gs6);
#endif
}
@@ -586,10 +596,10 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
gs->flags = geneve->flags;
#if IS_ENABLED(CONFIG_IPV6)
if (ipv6)
- geneve->sock6 = gs;
+ rcu_assign_pointer(geneve->sock6, gs);
else
#endif
- geneve->sock4 = gs;
+ rcu_assign_pointer(geneve->sock4, gs);
hash = geneve_net_vni_hash(geneve->vni);
hlist_add_head_rcu(&geneve->hlist, &gs->vni_list[hash]);
@@ -603,9 +613,7 @@ static int geneve_open(struct net_device *dev)
bool metadata = geneve->collect_md;
int ret = 0;
- geneve->sock4 = NULL;
#if IS_ENABLED(CONFIG_IPV6)
- geneve->sock6 = NULL;
if (ipv6 || metadata)
ret = geneve_sock_add(geneve, true);
#endif
@@ -720,6 +728,9 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
struct rtable *rt = NULL;
__u8 tos;
+ if (!rcu_dereference(geneve->sock4))
+ return ERR_PTR(-EIO);
+
memset(fl4, 0, sizeof(*fl4));
fl4->flowi4_mark = skb->mark;
fl4->flowi4_proto = IPPROTO_UDP;
@@ -772,11 +783,15 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
{
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
- struct geneve_sock *gs6 = geneve->sock6;
struct dst_entry *dst = NULL;
struct dst_cache *dst_cache;
+ struct geneve_sock *gs6;
__u8 prio;
+ gs6 = rcu_dereference(geneve->sock6);
+ if (!gs6)
+ return ERR_PTR(-EIO);
+
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_mark = skb->mark;
fl6->flowi6_proto = IPPROTO_UDP;
@@ -842,7 +857,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct ip_tunnel_info *info)
{
struct geneve_dev *geneve = netdev_priv(dev);
- struct geneve_sock *gs4 = geneve->sock4;
+ struct geneve_sock *gs4;
struct rtable *rt = NULL;
const struct iphdr *iip; /* interior IP header */
int err = -EINVAL;
@@ -853,6 +868,10 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
u32 flags = geneve->flags;
+ gs4 = rcu_dereference(geneve->sock4);
+ if (!gs4)
+ goto tx_error;
+
if (geneve->collect_md) {
if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
netdev_dbg(dev, "no tunnel metadata\n");
@@ -932,9 +951,9 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct ip_tunnel_info *info)
{
struct geneve_dev *geneve = netdev_priv(dev);
- struct geneve_sock *gs6 = geneve->sock6;
struct dst_entry *dst = NULL;
const struct iphdr *iip; /* interior IP header */
+ struct geneve_sock *gs6;
int err = -EINVAL;
struct flowi6 fl6;
__u8 prio, ttl;
@@ -943,6 +962,10 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
u32 flags = geneve->flags;
+ gs6 = rcu_dereference(geneve->sock6);
+ if (!gs6)
+ goto tx_error;
+
if (geneve->collect_md) {
if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
netdev_dbg(dev, "no tunnel metadata\n");
--
1.9.1
^ permalink raw reply related
* Re: [PATCHv2 iproute2 net-next] tc: m_mirred: Fix parsing of 'index' optional argument
From: Shmulik Ladkani @ 2016-10-27 19:00 UTC (permalink / raw)
To: Phil Sutter, Stephen Hemminger, Jamal Hadi Salim; +Cc: netdev
In-Reply-To: <20161027145643.GS5640@orbyte.nwl.cc>
Hi,
On Thu, 27 Oct 2016 16:56:43 +0200 Phil Sutter <phil@nwl.cc> wrote:
> > Actual code, since first committed, attempts to parse "index" as 1st
> > argument (without success), see parse_mirred():
> >
> > if (matches(*argv, "egress") == 0 || matches(*argv, "index") == 0) {
> > int ret = parse_egress(a, &argc, &argv, tca_id, n);
>
> Oh, I missed that! But to me this looks like the author wanted to avoid
> erroring out with "mirred option not supported index" in case of missing
> 'egress' keyword.
Could be; Not that it matters much, but evidence in parse_egress() shows
that it DOES try to parse and store "index" EVEN if no "egress" seen YET.
> Yeah, I'd go with least effort approach, i.e. not adding any additional
> flexibility in arg parsing. Since the docs never stated otherwise, I
> don't think it was a real issue for users.
