0628b123c9
This patch adds a batch support to nfnetlink. Basically, it adds two new control messages: * NFNL_MSG_BATCH_BEGIN, that indicates the beginning of a batch, the nfgenmsg->res_id indicates the nfnetlink subsystem ID. * NFNL_MSG_BATCH_END, that results in the invocation of the ss->commit callback function. If not specified or an error ocurred in the batch, the ss->abort function is invoked instead. The end message represents the commit operation in nftables, the lack of end message results in an abort. This patch also adds the .call_batch function that is only called from the batch receival path. This patch adds atomic rule updates and dumps based on bitmask generations. This allows to atomically commit a set of rule-set updates incrementally without altering the internal state of existing nf_tables expressions/matches/targets. The idea consists of using a generation cursor of 1 bit and a bitmask of 2 bits per rule. Assuming the gencursor is 0, then the genmask (expressed as a bitmask) can be interpreted as: 00 active in the present, will be active in the next generation. 01 inactive in the present, will be active in the next generation. 10 active in the present, will be deleted in the next generation. ^ gencursor Once you invoke the transition to the next generation, the global gencursor is updated: 00 active in the present, will be active in the next generation. 01 active in the present, needs to zero its future, it becomes 00. 10 inactive in the present, delete now. ^ gencursor If a dump is in progress and nf_tables enters a new generation, the dump will stop and return -EBUSY to let userspace know that it has to retry again. In order to invalidate dumps, a global genctr counter is increased everytime nf_tables enters a new generation. This new operation can be used from the user-space utility that controls the firewall, eg. nft -f restore The rule updates contained in `file' will be applied atomically. cat file ----- add filter INPUT ip saddr 1.1.1.1 counter accept #1 del filter INPUT ip daddr 2.2.2.2 counter drop #2 -EOF- Note that the rule 1 will be inactive until the transition to the next generation, the rule 2 will be evicted in the next generation. There is a penalty during the rule update due to the branch misprediction in the packet matching framework. But that should be quickly resolved once the iteration over the commit list that contain rules that require updates is finished. Event notification happens once the rule-set update has been committed. So we skip notifications is case the rule-set update is aborted, which can happen in case that the rule-set is tested to apply correctly. This patch squashed the following patches from Pablo: * nf_tables: atomic rule updates and dumps * nf_tables: get rid of per rule list_head for commits * nf_tables: use per netns commit list * nfnetlink: add batch support and use it from nf_tables * nf_tables: all rule updates are transactional * nf_tables: attach replacement rule after stale one * nf_tables: do not allow deletion/replacement of stale rules * nf_tables: remove unused NFTA_RULE_FLAGS Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
52 lines
1.7 KiB
C
52 lines
1.7 KiB
C
#ifndef _NFNETLINK_H
|
|
#define _NFNETLINK_H
|
|
|
|
|
|
#include <linux/netlink.h>
|
|
#include <linux/capability.h>
|
|
#include <net/netlink.h>
|
|
#include <uapi/linux/netfilter/nfnetlink.h>
|
|
|
|
struct nfnl_callback {
|
|
int (*call)(struct sock *nl, struct sk_buff *skb,
|
|
const struct nlmsghdr *nlh,
|
|
const struct nlattr * const cda[]);
|
|
int (*call_rcu)(struct sock *nl, struct sk_buff *skb,
|
|
const struct nlmsghdr *nlh,
|
|
const struct nlattr * const cda[]);
|
|
int (*call_batch)(struct sock *nl, struct sk_buff *skb,
|
|
const struct nlmsghdr *nlh,
|
|
const struct nlattr * const cda[]);
|
|
const struct nla_policy *policy; /* netlink attribute policy */
|
|
const u_int16_t attr_count; /* number of nlattr's */
|
|
};
|
|
|
|
struct nfnetlink_subsystem {
|
|
const char *name;
|
|
__u8 subsys_id; /* nfnetlink subsystem ID */
|
|
__u8 cb_count; /* number of callbacks */
|
|
const struct nfnl_callback *cb; /* callback for individual types */
|
|
int (*commit)(struct sk_buff *skb);
|
|
int (*abort)(struct sk_buff *skb);
|
|
};
|
|
|
|
int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n);
|
|
int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n);
|
|
|
|
int nfnetlink_has_listeners(struct net *net, unsigned int group);
|
|
struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size,
|
|
u32 dst_portid, gfp_t gfp_mask);
|
|
int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid,
|
|
unsigned int group, int echo, gfp_t flags);
|
|
int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error);
|
|
int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid,
|
|
int flags);
|
|
|
|
void nfnl_lock(__u8 subsys_id);
|
|
void nfnl_unlock(__u8 subsys_id);
|
|
|
|
#define MODULE_ALIAS_NFNL_SUBSYS(subsys) \
|
|
MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys))
|
|
|
|
#endif /* _NFNETLINK_H */
|