[Devel] [PATCH RHEL7 COMMIT] ms/net: ip, diag -- Add diag interface for raw sockets
Konstantin Khorenko
khorenko at virtuozzo.com
Wed Nov 23 07:28:12 PST 2016
The commit is pushed to "branch-rh7-3.10.0-327.36.1.vz7.20.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-327.36.1.vz7.20.1
------>
commit e2faf26c26103fb4494a4431f3b20670d95be86c
Author: Cyrill Gorcunov <gorcunov at virtuozzo.com>
Date: Wed Nov 23 19:28:11 2016 +0400
ms/net: ip, diag -- Add diag interface for raw sockets
Patchset description:
These are backports from net-next tree. The patches are needed
to support c/r of raw sockets (criu part is to be implemented).
https://jira.sw.ru/browse/PSBM-51614
===
This patch description:
net-next: 432490f9d455fb842d70219f22d9d2c812371676
In criu we are actively using diag interface to collect sockets
present in the system when dumping applications. And while for
unix, tcp, udp[lite], packet, netlink it works as expected,
the raw sockets do not have. Thus add it.
v2:
- add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@)
- implement @destroy for diag requests (by dsa@)
v3:
- add export of raw_abort for IPv6 (by dsa@)
- pass net-admin flag into inet_sk_diag_fill due to
changes in net-next branch (by dsa@)
v4:
- use @pad in struct inet_diag_req_v2 for raw socket
protocol specification: raw module carries sockets
which may have custom protocol passed from socket()
syscall and sole @sdiag_protocol is not enough to
match underlied ones
- start reporting protocol specifed in socket() call
when sockets are raw ones for the same reason: user
space tools like ss may parse this attribute and use
it for socket matching
v5 (by eric.dumazet@):
- use sock_hold in raw_sock_get instead of atomic_inc,
we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock
when looking up so counter won't be zero here.
v6:
- use sdiag_raw_protocol() helper which will access @pad
structure used for raw sockets protocol specification:
we can't simply rename this member without breaking uapi
v7:
- sine sdiag_raw_protocol() helper is not suitable for
uapi lets rather make an alias structure with proper
names. __check_inet_diag_req_raw helper will catch
if any of structure unintentionally changed.
CC: David S. Miller <davem at davemloft.net>
CC: Eric Dumazet <eric.dumazet at gmail.com>
CC: David Ahern <dsa at cumulusnetworks.com>
CC: Alexey Kuznetsov <kuznet at ms2.inr.ac.ru>
CC: James Morris <jmorris at namei.org>
CC: Hideaki YOSHIFUJI <yoshfuji at linux-ipv6.org>
CC: Patrick McHardy <kaber at trash.net>
CC: Andrey Vagin <avagin at openvz.org>
CC: Stephen Hemminger <stephen at networkplumber.org>
Signed-off-by: David S. Miller <davem at davemloft.net>
Signed-off-by: Cyrill Gorcunov <gorcunov at virtuozzo.com>
---
include/net/raw.h | 5 +
include/net/rawv6.h | 7 ++
include/uapi/linux/inet_diag.h | 17 +++
net/ipv4/Kconfig | 9 ++
net/ipv4/Makefile | 1 +
net/ipv4/inet_diag.c | 9 ++
net/ipv4/raw.c | 6 +-
net/ipv4/raw_diag.c | 241 +++++++++++++++++++++++++++++++++++++++++
net/ipv6/raw.c | 6 +-
9 files changed, 297 insertions(+), 4 deletions(-)
diff --git a/include/net/raw.h b/include/net/raw.h
index 42ce6fe..abf1aa5 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -23,6 +23,11 @@
extern struct proto raw_prot;
+extern struct raw_hashinfo raw_v4_hashinfo;
+struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
+ unsigned short num, __be32 raddr,
+ __be32 laddr, int dif);
+
void raw_icmp_error(struct sk_buff *, int, u32);
int raw_local_deliver(struct sk_buff *, int);
diff --git a/include/net/rawv6.h b/include/net/rawv6.h
index e7ea660..a0ca116 100644
--- a/include/net/rawv6.h
+++ b/include/net/rawv6.h
@@ -3,6 +3,13 @@
#include <net/protocol.h>
+extern struct raw_hashinfo raw_v6_hashinfo;
+struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
+ unsigned short num, const struct in6_addr *loc_addr,
+ const struct in6_addr *rmt_addr, int dif);
+
+int raw_abort(struct sock *sk, int err);
+
void raw6_icmp_error(struct sk_buff *, int nexthdr,
u8 type, u8 code, int inner_offset, __be32);
bool raw6_local_deliver(struct sk_buff *, int);
diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index 093d040..28507b3 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -43,6 +43,23 @@ struct inet_diag_req_v2 {
struct inet_diag_sockid id;
};
+/*
+ * SOCK_RAW sockets require the underlied protocol to be
+ * additionally specified so we can use @pad member for
+ * this, but we can't rename it because userspace programs
+ * still may depend on this name. Instead lets use another
+ * structure definition as an alias for struct
+ * @inet_diag_req_v2.