Sure. It never really worked ;)
If we go that way, then some code in parse_direction needs to be
eliminated/restructured; So we'll end up with:
- less code in parse_direction
- not adding any additional flexibility in arg parsing
- bigger diff than suggested
Stephen, Jamal, do you have any preference here?
^ permalink raw reply
* [PATCH 00/17] pull request for net-next: batman-adv 2016-10-27
From: Simon Wunderlich @ 2016-10-27 19:01 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: netdev-u79uwXL29TY76Z2rM5mHXA,
b.a.t.m.a.n-ZwoEplunGu2X36UT3dwllkB+6BGkLq7r
Hi David,
this is our first feature pull request for batman-adv (mostly containing
code cleanup stuff), there are at least two more to come.
Please pull or let me know of any problem!
Thank you,
Simon
The following changes since commit 29fbff8698fc0ac1a1d74584b258e0bf18b469f9:
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net (2016-10-13 21:40:23 -0700)
are available in the git repository at:
git://git.open-mesh.org/linux-merge.git tags/batadv-next-for-davem-20161027
for you to fetch changes up to 4c7da0f6dbcde2431d773ce03cde5e7abede54e0:
batman-adv: Avoid precedence issues in macros (2016-10-19 08:37:54 +0200)
----------------------------------------------------------------
This code cleanup patchset includes the following changes (chronological
order):
- bump version strings, by Simon Wunderlich
- README updates/clean up, by Sven Eckelmann (4 patches)
- Code clean up and restructuring by Sven Eckelmann (2 patches)
- Kerneldoc fix in forw_packet structure, by Linus Luessing
- Remove unused argument in dbg_arp, by Antonio Quartulli
- Add support to build batman-adv without wireless, by Linus Luessing
- Restructure error handling for is_ap_isolated, by Markus Elfring
- Remove unused initialization in various functions, by Sven Eckelmann
- Use better names for fragment and gateway list heads, by Sven
Eckelmann (2 patches)
- Convert to octal permissions for files, by Sven Eckelmann
- Avoid precedence issues for some macros, by Sven Eckelmann
----------------------------------------------------------------
Antonio Quartulli (1):
batman-adv: remove unsed argument from batadv_dbg_arp() function
Linus Lüssing (2):
batman-adv: fix batadv_forw_packet kerneldoc for list attribute
batman-adv: Allow selecting BATMAN V if CFG80211 is not built
Markus Elfring (1):
batman-adv: Less function calls in batadv_is_ap_isolated() after error detection
Simon Wunderlich (1):
batman-adv: Start new development cycle
Sven Eckelmann (12):
batman-adv: Add B.A.T.M.A.N. V sysfs files to README
batman-adv: Add network_coding and mcast sysfs files to README
batman-adv: Add dat, mcast, nc and neighbor debugfs files to README
batman-adv: Document new nc, mcast and tpmeter log levels
batman-adv: Remove unused function batadv_hash_delete
batman-adv: Move batadv_sum_counter to soft-interface.c
batman-adv: Remove unused batadv_icmp_user_cmd_type
batman-adv: Remove needless init of variables on stack
batman-adv: Use proper name for fragments list head
batman-adv: Use proper name for gateway list head
batman-adv: Use octal permissions instead of macros
batman-adv: Avoid precedence issues in macros
Documentation/networking/batman-adv.txt | 35 ++++++++++++----------
net/batman-adv/Kconfig | 2 +-
net/batman-adv/bat_iv_ogm.c | 6 ++--
net/batman-adv/bat_v.c | 8 ++---
net/batman-adv/bat_v_ogm.c | 4 +--
net/batman-adv/debugfs.c | 26 ++++++++--------
net/batman-adv/distributed-arp-table.c | 17 ++++-------
net/batman-adv/fragmentation.c | 18 +++++------
net/batman-adv/fragmentation.h | 2 +-
net/batman-adv/gateway_client.c | 9 +++---
net/batman-adv/hash.h | 30 -------------------
net/batman-adv/icmp_socket.c | 5 ++--
net/batman-adv/log.c | 4 +--
net/batman-adv/log.h | 12 ++++----
net/batman-adv/main.c | 2 +-
net/batman-adv/main.h | 27 ++---------------
net/batman-adv/network-coding.c | 8 ++---
net/batman-adv/originator.c | 10 +++----
net/batman-adv/packet.h | 12 +-------
net/batman-adv/send.c | 2 +-
net/batman-adv/soft-interface.c | 21 +++++++++++++
