kernel-ark/include/linux/netlink.h
Pablo Neira Ayuso 38938bfe34 netlink: add NETLINK_NO_ENOBUFS socket flag
This patch adds the NETLINK_NO_ENOBUFS socket flag. This flag can
be used by unicast and broadcast listeners to avoid receiving
ENOBUFS errors.

Generally speaking, ENOBUFS errors are useful to notify two things
to the listener:

a) You may increase the receiver buffer size via setsockopt().
b) You have lost messages, you may be out of sync.

In some cases, ignoring ENOBUFS errors can be useful. For example:

a) nfnetlink_queue: this subsystem does not have any sort of resync
method and you can decide to ignore ENOBUFS once you have set a
given buffer size.

b) ctnetlink: you can use this together with the socket flag
NETLINK_BROADCAST_SEND_ERROR to stop getting ENOBUFS errors as
you do not need to resync (packets whose event are not delivered
are drop to provide reliable logging and state-synchronization).

Moreover, the use of NETLINK_NO_ENOBUFS also reduces a "go up, go down"
effect in terms of performance which is due to the netlink congestion
control when the listener cannot back off. The effect is the following:

1) throughput rate goes up and netlink messages are inserted in the
receiver buffer.
2) Then, netlink buffer fills and overruns (set on nlk->state bit 0).
3) While the listener empties the receiver buffer, netlink keeps
dropping messages. Thus, throughput goes dramatically down.
4) Then, once the listener has emptied the buffer (nlk->state
bit 0 is set off), goto step 1.

This effect is easy to trigger with netlink broadcast under heavy
load, and it is more noticeable when using a big receiver buffer.
You can find some results in [1] that show this problem.

[1] http://1984.lsi.us.es/linux/netlink/

This patch also includes the use of sk_drop to account the number of
netlink messages drop due to overrun. This value is shown in
/proc/net/netlink.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-24 16:37:55 -07:00