+ */
+struct inet_diag_req_raw {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u8 idiag_ext;
+ __u8 sdiag_raw_protocol;
+ __u32 idiag_states;
+ struct inet_diag_sockid id;
+};
+
enum {
INET_DIAG_REQ_NONE,
INET_DIAG_REQ_BYTECODE,
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 7c39343..391953b 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -455,6 +455,15 @@ config INET_UDP_DIAG
Support for UDP socket monitoring interface used by the ss tool.
If unsure, say Y.
+config INET_RAW_DIAG
+ tristate "RAW: socket monitoring interface"
+ depends on INET_DIAG && (IPV6 || IPV6=n)
+ default n
+ ---help---
+ Support for RAW socket monitoring interface used by the ss tool.
+ If unsure, say Y.
+
+
menuconfig TCP_CONG_ADVANCED
bool "TCP: advanced congestion control"
---help---
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 989526a..5de7909 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -40,6 +40,7 @@ obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/
obj-$(CONFIG_INET_DIAG) += inet_diag.o
obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
+obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o
obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index add2ee0..d4baa80 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -174,6 +174,15 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
goto errout;
+ /*
+ * RAW sockets might have user-defined protocols assigned,
+ * so report the one supplied on socket creation.
+ */
+ if (sk->sk_type == SOCK_RAW) {
+ if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol))
+ goto errout;
+ }
+
if (icsk == NULL) {
handler->idiag_get_info(sk, r, NULL);
goto out;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 1f647ae..9224675 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -79,9 +79,10 @@
#include <linux/netfilter_ipv4.h>
#include <linux/compat.h>
-static struct raw_hashinfo raw_v4_hashinfo = {
+struct raw_hashinfo raw_v4_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
};
+EXPORT_SYMBOL_GPL(raw_v4_hashinfo);
void raw_hash_sk(struct sock *sk)
{
@@ -108,7 +109,7 @@ void raw_unhash_sk(struct sock *sk)
}
EXPORT_SYMBOL_GPL(raw_unhash_sk);
-static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
+struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
unsigned short num, __be32 raddr, __be32 laddr, int dif)
{
sk_for_each_from(sk) {
@@ -124,6 +125,7 @@ static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
found:
return sk;
}
+EXPORT_SYMBOL_GPL(__raw_v4_lookup);
/*
* 0 - deliver
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
new file mode 100644
index 0000000..d1dae28
--- /dev/null
+++ b/net/ipv4/raw_diag.c
@@ -0,0 +1,241 @@
+#include <linux/module.h>
+
+#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
+
+#include <net/raw.h>
+#include <net/rawv6.h>
+
+#ifdef pr_fmt
+# undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+static struct raw_hashinfo *
+raw_get_hashinfo(const struct inet_diag_req_v2 *r)
+{
+ if (r->sdiag_family == AF_INET) {
+ return &raw_v4_hashinfo;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (r->sdiag_family == AF_INET6) {
+ return &raw_v6_hashinfo;
+#endif
+ } else {
+ pr_warn_once("Unexpected inet family %d\n",
+ r->sdiag_family);
+ WARN_ON_ONCE(1);
+ return ERR_PTR(-EINVAL);
+ }
+}
+
+/*
+ * Due to requirement of not breaking user API we can't simply
+ * rename @pad field in inet_diag_req_v2 structure, instead
+ * use helper to figure it out.
+ */
+
+static struct sock *raw_lookup(struct net *net, struct sock *from,
+ const struct inet_diag_req_v2 *req)
+{
+ struct inet_diag_req_raw *r = (void *)req;
+ struct sock *sk = NULL;
+
+ if (r->sdiag_family == AF_INET)
+ sk = __raw_v4_lookup(net, from, r->sdiag_raw_protocol,
+ r->id.idiag_dst[0],
+ r->id.idiag_src[0],
+ r->id.idiag_if);
+#if IS_ENABLED(CONFIG_IPV6)
+ else
+ sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol,
+ (const struct in6_addr *)r->id.idiag_src,
+ (const struct in6_addr *)r->id.idiag_dst,
+ r->id.idiag_if);
+#endif
+ return sk;
+}
+
+static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r)
+{
+ struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
+ struct sock *sk = NULL, *s;
+ int slot;
+
+ if (IS_ERR(hashinfo))
+ return ERR_CAST(hashinfo);
+
+ read_lock(&hashinfo->lock);
+ for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) {
+ sk_for_each(s, &hashinfo->ht[slot]) {
+ sk = raw_lookup(net, s, r);
+ if (sk) {
+ /*
+ * Grab it and keep until we fill
+ * diag meaage to be reported, so
+ * caller should call sock_put then.
+ * We can do that because we're keeping
+ * hashinfo->lock here.