net/batman-adv/sysfs.c | 53 ++++++++++++++-------------------
net/batman-adv/translation-table.c | 25 +++++++---------
net/batman-adv/types.h | 16 +++++-----
24 files changed, 149 insertions(+), 205 deletions(-)
^ permalink raw reply
* [PATCH 01/17] batman-adv: Start new development cycle
From: Simon Wunderlich @ 2016-10-27 19:01 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: netdev-u79uwXL29TY76Z2rM5mHXA,
b.a.t.m.a.n-ZwoEplunGu2X36UT3dwllkB+6BGkLq7r
In-Reply-To: <20161027190150.7880-1-sw-2YrNx6rUIHYiY0qSoAWiAoQuADTiUCJX@public.gmane.org>
Signed-off-by: Simon Wunderlich <sw-2YrNx6rUIHYiY0qSoAWiAoQuADTiUCJX@public.gmane.org>
---
net/batman-adv/main.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 09af21e..8b0979b 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2016.4"
+#define BATADV_SOURCE_VERSION "2016.5"
#endif
/* B.A.T.M.A.N. parameters */
--
2.10.1
^ permalink raw reply related
* [PATCH 02/17] batman-adv: Add B.A.T.M.A.N. V sysfs files to README
From: Simon Wunderlich @ 2016-10-27 19:01 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: netdev-u79uwXL29TY76Z2rM5mHXA,
b.a.t.m.a.n-ZwoEplunGu2X36UT3dwllkB+6BGkLq7r
In-Reply-To: <20161027190150.7880-1-sw-2YrNx6rUIHYiY0qSoAWiAoQuADTiUCJX@public.gmane.org>
From: Sven Eckelmann <sven-KaDOiPu9UxWEi8DpZVb4nw@public.gmane.org>
Signed-off-by: Sven Eckelmann <sven-KaDOiPu9UxWEi8DpZVb4nw@public.gmane.org>
Signed-off-by: Simon Wunderlich <sw-2YrNx6rUIHYiY0qSoAWiAoQuADTiUCJX@public.gmane.org>
---
Documentation/networking/batman-adv.txt | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt
index 8a8d3d9..d414e60 100644
--- a/Documentation/networking/batman-adv.txt
+++ b/Documentation/networking/batman-adv.txt
@@ -32,7 +32,7 @@ compatible interfaces. Once found, it will create subfolders in
the /sys directories of each supported interface, e.g.
# ls /sys/class/net/eth0/batman_adv/
-# iface_status mesh_iface
+# elp_interval iface_status mesh_iface throughput_override
If an interface does not have the "batman_adv" subfolder it prob-
ably is not supported. Not supported interfaces are: loopback,
--
2.10.1
^ permalink raw reply related
* [PATCH 03/17] batman-adv: Add network_coding and mcast sysfs files to README
From: Simon Wunderlich @ 2016-10-27 19:01 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: netdev-u79uwXL29TY76Z2rM5mHXA,
b.a.t.m.a.n-ZwoEplunGu2X36UT3dwllkB+6BGkLq7r
In-Reply-To: <20161027190150.7880-1-sw-2YrNx6rUIHYiY0qSoAWiAoQuADTiUCJX@public.gmane.org>
From: Sven Eckelmann <sven-KaDOiPu9UxWEi8DpZVb4nw@public.gmane.org>
Signed-off-by: Sven Eckelmann <sven-KaDOiPu9UxWEi8DpZVb4nw@public.gmane.org>
Signed-off-by: Simon Wunderlich <sw-2YrNx6rUIHYiY0qSoAWiAoQuADTiUCJX@public.gmane.org>
---
Documentation/networking/batman-adv.txt | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt
index d414e60..8afa991 100644
--- a/Documentation/networking/batman-adv.txt
+++ b/Documentation/networking/batman-adv.txt
@@ -71,10 +71,11 @@ All mesh wide settings can be found in batman's own interface
folder:
# ls /sys/class/net/bat0/mesh/
-#aggregated_ogms distributed_arp_table gw_sel_class orig_interval
-#ap_isolation fragmentation hop_penalty routing_algo
-#bonding gw_bandwidth isolation_mark vlan0
-#bridge_loop_avoidance gw_mode log_level
+# aggregated_ogms fragmentation isolation_mark routing_algo
+# ap_isolation gw_bandwidth log_level vlan0
+# bonding gw_mode multicast_mode
+# bridge_loop_avoidance gw_sel_class network_coding
+# distributed_arp_table hop_penalty orig_interval
There is a special folder for debugging information:
--
2.10.1
^ permalink raw reply related
* [PATCH 06/17] batman-adv: Remove unused function batadv_hash_delete
From: Simon Wunderlich @ 2016-10-27 19:01 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: netdev-u79uwXL29TY76Z2rM5mHXA,
b.a.t.m.a.n-ZwoEplunGu2X36UT3dwllkB+6BGkLq7r
In-Reply-To: <20161027190150.7880-1-sw-2YrNx6rUIHYiY0qSoAWiAoQuADTiUCJX@public.gmane.org>
From: Sven Eckelmann <sven-KaDOiPu9UxWEi8DpZVb4nw@public.gmane.org>
Signed-off-by: Sven Eckelmann <sven-KaDOiPu9UxWEi8DpZVb4nw@public.gmane.org>