273 lines
8.4 KiB
C

#ifndef __LINUX_NETLINK_H
#define __LINUX_NETLINK_H
#include <linux/socket.h> /* for sa_family_t */
#include <linux/types.h>
#define NETLINK_ROUTE 0 /* Routing/device hook */
#define NETLINK_UNUSED 1 /* Unused number */
#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */
#define NETLINK_FIREWALL 3 /* Firewalling hook */
#define NETLINK_INET_DIAG 4 /* INET socket monitoring */
#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */
#define NETLINK_XFRM 6 /* ipsec */
#define NETLINK_SELINUX 7 /* SELinux event notifications */
#define NETLINK_ISCSI 8 /* Open-iSCSI */
#define NETLINK_AUDIT 9 /* auditing */
#define NETLINK_FIB_LOOKUP 10
#define NETLINK_CONNECTOR 11
#define NETLINK_NETFILTER 12 /* netfilter subsystem */
#define NETLINK_IP6_FW 13
#define NETLINK_DNRTMSG 14 /* DECnet routing messages */
#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */
#define NETLINK_GENERIC 16
/* leave room for NETLINK_DM (DM Events) */
#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */
#define NETLINK_ECRYPTFS 19
#define MAX_LINKS 32
struct net;
struct sockaddr_nl
{
sa_family_t nl_family; /* AF_NETLINK */
unsigned short nl_pad; /* zero */
__u32 nl_pid; /* port ID */
__u32 nl_groups; /* multicast groups mask */
};
struct nlmsghdr
{
__u32 nlmsg_len; /* Length of message including header */
__u16 nlmsg_type; /* Message content */
__u16 nlmsg_flags; /* Additional flags */
__u32 nlmsg_seq; /* Sequence number */
__u32 nlmsg_pid; /* Sending process port ID */
};
/* Flags values */
#define NLM_F_REQUEST 1 /* It is request message. */
#define NLM_F_MULTI 2 /* Multipart message, terminated by NLMSG_DONE */
#define NLM_F_ACK 4 /* Reply with ack, with zero or error code */
#define NLM_F_ECHO 8 /* Echo this request */
/* Modifiers to GET request */
#define NLM_F_ROOT 0x100 /* specify tree root */
#define NLM_F_MATCH 0x200 /* return all matching */
#define NLM_F_ATOMIC 0x400 /* atomic GET */
#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH)
/* Modifiers to NEW request */
#define NLM_F_REPLACE 0x100 /* Override existing */
#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */
#define NLM_F_CREATE 0x400 /* Create, if it does not exist */
#define NLM_F_APPEND 0x800 /* Add to end of list */
/*
4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL
4.4BSD CHANGE NLM_F_REPLACE
True CHANGE NLM_F_CREATE|NLM_F_REPLACE
Append NLM_F_CREATE
Check NLM_F_EXCL
*/
#define NLMSG_ALIGNTO 4
#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) )
#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
#define NLMSG_LENGTH(len) ((len)+NLMSG_ALIGN(NLMSG_HDRLEN))
#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
(struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
(nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
(nlh)->nlmsg_len <= (len))
#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len)))
#define NLMSG_NOOP 0x1 /* Nothing. */
#define NLMSG_ERROR 0x2 /* Error */
#define NLMSG_DONE 0x3 /* End of a dump */
#define NLMSG_OVERRUN 0x4 /* Data lost */
#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */
struct nlmsgerr
{
int error;
struct nlmsghdr msg;
};
#define NETLINK_ADD_MEMBERSHIP 1
#define NETLINK_DROP_MEMBERSHIP 2
#define NETLINK_PKTINFO 3
#define NETLINK_BROADCAST_ERROR 4
#define NETLINK_NO_ENOBUFS 5
struct nl_pktinfo
{
__u32 group;
};
#define NET_MAJOR 36 /* Major 36 is reserved for networking */
enum {
NETLINK_UNCONNECTED = 0,
NETLINK_CONNECTED,
};
/*
* <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)-->
* +---------------------+- - -+- - - - - - - - - -+- - -+
* | Header | Pad | Payload | Pad |
* | (struct nlattr) | ing | | ing |
* +---------------------+- - -+- - - - - - - - - -+- - -+
* <-------------- nlattr->nla_len -------------->
*/
struct nlattr
{
__u16 nla_len;
__u16 nla_type;
};
/*
* nla_type (16 bits)
* +---+---+-------------------------------+
* | N | O | Attribute Type |
* +---+---+-------------------------------+
* N := Carries nested attributes
* O := Payload stored in network byte order
*
* Note: The N and O flag are mutually exclusive.
*/
#define NLA_F_NESTED (1 << 15)
#define NLA_F_NET_BYTEORDER (1 << 14)
#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER)
#define NLA_ALIGNTO 4
#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1))
#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr)))
#ifdef __KERNEL__
#include <linux/capability.h>
#include <linux/skbuff.h>
static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb)
{
return (struct nlmsghdr *)skb->data;
}
struct netlink_skb_parms
{
struct ucred creds; /* Skb credentials */
__u32 pid;
__u32 dst_group;
kernel_cap_t eff_cap;
__u32 loginuid; /* Login (audit) uid */
__u32 sessionid; /* Session id (audit) */
__u32 sid; /* SELinux security id */
};
#define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb))
#define NETLINK_CREDS(skb) (&NETLINK_CB((skb)).creds)
extern struct sock *netlink_kernel_create(struct net *net,
int unit,unsigned int groups,
void (*input)(struct sk_buff *skb),
struct mutex *cb_mutex,
struct module *module);
extern void netlink_kernel_release(struct sock *sk);
extern int netlink_change_ngroups(struct sock *sk, unsigned int groups);
extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group);
extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
extern int netlink_has_listeners(struct sock *sk, unsigned int group);
extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock);
extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid,
__u32 group, gfp_t allocation);
extern void netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code);
extern int netlink_register_notifier(struct notifier_block *nb);
extern int netlink_unregister_notifier(struct notifier_block *nb);
/* finegrained unicast helpers: */
struct sock *netlink_getsockbyfilp(struct file *filp);
int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
long *timeo, struct sock *ssk);
void netlink_detachskb(struct sock *sk, struct sk_buff *skb);
int netlink_sendskb(struct sock *sk, struct sk_buff *skb);
/*
* skb should fit one page. This choice is good for headerless malloc.
* But we should limit to 8K so that userspace does not have to
* use enormous buffer sizes on recvmsg() calls just to avoid
* MSG_TRUNC when PAGE_SIZE is very large.
*/
#if PAGE_SIZE < 8192UL
#define NLMSG_GOODSIZE SKB_WITH_OVERHEAD(PAGE_SIZE)
#else
#define NLMSG_GOODSIZE SKB_WITH_OVERHEAD(8192UL)
#endif
#define NLMSG_DEFAULT_SIZE (NLMSG_GOODSIZE - NLMSG_HDRLEN)
struct netlink_callback
{
struct sk_buff *skb;
struct nlmsghdr *nlh;
int (*dump)(struct sk_buff * skb, struct netlink_callback *cb);
int (*done)(struct netlink_callback *cb);
int family;
long args[6];
};
struct netlink_notify
{
struct net *net;
int pid;
int protocol;
};
static __inline__ struct nlmsghdr *
__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags)
{
struct nlmsghdr *nlh;
int size = NLMSG_LENGTH(len);
nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size));
nlh->nlmsg_type = type;
nlh->nlmsg_len = size;
nlh->nlmsg_flags = flags;
nlh->nlmsg_pid = pid;
nlh->nlmsg_seq = seq;
if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0)
memset(NLMSG_DATA(nlh) + len, 0, NLMSG_ALIGN(size) - size);
return nlh;
}
#define NLMSG_NEW(skb, pid, seq, type, len, flags) \
({ if (unlikely(skb_tailroom(skb) < (int)NLMSG_SPACE(len))) \
goto nlmsg_failure; \
__nlmsg_put(skb, pid, seq, type, len, flags); })
#define NLMSG_PUT(skb, pid, seq, type, len) \
NLMSG_NEW(skb, pid, seq, type, len, 0)
extern int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
struct nlmsghdr *nlh,
int (*dump)(struct sk_buff *skb, struct netlink_callback*),
int (*done)(struct netlink_callback*));
#define NL_NONROOT_RECV 0x1
#define NL_NONROOT_SEND 0x2
extern void netlink_set_nonroot(int protocol, unsigned flag);
#endif /* __KERNEL__ */
#endif /* __LINUX_NETLINK_H */