From mboxrd@z Thu Jan 1 00:00:00 1970 From: Harald Welte Subject: [PATCH 2/*] nfnetlink layer Date: Wed, 20 Jul 2005 09:30:07 -0400 Message-ID: <20050720133007.GC4077@rama> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="B8ONY/mu/bqBak9m" Cc: Linux Netdev List , Netfilter Development Mailinglist Return-path: To: David Miller Content-Disposition: inline List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: netfilter-devel-bounces@lists.netfilter.org Errors-To: netfilter-devel-bounces@lists.netfilter.org List-Id: netdev.vger.kernel.org --B8ONY/mu/bqBak9m Content-Type: multipart/mixed; boundary="hUH5gZbnpyIv7Mn4" Content-Disposition: inline --hUH5gZbnpyIv7Mn4 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Hi Dave,=20 here comes the nfnetlink layer. Its first user (ctnetlink) is waiting for some last review and will follow tomorrow. Please apply to your 2.6.14 tree, thanks! --=20 - Harald Welte http://netfilter.org/ =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D "Fragmentation is like classful addressing -- an interesting early architectural error that shows how much experimentation was going on while IP was being designed." -- Paul Vixie --hUH5gZbnpyIv7Mn4 Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="02-nfnetlink.patch" Content-Transfer-Encoding: quoted-printable Introduce "nfnetlink" (netfilter netlink) layer. This layer is used as transport layer for all userspace communication of the new upcoming netfilter subsystems, such as ctnetlink, nfnetlink_queue and some day even the mythical pkttables ;) Signed-off-by: Harald Welte --- commit 41a00086e4c896f92c8a29f8e2e5f6d893118e77 tree db282fb2ed082b8a1b70b0c5bdf87928da6c594f parent 212c12f0005581d2625a1bd0add59cd8ac5725d0 author laforge Mi, 20 Jul 2005 09:02:40 -0400 committer laforge Mi, 20 Jul 2005 09:02:40 -0400 include/linux/netfilter/nfnetlink.h | 145 +++++++++++++++ net/Kconfig | 2=20 net/Makefile | 1=20 net/netfilter/Kconfig | 5 + net/netfilter/Makefile | 1=20 net/netfilter/nfnetlink.c | 343 +++++++++++++++++++++++++++++++= ++++ 6 files changed, 497 insertions(+), 0 deletions(-) diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/= nfnetlink.h new file mode 100644 --- /dev/null +++ b/include/linux/netfilter/nfnetlink.h @@ -0,0 +1,145 @@ +#ifndef _NFNETLINK_H +#define _NFNETLINK_H +#include + +/* nfnetlink groups: Up to 32 maximum */ +#define NF_NETLINK_CONNTRACK_NEW 0x00000001 +#define NF_NETLINK_CONNTRACK_UPDATE 0x00000002 +#define NF_NETLINK_CONNTRACK_DESTROY 0x00000004 +#define NF_NETLINK_CONNTRACK_EXP_NEW 0x00000008 +#define NF_NETLINK_CONNTRACK_EXP_UPDATE 0x00000010 +#define NF_NETLINK_CONNTRACK_EXP_DESTROY 0x00000020 + +/* Generic structure for encapsulation optional netfilter information. + * It is reminiscent of sockaddr, but with sa_family replaced + * with attribute type.=20 + * ! This should someday be put somewhere generic as now rtnetlink and + * ! nfnetlink use the same attributes methods. - J. Schulist. + */ + +struct nfattr +{ + u_int16_t nfa_len; + u_int16_t nfa_type; +} __attribute__ ((packed)); + +/* FIXME: Shamelessly copy and pasted from rtnetlink.h, it's time + * to put this in a generic file */ + +#define NFA_ALIGNTO 4 +#define NFA_ALIGN(len) (((len) + NFA_ALIGNTO - 1) & ~(NFA_ALIGNTO - 1)) +#define NFA_OK(nfa,len) ((len) > 0 && (nfa)->nfa_len >=3D sizeof(struct nf= attr) \ + && (nfa)->nfa_len <=3D (len)) +#define NFA_NEXT(nfa,attrlen) ((attrlen) -=3D NFA_ALIGN((nfa)->nfa_len), \ + (struct nfattr *)(((char *)(nfa)) + NFA_ALIGN((nfa)->nfa_len))) +#define