Signed-off-by: Simon Wunderlich <sw-2YrNx6rUIHYiY0qSoAWiAoQuADTiUCJX@public.gmane.org>
---
net/batman-adv/hash.h | 30 ------------------------------
1 file changed, 30 deletions(-)
diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h
index cbbf870..557a704 100644
--- a/net/batman-adv/hash.h
+++ b/net/batman-adv/hash.h
@@ -61,36 +61,6 @@ void batadv_hash_set_lock_class(struct batadv_hashtable *hash,
/* free only the hashtable and the hash itself. */
void batadv_hash_destroy(struct batadv_hashtable *hash);
-/* remove the hash structure. if hashdata_free_cb != NULL, this function will be
- * called to remove the elements inside of the hash. if you don't remove the
- * elements, memory might be leaked.
- */
-static inline void batadv_hash_delete(struct batadv_hashtable *hash,
- batadv_hashdata_free_cb free_cb,
- void *arg)
-{
- struct hlist_head *head;
- struct hlist_node *node, *node_tmp;
- spinlock_t *list_lock; /* spinlock to protect write access */
- u32 i;
-
- for (i = 0; i < hash->size; i++) {
- head = &hash->table[i];
- list_lock = &hash->list_locks[i];
-
- spin_lock_bh(list_lock);
- hlist_for_each_safe(node, node_tmp, head) {
- hlist_del_rcu(node);
-
- if (free_cb)
- free_cb(node, arg);
- }
- spin_unlock_bh(list_lock);
- }
-
- batadv_hash_destroy(hash);
-}
-
/**
* batadv_hash_add - adds data to the hashtable
* @hash: storage hash table
--
2.10.1
^ permalink raw reply related
* [PATCH 04/17] batman-adv: Add dat, mcast, nc and neighbor debugfs files to README
From: Simon Wunderlich @ 2016-10-27 19:01 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20161027190150.7880-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
Documentation/networking/batman-adv.txt | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt
index 8afa991..a918131 100644
--- a/Documentation/networking/batman-adv.txt
+++ b/Documentation/networking/batman-adv.txt
@@ -80,9 +80,10 @@ folder:
There is a special folder for debugging information:
# ls /sys/kernel/debug/batman_adv/bat0/
-# bla_backbone_table log transtable_global
-# bla_claim_table originators transtable_local
-# gateways socket
+# bla_backbone_table log neighbors transtable_local
+# bla_claim_table mcast_flags originators
+# dat_cache nc socket
+# gateways nc_nodes transtable_global
Some of the files contain all sort of status information regard-
ing the mesh network. For example, you can view the table of
--
2.10.1
^ permalink raw reply related
* [PATCH 08/17] batman-adv: Remove unused batadv_icmp_user_cmd_type
From: Simon Wunderlich @ 2016-10-27 19:01 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20161027190150.7880-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
net/batman-adv/packet.h | 10 ----------
1 file changed, 10 deletions(-)
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 6afc0b8..d2e9bbd 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -252,16 +252,6 @@ struct batadv_elp_packet {
#define BATADV_ELP_HLEN sizeof(struct batadv_elp_packet)
/**
- * enum batadv_icmp_user_cmd_type - types for batman-adv icmp cmd modes
- * @BATADV_TP_START: start a throughput meter run
- * @BATADV_TP_STOP: stop a throughput meter run
- */
-enum batadv_icmp_user_cmd_type {
- BATADV_TP_START = 0,
- BATADV_TP_STOP = 2,
-};
-
-/**
* struct batadv_icmp_header - common members among all the ICMP packets
* @packet_type: batman-adv packet type, part of the general header
* @version: batman-adv protocol version, part of the genereal header
--
2.10.1
^ permalink raw reply related
* [PATCH 05/17] batman-adv: Document new nc, mcast and tpmeter log levels
From: Simon Wunderlich @ 2016-10-27 19:01 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20161027190150.7880-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
Documentation/networking/batman-adv.txt | 17 ++++++++++-------
1 file changed, 10 insertions(+), 7 deletions(-)
diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt
index a918131..ccf9467 100644
--- a/Documentation/networking/batman-adv.txt
+++ b/Documentation/networking/batman-adv.txt
@@ -161,13 +161,16 @@ file in debugfs