+ */
+ sock_hold(sk);
+ break;
+ }
+ }
+ }
+ read_unlock(&hashinfo->lock);
+
+ return sk ? sk : ERR_PTR(-ENOENT);
+}
+
+static int raw_diag_dump_one(struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh,
+ struct inet_diag_req_v2 *r)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sk_buff *rep;
+ struct sock *sk;
+ int err;
+
+ sk = raw_sock_get(net, r);
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
+
+ rep = nlmsg_new(sizeof(struct inet_diag_msg) +
+ sizeof(struct inet_diag_meminfo) + 64,
+ GFP_KERNEL);
+ if (!rep) {
+ sock_put(sk);
+ return -ENOMEM;
+ }
+
+ err = inet_sk_diag_fill(sk, NULL, rep, r,
+ sk_user_ns(NETLINK_CB(in_skb).sk),
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0, nlh);
+ sock_put(sk);
+
+ if (err < 0) {
+ kfree_skb(rep);
+ return err;
+ }
+
+ err = netlink_unicast(net->diag_nlsk, rep,
+ NETLINK_CB(in_skb).portid,
+ MSG_DONTWAIT);
+ if (err > 0)
+ err = 0;
+ return err;
+}
+
+static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
+ struct netlink_callback *cb,
+ struct inet_diag_req_v2 *r,
+ struct nlattr *bc)
+{
+ if (!inet_diag_bc_sk(bc, sk))
+ return 0;
+
+ return inet_sk_diag_fill(sk, NULL, skb, r,
+ sk_user_ns(NETLINK_CB(cb->skb).sk),
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ cb->nlh);
+}
+
+static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ struct inet_diag_req_v2 *r, struct nlattr *bc)
+{
+ struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
+ struct net *net = sock_net(skb->sk);
+ int num, s_num, slot, s_slot;
+ struct sock *sk = NULL;
+
+ if (IS_ERR(hashinfo))
+ return;
+
+ s_slot = cb->args[0];
+ num = s_num = cb->args[1];
+
+ read_lock(&hashinfo->lock);
+ for (slot = s_slot; slot < RAW_HTABLE_SIZE; s_num = 0, slot++) {
+ num = 0;
+
+ sk_for_each(sk, &hashinfo->ht[slot]) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (!net_eq(sock_net(sk), net))
+ continue;
+ if (num < s_num)
+ goto next;
+ if (sk->sk_family != r->sdiag_family)
+ goto next;
+ if (r->id.idiag_sport != inet->inet_sport &&
+ r->id.idiag_sport)
+ goto next;
+ if (r->id.idiag_dport != inet->inet_dport &&
+ r->id.idiag_dport)
+ goto next;
+ if (sk_diag_dump(sk, skb, cb, r, bc) < 0)
+ goto out_unlock;
+next:
+ num++;
+ }
+ }
+
+out_unlock:
+ read_unlock(&hashinfo->lock);
+
+ cb->args[0] = slot;
+ cb->args[1] = num;
+}
+
+static void raw_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
+ void *info)
+{
+ r->idiag_rqueue = sk_rmem_alloc_get(sk);
+ r->idiag_wqueue = sk_wmem_alloc_get(sk);
+}
+
+static const struct inet_diag_handler raw_diag_handler = {
+ .dump = raw_diag_dump,
+ .dump_one = raw_diag_dump_one,
+ .idiag_get_info = raw_diag_get_info,
+ .idiag_type = IPPROTO_RAW,
+};
+
+static void __always_unused __check_inet_diag_req_raw(void)
+{
+ /*
+ * Make sure the two structures are identical,
+ * except the @pad field.
+ */
+#define __offset_mismatch(m1, m2) \
+ (offsetof(struct inet_diag_req_v2, m1) != \
+ offsetof(struct inet_diag_req_raw, m2))
+
+ BUILD_BUG_ON(sizeof(struct inet_diag_req_v2) !=
+ sizeof(struct inet_diag_req_raw));
+ BUILD_BUG_ON(__offset_mismatch(sdiag_family, sdiag_family));
+ BUILD_BUG_ON(__offset_mismatch(sdiag_protocol, sdiag_protocol));
+ BUILD_BUG_ON(__offset_mismatch(idiag_ext, idiag_ext));
+ BUILD_BUG_ON(__offset_mismatch(pad, sdiag_raw_protocol));
+ BUILD_BUG_ON(__offset_mismatch(idiag_states, idiag_states));
+ BUILD_BUG_ON(__offset_mismatch(id, id));
+#undef __offset_mismatch
+}
+
+static int __init raw_diag_init(void)
+{
+ return inet_diag_register(&raw_diag_handler);
+}
+
+static void __exit raw_diag_exit(void)
+{
+ inet_diag_unregister(&raw_diag_handler);
+}
+
+module_init(raw_diag_init);
+module_exit(raw_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 3d20cff..209fcf2 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -63,11 +63,12 @@
#include <linux/seq_file.h>
#include <linux/export.h>
-static struct raw_hashinfo raw_v6_hashinfo = {
+struct raw_hashinfo raw_v6_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock),
};
+EXPORT_SYMBOL_GPL(raw_v6_hashinfo);
-static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
+struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
unsigned short num, const struct in6_addr *loc_addr,
const struct in6_addr *rmt_addr, int dif)
{
@@ -100,6 +101,7 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
found:
return sk;
}
+EXPORT_SYMBOL_GPL(__raw_v6_lookup);
/*
* 0 - deliver
More information about the Devel
mailing list