NFA_LENGTH(len) (NFA_ALIGN(sizeof(struct nfattr)) + (len)) +#define NFA_SPACE(len) NFA_ALIGN(NFA_LENGTH(len)) +#define NFA_DATA(nfa) ((void *)(((char *)(nfa)) + NFA_LENGTH(0))) +#define NFA_PAYLOAD(nfa) ((int)((nfa)->nfa_len) - NFA_LENGTH(0)) +#define NFA_NEST(skb, type) \ +({ struct nfattr *__start =3D (struct nfattr *) (skb)->tail; \ + NFA_PUT(skb, type, 0, NULL); \ + __start; }) +#define NFA_NEST_END(skb, start) \ +({ (start)->nfa_len =3D ((skb)->tail - (unsigned char *) (start)); \ + (skb)->len; }) +#define NFA_NEST_CANCEL(skb, start) \ +({ if (start) \ + skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ + -1; }) + +/* General form of address family dependent message. + */ +struct nfgenmsg { + u_int8_t nfgen_family; /* AF_xxx */ + u_int8_t version; /* nfnetlink version */ + u_int16_t res_id; /* resource id */ +} __attribute__ ((packed)); + +#define NFNETLINK_V1 1 + +#define NFM_NFA(n) ((struct nfattr *)(((char *)(n)) \ + + NLMSG_ALIGN(sizeof(struct nfgenmsg)))) +#define NFM_PAYLOAD(n) NLMSG_PAYLOAD(n, sizeof(struct nfgenmsg)) + +/* netfilter netlink message types are split in two pieces: + * 8 bit subsystem, 8bit operation. + */ + +#define NFNL_SUBSYS_ID(x) ((x & 0xff00) >> 8) +#define NFNL_MSG_TYPE(x) (x & 0x00ff) + +enum nfnl_subsys_id { + NFNL_SUBSYS_NONE =3D 0, + NFNL_SUBSYS_CTNETLINK, + NFNL_SUBSYS_CTNETLINK_EXP, + NFNL_SUBSYS_IPTNETLINK, + NFNL_SUBSYS_QUEUE, + NFNL_SUBSYS_ULOG, + NFNL_SUBSYS_COUNT, +}; + +#ifdef __KERNEL__ + +#include + +struct nfnl_callback +{ + kernel_cap_t cap_required; /* capabilities required for this msg */ + int (*call)(struct sock *nl, struct sk_buff *skb,=20 + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp); +}; + +struct nfnetlink_subsystem +{ + const char *name; + __u8 subsys_id; /* nfnetlink subsystem ID */ + __u8 cb_count; /* number of callbacks */ + u_int32_t attr_count; /* number of nfattr's */ + struct nfnl_callback *cb; /* callback for individual types */ +}; + +extern void __nfa_fill(struct sk_buff *skb, int attrtype, + int attrlen, const void *data); +#define NFA_PUT(skb, attrtype, attrlen, data) \ +({ if (skb_tailroom(skb) < (int)NFA_SPACE(attrlen)) goto nfattr_failure; \ + __nfa_fill(skb, attrtype, attrlen, data); }) + +extern struct semaphore nfnl_sem; + +#define nfnl_shlock() down(&nfnl_sem) +#define nfnl_shlock_nowait() down_trylock(&nfnl_sem) + +#define nfnl_shunlock() do { up(&nfnl_sem); \ + if(nfnl && nfnl->sk_receive_queue.qlen) \ + nfnl->sk_data_ready(nfnl, 0); \ + } while(0) + +extern void nfnl_lock(void); +extern void nfnl_unlock(void); + +extern int nfnetlink_subsys_register(struct nfnetlink_subsystem *n); +extern int nfnetlink_subsys_unregister(struct nfnetlink_subsystem *n); + +extern int nfattr_parse(struct nfattr *tb[], int maxattr,=20 + struct nfattr *nfa, int len); + +#define nfattr_parse_nested(tb, max, nfa) \ + nfattr_parse((tb), (max), NFA_DATA((nfa)), NFA_PAYLOAD((nfa))) + +#define nfattr_bad_size(tb, max, cta_min) \ +({ int __i, __res =3D 0; \ + for (__i=3D0; __i, + * (C) 2002-2005 by Harald Welte + * (C) 2005 by Pablo Neira Ayuso + * + * Initial netfilter messages via netlink development funded and + * generally made possible by Network Robots, Inc. (www.networkrobots.com) + * + * Further development of this code funded by Astaro AG (http://www.astaro= =2Ecom) + * + * This software may be used and distributed according to the terms + * of the GNU General Public License, incorporated herein by reference. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +MODULE_LICENSE("GPL"); + +static char __initdata nfversion[] =3D "0.30"; + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + +static struct sock *nfnl =3D NULL; +static struct nfnetlink_subsystem *subsys_table[NFNL_SUBSYS_COUNT]; +DECLARE_MUTEX(nfnl_sem); + +void nfnl_lock(void) +{ + nfnl_shlock(); +} + +void nfnl_unlock(void) +{ + nfnl_shunlock(); +} + +int nfnetlink_subsys_register(struct nfnetlink_subsystem *n) +{ + DEBUGP("registering subsystem ID %u\n", n->subsys_id); + + /* If the netlink socket wasn't created, then fail */ + if (!nfnl) + return -1; + + nfnl_lock(); + subsys_table[n->subsys_id] =3D n; + nfnl_unlock(); + + return 0; +} + +int nfnetlink_subsys_unregister(struct nfnetlink_subsystem *n) +{ + DEBUGP("unregistering subsystem ID %u\n", n->subsys_id); + + nfnl_lock(); + subsys_table[n->subsys_id] =3D NULL; + nfnl_unlock(); + + return 0; +} + +static inline struct nfnetlink_subsystem *nfnetlink_get_subsys(u_int16_t t= ype) +{ + u_int8_t subsys_id =3D NFNL_SUBSYS_ID(type); + + if (subsys_id >=3D NFNL_SUBSYS_COUNT + || subsys_table[subsys_id] =3D=3D NULL) + return NULL; + + return subsys_table[subsys_id]; +} + +static inline struct nfnl_callback * +nfnetlink_find_client(u_int16_t type, struct nfnetlink_subsystem *ss) +{ + u_int8_t cb_id =3D NFNL_MSG_TYPE(type); +=09 + if (cb_id >=3D ss->cb_count) { + DEBUGP("msgtype %u >=3D %u, returning\n", type, ss->cb_count); + return NULL; + } + + return &ss->cb[cb_id]; +} + +void __nfa_fill(struct sk_buff *skb, int attrtype, int attrlen, + const void *data) +{ + struct nfattr *nfa; + int size =3D NFA_LENGTH(attrlen); + + nfa =3D (struct nfattr *)skb_put(skb, NFA_ALIGN(size)); + nfa->nfa_type =3D attrtype; + nfa->nfa_len =3D size; + memcpy(NFA_DATA(nfa), data, attrlen); +} + +int nfattr_parse(struct nfattr *tb[], int maxattr, struct nfattr *nfa, int= len) +{ + memset(tb, 0, sizeof(struct nfattr *) * maxattr); + + while (NFA_OK(nfa, len)) { + unsigned flavor =3D nfa->nfa_type; + if (flavor && flavor <=3D maxattr) + tb[flavor-1] =3D nfa; + nfa =3D NFA_NEXT(nfa, len); + } + + return 0; +} + +/** + * nfnetlink_check_attributes - check and parse nfnetlink attributes + * + * subsys: nfnl subsystem for which this message is to be parsed + * nlmsghdr: netlink message to be checked/parsed + * cda: array of pointers, needs to be at least subsys->attr_count big + * + */ +static int +nfnetlink_check_attributes(struct nfnetlink_subsystem *subsys, + struct nlmsghdr *nlh, struct nfattr *cda[]) +{ + int min_len; + + memset(cda, 0, sizeof(struct nfattr *) * subsys->attr_count); + + /* check attribute lengths. */ + min_len =3D NLMSG_ALIGN(sizeof(struct nfgenmsg)); + if (nlh->nlmsg_len < min_len) + return -EINVAL; + + if (nlh->nlmsg_len > min_len) { + struct nfattr *attr =3D NFM_NFA(NLMSG_DATA(nlh)); + int attrlen =3D nlh->nlmsg_len - NLMSG_ALIGN(min_len); + + while (NFA_OK(attr, attrlen)) { + unsigned flavor =3D attr->nfa_type; + if (flavor) { + if (flavor > subsys->attr_count) + return -EINVAL; + cda[flavor - 1] =3D attr; + } + attr =3D NFA_NEXT(attr, attrlen); + } + } else + return -EINVAL; + + return 0; +} + +int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo) +{ + int allocation =3D in_interrupt() ? GFP_ATOMIC : GFP_KERNEL; + int err =3D 0; + + NETLINK_CB(skb).dst_groups =3D group; + if (echo) + atomic_inc(&skb->users); + netlink_broadcast(nfnl, skb, pid, group, allocation); + if (echo) + err =3D netlink_unicast(nfnl, skb, pid, MSG_DONTWAIT); + + return err; +} + +int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags) +{ + return netlink_unicast(nfnl, skb, pid, flags); +} + +/* Process one complete nfnetlink message. */ +static inline int nfnetlink_rcv_msg(struct sk_buff *skb, + struct nlmsghdr *nlh, int *errp) +{ + struct nfnl_callback *nc; + struct nfnetlink_subsystem *ss; + int type, err =3D 0; + + DEBUGP("entered; subsys=3D%u, msgtype=3D%u\n", + NFNL_SUBSYS_ID(nlh->nlmsg_type), + NFNL_MSG_TYPE(nlh->nlmsg_type)); + + /* Only requests are handled by kernel now. */ + if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) { + DEBUGP("received non-request message\n"); + return 0; + } + + /* All the messages must at least contain nfgenmsg */ + if (nlh->nlmsg_len <=20 + NLMSG_LENGTH(NLMSG_ALIGN(sizeof(struct nfgenmsg)))) { + DEBUGP("received message was too short\n"); + return 0; + } + + type =3D nlh->nlmsg_type; + ss =3D nfnetlink_get_subsys(type); + if (!ss) + goto err_inval; + + nc =3D nfnetlink_find_client(type, ss); + if (!nc) { + DEBUGP("unable to find client for type %d\n", type); + goto err_inval; + } + + if (nc->cap_required &&=20 + !cap_raised(NETLINK_CB(skb).eff_cap, nc->cap_required)) { + DEBUGP("permission denied for type %d\n", type); + *errp =3D -EPERM; + return -1; + } + + { + struct nfattr *cda[ss->attr_count]; + + memset(cda, 0, ss->attr_count*sizeof(struct nfattr *)); + =09 + err =3D nfnetlink_check_attributes(ss, nlh, cda); + if (err < 0) + goto err_inval; + + err =3D nc->call(nfnl, skb, nlh, cda, errp); + *errp =3D err; + return err; + } + +err_inval: + *errp =3D -EINVAL; + return -1; +} + +/* Process one packet of messages. */ +static inline int nfnetlink_rcv_skb(struct sk_buff *skb) +{ + int err; + struct nlmsghdr *nlh; + + while (skb->len >=3D NLMSG_SPACE(0)) { + u32 rlen; + + nlh =3D (struct nlmsghdr *)skb->data; + if (nlh->nlmsg_len < sizeof(struct nlmsghdr) + || skb->len < nlh->nlmsg_len) + return 0; + rlen =3D NLMSG_ALIGN(nlh->nlmsg_len); + if (rlen > skb->len) + rlen =3D skb->len; + if (nfnetlink_rcv_msg(skb, nlh, &err)) { + if (!err) + return -1; + netlink_ack(skb, nlh, err); + } else + if (nlh->nlmsg_flags & NLM_F_ACK) + netlink_ack(skb, nlh, 0); + skb_pull(skb, rlen); + } + + return 0; +} + +static void nfnetlink_rcv(struct sock *sk, int len) +{ + do { + struct sk_buff *skb; + + if (nfnl_shlock_nowait()) + return; + + while ((skb =3D skb_dequeue(&sk->sk_receive_queue)) !=3D NULL) { + if (nfnetlink_rcv_skb(skb)) { + if (skb->len) + skb_queue_head(&sk->sk_receive_queue, + skb); + else + kfree_skb(skb); + break; + } + kfree_skb(skb); + } + + up(&nfnl_sem); + } while(nfnl && nfnl->sk_receive_queue.qlen); +} + +void __exit nfnetlink_exit(void) +{ + printk("Removing netfilter NETLINK layer.\n"); + sock_release(nfnl->sk_socket); + return; +} + +int __init nfnetlink_init(void) +{ + printk("Netfilter messages via NETLINK v%s.\n", nfversion); + + nfnl =3D netlink_kernel_create(NETLINK_NETFILTER, nfnetlink_rcv); + if (!nfnl) { + printk(KERN_ERR "cannot initialize nfnetlink!\n"); + return -1; + } + + return 0; +} + +module_init(nfnetlink_init); +module_exit(nfnetlink_exit); + +EXPORT_SYMBOL_GPL(nfnetlink_subsys_register); +EXPORT_SYMBOL_GPL(nfnetlink_subsys_unregister); +EXPORT_SYMBOL_GPL(nfnetlink_send); +EXPORT_SYMBOL_GPL(nfnetlink_unicast); +EXPORT_SYMBOL_GPL(nfattr_parse); +EXPORT_SYMBOL_GPL(__nfa_fill); --hUH5gZbnpyIv7Mn4-- --B8ONY/mu/bqBak9m Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (GNU/Linux) iD8DBQFC3lHeXaXGVTD0i/8RAnWMAJ9Df5f5deBJflJaxDBwfGxtjKFsAACZAfSQ 5bL1gFknXQaUjCvx7z1zCQk= =B/O+ -----END PGP SIGNATURE----- --B8ONY/mu/bqBak9m--