The additional debug output is by default disabled. It can be en-
abled during run time. Following log_levels are defined:
-0 - All debug output disabled
-1 - Enable messages related to routing / flooding / broadcasting
-2 - Enable messages related to route added / changed / deleted
-4 - Enable messages related to translation table operations
-8 - Enable messages related to bridge loop avoidance
-16 - Enable messaged related to DAT, ARP snooping and parsing
-31 - Enable all messages
+ 0 - All debug output disabled
+ 1 - Enable messages related to routing / flooding / broadcasting
+ 2 - Enable messages related to route added / changed / deleted
+ 4 - Enable messages related to translation table operations
+ 8 - Enable messages related to bridge loop avoidance
+ 16 - Enable messages related to DAT, ARP snooping and parsing
+ 32 - Enable messages related to network coding
+ 64 - Enable messages related to multicast
+128 - Enable messages related to throughput meter
+255 - Enable all messages
The debug output can be changed at runtime using the file
/sys/class/net/bat0/mesh/log_level. e.g.
--
2.10.1
^ permalink raw reply related
* [PATCH 07/17] batman-adv: Move batadv_sum_counter to soft-interface.c
From: Simon Wunderlich @ 2016-10-27 19:01 UTC (permalink / raw)
To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20161027190150.7880-1-sw@simonwunderlich.de>
From: Sven Eckelmann <sven@narfation.org>
The function batadv_sum_counter is only used in soft-interface.c and has no
special relevance for main.h.
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
net/batman-adv/main.h | 21 ---------------------
net/batman-adv/soft-interface.c | 21 +++++++++++++++++++++
2 files changed, 21 insertions(+), 21 deletions(-)
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 8b0979b..6a2328d 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -185,7 +185,6 @@ enum batadv_uev_type {
#include <linux/bitops.h> /* for packet.h */
#include <linux/compiler.h>
-#include <linux/cpumask.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h> /* for packet.h */
#include <linux/if_vlan.h>
@@ -284,26 +283,6 @@ static inline void batadv_add_counter(struct batadv_priv *bat_priv, size_t idx,
#define batadv_inc_counter(b, i) batadv_add_counter(b, i, 1)
-/**
- * batadv_sum_counter - Sum the cpu-local counters for index 'idx'
- * @bat_priv: the bat priv with all the soft interface information
- * @idx: index of counter to sum up
- *
- * Return: sum of all cpu-local counters
- */
-static inline u64 batadv_sum_counter(struct batadv_priv *bat_priv, size_t idx)
-{
- u64 *counters, sum = 0;
- int cpu;
-
- for_each_possible_cpu(cpu) {
- counters = per_cpu_ptr(bat_priv->bat_counters, cpu);
- sum += counters[idx];
- }
-
- return sum;
-}
-
/* Define a macro to reach the control buffer of the skb. The members of the
* control buffer are defined in struct batadv_skb_cb in types.h.
* The macro is inspired by the similar macro TCP_SKB_CB() in tcp.h.
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 49e16b6..f37c1c7 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -22,6 +22,7 @@
#include <linux/byteorder/generic.h>
#include <linux/cache.h>
#include <linux/compiler.h>
+#include <linux/cpumask.h>
#include <linux/errno.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
@@ -116,6 +117,26 @@ static int batadv_interface_release(struct net_device *dev)
return 0;
}
+/**
+ * batadv_sum_counter - Sum the cpu-local counters for index 'idx'
+ * @bat_priv: the bat priv with all the soft interface information
+ * @idx: index of counter to sum up
+ *
+ * Return: sum of all cpu-local counters
+ */
+static u64 batadv_sum_counter(struct batadv_priv *bat_priv, size_t idx)
+{
+ u64 *counters, sum = 0;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ counters = per_cpu_ptr(bat_priv->bat_counters, cpu);
+ sum += counters[idx];
+ }
+
+ return sum;
+}
+
static struct net_device_stats *batadv_interface_stats(struct net_device *dev)
{
struct batadv_priv *bat_priv = netdev_priv(dev);
--
2.10.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox