diff options
author | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
commit | 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 (patch) | |
tree | 0bba044c4ce775e45a88a51686b5d9f90697ea9d /net |
Linux-2.6.12-rc2v2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Diffstat (limited to 'net')
668 files changed, 356308 insertions, 0 deletions
diff --git a/net/802/Makefile b/net/802/Makefile new file mode 100644 index 000000000000..01861929591a --- /dev/null +++ b/net/802/Makefile @@ -0,0 +1,15 @@ +# +# Makefile for the Linux 802.x protocol layers. +# + +obj-y := p8023.o + +# Check the p8022 selections against net/core/Makefile. +obj-$(CONFIG_SYSCTL) += sysctl_net_802.o +obj-$(CONFIG_LLC) += p8022.o psnap.o +obj-$(CONFIG_TR) += p8022.o psnap.o tr.o sysctl_net_802.o +obj-$(CONFIG_NET_FC) += fc.o +obj-$(CONFIG_FDDI) += fddi.o +obj-$(CONFIG_HIPPI) += hippi.o +obj-$(CONFIG_IPX) += p8022.o psnap.o +obj-$(CONFIG_ATALK) += p8022.o psnap.o diff --git a/net/802/fc.c b/net/802/fc.c new file mode 100644 index 000000000000..640d34e026c2 --- /dev/null +++ b/net/802/fc.c @@ -0,0 +1,130 @@ +/* + * NET3: Fibre Channel device handling subroutines + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Vineet Abraham <vma@iol.unh.edu> + * v 1.0 03/22/99 + */ + +#include <linux/config.h> +#include <asm/uaccess.h> +#include <asm/system.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/socket.h> +#include <linux/in.h> +#include <linux/inet.h> +#include <linux/netdevice.h> +#include <linux/fcdevice.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/timer.h> +#include <linux/net.h> +#include <linux/proc_fs.h> +#include <linux/init.h> +#include <net/arp.h> + +/* + * Put the headers on a Fibre Channel packet. + */ + +static int fc_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, + void *daddr, void *saddr, unsigned len) +{ + struct fch_hdr *fch; + int hdr_len; + + /* + * Add the 802.2 SNAP header if IP as the IPv4 code calls + * dev->hard_header directly. + */ + if (type == ETH_P_IP || type == ETH_P_ARP) + { + struct fcllc *fcllc; + + hdr_len = sizeof(struct fch_hdr) + sizeof(struct fcllc); + fch = (struct fch_hdr *)skb_push(skb, hdr_len); + fcllc = (struct fcllc *)(fch+1); + fcllc->dsap = fcllc->ssap = EXTENDED_SAP; + fcllc->llc = UI_CMD; + fcllc->protid[0] = fcllc->protid[1] = fcllc->protid[2] = 0x00; + fcllc->ethertype = htons(type); + } + else + { + hdr_len = sizeof(struct fch_hdr); + fch = (struct fch_hdr *)skb_push(skb, hdr_len); + } + + if(saddr) + memcpy(fch->saddr,saddr,dev->addr_len); + else + memcpy(fch->saddr,dev->dev_addr,dev->addr_len); + + if(daddr) + { + memcpy(fch->daddr,daddr,dev->addr_len); + return(hdr_len); + } + return -hdr_len; +} + +/* + * A neighbour discovery of some species (eg arp) has completed. We + * can now send the packet. + */ + +static int fc_rebuild_header(struct sk_buff *skb) +{ + struct fch_hdr *fch=(struct fch_hdr *)skb->data; + struct fcllc *fcllc=(struct fcllc *)(skb->data+sizeof(struct fch_hdr)); + if(fcllc->ethertype != htons(ETH_P_IP)) { + printk("fc_rebuild_header: Don't know how to resolve type %04X addresses ?\n",(unsigned int)htons(fcllc->ethertype)); + return 0; + } +#ifdef CONFIG_INET + return arp_find(fch->daddr, skb); +#else + return 0; +#endif +} + +static void fc_setup(struct net_device *dev) +{ + dev->hard_header = fc_header; + dev->rebuild_header = fc_rebuild_header; + + dev->type = ARPHRD_IEEE802; + dev->hard_header_len = FC_HLEN; + dev->mtu = 2024; + dev->addr_len = FC_ALEN; + dev->tx_queue_len = 100; /* Long queues on fc */ + dev->flags = IFF_BROADCAST; + + memset(dev->broadcast, 0xFF, FC_ALEN); +} + +/** + * alloc_fcdev - Register fibre channel device + * @sizeof_priv: Size of additional driver-private structure to be allocated + * for this fibre channel device + * + * Fill in the fields of the device structure with fibre channel-generic values. + * + * Constructs a new net device, complete with a private data area of + * size @sizeof_priv. A 32-byte (not bit) alignment is enforced for + * this private data area. + */ +struct net_device *alloc_fcdev(int sizeof_priv) +{ + return alloc_netdev(sizeof_priv, "fc%d", fc_setup); +} +EXPORT_SYMBOL(alloc_fcdev); diff --git a/net/802/fddi.c b/net/802/fddi.c new file mode 100644 index 000000000000..f9a31a9f70f1 --- /dev/null +++ b/net/802/fddi.c @@ -0,0 +1,210 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * FDDI-type device handling. + * + * Version: @(#)fddi.c 1.0.0 08/12/96 + * + * Authors: Lawrence V. Stefani, <stefani@lkg.dec.com> + * + * fddi.c is based on previous eth.c and tr.c work by + * Ross Biro, <bir7@leland.Stanford.Edu> + * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> + * Mark Evans, <evansmp@uhura.aston.ac.uk> + * Florian La Roche, <rzsfl@rz.uni-sb.de> + * Alan Cox, <gw4pts@gw4pts.ampr.org> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Changes + * Alan Cox : New arp/rebuild header + * Maciej W. Rozycki : IPv6 support + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <asm/system.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/socket.h> +#include <linux/in.h> +#include <linux/inet.h> +#include <linux/netdevice.h> +#include <linux/fddidevice.h> +#include <linux/if_ether.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <net/arp.h> +#include <net/sock.h> + +/* + * Create the FDDI MAC header for an arbitrary protocol layer + * + * saddr=NULL means use device source address + * daddr=NULL means leave destination address (eg unresolved arp) + */ + +static int fddi_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, + void *daddr, void *saddr, unsigned len) +{ + int hl = FDDI_K_SNAP_HLEN; + struct fddihdr *fddi; + + if(type != ETH_P_IP && type != ETH_P_IPV6 && type != ETH_P_ARP) + hl=FDDI_K_8022_HLEN-3; + fddi = (struct fddihdr *)skb_push(skb, hl); + fddi->fc = FDDI_FC_K_ASYNC_LLC_DEF; + if(type == ETH_P_IP || type == ETH_P_IPV6 || type == ETH_P_ARP) + { + fddi->hdr.llc_snap.dsap = FDDI_EXTENDED_SAP; + fddi->hdr.llc_snap.ssap = FDDI_EXTENDED_SAP; + fddi->hdr.llc_snap.ctrl = FDDI_UI_CMD; + fddi->hdr.llc_snap.oui[0] = 0x00; + fddi->hdr.llc_snap.oui[1] = 0x00; + fddi->hdr.llc_snap.oui[2] = 0x00; + fddi->hdr.llc_snap.ethertype = htons(type); + } + + /* Set the source and destination hardware addresses */ + + if (saddr != NULL) + memcpy(fddi->saddr, saddr, dev->addr_len); + else + memcpy(fddi->saddr, dev->dev_addr, dev->addr_len); + + if (daddr != NULL) + { + memcpy(fddi->daddr, daddr, dev->addr_len); + return(hl); + } + + return(-hl); +} + + +/* + * Rebuild the FDDI MAC header. This is called after an ARP + * (or in future other address resolution) has completed on + * this sk_buff. We now let ARP fill in the other fields. + */ + +static int fddi_rebuild_header(struct sk_buff *skb) +{ + struct fddihdr *fddi = (struct fddihdr *)skb->data; + +#ifdef CONFIG_INET + if (fddi->hdr.llc_snap.ethertype == __constant_htons(ETH_P_IP)) + /* Try to get ARP to resolve the header and fill destination address */ + return arp_find(fddi->daddr, skb); + else +#endif + { + printk("%s: Don't know how to resolve type %02X addresses.\n", + skb->dev->name, htons(fddi->hdr.llc_snap.ethertype)); + return(0); + } +} + + +/* + * Determine the packet's protocol ID and fill in skb fields. + * This routine is called before an incoming packet is passed + * up. It's used to fill in specific skb fields and to set + * the proper pointer to the start of packet data (skb->data). + */ + +unsigned short fddi_type_trans(struct sk_buff *skb, struct net_device *dev) +{ + struct fddihdr *fddi = (struct fddihdr *)skb->data; + unsigned short type; + + /* + * Set mac.raw field to point to FC byte, set data field to point + * to start of packet data. Assume 802.2 SNAP frames for now. + */ + + skb->mac.raw = skb->data; /* point to frame control (FC) */ + + if(fddi->hdr.llc_8022_1.dsap==0xe0) + { + skb_pull(skb, FDDI_K_8022_HLEN-3); + type = __constant_htons(ETH_P_802_2); + } + else + { + skb_pull(skb, FDDI_K_SNAP_HLEN); /* adjust for 21 byte header */ + type=fddi->hdr.llc_snap.ethertype; + } + + /* Set packet type based on destination address and flag settings */ + + if (*fddi->daddr & 0x01) + { + if (memcmp(fddi->daddr, dev->broadcast, FDDI_K_ALEN) == 0) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } + + else if (dev->flags & IFF_PROMISC) + { + if (memcmp(fddi->daddr, dev->dev_addr, FDDI_K_ALEN)) + skb->pkt_type = PACKET_OTHERHOST; + } + + /* Assume 802.2 SNAP frames, for now */ + + return(type); +} + +EXPORT_SYMBOL(fddi_type_trans); + +static int fddi_change_mtu(struct net_device *dev, int new_mtu) +{ + if ((new_mtu < FDDI_K_SNAP_HLEN) || (new_mtu > FDDI_K_SNAP_DLEN)) + return(-EINVAL); + dev->mtu = new_mtu; + return(0); +} + +static void fddi_setup(struct net_device *dev) +{ + dev->change_mtu = fddi_change_mtu; + dev->hard_header = fddi_header; + dev->rebuild_header = fddi_rebuild_header; + + dev->type = ARPHRD_FDDI; + dev->hard_header_len = FDDI_K_SNAP_HLEN+3; /* Assume 802.2 SNAP hdr len + 3 pad bytes */ + dev->mtu = FDDI_K_SNAP_DLEN; /* Assume max payload of 802.2 SNAP frame */ + dev->addr_len = FDDI_K_ALEN; + dev->tx_queue_len = 100; /* Long queues on FDDI */ + dev->flags = IFF_BROADCAST | IFF_MULTICAST; + + memset(dev->broadcast, 0xFF, FDDI_K_ALEN); +} + +/** + * alloc_fddidev - Register FDDI device + * @sizeof_priv: Size of additional driver-private structure to be allocated + * for this FDDI device + * + * Fill in the fields of the device structure with FDDI-generic values. + * + * Constructs a new net device, complete with a private data area of + * size @sizeof_priv. A 32-byte (not bit) alignment is enforced for + * this private data area. + */ +struct net_device *alloc_fddidev(int sizeof_priv) +{ + return alloc_netdev(sizeof_priv, "fddi%d", fddi_setup); +} +EXPORT_SYMBOL(alloc_fddidev); diff --git a/net/802/hippi.c b/net/802/hippi.c new file mode 100644 index 000000000000..4eb135c0afbb --- /dev/null +++ b/net/802/hippi.c @@ -0,0 +1,234 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * HIPPI-type device handling. + * + * Version: @(#)hippi.c 1.0.0 05/29/97 + * + * Authors: Ross Biro, <bir7@leland.Stanford.Edu> + * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> + * Mark Evans, <evansmp@uhura.aston.ac.uk> + * Florian La Roche, <rzsfl@rz.uni-sb.de> + * Alan Cox, <gw4pts@gw4pts.ampr.org> + * Jes Sorensen, <Jes.Sorensen@cern.ch> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/socket.h> +#include <linux/in.h> +#include <linux/inet.h> +#include <linux/netdevice.h> +#include <linux/hippidevice.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <net/arp.h> +#include <net/sock.h> +#include <asm/uaccess.h> +#include <asm/checksum.h> +#include <asm/system.h> + +/* + * Create the HIPPI MAC header for an arbitrary protocol layer + * + * saddr=NULL means use device source address + * daddr=NULL means leave destination address (eg unresolved arp) + */ + +static int hippi_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, void *daddr, void *saddr, + unsigned len) +{ + struct hippi_hdr *hip = (struct hippi_hdr *)skb_push(skb, HIPPI_HLEN); + + if (!len){ + len = skb->len - HIPPI_HLEN; + printk("hippi_header(): length not supplied\n"); + } + + /* + * Due to the stupidity of the little endian byte-order we + * have to set the fp field this way. + */ + hip->fp.fixed = __constant_htonl(0x04800018); + hip->fp.d2_size = htonl(len + 8); + hip->le.fc = 0; + hip->le.double_wide = 0; /* only HIPPI 800 for the time being */ + hip->le.message_type = 0; /* Data PDU */ + + hip->le.dest_addr_type = 2; /* 12 bit SC address */ + hip->le.src_addr_type = 2; /* 12 bit SC address */ + + memcpy(hip->le.src_switch_addr, dev->dev_addr + 3, 3); + memset(&hip->le.reserved, 0, 16); + + hip->snap.dsap = HIPPI_EXTENDED_SAP; + hip->snap.ssap = HIPPI_EXTENDED_SAP; + hip->snap.ctrl = HIPPI_UI_CMD; + hip->snap.oui[0] = 0x00; + hip->snap.oui[1] = 0x00; + hip->snap.oui[2] = 0x00; + hip->snap.ethertype = htons(type); + + if (daddr) + { + memcpy(hip->le.dest_switch_addr, daddr + 3, 3); + memcpy(&skb->private.ifield, daddr + 2, 4); + return HIPPI_HLEN; + } + return -((int)HIPPI_HLEN); +} + + +/* + * Rebuild the HIPPI MAC header. This is called after an ARP has + * completed on this sk_buff. We now let ARP fill in the other fields. + */ + +static int hippi_rebuild_header(struct sk_buff *skb) +{ + struct hippi_hdr *hip = (struct hippi_hdr *)skb->data; + + /* + * Only IP is currently supported + */ + + if(hip->snap.ethertype != __constant_htons(ETH_P_IP)) + { + printk(KERN_DEBUG "%s: unable to resolve type %X addresses.\n",skb->dev->name,ntohs(hip->snap.ethertype)); + return 0; + } + + /* + * We don't support dynamic ARP on HIPPI, but we use the ARP + * static ARP tables to hold the I-FIELDs. + */ + return arp_find(hip->le.daddr, skb); +} + + +/* + * Determine the packet's protocol ID. + */ + +unsigned short hippi_type_trans(struct sk_buff *skb, struct net_device *dev) +{ + struct hippi_hdr *hip; + + hip = (struct hippi_hdr *) skb->data; + + /* + * This is actually wrong ... question is if we really should + * set the raw address here. + */ + skb->mac.raw = skb->data; + skb_pull(skb, HIPPI_HLEN); + + /* + * No fancy promisc stuff here now. + */ + + return hip->snap.ethertype; +} + +EXPORT_SYMBOL(hippi_type_trans); + +static int hippi_change_mtu(struct net_device *dev, int new_mtu) +{ + /* + * HIPPI's got these nice large MTUs. + */ + if ((new_mtu < 68) || (new_mtu > 65280)) + return -EINVAL; + dev->mtu = new_mtu; + return(0); +} + +/* + * For HIPPI we will actually use the lower 4 bytes of the hardware + * address as the I-FIELD rather than the actual hardware address. + */ +static int hippi_mac_addr(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + if (netif_running(dev)) + return -EBUSY; + memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + return 0; +} + +static int hippi_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p) +{ + /* Never send broadcast/multicast ARP messages */ + p->mcast_probes = 0; + + /* In IPv6 unicast probes are valid even on NBMA, + * because they are encapsulated in normal IPv6 protocol. + * Should be a generic flag. + */ + if (p->tbl->family != AF_INET6) + p->ucast_probes = 0; + return 0; +} + +static void hippi_setup(struct net_device *dev) +{ + dev->set_multicast_list = NULL; + dev->change_mtu = hippi_change_mtu; + dev->hard_header = hippi_header; + dev->rebuild_header = hippi_rebuild_header; + dev->set_mac_address = hippi_mac_addr; + dev->hard_header_parse = NULL; + dev->hard_header_cache = NULL; + dev->header_cache_update = NULL; + dev->neigh_setup = hippi_neigh_setup_dev; + + /* + * We don't support HIPPI `ARP' for the time being, and probably + * never will unless someone else implements it. However we + * still need a fake ARPHRD to make ifconfig and friends play ball. + */ + dev->type = ARPHRD_HIPPI; + dev->hard_header_len = HIPPI_HLEN; + dev->mtu = 65280; + dev->addr_len = HIPPI_ALEN; + dev->tx_queue_len = 25 /* 5 */; + memset(dev->broadcast, 0xFF, HIPPI_ALEN); + + + /* + * HIPPI doesn't support broadcast+multicast and we only use + * static ARP tables. ARP is disabled by hippi_neigh_setup_dev. + */ + dev->flags = 0; +} + +/** + * alloc_hippi_dev - Register HIPPI device + * @sizeof_priv: Size of additional driver-private structure to be allocated + * for this HIPPI device + * + * Fill in the fields of the device structure with HIPPI-generic values. + * + * Constructs a new net device, complete with a private data area of + * size @sizeof_priv. A 32-byte (not bit) alignment is enforced for + * this private data area. + */ + +struct net_device *alloc_hippi_dev(int sizeof_priv) +{ + return alloc_netdev(sizeof_priv, "hip%d", hippi_setup); +} + +EXPORT_SYMBOL(alloc_hippi_dev); diff --git a/net/802/p8022.c b/net/802/p8022.c new file mode 100644 index 000000000000..5ae63416df6d --- /dev/null +++ b/net/802/p8022.c @@ -0,0 +1,65 @@ +/* + * NET3: Support for 802.2 demultiplexing off Ethernet (Token ring + * is kept separate see p8022tr.c) + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Demultiplex 802.2 encoded protocols. We match the entry by the + * SSAP/DSAP pair and then deliver to the registered datalink that + * matches. The control byte is ignored and handling of such items + * is up to the routine passed the frame. + * + * Unlike the 802.3 datalink we have a list of 802.2 entries as + * there are multiple protocols to demux. The list is currently + * short (3 or 4 entries at most). The current demux assumes this. + */ +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <net/datalink.h> +#include <linux/mm.h> +#include <linux/in.h> +#include <linux/init.h> +#include <net/llc.h> +#include <net/p8022.h> + +static int p8022_request(struct datalink_proto *dl, struct sk_buff *skb, + unsigned char *dest) +{ + llc_build_and_send_ui_pkt(dl->sap, skb, dest, dl->sap->laddr.lsap); + return 0; +} + +struct datalink_proto *register_8022_client(unsigned char type, + int (*func)(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt)) +{ + struct datalink_proto *proto; + + proto = kmalloc(sizeof(*proto), GFP_ATOMIC); + if (proto) { + proto->type[0] = type; + proto->header_length = 3; + proto->request = p8022_request; + proto->sap = llc_sap_open(type, func); + if (!proto->sap) { + kfree(proto); + proto = NULL; + } + } + return proto; +} + +void unregister_8022_client(struct datalink_proto *proto) +{ + llc_sap_close(proto->sap); + kfree(proto); +} + +EXPORT_SYMBOL(register_8022_client); +EXPORT_SYMBOL(unregister_8022_client); + +MODULE_LICENSE("GPL"); diff --git a/net/802/p8023.c b/net/802/p8023.c new file mode 100644 index 000000000000..a0b61b40225f --- /dev/null +++ b/net/802/p8023.c @@ -0,0 +1,61 @@ +/* + * NET3: 802.3 data link hooks used for IPX 802.3 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * 802.3 isn't really a protocol data link layer. Some old IPX stuff + * uses it however. Note that there is only one 802.3 protocol layer + * in the system. We don't currently support different protocols + * running raw 802.3 on different devices. Thankfully nobody else + * has done anything like the old IPX. + */ + +#include <linux/in.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> + +#include <net/datalink.h> + +/* + * Place an 802.3 header on a packet. The driver will do the mac + * addresses, we just need to give it the buffer length. + */ +static int p8023_request(struct datalink_proto *dl, + struct sk_buff *skb, unsigned char *dest_node) +{ + struct net_device *dev = skb->dev; + + dev->hard_header(skb, dev, ETH_P_802_3, dest_node, NULL, skb->len); + return dev_queue_xmit(skb); +} + +/* + * Create an 802.3 client. Note there can be only one 802.3 client + */ +struct datalink_proto *make_8023_client(void) +{ + struct datalink_proto *proto = kmalloc(sizeof(*proto), GFP_ATOMIC); + + if (proto) { + proto->header_length = 0; + proto->request = p8023_request; + } + return proto; +} + +/* + * Destroy the 802.3 client. + */ +void destroy_8023_client(struct datalink_proto *dl) +{ + if (dl) + kfree(dl); +} + +EXPORT_SYMBOL(destroy_8023_client); +EXPORT_SYMBOL(make_8023_client); diff --git a/net/802/psnap.c b/net/802/psnap.c new file mode 100644 index 000000000000..1053821ddf93 --- /dev/null +++ b/net/802/psnap.c @@ -0,0 +1,159 @@ +/* + * SNAP data link layer. Derived from 802.2 + * + * Alan Cox <Alan.Cox@linux.org>, + * from the 802.2 layer by Greg Page. + * Merged in additions from Greg Page's psnap.c. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <net/datalink.h> +#include <net/llc.h> +#include <net/psnap.h> +#include <linux/mm.h> +#include <linux/in.h> +#include <linux/init.h> + +static LIST_HEAD(snap_list); +static DEFINE_SPINLOCK(snap_lock); +static struct llc_sap *snap_sap; + +/* + * Find a snap client by matching the 5 bytes. + */ +static struct datalink_proto *find_snap_client(unsigned char *desc) +{ + struct list_head *entry; + struct datalink_proto *proto = NULL, *p; + + list_for_each_rcu(entry, &snap_list) { + p = list_entry(entry, struct datalink_proto, node); + if (!memcmp(p->type, desc, 5)) { + proto = p; + break; + } + } + return proto; +} + +/* + * A SNAP packet has arrived + */ +static int snap_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + int rc = 1; + struct datalink_proto *proto; + static struct packet_type snap_packet_type = { + .type = __constant_htons(ETH_P_SNAP), + }; + + rcu_read_lock(); + proto = find_snap_client(skb->h.raw); + if (proto) { + /* Pass the frame on. */ + skb->h.raw += 5; + skb_pull(skb, 5); + rc = proto->rcvfunc(skb, dev, &snap_packet_type); + } else { + skb->sk = NULL; + kfree_skb(skb); + rc = 1; + } + + rcu_read_unlock(); + return rc; +} + +/* + * Put a SNAP header on a frame and pass to 802.2 + */ +static int snap_request(struct datalink_proto *dl, + struct sk_buff *skb, u8 *dest) +{ + memcpy(skb_push(skb, 5), dl->type, 5); + llc_build_and_send_ui_pkt(snap_sap, skb, dest, snap_sap->laddr.lsap); + return 0; +} + +/* + * Set up the SNAP layer + */ +EXPORT_SYMBOL(register_snap_client); +EXPORT_SYMBOL(unregister_snap_client); + +static char snap_err_msg[] __initdata = + KERN_CRIT "SNAP - unable to register with 802.2\n"; + +static int __init snap_init(void) +{ + snap_sap = llc_sap_open(0xAA, snap_rcv); + + if (!snap_sap) + printk(snap_err_msg); + + return 0; +} + +module_init(snap_init); + +static void __exit snap_exit(void) +{ + llc_sap_close(snap_sap); +} + +module_exit(snap_exit); + + +/* + * Register SNAP clients. We don't yet use this for IP. + */ +struct datalink_proto *register_snap_client(unsigned char *desc, + int (*rcvfunc)(struct sk_buff *, + struct net_device *, + struct packet_type *)) +{ + struct datalink_proto *proto = NULL; + + spin_lock_bh(&snap_lock); + + if (find_snap_client(desc)) + goto out; + + proto = kmalloc(sizeof(*proto), GFP_ATOMIC); + if (proto) { + memcpy(proto->type, desc,5); + proto->rcvfunc = rcvfunc; + proto->header_length = 5 + 3; /* snap + 802.2 */ + proto->request = snap_request; + list_add_rcu(&proto->node, &snap_list); + } +out: + spin_unlock_bh(&snap_lock); + + synchronize_net(); + return proto; +} + +/* + * Unregister SNAP clients. Protocols no longer want to play with us ... + */ +void unregister_snap_client(struct datalink_proto *proto) +{ + spin_lock_bh(&snap_lock); + list_del_rcu(&proto->node); + spin_unlock_bh(&snap_lock); + + synchronize_net(); + + kfree(proto); +} + +MODULE_LICENSE("GPL"); diff --git a/net/802/sysctl_net_802.c b/net/802/sysctl_net_802.c new file mode 100644 index 000000000000..36079630c49f --- /dev/null +++ b/net/802/sysctl_net_802.c @@ -0,0 +1,33 @@ +/* -*- linux-c -*- + * sysctl_net_802.c: sysctl interface to net 802 subsystem. + * + * Begun April 1, 1996, Mike Shaver. + * Added /proc/sys/net/802 directory entry (empty =) ). [MS] + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/mm.h> +#include <linux/sysctl.h> +#include <linux/config.h> + +#ifdef CONFIG_TR +extern int sysctl_tr_rif_timeout; +#endif + +struct ctl_table tr_table[] = { +#ifdef CONFIG_TR + { + .ctl_name = NET_TR_RIF_TIMEOUT, + .procname = "rif_timeout", + .data = &sysctl_tr_rif_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec + }, +#endif /* CONFIG_TR */ + { 0 }, +}; diff --git a/net/802/tr.c b/net/802/tr.c new file mode 100644 index 000000000000..85293ccf7efc --- /dev/null +++ b/net/802/tr.c @@ -0,0 +1,645 @@ +/* + * NET3: Token ring device handling subroutines + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Fixes: 3 Feb 97 Paul Norton <pnorton@cts.com> Minor routing fixes. + * Added rif table to /proc/net/tr_rif and rif timeout to + * /proc/sys/net/token-ring/rif_timeout. + * 22 Jun 98 Paul Norton <p.norton@computer.org> Rearranged + * tr_header and tr_type_trans to handle passing IPX SNAP and + * 802.2 through the correct layers. Eliminated tr_reformat. + * + */ + +#include <asm/uaccess.h> +#include <asm/system.h> +#include <linux/config.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/jiffies.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/socket.h> +#include <linux/in.h> +#include <linux/inet.h> +#include <linux/netdevice.h> +#include <linux/trdevice.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/timer.h> +#include <linux/net.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/init.h> +#include <net/arp.h> + +static void tr_add_rif_info(struct trh_hdr *trh, struct net_device *dev); +static void rif_check_expire(unsigned long dummy); + +#define TR_SR_DEBUG 0 + +/* + * Each RIF entry we learn is kept this way + */ + +struct rif_cache_s { + unsigned char addr[TR_ALEN]; + int iface; + __u16 rcf; + __u16 rseg[8]; + struct rif_cache_s *next; + unsigned long last_used; + unsigned char local_ring; +}; + +#define RIF_TABLE_SIZE 32 + +/* + * We hash the RIF cache 32 ways. We do after all have to look it + * up a lot. + */ + +static struct rif_cache_s *rif_table[RIF_TABLE_SIZE]; + +static DEFINE_SPINLOCK(rif_lock); + + +/* + * Garbage disposal timer. + */ + +static struct timer_list rif_timer; + +int sysctl_tr_rif_timeout = 60*10*HZ; + +static inline unsigned long rif_hash(const unsigned char *addr) +{ + unsigned long x; + + x = addr[0]; + x = (x << 2) ^ addr[1]; + x = (x << 2) ^ addr[2]; + x = (x << 2) ^ addr[3]; + x = (x << 2) ^ addr[4]; + x = (x << 2) ^ addr[5]; + + x ^= x >> 8; + + return x & (RIF_TABLE_SIZE - 1); +} + +/* + * Put the headers on a token ring packet. Token ring source routing + * makes this a little more exciting than on ethernet. + */ + +static int tr_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, + void *daddr, void *saddr, unsigned len) +{ + struct trh_hdr *trh; + int hdr_len; + + /* + * Add the 802.2 SNAP header if IP as the IPv4/IPv6 code calls + * dev->hard_header directly. + */ + if (type == ETH_P_IP || type == ETH_P_IPV6 || type == ETH_P_ARP) + { + struct trllc *trllc; + + hdr_len = sizeof(struct trh_hdr) + sizeof(struct trllc); + trh = (struct trh_hdr *)skb_push(skb, hdr_len); + trllc = (struct trllc *)(trh+1); + trllc->dsap = trllc->ssap = EXTENDED_SAP; + trllc->llc = UI_CMD; + trllc->protid[0] = trllc->protid[1] = trllc->protid[2] = 0x00; + trllc->ethertype = htons(type); + } + else + { + hdr_len = sizeof(struct trh_hdr); + trh = (struct trh_hdr *)skb_push(skb, hdr_len); + } + + trh->ac=AC; + trh->fc=LLC_FRAME; + + if(saddr) + memcpy(trh->saddr,saddr,dev->addr_len); + else + memcpy(trh->saddr,dev->dev_addr,dev->addr_len); + + /* + * Build the destination and then source route the frame + */ + + if(daddr) + { + memcpy(trh->daddr,daddr,dev->addr_len); + tr_source_route(skb,trh,dev); + return(hdr_len); + } + + return -hdr_len; +} + +/* + * A neighbour discovery of some species (eg arp) has completed. We + * can now send the packet. + */ + +static int tr_rebuild_header(struct sk_buff *skb) +{ + struct trh_hdr *trh=(struct trh_hdr *)skb->data; + struct trllc *trllc=(struct trllc *)(skb->data+sizeof(struct trh_hdr)); + struct net_device *dev = skb->dev; + + /* + * FIXME: We don't yet support IPv6 over token rings + */ + + if(trllc->ethertype != htons(ETH_P_IP)) { + printk("tr_rebuild_header: Don't know how to resolve type %04X addresses ?\n",(unsigned int)htons(trllc->ethertype)); + return 0; + } + +#ifdef CONFIG_INET + if(arp_find(trh->daddr, skb)) { + return 1; + } + else +#endif + { + tr_source_route(skb,trh,dev); + return 0; + } +} + +/* + * Some of this is a bit hackish. We intercept RIF information + * used for source routing. We also grab IP directly and don't feed + * it via SNAP. + */ + +unsigned short tr_type_trans(struct sk_buff *skb, struct net_device *dev) +{ + + struct trh_hdr *trh=(struct trh_hdr *)skb->data; + struct trllc *trllc; + unsigned riflen=0; + + skb->mac.raw = skb->data; + + if(trh->saddr[0] & TR_RII) + riflen = (ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8; + + trllc = (struct trllc *)(skb->data+sizeof(struct trh_hdr)-TR_MAXRIFLEN+riflen); + + skb_pull(skb,sizeof(struct trh_hdr)-TR_MAXRIFLEN+riflen); + + if(*trh->daddr & 0x80) + { + if(!memcmp(trh->daddr,dev->broadcast,TR_ALEN)) + skb->pkt_type=PACKET_BROADCAST; + else + skb->pkt_type=PACKET_MULTICAST; + } + else if ( (trh->daddr[0] & 0x01) && (trh->daddr[1] & 0x00) && (trh->daddr[2] & 0x5E)) + { + skb->pkt_type=PACKET_MULTICAST; + } + else if(dev->flags & IFF_PROMISC) + { + if(memcmp(trh->daddr, dev->dev_addr, TR_ALEN)) + skb->pkt_type=PACKET_OTHERHOST; + } + + if ((skb->pkt_type != PACKET_BROADCAST) && + (skb->pkt_type != PACKET_MULTICAST)) + tr_add_rif_info(trh,dev) ; + + /* + * Strip the SNAP header from ARP packets since we don't + * pass them through to the 802.2/SNAP layers. + */ + + if (trllc->dsap == EXTENDED_SAP && + (trllc->ethertype == ntohs(ETH_P_IP) || + trllc->ethertype == ntohs(ETH_P_IPV6) || + trllc->ethertype == ntohs(ETH_P_ARP))) + { + skb_pull(skb, sizeof(struct trllc)); + return trllc->ethertype; + } + + return ntohs(ETH_P_802_2); +} + +/* + * We try to do source routing... + */ + +void tr_source_route(struct sk_buff *skb,struct trh_hdr *trh,struct net_device *dev) +{ + int slack; + unsigned int hash; + struct rif_cache_s *entry; + unsigned char *olddata; + static const unsigned char mcast_func_addr[] + = {0xC0,0x00,0x00,0x04,0x00,0x00}; + + spin_lock_bh(&rif_lock); + + /* + * Broadcasts are single route as stated in RFC 1042 + */ + if( (!memcmp(&(trh->daddr[0]),&(dev->broadcast[0]),TR_ALEN)) || + (!memcmp(&(trh->daddr[0]),&(mcast_func_addr[0]), TR_ALEN)) ) + { + trh->rcf=htons((((sizeof(trh->rcf)) << 8) & TR_RCF_LEN_MASK) + | TR_RCF_FRAME2K | TR_RCF_LIMITED_BROADCAST); + trh->saddr[0]|=TR_RII; + } + else + { + hash = rif_hash(trh->daddr); + /* + * Walk the hash table and look for an entry + */ + for(entry=rif_table[hash];entry && memcmp(&(entry->addr[0]),&(trh->daddr[0]),TR_ALEN);entry=entry->next); + + /* + * If we found an entry we can route the frame. + */ + if(entry) + { +#if TR_SR_DEBUG +printk("source routing for %02X:%02X:%02X:%02X:%02X:%02X\n",trh->daddr[0], + trh->daddr[1],trh->daddr[2],trh->daddr[3],trh->daddr[4],trh->daddr[5]); +#endif + if(!entry->local_ring && (ntohs(entry->rcf) & TR_RCF_LEN_MASK) >> 8) + { + trh->rcf=entry->rcf; + memcpy(&trh->rseg[0],&entry->rseg[0],8*sizeof(unsigned short)); + trh->rcf^=htons(TR_RCF_DIR_BIT); + trh->rcf&=htons(0x1fff); /* Issam Chehab <ichehab@madge1.demon.co.uk> */ + + trh->saddr[0]|=TR_RII; +#if TR_SR_DEBUG + printk("entry found with rcf %04x\n", entry->rcf); + } + else + { + printk("entry found but without rcf length, local=%02x\n", entry->local_ring); +#endif + } + entry->last_used=jiffies; + } + else + { + /* + * Without the information we simply have to shout + * on the wire. The replies should rapidly clean this + * situation up. + */ + trh->rcf=htons((((sizeof(trh->rcf)) << 8) & TR_RCF_LEN_MASK) + | TR_RCF_FRAME2K | TR_RCF_LIMITED_BROADCAST); + trh->saddr[0]|=TR_RII; +#if TR_SR_DEBUG + printk("no entry in rif table found - broadcasting frame\n"); +#endif + } + } + + /* Compress the RIF here so we don't have to do it in the driver(s) */ + if (!(trh->saddr[0] & 0x80)) + slack = 18; + else + slack = 18 - ((ntohs(trh->rcf) & TR_RCF_LEN_MASK)>>8); + olddata = skb->data; + spin_unlock_bh(&rif_lock); + + skb_pull(skb, slack); + memmove(skb->data, olddata, sizeof(struct trh_hdr) - slack); +} + +/* + * We have learned some new RIF information for our source + * routing. + */ + +static void tr_add_rif_info(struct trh_hdr *trh, struct net_device *dev) +{ + unsigned int hash, rii_p = 0; + struct rif_cache_s *entry; + + + spin_lock_bh(&rif_lock); + + /* + * Firstly see if the entry exists + */ + + if(trh->saddr[0] & TR_RII) + { + trh->saddr[0]&=0x7f; + if (((ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8) > 2) + { + rii_p = 1; + } + } + + hash = rif_hash(trh->saddr); + for(entry=rif_table[hash];entry && memcmp(&(entry->addr[0]),&(trh->saddr[0]),TR_ALEN);entry=entry->next); + + if(entry==NULL) + { +#if TR_SR_DEBUG +printk("adding rif_entry: addr:%02X:%02X:%02X:%02X:%02X:%02X rcf:%04X\n", + trh->saddr[0],trh->saddr[1],trh->saddr[2], + trh->saddr[3],trh->saddr[4],trh->saddr[5], + ntohs(trh->rcf)); +#endif + /* + * Allocate our new entry. A failure to allocate loses + * use the information. This is harmless. + * + * FIXME: We ought to keep some kind of cache size + * limiting and adjust the timers to suit. + */ + entry=kmalloc(sizeof(struct rif_cache_s),GFP_ATOMIC); + + if(!entry) + { + printk(KERN_DEBUG "tr.c: Couldn't malloc rif cache entry !\n"); + spin_unlock_bh(&rif_lock); + return; + } + + memcpy(&(entry->addr[0]),&(trh->saddr[0]),TR_ALEN); + entry->iface = dev->ifindex; + entry->next=rif_table[hash]; + entry->last_used=jiffies; + rif_table[hash]=entry; + + if (rii_p) + { + entry->rcf = trh->rcf & htons((unsigned short)~TR_RCF_BROADCAST_MASK); + memcpy(&(entry->rseg[0]),&(trh->rseg[0]),8*sizeof(unsigned short)); + entry->local_ring = 0; + trh->saddr[0]|=TR_RII; /* put the routing indicator back for tcpdump */ + } + else + { + entry->local_ring = 1; + } + } + else /* Y. Tahara added */ + { + /* + * Update existing entries + */ + if (!entry->local_ring) + if (entry->rcf != (trh->rcf & htons((unsigned short)~TR_RCF_BROADCAST_MASK)) && + !(trh->rcf & htons(TR_RCF_BROADCAST_MASK))) + { +#if TR_SR_DEBUG +printk("updating rif_entry: addr:%02X:%02X:%02X:%02X:%02X:%02X rcf:%04X\n", + trh->saddr[0],trh->saddr[1],trh->saddr[2], + trh->saddr[3],trh->saddr[4],trh->saddr[5], + ntohs(trh->rcf)); +#endif + entry->rcf = trh->rcf & htons((unsigned short)~TR_RCF_BROADCAST_MASK); + memcpy(&(entry->rseg[0]),&(trh->rseg[0]),8*sizeof(unsigned short)); + } + entry->last_used=jiffies; + } + spin_unlock_bh(&rif_lock); +} + +/* + * Scan the cache with a timer and see what we need to throw out. + */ + +static void rif_check_expire(unsigned long dummy) +{ + int i; + unsigned long next_interval = jiffies + sysctl_tr_rif_timeout/2; + + spin_lock_bh(&rif_lock); + + for(i =0; i < RIF_TABLE_SIZE; i++) { + struct rif_cache_s *entry, **pentry; + + pentry = rif_table+i; + while((entry=*pentry) != NULL) { + unsigned long expires + = entry->last_used + sysctl_tr_rif_timeout; + + if (time_before_eq(expires, jiffies)) { + *pentry = entry->next; + kfree(entry); + } else { + pentry = &entry->next; + + if (time_before(expires, next_interval)) + next_interval = expires; + } + } + } + + spin_unlock_bh(&rif_lock); + + mod_timer(&rif_timer, next_interval); + +} + +/* + * Generate the /proc/net information for the token ring RIF + * routing. + */ + +#ifdef CONFIG_PROC_FS + +static struct rif_cache_s *rif_get_idx(loff_t pos) +{ + int i; + struct rif_cache_s *entry; + loff_t off = 0; + + for(i = 0; i < RIF_TABLE_SIZE; i++) + for(entry = rif_table[i]; entry; entry = entry->next) { + if (off == pos) + return entry; + ++off; + } + + return NULL; +} + +static void *rif_seq_start(struct seq_file *seq, loff_t *pos) +{ + spin_lock_bh(&rif_lock); + + return *pos ? rif_get_idx(*pos - 1) : SEQ_START_TOKEN; +} + +static void *rif_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + int i; + struct rif_cache_s *ent = v; + + ++*pos; + + if (v == SEQ_START_TOKEN) { + i = -1; + goto scan; + } + + if (ent->next) + return ent->next; + + i = rif_hash(ent->addr); + scan: + while (++i < RIF_TABLE_SIZE) { + if ((ent = rif_table[i]) != NULL) + return ent; + } + return NULL; +} + +static void rif_seq_stop(struct seq_file *seq, void *v) +{ + spin_unlock_bh(&rif_lock); +} + +static int rif_seq_show(struct seq_file *seq, void *v) +{ + int j, rcf_len, segment, brdgnmb; + struct rif_cache_s *entry = v; + + if (v == SEQ_START_TOKEN) + seq_puts(seq, + "if TR address TTL rcf routing segments\n"); + else { + struct net_device *dev = dev_get_by_index(entry->iface); + long ttl = (long) (entry->last_used + sysctl_tr_rif_timeout) + - (long) jiffies; + + seq_printf(seq, "%s %02X:%02X:%02X:%02X:%02X:%02X %7li ", + dev?dev->name:"?", + entry->addr[0],entry->addr[1],entry->addr[2], + entry->addr[3],entry->addr[4],entry->addr[5], + ttl/HZ); + + if (entry->local_ring) + seq_puts(seq, "local\n"); + else { + + seq_printf(seq, "%04X", ntohs(entry->rcf)); + rcf_len = ((ntohs(entry->rcf) & TR_RCF_LEN_MASK)>>8)-2; + if (rcf_len) + rcf_len >>= 1; + for(j = 1; j < rcf_len; j++) { + if(j==1) { + segment=ntohs(entry->rseg[j-1])>>4; + seq_printf(seq," %03X",segment); + }; + segment=ntohs(entry->rseg[j])>>4; + brdgnmb=ntohs(entry->rseg[j-1])&0x00f; + seq_printf(seq,"-%01X-%03X",brdgnmb,segment); + } + seq_putc(seq, '\n'); + } + } + return 0; +} + + +static struct seq_operations rif_seq_ops = { + .start = rif_seq_start, + .next = rif_seq_next, + .stop = rif_seq_stop, + .show = rif_seq_show, +}; + +static int rif_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &rif_seq_ops); +} + +static struct file_operations rif_seq_fops = { + .owner = THIS_MODULE, + .open = rif_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +#endif + +static void tr_setup(struct net_device *dev) +{ + /* + * Configure and register + */ + + dev->hard_header = tr_header; + dev->rebuild_header = tr_rebuild_header; + + dev->type = ARPHRD_IEEE802_TR; + dev->hard_header_len = TR_HLEN; + dev->mtu = 2000; + dev->addr_len = TR_ALEN; + dev->tx_queue_len = 100; /* Long queues on tr */ + + memset(dev->broadcast,0xFF, TR_ALEN); + + /* New-style flags. */ + dev->flags = IFF_BROADCAST | IFF_MULTICAST ; +} + +/** + * alloc_trdev - Register token ring device + * @sizeof_priv: Size of additional driver-private structure to be allocated + * for this token ring device + * + * Fill in the fields of the device structure with token ring-generic values. + * + * Constructs a new net device, complete with a private data area of + * size @sizeof_priv. A 32-byte (not bit) alignment is enforced for + * this private data area. + */ +struct net_device *alloc_trdev(int sizeof_priv) +{ + return alloc_netdev(sizeof_priv, "tr%d", tr_setup); +} + +/* + * Called during bootup. We don't actually have to initialise + * too much for this. + */ + +static int __init rif_init(void) +{ + init_timer(&rif_timer); + rif_timer.expires = sysctl_tr_rif_timeout; + rif_timer.data = 0L; + rif_timer.function = rif_check_expire; + add_timer(&rif_timer); + + proc_net_fops_create("tr_rif", S_IRUGO, &rif_seq_fops); + return 0; +} + +module_init(rif_init); + +EXPORT_SYMBOL(tr_source_route); +EXPORT_SYMBOL(tr_type_trans); +EXPORT_SYMBOL(alloc_trdev); diff --git a/net/8021q/Makefile b/net/8021q/Makefile new file mode 100644 index 000000000000..97feb44dbdce --- /dev/null +++ b/net/8021q/Makefile @@ -0,0 +1,12 @@ +# +# Makefile for the Linux VLAN layer. +# + +obj-$(CONFIG_VLAN_8021Q) += 8021q.o + +8021q-objs := vlan.o vlan_dev.o + +ifeq ($(CONFIG_PROC_FS),y) +8021q-objs += vlanproc.o +endif + diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c new file mode 100644 index 000000000000..1f6d31670bc7 --- /dev/null +++ b/net/8021q/vlan.c @@ -0,0 +1,774 @@ +/* + * INET 802.1Q VLAN + * Ethernet-type device handling. + * + * Authors: Ben Greear <greearb@candelatech.com> + * Please send support related email to: vlan@scry.wanfear.com + * VLAN Home Page: http://www.candelatech.com/~greear/vlan.html + * + * Fixes: + * Fix for packet capture - Nick Eggleston <nick@dccinc.com>; + * Add HW acceleration hooks - David S. Miller <davem@redhat.com>; + * Correct all the locking - David S. Miller <davem@redhat.com>; + * Use hash table for VLAN groups - David S. Miller <davem@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <asm/uaccess.h> /* for copy_from_user */ +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <net/datalink.h> +#include <linux/mm.h> +#include <linux/in.h> +#include <linux/init.h> +#include <net/p8022.h> +#include <net/arp.h> +#include <linux/rtnetlink.h> +#include <linux/notifier.h> + +#include <linux/if_vlan.h> +#include "vlan.h" +#include "vlanproc.h" + +#define DRV_VERSION "1.8" + +/* Global VLAN variables */ + +/* Our listing of VLAN group(s) */ +static struct hlist_head vlan_group_hash[VLAN_GRP_HASH_SIZE]; +#define vlan_grp_hashfn(IDX) ((((IDX) >> VLAN_GRP_HASH_SHIFT) ^ (IDX)) & VLAN_GRP_HASH_MASK) + +static char vlan_fullname[] = "802.1Q VLAN Support"; +static char vlan_version[] = DRV_VERSION; +static char vlan_copyright[] = "Ben Greear <greearb@candelatech.com>"; +static char vlan_buggyright[] = "David S. Miller <davem@redhat.com>"; + +static int vlan_device_event(struct notifier_block *, unsigned long, void *); +static int vlan_ioctl_handler(void __user *); +static int unregister_vlan_dev(struct net_device *, unsigned short ); + +static struct notifier_block vlan_notifier_block = { + .notifier_call = vlan_device_event, +}; + +/* These may be changed at run-time through IOCTLs */ + +/* Determines interface naming scheme. */ +unsigned short vlan_name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD; + +static struct packet_type vlan_packet_type = { + .type = __constant_htons(ETH_P_8021Q), + .func = vlan_skb_recv, /* VLAN receive method */ +}; + +/* Bits of netdev state that are propagated from real device to virtual */ +#define VLAN_LINK_STATE_MASK \ + ((1<<__LINK_STATE_PRESENT)|(1<<__LINK_STATE_NOCARRIER)) + +/* End of global variables definitions. */ + +/* + * Function vlan_proto_init (pro) + * + * Initialize VLAN protocol layer, + * + */ +static int __init vlan_proto_init(void) +{ + int err; + + printk(VLAN_INF "%s v%s %s\n", + vlan_fullname, vlan_version, vlan_copyright); + printk(VLAN_INF "All bugs added by %s\n", + vlan_buggyright); + + /* proc file system initialization */ + err = vlan_proc_init(); + if (err < 0) { + printk(KERN_ERR + "%s %s: can't create entry in proc filesystem!\n", + __FUNCTION__, VLAN_NAME); + return err; + } + + dev_add_pack(&vlan_packet_type); + + /* Register us to receive netdevice events */ + err = register_netdevice_notifier(&vlan_notifier_block); + if (err < 0) { + dev_remove_pack(&vlan_packet_type); + vlan_proc_cleanup(); + return err; + } + + vlan_ioctl_set(vlan_ioctl_handler); + + return 0; +} + +/* Cleanup all vlan devices + * Note: devices that have been registered that but not + * brought up will exist but have no module ref count. + */ +static void __exit vlan_cleanup_devices(void) +{ + struct net_device *dev, *nxt; + + rtnl_lock(); + for (dev = dev_base; dev; dev = nxt) { + nxt = dev->next; + if (dev->priv_flags & IFF_802_1Q_VLAN) { + unregister_vlan_dev(VLAN_DEV_INFO(dev)->real_dev, + VLAN_DEV_INFO(dev)->vlan_id); + + unregister_netdevice(dev); + } + } + rtnl_unlock(); +} + +/* + * Module 'remove' entry point. + * o delete /proc/net/router directory and static entries. + */ +static void __exit vlan_cleanup_module(void) +{ + int i; + + vlan_ioctl_set(NULL); + + /* Un-register us from receiving netdevice events */ + unregister_netdevice_notifier(&vlan_notifier_block); + + dev_remove_pack(&vlan_packet_type); + vlan_cleanup_devices(); + + /* This table must be empty if there are no module + * references left. + */ + for (i = 0; i < VLAN_GRP_HASH_SIZE; i++) { + BUG_ON(!hlist_empty(&vlan_group_hash[i])); + } + vlan_proc_cleanup(); + + synchronize_net(); +} + +module_init(vlan_proto_init); +module_exit(vlan_cleanup_module); + +/* Must be invoked with RCU read lock (no preempt) */ +static struct vlan_group *__vlan_find_group(int real_dev_ifindex) +{ + struct vlan_group *grp; + struct hlist_node *n; + int hash = vlan_grp_hashfn(real_dev_ifindex); + + hlist_for_each_entry_rcu(grp, n, &vlan_group_hash[hash], hlist) { + if (grp->real_dev_ifindex == real_dev_ifindex) + return grp; + } + + return NULL; +} + +/* Find the protocol handler. Assumes VID < VLAN_VID_MASK. + * + * Must be invoked with RCU read lock (no preempt) + */ +struct net_device *__find_vlan_dev(struct net_device *real_dev, + unsigned short VID) +{ + struct vlan_group *grp = __vlan_find_group(real_dev->ifindex); + + if (grp) + return grp->vlan_devices[VID]; + + return NULL; +} + +static void vlan_rcu_free(struct rcu_head *rcu) +{ + kfree(container_of(rcu, struct vlan_group, rcu)); +} + + +/* This returns 0 if everything went fine. + * It will return 1 if the group was killed as a result. + * A negative return indicates failure. + * + * The RTNL lock must be held. + */ +static int unregister_vlan_dev(struct net_device *real_dev, + unsigned short vlan_id) +{ + struct net_device *dev = NULL; + int real_dev_ifindex = real_dev->ifindex; + struct vlan_group *grp; + int i, ret; + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: VID: %i\n", __FUNCTION__, vlan_id); +#endif + + /* sanity check */ + if (vlan_id >= VLAN_VID_MASK) + return -EINVAL; + + ASSERT_RTNL(); + grp = __vlan_find_group(real_dev_ifindex); + + ret = 0; + + if (grp) { + dev = grp->vlan_devices[vlan_id]; + if (dev) { + /* Remove proc entry */ + vlan_proc_rem_dev(dev); + + /* Take it out of our own structures, but be sure to + * interlock with HW accelerating devices or SW vlan + * input packet processing. + */ + if (real_dev->features & + (NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER)) { + real_dev->vlan_rx_kill_vid(real_dev, vlan_id); + } + + grp->vlan_devices[vlan_id] = NULL; + synchronize_net(); + + + /* Caller unregisters (and if necessary, puts) + * VLAN device, but we get rid of the reference to + * real_dev here. + */ + dev_put(real_dev); + + /* If the group is now empty, kill off the + * group. + */ + for (i = 0; i < VLAN_VID_MASK; i++) + if (grp->vlan_devices[i]) + break; + + if (i == VLAN_VID_MASK) { + if (real_dev->features & NETIF_F_HW_VLAN_RX) + real_dev->vlan_rx_register(real_dev, NULL); + + hlist_del_rcu(&grp->hlist); + + /* Free the group, after all cpu's are done. */ + call_rcu(&grp->rcu, vlan_rcu_free); + + grp = NULL; + ret = 1; + } + } + } + + return ret; +} + +static int unregister_vlan_device(const char *vlan_IF_name) +{ + struct net_device *dev = NULL; + int ret; + + + dev = dev_get_by_name(vlan_IF_name); + ret = -EINVAL; + if (dev) { + if (dev->priv_flags & IFF_802_1Q_VLAN) { + rtnl_lock(); + + ret = unregister_vlan_dev(VLAN_DEV_INFO(dev)->real_dev, + VLAN_DEV_INFO(dev)->vlan_id); + + dev_put(dev); + unregister_netdevice(dev); + + rtnl_unlock(); + + if (ret == 1) + ret = 0; + } else { + printk(VLAN_ERR + "%s: ERROR: Tried to remove a non-vlan device " + "with VLAN code, name: %s priv_flags: %hX\n", + __FUNCTION__, dev->name, dev->priv_flags); + dev_put(dev); + ret = -EPERM; + } + } else { +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: WARNING: Could not find dev.\n", __FUNCTION__); +#endif + ret = -EINVAL; + } + + return ret; +} + +static void vlan_setup(struct net_device *new_dev) +{ + SET_MODULE_OWNER(new_dev); + + /* new_dev->ifindex = 0; it will be set when added to + * the global list. + * iflink is set as well. + */ + new_dev->get_stats = vlan_dev_get_stats; + + /* Make this thing known as a VLAN device */ + new_dev->priv_flags |= IFF_802_1Q_VLAN; + + /* Set us up to have no queue, as the underlying Hardware device + * can do all the queueing we could want. + */ + new_dev->tx_queue_len = 0; + + /* set up method calls */ + new_dev->change_mtu = vlan_dev_change_mtu; + new_dev->open = vlan_dev_open; + new_dev->stop = vlan_dev_stop; + new_dev->set_mac_address = vlan_dev_set_mac_address; + new_dev->set_multicast_list = vlan_dev_set_multicast_list; + new_dev->destructor = free_netdev; + new_dev->do_ioctl = vlan_dev_ioctl; +} + +/* Attach a VLAN device to a mac address (ie Ethernet Card). + * Returns the device that was created, or NULL if there was + * an error of some kind. + */ +static struct net_device *register_vlan_device(const char *eth_IF_name, + unsigned short VLAN_ID) +{ + struct vlan_group *grp; + struct net_device *new_dev; + struct net_device *real_dev; /* the ethernet device */ + char name[IFNAMSIZ]; + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: if_name -:%s:- vid: %i\n", + __FUNCTION__, eth_IF_name, VLAN_ID); +#endif + + if (VLAN_ID >= VLAN_VID_MASK) + goto out_ret_null; + + /* find the device relating to eth_IF_name. */ + real_dev = dev_get_by_name(eth_IF_name); + if (!real_dev) + goto out_ret_null; + + if (real_dev->features & NETIF_F_VLAN_CHALLENGED) { + printk(VLAN_DBG "%s: VLANs not supported on %s.\n", + __FUNCTION__, real_dev->name); + goto out_put_dev; + } + + if ((real_dev->features & NETIF_F_HW_VLAN_RX) && + (real_dev->vlan_rx_register == NULL || + real_dev->vlan_rx_kill_vid == NULL)) { + printk(VLAN_DBG "%s: Device %s has buggy VLAN hw accel.\n", + __FUNCTION__, real_dev->name); + goto out_put_dev; + } + + if ((real_dev->features & NETIF_F_HW_VLAN_FILTER) && + (real_dev->vlan_rx_add_vid == NULL || + real_dev->vlan_rx_kill_vid == NULL)) { + printk(VLAN_DBG "%s: Device %s has buggy VLAN hw accel.\n", + __FUNCTION__, real_dev->name); + goto out_put_dev; + } + + /* From this point on, all the data structures must remain + * consistent. + */ + rtnl_lock(); + + /* The real device must be up and operating in order to + * assosciate a VLAN device with it. + */ + if (!(real_dev->flags & IFF_UP)) + goto out_unlock; + + if (__find_vlan_dev(real_dev, VLAN_ID) != NULL) { + /* was already registered. */ + printk(VLAN_DBG "%s: ALREADY had VLAN registered\n", __FUNCTION__); + goto out_unlock; + } + + /* Gotta set up the fields for the device. */ +#ifdef VLAN_DEBUG + printk(VLAN_DBG "About to allocate name, vlan_name_type: %i\n", + vlan_name_type); +#endif + switch (vlan_name_type) { + case VLAN_NAME_TYPE_RAW_PLUS_VID: + /* name will look like: eth1.0005 */ + snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, VLAN_ID); + break; + case VLAN_NAME_TYPE_PLUS_VID_NO_PAD: + /* Put our vlan.VID in the name. + * Name will look like: vlan5 + */ + snprintf(name, IFNAMSIZ, "vlan%i", VLAN_ID); + break; + case VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD: + /* Put our vlan.VID in the name. + * Name will look like: eth0.5 + */ + snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, VLAN_ID); + break; + case VLAN_NAME_TYPE_PLUS_VID: + /* Put our vlan.VID in the name. + * Name will look like: vlan0005 + */ + default: + snprintf(name, IFNAMSIZ, "vlan%.4i", VLAN_ID); + }; + + new_dev = alloc_netdev(sizeof(struct vlan_dev_info), name, + vlan_setup); + if (new_dev == NULL) + goto out_unlock; + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "Allocated new name -:%s:-\n", new_dev->name); +#endif + /* IFF_BROADCAST|IFF_MULTICAST; ??? */ + new_dev->flags = real_dev->flags; + new_dev->flags &= ~IFF_UP; + + new_dev->state = real_dev->state & VLAN_LINK_STATE_MASK; + + /* need 4 bytes for extra VLAN header info, + * hope the underlying device can handle it. + */ + new_dev->mtu = real_dev->mtu; + + /* TODO: maybe just assign it to be ETHERNET? */ + new_dev->type = real_dev->type; + + new_dev->hard_header_len = real_dev->hard_header_len; + if (!(real_dev->features & NETIF_F_HW_VLAN_TX)) { + /* Regular ethernet + 4 bytes (18 total). */ + new_dev->hard_header_len += VLAN_HLEN; + } + + VLAN_MEM_DBG("new_dev->priv malloc, addr: %p size: %i\n", + new_dev->priv, + sizeof(struct vlan_dev_info)); + + memcpy(new_dev->broadcast, real_dev->broadcast, real_dev->addr_len); + memcpy(new_dev->dev_addr, real_dev->dev_addr, real_dev->addr_len); + new_dev->addr_len = real_dev->addr_len; + + if (real_dev->features & NETIF_F_HW_VLAN_TX) { + new_dev->hard_header = real_dev->hard_header; + new_dev->hard_start_xmit = vlan_dev_hwaccel_hard_start_xmit; + new_dev->rebuild_header = real_dev->rebuild_header; + } else { + new_dev->hard_header = vlan_dev_hard_header; + new_dev->hard_start_xmit = vlan_dev_hard_start_xmit; + new_dev->rebuild_header = vlan_dev_rebuild_header; + } + new_dev->hard_header_parse = real_dev->hard_header_parse; + + VLAN_DEV_INFO(new_dev)->vlan_id = VLAN_ID; /* 1 through VLAN_VID_MASK */ + VLAN_DEV_INFO(new_dev)->real_dev = real_dev; + VLAN_DEV_INFO(new_dev)->dent = NULL; + VLAN_DEV_INFO(new_dev)->flags = 1; + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "About to go find the group for idx: %i\n", + real_dev->ifindex); +#endif + + if (register_netdevice(new_dev)) + goto out_free_newdev; + + /* So, got the sucker initialized, now lets place + * it into our local structure. + */ + grp = __vlan_find_group(real_dev->ifindex); + + /* Note, we are running under the RTNL semaphore + * so it cannot "appear" on us. + */ + if (!grp) { /* need to add a new group */ + grp = kmalloc(sizeof(struct vlan_group), GFP_KERNEL); + if (!grp) + goto out_free_unregister; + + /* printk(KERN_ALERT "VLAN REGISTER: Allocated new group.\n"); */ + memset(grp, 0, sizeof(struct vlan_group)); + grp->real_dev_ifindex = real_dev->ifindex; + + hlist_add_head_rcu(&grp->hlist, + &vlan_group_hash[vlan_grp_hashfn(real_dev->ifindex)]); + + if (real_dev->features & NETIF_F_HW_VLAN_RX) + real_dev->vlan_rx_register(real_dev, grp); + } + + grp->vlan_devices[VLAN_ID] = new_dev; + + if (vlan_proc_add_dev(new_dev)<0)/* create it's proc entry */ + printk(KERN_WARNING "VLAN: failed to add proc entry for %s\n", + new_dev->name); + + if (real_dev->features & NETIF_F_HW_VLAN_FILTER) + real_dev->vlan_rx_add_vid(real_dev, VLAN_ID); + + rtnl_unlock(); + + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "Allocated new device successfully, returning.\n"); +#endif + return new_dev; + +out_free_unregister: + unregister_netdev(new_dev); + goto out_unlock; + +out_free_newdev: + free_netdev(new_dev); + +out_unlock: + rtnl_unlock(); + +out_put_dev: + dev_put(real_dev); + +out_ret_null: + return NULL; +} + +static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) +{ + struct net_device *dev = ptr; + struct vlan_group *grp = __vlan_find_group(dev->ifindex); + int i, flgs; + struct net_device *vlandev; + + if (!grp) + goto out; + + /* It is OK that we do not hold the group lock right now, + * as we run under the RTNL lock. + */ + + switch (event) { + case NETDEV_CHANGE: + /* Propagate real device state to vlan devices */ + flgs = dev->state & VLAN_LINK_STATE_MASK; + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + vlandev = grp->vlan_devices[i]; + if (!vlandev) + continue; + + if ((vlandev->state & VLAN_LINK_STATE_MASK) != flgs) { + vlandev->state = (vlandev->state &~ VLAN_LINK_STATE_MASK) + | flgs; + netdev_state_change(vlandev); + } + } + break; + + case NETDEV_DOWN: + /* Put all VLANs for this dev in the down state too. */ + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + vlandev = grp->vlan_devices[i]; + if (!vlandev) + continue; + + flgs = vlandev->flags; + if (!(flgs & IFF_UP)) + continue; + + dev_change_flags(vlandev, flgs & ~IFF_UP); + } + break; + + case NETDEV_UP: + /* Put all VLANs for this dev in the up state too. */ + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + vlandev = grp->vlan_devices[i]; + if (!vlandev) + continue; + + flgs = vlandev->flags; + if (flgs & IFF_UP) + continue; + + dev_change_flags(vlandev, flgs | IFF_UP); + } + break; + + case NETDEV_UNREGISTER: + /* Delete all VLANs for this dev. */ + for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { + int ret; + + vlandev = grp->vlan_devices[i]; + if (!vlandev) + continue; + + ret = unregister_vlan_dev(dev, + VLAN_DEV_INFO(vlandev)->vlan_id); + + unregister_netdevice(vlandev); + + /* Group was destroyed? */ + if (ret == 1) + break; + } + break; + }; + +out: + return NOTIFY_DONE; +} + +/* + * VLAN IOCTL handler. + * o execute requested action or pass command to the device driver + * arg is really a struct vlan_ioctl_args __user *. + */ +static int vlan_ioctl_handler(void __user *arg) +{ + int err = 0; + unsigned short vid = 0; + struct vlan_ioctl_args args; + + if (copy_from_user(&args, arg, sizeof(struct vlan_ioctl_args))) + return -EFAULT; + + /* Null terminate this sucker, just in case. */ + args.device1[23] = 0; + args.u.device2[23] = 0; + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: args.cmd: %x\n", __FUNCTION__, args.cmd); +#endif + + switch (args.cmd) { + case SET_VLAN_INGRESS_PRIORITY_CMD: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + err = vlan_dev_set_ingress_priority(args.device1, + args.u.skb_priority, + args.vlan_qos); + break; + + case SET_VLAN_EGRESS_PRIORITY_CMD: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + err = vlan_dev_set_egress_priority(args.device1, + args.u.skb_priority, + args.vlan_qos); + break; + + case SET_VLAN_FLAG_CMD: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + err = vlan_dev_set_vlan_flag(args.device1, + args.u.flag, + args.vlan_qos); + break; + + case SET_VLAN_NAME_TYPE_CMD: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if ((args.u.name_type >= 0) && + (args.u.name_type < VLAN_NAME_TYPE_HIGHEST)) { + vlan_name_type = args.u.name_type; + err = 0; + } else { + err = -EINVAL; + } + break; + + case ADD_VLAN_CMD: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* we have been given the name of the Ethernet Device we want to + * talk to: args.dev1 We also have the + * VLAN ID: args.u.VID + */ + if (register_vlan_device(args.device1, args.u.VID)) { + err = 0; + } else { + err = -EINVAL; + } + break; + + case DEL_VLAN_CMD: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* Here, the args.dev1 is the actual VLAN we want + * to get rid of. + */ + err = unregister_vlan_device(args.device1); + break; + + case GET_VLAN_INGRESS_PRIORITY_CMD: + /* TODO: Implement + err = vlan_dev_get_ingress_priority(args); + if (copy_to_user((void*)arg, &args, + sizeof(struct vlan_ioctl_args))) { + err = -EFAULT; + } + */ + err = -EINVAL; + break; + case GET_VLAN_EGRESS_PRIORITY_CMD: + /* TODO: Implement + err = vlan_dev_get_egress_priority(args.device1, &(args.args); + if (copy_to_user((void*)arg, &args, + sizeof(struct vlan_ioctl_args))) { + err = -EFAULT; + } + */ + err = -EINVAL; + break; + case GET_VLAN_REALDEV_NAME_CMD: + err = vlan_dev_get_realdev_name(args.device1, args.u.device2); + if (copy_to_user(arg, &args, + sizeof(struct vlan_ioctl_args))) { + err = -EFAULT; + } + break; + + case GET_VLAN_VID_CMD: + err = vlan_dev_get_vid(args.device1, &vid); + args.u.VID = vid; + if (copy_to_user(arg, &args, + sizeof(struct vlan_ioctl_args))) { + err = -EFAULT; + } + break; + + default: + /* pass on to underlying device instead?? */ + printk(VLAN_DBG "%s: Unknown VLAN CMD: %x \n", + __FUNCTION__, args.cmd); + return -EINVAL; + }; + + return err; +} + +MODULE_LICENSE("GPL"); +MODULE_VERSION(DRV_VERSION); diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h new file mode 100644 index 000000000000..508b1fa14546 --- /dev/null +++ b/net/8021q/vlan.h @@ -0,0 +1,72 @@ +#ifndef __BEN_VLAN_802_1Q_INC__ +#define __BEN_VLAN_802_1Q_INC__ + +#include <linux/if_vlan.h> + +/* Uncomment this if you want debug traces to be shown. */ +/* #define VLAN_DEBUG */ + +#define VLAN_ERR KERN_ERR +#define VLAN_INF KERN_INFO +#define VLAN_DBG KERN_ALERT /* change these... to debug, having a hard time + * changing the log level at run-time..for some reason. + */ + +/* + +These I use for memory debugging. I feared a leak at one time, but +I never found it..and the problem seems to have dissappeared. Still, +I'll bet they might prove useful again... --Ben + + +#define VLAN_MEM_DBG(x, y, z) printk(VLAN_DBG "%s: " x, __FUNCTION__, y, z); +#define VLAN_FMEM_DBG(x, y) printk(VLAN_DBG "%s: " x, __FUNCTION__, y); +*/ + +/* This way they don't do anything! */ +#define VLAN_MEM_DBG(x, y, z) +#define VLAN_FMEM_DBG(x, y) + + +extern unsigned short vlan_name_type; + +#define VLAN_GRP_HASH_SHIFT 5 +#define VLAN_GRP_HASH_SIZE (1 << VLAN_GRP_HASH_SHIFT) +#define VLAN_GRP_HASH_MASK (VLAN_GRP_HASH_SIZE - 1) + +/* Find a VLAN device by the MAC address of its Ethernet device, and + * it's VLAN ID. The default configuration is to have VLAN's scope + * to be box-wide, so the MAC will be ignored. The mac will only be + * looked at if we are configured to have a separate set of VLANs per + * each MAC addressable interface. Note that this latter option does + * NOT follow the spec for VLANs, but may be useful for doing very + * large quantities of VLAN MUX/DEMUX onto FrameRelay or ATM PVCs. + * + * Must be invoked with rcu_read_lock (ie preempt disabled) + * or with RTNL. + */ +struct net_device *__find_vlan_dev(struct net_device* real_dev, + unsigned short VID); /* vlan.c */ + +/* found in vlan_dev.c */ +int vlan_dev_rebuild_header(struct sk_buff *skb); +int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, + struct packet_type* ptype); +int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, void *daddr, void *saddr, + unsigned len); +int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev); +int vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, struct net_device *dev); +int vlan_dev_change_mtu(struct net_device *dev, int new_mtu); +int vlan_dev_set_mac_address(struct net_device *dev, void* addr); +int vlan_dev_open(struct net_device* dev); +int vlan_dev_stop(struct net_device* dev); +int vlan_dev_ioctl(struct net_device* dev, struct ifreq *ifr, int cmd); +int vlan_dev_set_ingress_priority(char* dev_name, __u32 skb_prio, short vlan_prio); +int vlan_dev_set_egress_priority(char* dev_name, __u32 skb_prio, short vlan_prio); +int vlan_dev_set_vlan_flag(char* dev_name, __u32 flag, short flag_val); +int vlan_dev_get_realdev_name(const char* dev_name, char* result); +int vlan_dev_get_vid(const char* dev_name, unsigned short* result); +void vlan_dev_set_multicast_list(struct net_device *vlan_dev); + +#endif /* !(__BEN_VLAN_802_1Q_INC__) */ diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c new file mode 100644 index 000000000000..49c487413518 --- /dev/null +++ b/net/8021q/vlan_dev.c @@ -0,0 +1,890 @@ +/* -*- linux-c -*- + * INET 802.1Q VLAN + * Ethernet-type device handling. + * + * Authors: Ben Greear <greearb@candelatech.com> + * Please send support related email to: vlan@scry.wanfear.com + * VLAN Home Page: http://www.candelatech.com/~greear/vlan.html + * + * Fixes: Mar 22 2001: Martin Bokaemper <mbokaemper@unispherenetworks.com> + * - reset skb->pkt_type on incoming packets when MAC was changed + * - see that changed MAC is saddr for outgoing packets + * Oct 20, 2001: Ard van Breeman: + * - Fix MC-list, finally. + * - Flush MC-list on VLAN destroy. + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/in.h> +#include <linux/init.h> +#include <asm/uaccess.h> /* for copy_from_user */ +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <net/datalink.h> +#include <net/p8022.h> +#include <net/arp.h> + +#include "vlan.h" +#include "vlanproc.h" +#include <linux/if_vlan.h> +#include <net/ip.h> + +/* + * Rebuild the Ethernet MAC header. This is called after an ARP + * (or in future other address resolution) has completed on this + * sk_buff. We now let ARP fill in the other fields. + * + * This routine CANNOT use cached dst->neigh! + * Really, it is used only when dst->neigh is wrong. + * + * TODO: This needs a checkup, I'm ignorant here. --BLG + */ +int vlan_dev_rebuild_header(struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); + + switch (veth->h_vlan_encapsulated_proto) { +#ifdef CONFIG_INET + case __constant_htons(ETH_P_IP): + + /* TODO: Confirm this will work with VLAN headers... */ + return arp_find(veth->h_dest, skb); +#endif + default: + printk(VLAN_DBG + "%s: unable to resolve type %X addresses.\n", + dev->name, (int)veth->h_vlan_encapsulated_proto); + + memcpy(veth->h_source, dev->dev_addr, ETH_ALEN); + break; + }; + + return 0; +} + +static inline struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb) +{ + if (VLAN_DEV_INFO(skb->dev)->flags & 1) { + if (skb_shared(skb) || skb_cloned(skb)) { + struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); + kfree_skb(skb); + skb = nskb; + } + if (skb) { + /* Lifted from Gleb's VLAN code... */ + memmove(skb->data - ETH_HLEN, + skb->data - VLAN_ETH_HLEN, 12); + skb->mac.raw += VLAN_HLEN; + } + } + + return skb; +} + +/* + * Determine the packet's protocol ID. The rule here is that we + * assume 802.3 if the type field is short enough to be a length. + * This is normal practice and works for any 'now in use' protocol. + * + * Also, at this point we assume that we ARE dealing exclusively with + * VLAN packets, or packets that should be made into VLAN packets based + * on a default VLAN ID. + * + * NOTE: Should be similar to ethernet/eth.c. + * + * SANITY NOTE: This method is called when a packet is moving up the stack + * towards userland. To get here, it would have already passed + * through the ethernet/eth.c eth_type_trans() method. + * SANITY NOTE 2: We are referencing to the VLAN_HDR frields, which MAY be + * stored UNALIGNED in the memory. RISC systems don't like + * such cases very much... + * SANITY NOTE 2a: According to Dave Miller & Alexey, it will always be aligned, + * so there doesn't need to be any of the unaligned stuff. It has + * been commented out now... --Ben + * + */ +int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, + struct packet_type* ptype) +{ + unsigned char *rawp = NULL; + struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data); + unsigned short vid; + struct net_device_stats *stats; + unsigned short vlan_TCI; + unsigned short proto; + + /* vlan_TCI = ntohs(get_unaligned(&vhdr->h_vlan_TCI)); */ + vlan_TCI = ntohs(vhdr->h_vlan_TCI); + + vid = (vlan_TCI & VLAN_VID_MASK); + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: skb: %p vlan_id: %hx\n", + __FUNCTION__, skb, vid); +#endif + + /* Ok, we will find the correct VLAN device, strip the header, + * and then go on as usual. + */ + + /* We have 12 bits of vlan ID. + * + * We must not drop allow preempt until we hold a + * reference to the device (netif_rx does that) or we + * fail. + */ + + rcu_read_lock(); + skb->dev = __find_vlan_dev(dev, vid); + if (!skb->dev) { + rcu_read_unlock(); + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: ERROR: No net_device for VID: %i on dev: %s [%i]\n", + __FUNCTION__, (unsigned int)(vid), dev->name, dev->ifindex); +#endif + kfree_skb(skb); + return -1; + } + + skb->dev->last_rx = jiffies; + + /* Bump the rx counters for the VLAN device. */ + stats = vlan_dev_get_stats(skb->dev); + stats->rx_packets++; + stats->rx_bytes += skb->len; + + skb_pull(skb, VLAN_HLEN); /* take off the VLAN header (4 bytes currently) */ + + /* Ok, lets check to make sure the device (dev) we + * came in on is what this VLAN is attached to. + */ + + if (dev != VLAN_DEV_INFO(skb->dev)->real_dev) { + rcu_read_unlock(); + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: dropping skb: %p because came in on wrong device, dev: %s real_dev: %s, skb_dev: %s\n", + __FUNCTION__, skb, dev->name, + VLAN_DEV_INFO(skb->dev)->real_dev->name, + skb->dev->name); +#endif + kfree_skb(skb); + stats->rx_errors++; + return -1; + } + + /* + * Deal with ingress priority mapping. + */ + skb->priority = vlan_get_ingress_priority(skb->dev, ntohs(vhdr->h_vlan_TCI)); + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: priority: %lu for TCI: %hu (hbo)\n", + __FUNCTION__, (unsigned long)(skb->priority), + ntohs(vhdr->h_vlan_TCI)); +#endif + + /* The ethernet driver already did the pkt_type calculations + * for us... + */ + switch (skb->pkt_type) { + case PACKET_BROADCAST: /* Yeah, stats collect these together.. */ + // stats->broadcast ++; // no such counter :-( + break; + + case PACKET_MULTICAST: + stats->multicast++; + break; + + case PACKET_OTHERHOST: + /* Our lower layer thinks this is not local, let's make sure. + * This allows the VLAN to have a different MAC than the underlying + * device, and still route correctly. + */ + if (memcmp(eth_hdr(skb)->h_dest, skb->dev->dev_addr, ETH_ALEN) == 0) { + /* It is for our (changed) MAC-address! */ + skb->pkt_type = PACKET_HOST; + } + break; + default: + break; + }; + + /* Was a VLAN packet, grab the encapsulated protocol, which the layer + * three protocols care about. + */ + /* proto = get_unaligned(&vhdr->h_vlan_encapsulated_proto); */ + proto = vhdr->h_vlan_encapsulated_proto; + + skb->protocol = proto; + if (ntohs(proto) >= 1536) { + /* place it back on the queue to be handled by + * true layer 3 protocols. + */ + + /* See if we are configured to re-write the VLAN header + * to make it look like ethernet... + */ + skb = vlan_check_reorder_header(skb); + + /* Can be null if skb-clone fails when re-ordering */ + if (skb) { + netif_rx(skb); + } else { + /* TODO: Add a more specific counter here. */ + stats->rx_errors++; + } + rcu_read_unlock(); + return 0; + } + + rawp = skb->data; + + /* + * This is a magic hack to spot IPX packets. Older Novell breaks + * the protocol design and runs IPX over 802.3 without an 802.2 LLC + * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This + * won't work for fault tolerant netware but does for the rest. + */ + if (*(unsigned short *)rawp == 0xFFFF) { + skb->protocol = __constant_htons(ETH_P_802_3); + /* place it back on the queue to be handled by true layer 3 protocols. + */ + + /* See if we are configured to re-write the VLAN header + * to make it look like ethernet... + */ + skb = vlan_check_reorder_header(skb); + + /* Can be null if skb-clone fails when re-ordering */ + if (skb) { + netif_rx(skb); + } else { + /* TODO: Add a more specific counter here. */ + stats->rx_errors++; + } + rcu_read_unlock(); + return 0; + } + + /* + * Real 802.2 LLC + */ + skb->protocol = __constant_htons(ETH_P_802_2); + /* place it back on the queue to be handled by upper layer protocols. + */ + + /* See if we are configured to re-write the VLAN header + * to make it look like ethernet... + */ + skb = vlan_check_reorder_header(skb); + + /* Can be null if skb-clone fails when re-ordering */ + if (skb) { + netif_rx(skb); + } else { + /* TODO: Add a more specific counter here. */ + stats->rx_errors++; + } + rcu_read_unlock(); + return 0; +} + +static inline unsigned short vlan_dev_get_egress_qos_mask(struct net_device* dev, + struct sk_buff* skb) +{ + struct vlan_priority_tci_mapping *mp = + VLAN_DEV_INFO(dev)->egress_priority_map[(skb->priority & 0xF)]; + + while (mp) { + if (mp->priority == skb->priority) { + return mp->vlan_qos; /* This should already be shifted to mask + * correctly with the VLAN's TCI + */ + } + mp = mp->next; + } + return 0; +} + +/* + * Create the VLAN header for an arbitrary protocol layer + * + * saddr=NULL means use device source address + * daddr=NULL means leave destination address (eg unresolved arp) + * + * This is called when the SKB is moving down the stack towards the + * physical devices. + */ +int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, void *daddr, void *saddr, + unsigned len) +{ + struct vlan_hdr *vhdr; + unsigned short veth_TCI = 0; + int rc = 0; + int build_vlan_header = 0; + struct net_device *vdev = dev; /* save this for the bottom of the method */ + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: skb: %p type: %hx len: %x vlan_id: %hx, daddr: %p\n", + __FUNCTION__, skb, type, len, VLAN_DEV_INFO(dev)->vlan_id, daddr); +#endif + + /* build vlan header only if re_order_header flag is NOT set. This + * fixes some programs that get confused when they see a VLAN device + * sending a frame that is VLAN encoded (the consensus is that the VLAN + * device should look completely like an Ethernet device when the + * REORDER_HEADER flag is set) The drawback to this is some extra + * header shuffling in the hard_start_xmit. Users can turn off this + * REORDER behaviour with the vconfig tool. + */ + build_vlan_header = ((VLAN_DEV_INFO(dev)->flags & 1) == 0); + + if (build_vlan_header) { + vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN); + + /* build the four bytes that make this a VLAN header. */ + + /* Now, construct the second two bytes. This field looks something + * like: + * usr_priority: 3 bits (high bits) + * CFI 1 bit + * VLAN ID 12 bits (low bits) + * + */ + veth_TCI = VLAN_DEV_INFO(dev)->vlan_id; + veth_TCI |= vlan_dev_get_egress_qos_mask(dev, skb); + + vhdr->h_vlan_TCI = htons(veth_TCI); + + /* + * Set the protocol type. + * For a packet of type ETH_P_802_3 we put the length in here instead. + * It is up to the 802.2 layer to carry protocol information. + */ + + if (type != ETH_P_802_3) { + vhdr->h_vlan_encapsulated_proto = htons(type); + } else { + vhdr->h_vlan_encapsulated_proto = htons(len); + } + } + + /* Before delegating work to the lower layer, enter our MAC-address */ + if (saddr == NULL) + saddr = dev->dev_addr; + + dev = VLAN_DEV_INFO(dev)->real_dev; + + /* MPLS can send us skbuffs w/out enough space. This check will grow the + * skb if it doesn't have enough headroom. Not a beautiful solution, so + * I'll tick a counter so that users can know it's happening... If they + * care... + */ + + /* NOTE: This may still break if the underlying device is not the final + * device (and thus there are more headers to add...) It should work for + * good-ole-ethernet though. + */ + if (skb_headroom(skb) < dev->hard_header_len) { + struct sk_buff *sk_tmp = skb; + skb = skb_realloc_headroom(sk_tmp, dev->hard_header_len); + kfree_skb(sk_tmp); + if (skb == NULL) { + struct net_device_stats *stats = vlan_dev_get_stats(vdev); + stats->tx_dropped++; + return -ENOMEM; + } + VLAN_DEV_INFO(vdev)->cnt_inc_headroom_on_tx++; +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: %s: had to grow skb.\n", __FUNCTION__, vdev->name); +#endif + } + + if (build_vlan_header) { + /* Now make the underlying real hard header */ + rc = dev->hard_header(skb, dev, ETH_P_8021Q, daddr, saddr, len + VLAN_HLEN); + + if (rc > 0) { + rc += VLAN_HLEN; + } else if (rc < 0) { + rc -= VLAN_HLEN; + } + } else { + /* If here, then we'll just make a normal looking ethernet frame, + * but, the hard_start_xmit method will insert the tag (it has to + * be able to do this for bridged and other skbs that don't come + * down the protocol stack in an orderly manner. + */ + rc = dev->hard_header(skb, dev, type, daddr, saddr, len); + } + + return rc; +} + +int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct net_device_stats *stats = vlan_dev_get_stats(dev); + struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); + + /* Handle non-VLAN frames if they are sent to us, for example by DHCP. + * + * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING + * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... + */ + + if (veth->h_vlan_proto != __constant_htons(ETH_P_8021Q)) { + int orig_headroom = skb_headroom(skb); + unsigned short veth_TCI; + + /* This is not a VLAN frame...but we can fix that! */ + VLAN_DEV_INFO(dev)->cnt_encap_on_xmit++; + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: proto to encap: 0x%hx (hbo)\n", + __FUNCTION__, htons(veth->h_vlan_proto)); +#endif + /* Construct the second two bytes. This field looks something + * like: + * usr_priority: 3 bits (high bits) + * CFI 1 bit + * VLAN ID 12 bits (low bits) + */ + veth_TCI = VLAN_DEV_INFO(dev)->vlan_id; + veth_TCI |= vlan_dev_get_egress_qos_mask(dev, skb); + + skb = __vlan_put_tag(skb, veth_TCI); + if (!skb) { + stats->tx_dropped++; + return 0; + } + + if (orig_headroom < VLAN_HLEN) { + VLAN_DEV_INFO(dev)->cnt_inc_headroom_on_tx++; + } + } + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: about to send skb: %p to dev: %s\n", + __FUNCTION__, skb, skb->dev->name); + printk(VLAN_DBG " %2hx.%2hx.%2hx.%2xh.%2hx.%2hx %2hx.%2hx.%2hx.%2hx.%2hx.%2hx %4hx %4hx %4hx\n", + veth->h_dest[0], veth->h_dest[1], veth->h_dest[2], veth->h_dest[3], veth->h_dest[4], veth->h_dest[5], + veth->h_source[0], veth->h_source[1], veth->h_source[2], veth->h_source[3], veth->h_source[4], veth->h_source[5], + veth->h_vlan_proto, veth->h_vlan_TCI, veth->h_vlan_encapsulated_proto); +#endif + + stats->tx_packets++; /* for statics only */ + stats->tx_bytes += skb->len; + + skb->dev = VLAN_DEV_INFO(dev)->real_dev; + dev_queue_xmit(skb); + + return 0; +} + +int vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct net_device_stats *stats = vlan_dev_get_stats(dev); + unsigned short veth_TCI; + + /* Construct the second two bytes. This field looks something + * like: + * usr_priority: 3 bits (high bits) + * CFI 1 bit + * VLAN ID 12 bits (low bits) + */ + veth_TCI = VLAN_DEV_INFO(dev)->vlan_id; + veth_TCI |= vlan_dev_get_egress_qos_mask(dev, skb); + skb = __vlan_hwaccel_put_tag(skb, veth_TCI); + + stats->tx_packets++; + stats->tx_bytes += skb->len; + + skb->dev = VLAN_DEV_INFO(dev)->real_dev; + dev_queue_xmit(skb); + + return 0; +} + +int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) +{ + /* TODO: gotta make sure the underlying layer can handle it, + * maybe an IFF_VLAN_CAPABLE flag for devices? + */ + if (VLAN_DEV_INFO(dev)->real_dev->mtu < new_mtu) + return -ERANGE; + + dev->mtu = new_mtu; + + return 0; +} + +int vlan_dev_set_ingress_priority(char *dev_name, __u32 skb_prio, short vlan_prio) +{ + struct net_device *dev = dev_get_by_name(dev_name); + + if (dev) { + if (dev->priv_flags & IFF_802_1Q_VLAN) { + /* see if a priority mapping exists.. */ + VLAN_DEV_INFO(dev)->ingress_priority_map[vlan_prio & 0x7] = skb_prio; + dev_put(dev); + return 0; + } + + dev_put(dev); + } + return -EINVAL; +} + +int vlan_dev_set_egress_priority(char *dev_name, __u32 skb_prio, short vlan_prio) +{ + struct net_device *dev = dev_get_by_name(dev_name); + struct vlan_priority_tci_mapping *mp = NULL; + struct vlan_priority_tci_mapping *np; + + if (dev) { + if (dev->priv_flags & IFF_802_1Q_VLAN) { + /* See if a priority mapping exists.. */ + mp = VLAN_DEV_INFO(dev)->egress_priority_map[skb_prio & 0xF]; + while (mp) { + if (mp->priority == skb_prio) { + mp->vlan_qos = ((vlan_prio << 13) & 0xE000); + dev_put(dev); + return 0; + } + mp = mp->next; + } + + /* Create a new mapping then. */ + mp = VLAN_DEV_INFO(dev)->egress_priority_map[skb_prio & 0xF]; + np = kmalloc(sizeof(struct vlan_priority_tci_mapping), GFP_KERNEL); + if (np) { + np->next = mp; + np->priority = skb_prio; + np->vlan_qos = ((vlan_prio << 13) & 0xE000); + VLAN_DEV_INFO(dev)->egress_priority_map[skb_prio & 0xF] = np; + dev_put(dev); + return 0; + } else { + dev_put(dev); + return -ENOBUFS; + } + } + dev_put(dev); + } + return -EINVAL; +} + +/* Flags are defined in the vlan_dev_info class in include/linux/if_vlan.h file. */ +int vlan_dev_set_vlan_flag(char *dev_name, __u32 flag, short flag_val) +{ + struct net_device *dev = dev_get_by_name(dev_name); + + if (dev) { + if (dev->priv_flags & IFF_802_1Q_VLAN) { + /* verify flag is supported */ + if (flag == 1) { + if (flag_val) { + VLAN_DEV_INFO(dev)->flags |= 1; + } else { + VLAN_DEV_INFO(dev)->flags &= ~1; + } + dev_put(dev); + return 0; + } else { + printk(KERN_ERR "%s: flag %i is not valid.\n", + __FUNCTION__, (int)(flag)); + dev_put(dev); + return -EINVAL; + } + } else { + printk(KERN_ERR + "%s: %s is not a vlan device, priv_flags: %hX.\n", + __FUNCTION__, dev->name, dev->priv_flags); + dev_put(dev); + } + } else { + printk(KERN_ERR "%s: Could not find device: %s\n", + __FUNCTION__, dev_name); + } + + return -EINVAL; +} + + +int vlan_dev_get_realdev_name(const char *dev_name, char* result) +{ + struct net_device *dev = dev_get_by_name(dev_name); + int rv = 0; + if (dev) { + if (dev->priv_flags & IFF_802_1Q_VLAN) { + strncpy(result, VLAN_DEV_INFO(dev)->real_dev->name, 23); + rv = 0; + } else { + rv = -EINVAL; + } + dev_put(dev); + } else { + rv = -ENODEV; + } + return rv; +} + +int vlan_dev_get_vid(const char *dev_name, unsigned short* result) +{ + struct net_device *dev = dev_get_by_name(dev_name); + int rv = 0; + if (dev) { + if (dev->priv_flags & IFF_802_1Q_VLAN) { + *result = VLAN_DEV_INFO(dev)->vlan_id; + rv = 0; + } else { + rv = -EINVAL; + } + dev_put(dev); + } else { + rv = -ENODEV; + } + return rv; +} + + +int vlan_dev_set_mac_address(struct net_device *dev, void *addr_struct_p) +{ + struct sockaddr *addr = (struct sockaddr *)(addr_struct_p); + int i; + + if (netif_running(dev)) + return -EBUSY; + + memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + + printk("%s: Setting MAC address to ", dev->name); + for (i = 0; i < 6; i++) + printk(" %2.2x", dev->dev_addr[i]); + printk(".\n"); + + if (memcmp(VLAN_DEV_INFO(dev)->real_dev->dev_addr, + dev->dev_addr, + dev->addr_len) != 0) { + if (!(VLAN_DEV_INFO(dev)->real_dev->flags & IFF_PROMISC)) { + int flgs = VLAN_DEV_INFO(dev)->real_dev->flags; + + /* Increment our in-use promiscuity counter */ + dev_set_promiscuity(VLAN_DEV_INFO(dev)->real_dev, 1); + + /* Make PROMISC visible to the user. */ + flgs |= IFF_PROMISC; + printk("VLAN (%s): Setting underlying device (%s) to promiscious mode.\n", + dev->name, VLAN_DEV_INFO(dev)->real_dev->name); + dev_change_flags(VLAN_DEV_INFO(dev)->real_dev, flgs); + } + } else { + printk("VLAN (%s): Underlying device (%s) has same MAC, not checking promiscious mode.\n", + dev->name, VLAN_DEV_INFO(dev)->real_dev->name); + } + + return 0; +} + +static inline int vlan_dmi_equals(struct dev_mc_list *dmi1, + struct dev_mc_list *dmi2) +{ + return ((dmi1->dmi_addrlen == dmi2->dmi_addrlen) && + (memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0)); +} + +/** dmi is a single entry into a dev_mc_list, a single node. mc_list is + * an entire list, and we'll iterate through it. + */ +static int vlan_should_add_mc(struct dev_mc_list *dmi, struct dev_mc_list *mc_list) +{ + struct dev_mc_list *idmi; + + for (idmi = mc_list; idmi != NULL; ) { + if (vlan_dmi_equals(dmi, idmi)) { + if (dmi->dmi_users > idmi->dmi_users) + return 1; + else + return 0; + } else { + idmi = idmi->next; + } + } + + return 1; +} + +static inline void vlan_destroy_mc_list(struct dev_mc_list *mc_list) +{ + struct dev_mc_list *dmi = mc_list; + struct dev_mc_list *next; + + while(dmi) { + next = dmi->next; + kfree(dmi); + dmi = next; + } +} + +static void vlan_copy_mc_list(struct dev_mc_list *mc_list, struct vlan_dev_info *vlan_info) +{ + struct dev_mc_list *dmi, *new_dmi; + + vlan_destroy_mc_list(vlan_info->old_mc_list); + vlan_info->old_mc_list = NULL; + + for (dmi = mc_list; dmi != NULL; dmi = dmi->next) { + new_dmi = kmalloc(sizeof(*new_dmi), GFP_ATOMIC); + if (new_dmi == NULL) { + printk(KERN_ERR "vlan: cannot allocate memory. " + "Multicast may not work properly from now.\n"); + return; + } + + /* Copy whole structure, then make new 'next' pointer */ + *new_dmi = *dmi; + new_dmi->next = vlan_info->old_mc_list; + vlan_info->old_mc_list = new_dmi; + } +} + +static void vlan_flush_mc_list(struct net_device *dev) +{ + struct dev_mc_list *dmi = dev->mc_list; + + while (dmi) { + printk(KERN_DEBUG "%s: del %.2x:%.2x:%.2x:%.2x:%.2x:%.2x mcast address from vlan interface\n", + dev->name, + dmi->dmi_addr[0], + dmi->dmi_addr[1], + dmi->dmi_addr[2], + dmi->dmi_addr[3], + dmi->dmi_addr[4], + dmi->dmi_addr[5]); + dev_mc_delete(dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); + dmi = dev->mc_list; + } + + /* dev->mc_list is NULL by the time we get here. */ + vlan_destroy_mc_list(VLAN_DEV_INFO(dev)->old_mc_list); + VLAN_DEV_INFO(dev)->old_mc_list = NULL; +} + +int vlan_dev_open(struct net_device *dev) +{ + if (!(VLAN_DEV_INFO(dev)->real_dev->flags & IFF_UP)) + return -ENETDOWN; + + return 0; +} + +int vlan_dev_stop(struct net_device *dev) +{ + vlan_flush_mc_list(dev); + return 0; +} + +int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct net_device *real_dev = VLAN_DEV_INFO(dev)->real_dev; + struct ifreq ifrr; + int err = -EOPNOTSUPP; + + strncpy(ifrr.ifr_name, real_dev->name, IFNAMSIZ); + ifrr.ifr_ifru = ifr->ifr_ifru; + + switch(cmd) { + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSMIIREG: + if (real_dev->do_ioctl && netif_device_present(real_dev)) + err = real_dev->do_ioctl(real_dev, &ifrr, cmd); + break; + + case SIOCETHTOOL: + err = dev_ethtool(&ifrr); + } + + if (!err) + ifr->ifr_ifru = ifrr.ifr_ifru; + + return err; +} + +/** Taken from Gleb + Lennert's VLAN code, and modified... */ +void vlan_dev_set_multicast_list(struct net_device *vlan_dev) +{ + struct dev_mc_list *dmi; + struct net_device *real_dev; + int inc; + + if (vlan_dev && (vlan_dev->priv_flags & IFF_802_1Q_VLAN)) { + /* Then it's a real vlan device, as far as we can tell.. */ + real_dev = VLAN_DEV_INFO(vlan_dev)->real_dev; + + /* compare the current promiscuity to the last promisc we had.. */ + inc = vlan_dev->promiscuity - VLAN_DEV_INFO(vlan_dev)->old_promiscuity; + if (inc) { + printk(KERN_INFO "%s: dev_set_promiscuity(master, %d)\n", + vlan_dev->name, inc); + dev_set_promiscuity(real_dev, inc); /* found in dev.c */ + VLAN_DEV_INFO(vlan_dev)->old_promiscuity = vlan_dev->promiscuity; + } + + inc = vlan_dev->allmulti - VLAN_DEV_INFO(vlan_dev)->old_allmulti; + if (inc) { + printk(KERN_INFO "%s: dev_set_allmulti(master, %d)\n", + vlan_dev->name, inc); + dev_set_allmulti(real_dev, inc); /* dev.c */ + VLAN_DEV_INFO(vlan_dev)->old_allmulti = vlan_dev->allmulti; + } + + /* looking for addresses to add to master's list */ + for (dmi = vlan_dev->mc_list; dmi != NULL; dmi = dmi->next) { + if (vlan_should_add_mc(dmi, VLAN_DEV_INFO(vlan_dev)->old_mc_list)) { + dev_mc_add(real_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); + printk(KERN_DEBUG "%s: add %.2x:%.2x:%.2x:%.2x:%.2x:%.2x mcast address to master interface\n", + vlan_dev->name, + dmi->dmi_addr[0], + dmi->dmi_addr[1], + dmi->dmi_addr[2], + dmi->dmi_addr[3], + dmi->dmi_addr[4], + dmi->dmi_addr[5]); + } + } + + /* looking for addresses to delete from master's list */ + for (dmi = VLAN_DEV_INFO(vlan_dev)->old_mc_list; dmi != NULL; dmi = dmi->next) { + if (vlan_should_add_mc(dmi, vlan_dev->mc_list)) { + /* if we think we should add it to the new list, then we should really + * delete it from the real list on the underlying device. + */ + dev_mc_delete(real_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); + printk(KERN_DEBUG "%s: del %.2x:%.2x:%.2x:%.2x:%.2x:%.2x mcast address from master interface\n", + vlan_dev->name, + dmi->dmi_addr[0], + dmi->dmi_addr[1], + dmi->dmi_addr[2], + dmi->dmi_addr[3], + dmi->dmi_addr[4], + dmi->dmi_addr[5]); + } + } + + /* save multicast list */ + vlan_copy_mc_list(vlan_dev->mc_list, VLAN_DEV_INFO(vlan_dev)); + } +} diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c new file mode 100644 index 000000000000..c32d27af0a3f --- /dev/null +++ b/net/8021q/vlanproc.c @@ -0,0 +1,357 @@ +/****************************************************************************** + * vlanproc.c VLAN Module. /proc filesystem interface. + * + * This module is completely hardware-independent and provides + * access to the router using Linux /proc filesystem. + * + * Author: Ben Greear, <greearb@candelatech.com> coppied from wanproc.c + * by: Gene Kozin <genek@compuserve.com> + * + * Copyright: (c) 1998 Ben Greear + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * ============================================================================ + * Jan 20, 1998 Ben Greear Initial Version + *****************************************************************************/ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/stddef.h> /* offsetof(), etc. */ +#include <linux/errno.h> /* return codes */ +#include <linux/kernel.h> +#include <linux/slab.h> /* kmalloc(), kfree() */ +#include <linux/mm.h> /* verify_area(), etc. */ +#include <linux/string.h> /* inline mem*, str* functions */ +#include <linux/init.h> /* __initfunc et al. */ +#include <asm/byteorder.h> /* htons(), etc. */ +#include <asm/uaccess.h> /* copy_to_user */ +#include <asm/io.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/fs.h> +#include <linux/netdevice.h> +#include <linux/if_vlan.h> +#include "vlanproc.h" +#include "vlan.h" + +/****** Function Prototypes *************************************************/ + +/* Methods for preparing data for reading proc entries */ +static int vlan_seq_show(struct seq_file *seq, void *v); +static void *vlan_seq_start(struct seq_file *seq, loff_t *pos); +static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos); +static void vlan_seq_stop(struct seq_file *seq, void *); +static int vlandev_seq_show(struct seq_file *seq, void *v); + +/* + * Global Data + */ + + +/* + * Names of the proc directory entries + */ + +static const char name_root[] = "vlan"; +static const char name_conf[] = "config"; + +/* + * Structures for interfacing with the /proc filesystem. + * VLAN creates its own directory /proc/net/vlan with the folowing + * entries: + * config device status/configuration + * <device> entry for each device + */ + +/* + * Generic /proc/net/vlan/<file> file and inode operations + */ + +static struct seq_operations vlan_seq_ops = { + .start = vlan_seq_start, + .next = vlan_seq_next, + .stop = vlan_seq_stop, + .show = vlan_seq_show, +}; + +static int vlan_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &vlan_seq_ops); +} + +static struct file_operations vlan_fops = { + .owner = THIS_MODULE, + .open = vlan_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* + * /proc/net/vlan/<device> file and inode operations + */ + +static int vlandev_seq_open(struct inode *inode, struct file *file) +{ + return single_open(file, vlandev_seq_show, PDE(inode)->data); +} + +static struct file_operations vlandev_fops = { + .owner = THIS_MODULE, + .open = vlandev_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +/* + * Proc filesystem derectory entries. + */ + +/* + * /proc/net/vlan + */ + +static struct proc_dir_entry *proc_vlan_dir; + +/* + * /proc/net/vlan/config + */ + +static struct proc_dir_entry *proc_vlan_conf; + +/* Strings */ +static const char *vlan_name_type_str[VLAN_NAME_TYPE_HIGHEST] = { + [VLAN_NAME_TYPE_RAW_PLUS_VID] = "VLAN_NAME_TYPE_RAW_PLUS_VID", + [VLAN_NAME_TYPE_PLUS_VID_NO_PAD] = "VLAN_NAME_TYPE_PLUS_VID_NO_PAD", + [VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD]= "VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD", + [VLAN_NAME_TYPE_PLUS_VID] = "VLAN_NAME_TYPE_PLUS_VID", +}; +/* + * Interface functions + */ + +/* + * Clean up /proc/net/vlan entries + */ + +void vlan_proc_cleanup(void) +{ + if (proc_vlan_conf) + remove_proc_entry(name_conf, proc_vlan_dir); + + if (proc_vlan_dir) + proc_net_remove(name_root); + + /* Dynamically added entries should be cleaned up as their vlan_device + * is removed, so we should not have to take care of it here... + */ +} + +/* + * Create /proc/net/vlan entries + */ + +int __init vlan_proc_init(void) +{ + proc_vlan_dir = proc_mkdir(name_root, proc_net); + if (proc_vlan_dir) { + proc_vlan_conf = create_proc_entry(name_conf, + S_IFREG|S_IRUSR|S_IWUSR, + proc_vlan_dir); + if (proc_vlan_conf) { + proc_vlan_conf->proc_fops = &vlan_fops; + return 0; + } + } + vlan_proc_cleanup(); + return -ENOBUFS; +} + +/* + * Add directory entry for VLAN device. + */ + +int vlan_proc_add_dev (struct net_device *vlandev) +{ + struct vlan_dev_info *dev_info = VLAN_DEV_INFO(vlandev); + + if (!(vlandev->priv_flags & IFF_802_1Q_VLAN)) { + printk(KERN_ERR + "ERROR: vlan_proc_add, device -:%s:- is NOT a VLAN\n", + vlandev->name); + return -EINVAL; + } + + dev_info->dent = create_proc_entry(vlandev->name, + S_IFREG|S_IRUSR|S_IWUSR, + proc_vlan_dir); + if (!dev_info->dent) + return -ENOBUFS; + + dev_info->dent->proc_fops = &vlandev_fops; + dev_info->dent->data = vlandev; + +#ifdef VLAN_DEBUG + printk(KERN_ERR "vlan_proc_add, device -:%s:- being added.\n", + vlandev->name); +#endif + return 0; +} + +/* + * Delete directory entry for VLAN device. + */ +int vlan_proc_rem_dev(struct net_device *vlandev) +{ + if (!vlandev) { + printk(VLAN_ERR "%s: invalid argument: %p\n", + __FUNCTION__, vlandev); + return -EINVAL; + } + + if (!(vlandev->priv_flags & IFF_802_1Q_VLAN)) { + printk(VLAN_DBG "%s: invalid argument, device: %s is not a VLAN device, priv_flags: 0x%4hX.\n", + __FUNCTION__, vlandev->name, vlandev->priv_flags); + return -EINVAL; + } + +#ifdef VLAN_DEBUG + printk(VLAN_DBG "%s: dev: %p\n", __FUNCTION__, vlandev); +#endif + + /** NOTE: This will consume the memory pointed to by dent, it seems. */ + if (VLAN_DEV_INFO(vlandev)->dent) { + remove_proc_entry(VLAN_DEV_INFO(vlandev)->dent->name, proc_vlan_dir); + VLAN_DEV_INFO(vlandev)->dent = NULL; + } + + return 0; +} + +/****** Proc filesystem entry points ****************************************/ + +/* + * The following few functions build the content of /proc/net/vlan/config + */ + +/* starting at dev, find a VLAN device */ +static struct net_device *vlan_skip(struct net_device *dev) +{ + while (dev && !(dev->priv_flags & IFF_802_1Q_VLAN)) + dev = dev->next; + + return dev; +} + +/* start read of /proc/net/vlan/config */ +static void *vlan_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct net_device *dev; + loff_t i = 1; + + read_lock(&dev_base_lock); + + if (*pos == 0) + return SEQ_START_TOKEN; + + for (dev = vlan_skip(dev_base); dev && i < *pos; + dev = vlan_skip(dev->next), ++i); + + return (i == *pos) ? dev : NULL; +} + +static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + + return vlan_skip((v == SEQ_START_TOKEN) + ? dev_base + : ((struct net_device *)v)->next); +} + +static void vlan_seq_stop(struct seq_file *seq, void *v) +{ + read_unlock(&dev_base_lock); +} + +static int vlan_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) { + const char *nmtype = NULL; + + seq_puts(seq, "VLAN Dev name | VLAN ID\n"); + + if (vlan_name_type < ARRAY_SIZE(vlan_name_type_str)) + nmtype = vlan_name_type_str[vlan_name_type]; + + seq_printf(seq, "Name-Type: %s\n", + nmtype ? nmtype : "UNKNOWN" ); + } else { + const struct net_device *vlandev = v; + const struct vlan_dev_info *dev_info = VLAN_DEV_INFO(vlandev); + + seq_printf(seq, "%-15s| %d | %s\n", vlandev->name, + dev_info->vlan_id, dev_info->real_dev->name); + } + return 0; +} + +static int vlandev_seq_show(struct seq_file *seq, void *offset) +{ + struct net_device *vlandev = (struct net_device *) seq->private; + const struct vlan_dev_info *dev_info = VLAN_DEV_INFO(vlandev); + struct net_device_stats *stats; + static const char fmt[] = "%30s %12lu\n"; + int i; + + if ((vlandev == NULL) || (!(vlandev->priv_flags & IFF_802_1Q_VLAN))) + return 0; + + seq_printf(seq, "%s VID: %d REORDER_HDR: %i dev->priv_flags: %hx\n", + vlandev->name, dev_info->vlan_id, + (int)(dev_info->flags & 1), vlandev->priv_flags); + + + stats = vlan_dev_get_stats(vlandev); + + seq_printf(seq, fmt, "total frames received", stats->rx_packets); + seq_printf(seq, fmt, "total bytes received", stats->rx_bytes); + seq_printf(seq, fmt, "Broadcast/Multicast Rcvd", stats->multicast); + seq_puts(seq, "\n"); + seq_printf(seq, fmt, "total frames transmitted", stats->tx_packets); + seq_printf(seq, fmt, "total bytes transmitted", stats->tx_bytes); + seq_printf(seq, fmt, "total headroom inc", + dev_info->cnt_inc_headroom_on_tx); + seq_printf(seq, fmt, "total encap on xmit", + dev_info->cnt_encap_on_xmit); + seq_printf(seq, "Device: %s", dev_info->real_dev->name); + /* now show all PRIORITY mappings relating to this VLAN */ + seq_printf(seq, + "\nINGRESS priority mappings: 0:%lu 1:%lu 2:%lu 3:%lu 4:%lu 5:%lu 6:%lu 7:%lu\n", + dev_info->ingress_priority_map[0], + dev_info->ingress_priority_map[1], + dev_info->ingress_priority_map[2], + dev_info->ingress_priority_map[3], + dev_info->ingress_priority_map[4], + dev_info->ingress_priority_map[5], + dev_info->ingress_priority_map[6], + dev_info->ingress_priority_map[7]); + + seq_printf(seq, "EGRESSS priority Mappings: "); + for (i = 0; i < 16; i++) { + const struct vlan_priority_tci_mapping *mp + = dev_info->egress_priority_map[i]; + while (mp) { + seq_printf(seq, "%lu:%hu ", + mp->priority, ((mp->vlan_qos >> 13) & 0x7)); + mp = mp->next; + } + } + seq_puts(seq, "\n"); + + return 0; +} diff --git a/net/8021q/vlanproc.h b/net/8021q/vlanproc.h new file mode 100644 index 000000000000..f908ee332fd8 --- /dev/null +++ b/net/8021q/vlanproc.h @@ -0,0 +1,19 @@ +#ifndef __BEN_VLAN_PROC_INC__ +#define __BEN_VLAN_PROC_INC__ + +#ifdef CONFIG_PROC_FS +int vlan_proc_init(void); +int vlan_proc_rem_dev(struct net_device *vlandev); +int vlan_proc_add_dev (struct net_device *vlandev); +void vlan_proc_cleanup (void); + +#else /* No CONFIG_PROC_FS */ + +#define vlan_proc_init() (0) +#define vlan_proc_cleanup() do {} while(0) +#define vlan_proc_add_dev(dev) ({(void)(dev), 0;}) +#define vlan_proc_rem_dev(dev) ({(void)(dev), 0;}) + +#endif + +#endif /* !(__BEN_VLAN_PROC_INC__) */ diff --git a/net/Kconfig b/net/Kconfig new file mode 100644 index 000000000000..9251b28e8d5d --- /dev/null +++ b/net/Kconfig @@ -0,0 +1,646 @@ +# +# Network configuration +# + +menu "Networking support" + +config NET + bool "Networking support" + ---help--- + Unless you really know what you are doing, you should say Y here. + The reason is that some programs need kernel networking support even + when running on a stand-alone machine that isn't connected to any + other computer. If you are upgrading from an older kernel, you + should consider updating your networking tools too because changes + in the kernel and the tools often go hand in hand. The tools are + contained in the package net-tools, the location and version number + of which are given in <file:Documentation/Changes>. + + For a general introduction to Linux networking, it is highly + recommended to read the NET-HOWTO, available from + <http://www.tldp.org/docs.html#howto>. + +menu "Networking options" + depends on NET + +config PACKET + tristate "Packet socket" + ---help--- + The Packet protocol is used by applications which communicate + directly with network devices without an intermediate network + protocol implemented in the kernel, e.g. tcpdump. If you want them + to work, choose Y. + + To compile this driver as a module, choose M here: the module will + be called af_packet. + + If unsure, say Y. + +config PACKET_MMAP + bool "Packet socket: mmapped IO" + depends on PACKET + help + If you say Y here, the Packet protocol driver will use an IO + mechanism that results in faster communication. + + If unsure, say N. + +config UNIX + tristate "Unix domain sockets" + ---help--- + If you say Y here, you will include support for Unix domain sockets; + sockets are the standard Unix mechanism for establishing and + accessing network connections. Many commonly used programs such as + the X Window system and syslog use these sockets even if your + machine is not connected to any network. Unless you are working on + an embedded system or something similar, you therefore definitely + want to say Y here. + + To compile this driver as a module, choose M here: the module will be + called unix. Note that several important services won't work + correctly if you say M here and then neglect to load the module. + + Say Y unless you know what you are doing. + +config NET_KEY + tristate "PF_KEY sockets" + select XFRM + ---help--- + PF_KEYv2 socket family, compatible to KAME ones. + They are required if you are going to use IPsec tools ported + from KAME. + + Say Y unless you know what you are doing. + +config INET + bool "TCP/IP networking" + ---help--- + These are the protocols used on the Internet and on most local + Ethernets. It is highly recommended to say Y here (this will enlarge + your kernel by about 144 KB), since some programs (e.g. the X window + system) use TCP/IP even if your machine is not connected to any + other computer. You will get the so-called loopback device which + allows you to ping yourself (great fun, that!). + + For an excellent introduction to Linux networking, please read the + Linux Networking HOWTO, available from + <http://www.tldp.org/docs.html#howto>. + + If you say Y here and also to "/proc file system support" and + "Sysctl support" below, you can change various aspects of the + behavior of the TCP/IP code by writing to the (virtual) files in + /proc/sys/net/ipv4/*; the options are explained in the file + <file:Documentation/networking/ip-sysctl.txt>. + + Short answer: say Y. + +source "net/ipv4/Kconfig" + +# IPv6 as module will cause a CRASH if you try to unload it +config IPV6 + tristate "The IPv6 protocol" + depends on INET + default m + select CRYPTO if IPV6_PRIVACY + select CRYPTO_MD5 if IPV6_PRIVACY + ---help--- + This is complemental support for the IP version 6. + You will still be able to do traditional IPv4 networking as well. + + For general information about IPv6, see + <http://playground.sun.com/pub/ipng/html/ipng-main.html>. + For Linux IPv6 development information, see <http://www.linux-ipv6.org>. + For specific information about IPv6 under Linux, read the HOWTO at + <http://www.bieringer.de/linux/IPv6/>. + + To compile this protocol support as a module, choose M here: the + module will be called ipv6. + +source "net/ipv6/Kconfig" + +menuconfig NETFILTER + bool "Network packet filtering (replaces ipchains)" + ---help--- + Netfilter is a framework for filtering and mangling network packets + that pass through your Linux box. + + The most common use of packet filtering is to run your Linux box as + a firewall protecting a local network from the Internet. The type of + firewall provided by this kernel support is called a "packet + filter", which means that it can reject individual network packets + based on type, source, destination etc. The other kind of firewall, + a "proxy-based" one, is more secure but more intrusive and more + bothersome to set up; it inspects the network traffic much more + closely, modifies it and has knowledge about the higher level + protocols, which a packet filter lacks. Moreover, proxy-based + firewalls often require changes to the programs running on the local + clients. Proxy-based firewalls don't need support by the kernel, but + they are often combined with a packet filter, which only works if + you say Y here. + + You should also say Y here if you intend to use your Linux box as + the gateway to the Internet for a local network of machines without + globally valid IP addresses. This is called "masquerading": if one + of the computers on your local network wants to send something to + the outside, your box can "masquerade" as that computer, i.e. it + forwards the traffic to the intended outside destination, but + modifies the packets to make it look like they came from the + firewall box itself. It works both ways: if the outside host + replies, the Linux box will silently forward the traffic to the + correct local computer. This way, the computers on your local net + are completely invisible to the outside world, even though they can + reach the outside and can receive replies. It is even possible to + run globally visible servers from within a masqueraded local network + using a mechanism called portforwarding. Masquerading is also often + called NAT (Network Address Translation). + + Another use of Netfilter is in transparent proxying: if a machine on + the local network tries to connect to an outside host, your Linux + box can transparently forward the traffic to a local server, + typically a caching proxy server. + + Yet another use of Netfilter is building a bridging firewall. Using + a bridge with Network packet filtering enabled makes iptables "see" + the bridged traffic. For filtering on the lower network and Ethernet + protocols over the bridge, use ebtables (under bridge netfilter + configuration). + + Various modules exist for netfilter which replace the previous + masquerading (ipmasqadm), packet filtering (ipchains), transparent + proxying, and portforwarding mechanisms. Please see + <file:Documentation/Changes> under "iptables" for the location of + these packages. + + Make sure to say N to "Fast switching" below if you intend to say Y + here, as Fast switching currently bypasses netfilter. + + Chances are that you should say Y here if you compile a kernel which + will run as a router and N for regular hosts. If unsure, say N. + +if NETFILTER + +config NETFILTER_DEBUG + bool "Network packet filtering debugging" + depends on NETFILTER + help + You can say Y here if you want to get additional messages useful in + debugging the netfilter code. + +config BRIDGE_NETFILTER + bool "Bridged IP/ARP packets filtering" + depends on BRIDGE && NETFILTER && INET + default y + ---help--- + Enabling this option will let arptables resp. iptables see bridged + ARP resp. IP traffic. If you want a bridging firewall, you probably + want this option enabled. + Enabling or disabling this option doesn't enable or disable + ebtables. + + If unsure, say N. + +source "net/ipv4/netfilter/Kconfig" +source "net/ipv6/netfilter/Kconfig" +source "net/decnet/netfilter/Kconfig" +source "net/bridge/netfilter/Kconfig" + +endif + +config XFRM + bool + depends on NET + +source "net/xfrm/Kconfig" + +source "net/sctp/Kconfig" + +config ATM + tristate "Asynchronous Transfer Mode (ATM) (EXPERIMENTAL)" + depends on EXPERIMENTAL + ---help--- + ATM is a high-speed networking technology for Local Area Networks + and Wide Area Networks. It uses a fixed packet size and is + connection oriented, allowing for the negotiation of minimum + bandwidth requirements. + + In order to participate in an ATM network, your Linux box needs an + ATM networking card. If you have that, say Y here and to the driver + of your ATM card below. + + Note that you need a set of user-space programs to actually make use + of ATM. See the file <file:Documentation/networking/atm.txt> for + further details. + +config ATM_CLIP + tristate "Classical IP over ATM (EXPERIMENTAL)" + depends on ATM && INET + help + Classical IP over ATM for PVCs and SVCs, supporting InARP and + ATMARP. If you want to communication with other IP hosts on your ATM + network, you will typically either say Y here or to "LAN Emulation + (LANE)" below. + +config ATM_CLIP_NO_ICMP + bool "Do NOT send ICMP if no neighbour (EXPERIMENTAL)" + depends on ATM_CLIP + help + Normally, an "ICMP host unreachable" message is sent if a neighbour + cannot be reached because there is no VC to it in the kernel's + ATMARP table. This may cause problems when ATMARP table entries are + briefly removed during revalidation. If you say Y here, packets to + such neighbours are silently discarded instead. + +config ATM_LANE + tristate "LAN Emulation (LANE) support (EXPERIMENTAL)" + depends on ATM + help + LAN Emulation emulates services of existing LANs across an ATM + network. Besides operating as a normal ATM end station client, Linux + LANE client can also act as an proxy client bridging packets between + ELAN and Ethernet segments. You need LANE if you want to try MPOA. + +config ATM_MPOA + tristate "Multi-Protocol Over ATM (MPOA) support (EXPERIMENTAL)" + depends on ATM && INET && ATM_LANE!=n + help + Multi-Protocol Over ATM allows ATM edge devices such as routers, + bridges and ATM attached hosts establish direct ATM VCs across + subnetwork boundaries. These shortcut connections bypass routers + enhancing overall network performance. + +config ATM_BR2684 + tristate "RFC1483/2684 Bridged protocols" + depends on ATM && INET + help + ATM PVCs can carry ethernet PDUs according to rfc2684 (formerly 1483) + This device will act like an ethernet from the kernels point of view, + with the traffic being carried by ATM PVCs (currently 1 PVC/device). + This is sometimes used over DSL lines. If in doubt, say N. + +config ATM_BR2684_IPFILTER + bool "Per-VC IP filter kludge" + depends on ATM_BR2684 + help + This is an experimental mechanism for users who need to terminating a + large number of IP-only vcc's. Do not enable this unless you are sure + you know what you are doing. + +config BRIDGE + tristate "802.1d Ethernet Bridging" + ---help--- + If you say Y here, then your Linux box will be able to act as an + Ethernet bridge, which means that the different Ethernet segments it + is connected to will appear as one Ethernet to the participants. + Several such bridges can work together to create even larger + networks of Ethernets using the IEEE 802.1 spanning tree algorithm. + As this is a standard, Linux bridges will cooperate properly with + other third party bridge products. + + In order to use the Ethernet bridge, you'll need the bridge + configuration tools; see <file:Documentation/networking/bridge.txt> + for location. Please read the Bridge mini-HOWTO for more + information. + + If you enable iptables support along with the bridge support then you + turn your bridge into a bridging IP firewall. + iptables will then see the IP packets being bridged, so you need to + take this into account when setting up your firewall rules. + Enabling arptables support when bridging will let arptables see + bridged ARP traffic in the arptables FORWARD chain. + + To compile this code as a module, choose M here: the module + will be called bridge. + + If unsure, say N. + +config VLAN_8021Q + tristate "802.1Q VLAN Support" + ---help--- + Select this and you will be able to create 802.1Q VLAN interfaces + on your ethernet interfaces. 802.1Q VLAN supports almost + everything a regular ethernet interface does, including + firewalling, bridging, and of course IP traffic. You will need + the 'vconfig' tool from the VLAN project in order to effectively + use VLANs. See the VLAN web page for more information: + <http://www.candelatech.com/~greear/vlan.html> + + To compile this code as a module, choose M here: the module + will be called 8021q. + + If unsure, say N. + +config DECNET + tristate "DECnet Support" + ---help--- + The DECnet networking protocol was used in many products made by + Digital (now Compaq). It provides reliable stream and sequenced + packet communications over which run a variety of services similar + to those which run over TCP/IP. + + To find some tools to use with the kernel layer support, please + look at Patrick Caulfield's web site: + <http://linux-decnet.sourceforge.net/>. + + More detailed documentation is available in + <file:Documentation/networking/decnet.txt>. + + Be sure to say Y to "/proc file system support" and "Sysctl support" + below when using DECnet, since you will need sysctl support to aid + in configuration at run time. + + The DECnet code is also available as a module ( = code which can be + inserted in and removed from the running kernel whenever you want). + The module is called decnet. + +source "net/decnet/Kconfig" + +source "net/llc/Kconfig" + +config IPX + tristate "The IPX protocol" + select LLC + ---help--- + This is support for the Novell networking protocol, IPX, commonly + used for local networks of Windows machines. You need it if you + want to access Novell NetWare file or print servers using the Linux + Novell client ncpfs (available from + <ftp://platan.vc.cvut.cz/pub/linux/ncpfs/>) or from + within the Linux DOS emulator DOSEMU (read the DOSEMU-HOWTO, + available from <http://www.tldp.org/docs.html#howto>). In order + to do the former, you'll also have to say Y to "NCP file system + support", below. + + IPX is similar in scope to IP, while SPX, which runs on top of IPX, + is similar to TCP. There is also experimental support for SPX in + Linux (see "SPX networking", below). + + To turn your Linux box into a fully featured NetWare file server and + IPX router, say Y here and fetch either lwared from + <ftp://ibiblio.org/pub/Linux/system/network/daemons/> or + mars_nwe from <ftp://www.compu-art.de/mars_nwe/>. For more + information, read the IPX-HOWTO available from + <http://www.tldp.org/docs.html#howto>. + + General information about how to connect Linux, Windows machines and + Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. + + The IPX driver would enlarge your kernel by about 16 KB. To compile + this driver as a module, choose M here: the module will be called ipx. + Unless you want to integrate your Linux box with a local Novell + network, say N. + +source "net/ipx/Kconfig" + +config ATALK + tristate "Appletalk protocol support" + select LLC + ---help--- + AppleTalk is the protocol that Apple computers can use to communicate + on a network. If your Linux box is connected to such a network and you + wish to connect to it, say Y. You will need to use the netatalk package + so that your Linux box can act as a print and file server for Macs as + well as access AppleTalk printers. Check out + <http://www.zettabyte.net/netatalk/> on the WWW for details. + EtherTalk is the name used for AppleTalk over Ethernet and the + cheaper and slower LocalTalk is AppleTalk over a proprietary Apple + network using serial links. EtherTalk and LocalTalk are fully + supported by Linux. + + General information about how to connect Linux, Windows machines and + Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. The + NET-3-HOWTO, available from + <http://www.tldp.org/docs.html#howto>, contains valuable + information as well. + + To compile this driver as a module, choose M here: the module will be + called appletalk. You almost certainly want to compile it as a + module so you can restart your AppleTalk stack without rebooting + your machine. I hear that the GNU boycott of Apple is over, so + even politically correct people are allowed to say Y here. + +source "drivers/net/appletalk/Kconfig" + +config X25 + tristate "CCITT X.25 Packet Layer (EXPERIMENTAL)" + depends on EXPERIMENTAL + ---help--- + X.25 is a set of standardized network protocols, similar in scope to + frame relay; the one physical line from your box to the X.25 network + entry point can carry several logical point-to-point connections + (called "virtual circuits") to other computers connected to the X.25 + network. Governments, banks, and other organizations tend to use it + to connect to each other or to form Wide Area Networks (WANs). Many + countries have public X.25 networks. X.25 consists of two + protocols: the higher level Packet Layer Protocol (PLP) (say Y here + if you want that) and the lower level data link layer protocol LAPB + (say Y to "LAPB Data Link Driver" below if you want that). + + You can read more about X.25 at <http://www.sangoma.com/x25.htm> and + <http://www.cisco.com/univercd/cc/td/doc/product/software/ios11/cbook/cx25.htm>. + Information about X.25 for Linux is contained in the files + <file:Documentation/networking/x25.txt> and + <file:Documentation/networking/x25-iface.txt>. + + One connects to an X.25 network either with a dedicated network card + using the X.21 protocol (not yet supported by Linux) or one can do + X.25 over a standard telephone line using an ordinary modem (say Y + to "X.25 async driver" below) or over Ethernet using an ordinary + Ethernet card and the LAPB over Ethernet (say Y to "LAPB Data Link + Driver" and "LAPB over Ethernet driver" below). + + To compile this driver as a module, choose M here: the module + will be called x25. If unsure, say N. + +config LAPB + tristate "LAPB Data Link Driver (EXPERIMENTAL)" + depends on EXPERIMENTAL + ---help--- + Link Access Procedure, Balanced (LAPB) is the data link layer (i.e. + the lower) part of the X.25 protocol. It offers a reliable + connection service to exchange data frames with one other host, and + it is used to transport higher level protocols (mostly X.25 Packet + Layer, the higher part of X.25, but others are possible as well). + Usually, LAPB is used with specialized X.21 network cards, but Linux + currently supports LAPB only over Ethernet connections. If you want + to use LAPB connections over Ethernet, say Y here and to "LAPB over + Ethernet driver" below. Read + <file:Documentation/networking/lapb-module.txt> for technical + details. + + To compile this driver as a module, choose M here: the + module will be called lapb. If unsure, say N. + +config NET_DIVERT + bool "Frame Diverter (EXPERIMENTAL)" + depends on EXPERIMENTAL + ---help--- + The Frame Diverter allows you to divert packets from the + network, that are not aimed at the interface receiving it (in + promisc. mode). Typically, a Linux box setup as an Ethernet bridge + with the Frames Diverter on, can do some *really* transparent www + caching using a Squid proxy for example. + + This is very useful when you don't want to change your router's + config (or if you simply don't have access to it). + + The other possible usages of diverting Ethernet Frames are + numberous: + - reroute smtp traffic to another interface + - traffic-shape certain network streams + - transparently proxy smtp connections + - etc... + + For more informations, please refer to: + <http://diverter.sourceforge.net/> + <http://perso.wanadoo.fr/magpie/EtherDivert.html> + + If unsure, say N. + +config ECONET + tristate "Acorn Econet/AUN protocols (EXPERIMENTAL)" + depends on EXPERIMENTAL && INET + ---help--- + Econet is a fairly old and slow networking protocol mainly used by + Acorn computers to access file and print servers. It uses native + Econet network cards. AUN is an implementation of the higher level + parts of Econet that runs over ordinary Ethernet connections, on + top of the UDP packet protocol, which in turn runs on top of the + Internet protocol IP. + + If you say Y here, you can choose with the next two options whether + to send Econet/AUN traffic over a UDP Ethernet connection or over + a native Econet network card. + + To compile this driver as a module, choose M here: the module + will be called econet. + +config ECONET_AUNUDP + bool "AUN over UDP" + depends on ECONET + help + Say Y here if you want to send Econet/AUN traffic over a UDP + connection (UDP is a packet based protocol that runs on top of the + Internet protocol IP) using an ordinary Ethernet network card. + +config ECONET_NATIVE + bool "Native Econet" + depends on ECONET + help + Say Y here if you have a native Econet network card installed in + your computer. + +config WAN_ROUTER + tristate "WAN router" + depends on EXPERIMENTAL + ---help--- + Wide Area Networks (WANs), such as X.25, frame relay and leased + lines, are used to interconnect Local Area Networks (LANs) over vast + distances with data transfer rates significantly higher than those + achievable with commonly used asynchronous modem connections. + Usually, a quite expensive external device called a `WAN router' is + needed to connect to a WAN. + + As an alternative, WAN routing can be built into the Linux kernel. + With relatively inexpensive WAN interface cards available on the + market, a perfectly usable router can be built for less than half + the price of an external router. If you have one of those cards and + wish to use your Linux box as a WAN router, say Y here and also to + the WAN driver for your card, below. You will then need the + wan-tools package which is available from <ftp://ftp.sangoma.com/>. + Read <file:Documentation/networking/wan-router.txt> for more + information. + + To compile WAN routing support as a module, choose M here: the + module will be called wanrouter. + + If unsure, say N. + +menu "QoS and/or fair queueing" + +config NET_SCHED + bool "QoS and/or fair queueing" + ---help--- + When the kernel has several packets to send out over a network + device, it has to decide which ones to send first, which ones to + delay, and which ones to drop. This is the job of the packet + scheduler, and several different algorithms for how to do this + "fairly" have been proposed. + + If you say N here, you will get the standard packet scheduler, which + is a FIFO (first come, first served). If you say Y here, you will be + able to choose from among several alternative algorithms which can + then be attached to different network devices. This is useful for + example if some of your network devices are real time devices that + need a certain minimum data flow rate, or if you need to limit the + maximum data flow rate for traffic which matches specified criteria. + This code is considered to be experimental. + + To administer these schedulers, you'll need the user-level utilities + from the package iproute2+tc at <ftp://ftp.tux.org/pub/net/ip-routing/>. + That package also contains some documentation; for more, check out + <http://snafu.freedom.org/linux2.2/iproute-notes.html>. + + This Quality of Service (QoS) support will enable you to use + Differentiated Services (diffserv) and Resource Reservation Protocol + (RSVP) on your Linux router if you also say Y to "QoS support", + "Packet classifier API" and to some classifiers below. Documentation + and software is at <http://diffserv.sourceforge.net/>. + + If you say Y here and to "/proc file system" below, you will be able + to read status information about packet schedulers from the file + /proc/net/psched. + + The available schedulers are listed in the following questions; you + can say Y to as many as you like. If unsure, say N now. + +source "net/sched/Kconfig" + +endmenu + +menu "Network testing" + +config NET_PKTGEN + tristate "Packet Generator (USE WITH CAUTION)" + depends on PROC_FS + ---help--- + This module will inject preconfigured packets, at a configurable + rate, out of a given interface. It is used for network interface + stress testing and performance analysis. If you don't understand + what was just said, you don't need it: say N. + + Documentation on how to use the packet generator can be found + at <file:Documentation/networking/pktgen.txt>. + + To compile this code as a module, choose M here: the + module will be called pktgen. + +endmenu + +endmenu + +config NETPOLL + def_bool NETCONSOLE + +config NETPOLL_RX + bool "Netpoll support for trapping incoming packets" + default n + depends on NETPOLL + +config NETPOLL_TRAP + bool "Netpoll traffic trapping" + default n + depends on NETPOLL + +config NET_POLL_CONTROLLER + def_bool NETPOLL + +source "net/ax25/Kconfig" + +source "net/irda/Kconfig" + +source "net/bluetooth/Kconfig" + +source "drivers/net/Kconfig" + +endmenu + diff --git a/net/Makefile b/net/Makefile new file mode 100644 index 000000000000..8e2bdc025ab8 --- /dev/null +++ b/net/Makefile @@ -0,0 +1,48 @@ +# +# Makefile for the linux networking. +# +# 2 Sep 2000, Christoph Hellwig <hch@infradead.org> +# Rewritten to use lists instead of if-statements. +# + +obj-y := nonet.o + +obj-$(CONFIG_NET) := socket.o core/ + +tmp-$(CONFIG_COMPAT) := compat.o +obj-$(CONFIG_NET) += $(tmp-y) + +# LLC has to be linked before the files in net/802/ +obj-$(CONFIG_LLC) += llc/ +obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ +obj-$(CONFIG_INET) += ipv4/ +obj-$(CONFIG_XFRM) += xfrm/ +obj-$(CONFIG_UNIX) += unix/ +ifneq ($(CONFIG_IPV6),) +obj-y += ipv6/ +endif +obj-$(CONFIG_PACKET) += packet/ +obj-$(CONFIG_NET_KEY) += key/ +obj-$(CONFIG_NET_SCHED) += sched/ +obj-$(CONFIG_BRIDGE) += bridge/ +obj-$(CONFIG_IPX) += ipx/ +obj-$(CONFIG_ATALK) += appletalk/ +obj-$(CONFIG_WAN_ROUTER) += wanrouter/ +obj-$(CONFIG_X25) += x25/ +obj-$(CONFIG_LAPB) += lapb/ +obj-$(CONFIG_NETROM) += netrom/ +obj-$(CONFIG_ROSE) += rose/ +obj-$(CONFIG_AX25) += ax25/ +obj-$(CONFIG_IRDA) += irda/ +obj-$(CONFIG_BT) += bluetooth/ +obj-$(CONFIG_SUNRPC) += sunrpc/ +obj-$(CONFIG_RXRPC) += rxrpc/ +obj-$(CONFIG_ATM) += atm/ +obj-$(CONFIG_DECNET) += decnet/ +obj-$(CONFIG_ECONET) += econet/ +obj-$(CONFIG_VLAN_8021Q) += 8021q/ +obj-$(CONFIG_IP_SCTP) += sctp/ + +ifeq ($(CONFIG_NET),y) +obj-$(CONFIG_SYSCTL) += sysctl_net.o +endif diff --git a/net/TUNABLE b/net/TUNABLE new file mode 100644 index 000000000000..9913211f07a7 --- /dev/null +++ b/net/TUNABLE @@ -0,0 +1,50 @@ +The following parameters should be tunable at compile time. Some of them +exist as sysctls too. + +This is far from complete + +Item Description +---------------------------------------------------------------------------- +MAX_LINKS Maximum number of netlink minor devices. (1-32) +RIF_TABLE_SIZE Token ring RIF cache size (tunable) +AARP_HASH_SIZE Size of Appletalk hash table (tunable) +AX25_DEF_T1 AX.25 parameters. These are all tunable via +AX25_DEF_T2 SIOCAX25SETPARMS +AX25_DEF_T3 T1-T3,N2 have the meanings in the specification +AX25_DEF_N2 +AX25_DEF_AXDEFMODE 8 = normal 128 is PE1CHL extended +AX25_DEF_IPDEFMODE 'D' - datagram 'V' - virtual connection +AX25_DEF_BACKOFF 'E'xponential 'L'inear +AX25_DEF_NETROM Allow netrom 1=Y +AX25_DF_TEXT Allow PID=Text 1=Y +AX25_DEF_WINDOW Window for normal mode +AX25_DEF_EWINDOW Window for PE1CHL mode +AX25_DEF_DIGI 1 for inband 2 for cross band 3 for both +AX25_DEF_CONMODE Allow connected modes 1=Yes +AX25_ROUTE_MAX AX.25 route cache size - no currently tunable +Unnamed (16) Number of protocol hash slots (tunable) +DEV_NUMBUFFS Number of priority levels (not easily tunable) +Unnamed (300) Maximum packet backlog queue (tunable) +MAX_IOVEC Maximum number of iovecs in a message (tunable) +MIN_WINDOW Offered minimum window (tunable) +MAX_WINDOW Offered maximum window (tunable) +MAX_HEADER Largest physical header (tunable) +MAX_ADDR_LEN Largest physical address (tunable) +SOCK_ARRAY_SIZE IP socket array hash size (tunable) +IP_MAX_MEMBERSHIPS Largest number of groups per socket (BSD style) (tunable) +16 Hard coded constant for amount of room allowed for + cache align and faster forwarding (tunable) +IP_FRAG_TIME Time we hold a fragment for. (tunable) +PORT_MASQ_BEGIN First port reserved for masquerade (tunable) +PORT_MASQ_END Last port used for masquerade (tunable) +MASQUERADE_EXPIRE_TCP_FIN Time we keep a masquerade for after a FIN +MASQUERADE_EXPIRE_UDP Time we keep a UDP masquerade for (tunable) +MAXVIFS Maximum mrouted vifs (1-32) +MFC_LINES Lines in the multicast router cache (tunable) + +NetROM parameters are tunable via an ioctl passing a struct + +4000 Size a Unix domain socket malloc falls back to + (tunable) should be 8K - a bit for 8K machines like + the ALPHA + diff --git a/net/appletalk/Makefile b/net/appletalk/Makefile new file mode 100644 index 000000000000..5cda56edef57 --- /dev/null +++ b/net/appletalk/Makefile @@ -0,0 +1,9 @@ +# +# Makefile for the Linux AppleTalk layer. +# + +obj-$(CONFIG_ATALK) += appletalk.o + +appletalk-y := aarp.o ddp.o dev.o +appletalk-$(CONFIG_PROC_FS) += atalk_proc.o +appletalk-$(CONFIG_SYSCTL) += sysctl_net_atalk.o diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c new file mode 100644 index 000000000000..54640c01b50c --- /dev/null +++ b/net/appletalk/aarp.c @@ -0,0 +1,1069 @@ +/* + * AARP: An implementation of the AppleTalk AARP protocol for + * Ethernet 'ELAP'. + * + * Alan Cox <Alan.Cox@linux.org> + * + * This doesn't fit cleanly with the IP arp. Potentially we can use + * the generic neighbour discovery code to clean this up. + * + * FIXME: + * We ought to handle the retransmits with a single list and a + * separate fast timer for when it is needed. + * Use neighbour discovery code. + * Token Ring Support. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * + * References: + * Inside AppleTalk (2nd Ed). + * Fixes: + * Jaume Grau - flush caches on AARP_PROBE + * Rob Newberry - Added proxy AARP and AARP proc fs, + * moved probing from DDP module. + * Arnaldo C. Melo - don't mangle rx packets + * + */ + +#include <linux/config.h> +#include <linux/if_arp.h> +#include <net/sock.h> +#include <net/datalink.h> +#include <net/psnap.h> +#include <linux/atalk.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME; +int sysctl_aarp_tick_time = AARP_TICK_TIME; +int sysctl_aarp_retransmit_limit = AARP_RETRANSMIT_LIMIT; +int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME; + +/* Lists of aarp entries */ +/** + * struct aarp_entry - AARP entry + * @last_sent - Last time we xmitted the aarp request + * @packet_queue - Queue of frames wait for resolution + * @status - Used for proxy AARP + * expires_at - Entry expiry time + * target_addr - DDP Address + * dev - Device to use + * hwaddr - Physical i/f address of target/router + * xmit_count - When this hits 10 we give up + * next - Next entry in chain + */ +struct aarp_entry { + /* These first two are only used for unresolved entries */ + unsigned long last_sent; + struct sk_buff_head packet_queue; + int status; + unsigned long expires_at; + struct atalk_addr target_addr; + struct net_device *dev; + char hwaddr[6]; + unsigned short xmit_count; + struct aarp_entry *next; +}; + +/* Hashed list of resolved, unresolved and proxy entries */ +static struct aarp_entry *resolved[AARP_HASH_SIZE]; +static struct aarp_entry *unresolved[AARP_HASH_SIZE]; +static struct aarp_entry *proxies[AARP_HASH_SIZE]; +static int unresolved_count; + +/* One lock protects it all. */ +static DEFINE_RWLOCK(aarp_lock); + +/* Used to walk the list and purge/kick entries. */ +static struct timer_list aarp_timer; + +/* + * Delete an aarp queue + * + * Must run under aarp_lock. + */ +static void __aarp_expire(struct aarp_entry *a) +{ + skb_queue_purge(&a->packet_queue); + kfree(a); +} + +/* + * Send an aarp queue entry request + * + * Must run under aarp_lock. + */ +static void __aarp_send_query(struct aarp_entry *a) +{ + static unsigned char aarp_eth_multicast[ETH_ALEN] = + { 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF }; + struct net_device *dev = a->dev; + struct elapaarp *eah; + int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length; + struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC); + struct atalk_addr *sat = atalk_find_dev_addr(dev); + + if (!skb) + return; + + if (!sat) { + kfree_skb(skb); + return; + } + + /* Set up the buffer */ + skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length); + skb->nh.raw = skb->h.raw = skb_put(skb, sizeof(*eah)); + skb->protocol = htons(ETH_P_ATALK); + skb->dev = dev; + eah = aarp_hdr(skb); + + /* Set up the ARP */ + eah->hw_type = htons(AARP_HW_TYPE_ETHERNET); + eah->pa_type = htons(ETH_P_ATALK); + eah->hw_len = ETH_ALEN; + eah->pa_len = AARP_PA_ALEN; + eah->function = htons(AARP_REQUEST); + + memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN); + + eah->pa_src_zero = 0; + eah->pa_src_net = sat->s_net; + eah->pa_src_node = sat->s_node; + + memset(eah->hw_dst, '\0', ETH_ALEN); + + eah->pa_dst_zero = 0; + eah->pa_dst_net = a->target_addr.s_net; + eah->pa_dst_node = a->target_addr.s_node; + + /* Send it */ + aarp_dl->request(aarp_dl, skb, aarp_eth_multicast); + /* Update the sending count */ + a->xmit_count++; + a->last_sent = jiffies; +} + +/* This runs under aarp_lock and in softint context, so only atomic memory + * allocations can be used. */ +static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us, + struct atalk_addr *them, unsigned char *sha) +{ + struct elapaarp *eah; + int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length; + struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC); + + if (!skb) + return; + + /* Set up the buffer */ + skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length); + skb->nh.raw = skb->h.raw = skb_put(skb, sizeof(*eah)); + skb->protocol = htons(ETH_P_ATALK); + skb->dev = dev; + eah = aarp_hdr(skb); + + /* Set up the ARP */ + eah->hw_type = htons(AARP_HW_TYPE_ETHERNET); + eah->pa_type = htons(ETH_P_ATALK); + eah->hw_len = ETH_ALEN; + eah->pa_len = AARP_PA_ALEN; + eah->function = htons(AARP_REPLY); + + memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN); + + eah->pa_src_zero = 0; + eah->pa_src_net = us->s_net; + eah->pa_src_node = us->s_node; + + if (!sha) + memset(eah->hw_dst, '\0', ETH_ALEN); + else + memcpy(eah->hw_dst, sha, ETH_ALEN); + + eah->pa_dst_zero = 0; + eah->pa_dst_net = them->s_net; + eah->pa_dst_node = them->s_node; + + /* Send it */ + aarp_dl->request(aarp_dl, skb, sha); +} + +/* + * Send probe frames. Called from aarp_probe_network and + * aarp_proxy_probe_network. + */ + +static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us) +{ + struct elapaarp *eah; + int len = dev->hard_header_len + sizeof(*eah) + aarp_dl->header_length; + struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC); + static unsigned char aarp_eth_multicast[ETH_ALEN] = + { 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF }; + + if (!skb) + return; + + /* Set up the buffer */ + skb_reserve(skb, dev->hard_header_len + aarp_dl->header_length); + skb->nh.raw = skb->h.raw = skb_put(skb, sizeof(*eah)); + skb->protocol = htons(ETH_P_ATALK); + skb->dev = dev; + eah = aarp_hdr(skb); + + /* Set up the ARP */ + eah->hw_type = htons(AARP_HW_TYPE_ETHERNET); + eah->pa_type = htons(ETH_P_ATALK); + eah->hw_len = ETH_ALEN; + eah->pa_len = AARP_PA_ALEN; + eah->function = htons(AARP_PROBE); + + memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN); + + eah->pa_src_zero = 0; + eah->pa_src_net = us->s_net; + eah->pa_src_node = us->s_node; + + memset(eah->hw_dst, '\0', ETH_ALEN); + + eah->pa_dst_zero = 0; + eah->pa_dst_net = us->s_net; + eah->pa_dst_node = us->s_node; + + /* Send it */ + aarp_dl->request(aarp_dl, skb, aarp_eth_multicast); +} + +/* + * Handle an aarp timer expire + * + * Must run under the aarp_lock. + */ + +static void __aarp_expire_timer(struct aarp_entry **n) +{ + struct aarp_entry *t; + + while (*n) + /* Expired ? */ + if (time_after(jiffies, (*n)->expires_at)) { + t = *n; + *n = (*n)->next; + __aarp_expire(t); + } else + n = &((*n)->next); +} + +/* + * Kick all pending requests 5 times a second. + * + * Must run under the aarp_lock. + */ +static void __aarp_kick(struct aarp_entry **n) +{ + struct aarp_entry *t; + + while (*n) + /* Expired: if this will be the 11th tx, we delete instead. */ + if ((*n)->xmit_count >= sysctl_aarp_retransmit_limit) { + t = *n; + *n = (*n)->next; + __aarp_expire(t); + } else { + __aarp_send_query(*n); + n = &((*n)->next); + } +} + +/* + * A device has gone down. Take all entries referring to the device + * and remove them. + * + * Must run under the aarp_lock. + */ +static void __aarp_expire_device(struct aarp_entry **n, struct net_device *dev) +{ + struct aarp_entry *t; + + while (*n) + if ((*n)->dev == dev) { + t = *n; + *n = (*n)->next; + __aarp_expire(t); + } else + n = &((*n)->next); +} + +/* Handle the timer event */ +static void aarp_expire_timeout(unsigned long unused) +{ + int ct; + + write_lock_bh(&aarp_lock); + + for (ct = 0; ct < AARP_HASH_SIZE; ct++) { + __aarp_expire_timer(&resolved[ct]); + __aarp_kick(&unresolved[ct]); + __aarp_expire_timer(&unresolved[ct]); + __aarp_expire_timer(&proxies[ct]); + } + + write_unlock_bh(&aarp_lock); + mod_timer(&aarp_timer, jiffies + + (unresolved_count ? sysctl_aarp_tick_time : + sysctl_aarp_expiry_time)); +} + +/* Network device notifier chain handler. */ +static int aarp_device_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + int ct; + + if (event == NETDEV_DOWN) { + write_lock_bh(&aarp_lock); + + for (ct = 0; ct < AARP_HASH_SIZE; ct++) { + __aarp_expire_device(&resolved[ct], ptr); + __aarp_expire_device(&unresolved[ct], ptr); + __aarp_expire_device(&proxies[ct], ptr); + } + + write_unlock_bh(&aarp_lock); + } + return NOTIFY_DONE; +} + +/* Expire all entries in a hash chain */ +static void __aarp_expire_all(struct aarp_entry **n) +{ + struct aarp_entry *t; + + while (*n) { + t = *n; + *n = (*n)->next; + __aarp_expire(t); + } +} + +/* Cleanup all hash chains -- module unloading */ +static void aarp_purge(void) +{ + int ct; + + write_lock_bh(&aarp_lock); + for (ct = 0; ct < AARP_HASH_SIZE; ct++) { + __aarp_expire_all(&resolved[ct]); + __aarp_expire_all(&unresolved[ct]); + __aarp_expire_all(&proxies[ct]); + } + write_unlock_bh(&aarp_lock); +} + +/* + * Create a new aarp entry. This must use GFP_ATOMIC because it + * runs while holding spinlocks. + */ +static struct aarp_entry *aarp_alloc(void) +{ + struct aarp_entry *a = kmalloc(sizeof(*a), GFP_ATOMIC); + + if (a) + skb_queue_head_init(&a->packet_queue); + return a; +} + +/* + * Find an entry. We might return an expired but not yet purged entry. We + * don't care as it will do no harm. + * + * This must run under the aarp_lock. + */ +static struct aarp_entry *__aarp_find_entry(struct aarp_entry *list, + struct net_device *dev, + struct atalk_addr *sat) +{ + while (list) { + if (list->target_addr.s_net == sat->s_net && + list->target_addr.s_node == sat->s_node && + list->dev == dev) + break; + list = list->next; + } + + return list; +} + +/* Called from the DDP code, and thus must be exported. */ +void aarp_proxy_remove(struct net_device *dev, struct atalk_addr *sa) +{ + int hash = sa->s_node % (AARP_HASH_SIZE - 1); + struct aarp_entry *a; + + write_lock_bh(&aarp_lock); + + a = __aarp_find_entry(proxies[hash], dev, sa); + if (a) + a->expires_at = jiffies - 1; + + write_unlock_bh(&aarp_lock); +} + +/* This must run under aarp_lock. */ +static struct atalk_addr *__aarp_proxy_find(struct net_device *dev, + struct atalk_addr *sa) +{ + int hash = sa->s_node % (AARP_HASH_SIZE - 1); + struct aarp_entry *a = __aarp_find_entry(proxies[hash], dev, sa); + + return a ? sa : NULL; +} + +/* + * Probe a Phase 1 device or a device that requires its Net:Node to + * be set via an ioctl. + */ +static void aarp_send_probe_phase1(struct atalk_iface *iface) +{ + struct ifreq atreq; + struct sockaddr_at *sa = (struct sockaddr_at *)&atreq.ifr_addr; + + sa->sat_addr.s_node = iface->address.s_node; + sa->sat_addr.s_net = ntohs(iface->address.s_net); + + /* We pass the Net:Node to the drivers/cards by a Device ioctl. */ + if (!(iface->dev->do_ioctl(iface->dev, &atreq, SIOCSIFADDR))) { + (void)iface->dev->do_ioctl(iface->dev, &atreq, SIOCGIFADDR); + if (iface->address.s_net != htons(sa->sat_addr.s_net) || + iface->address.s_node != sa->sat_addr.s_node) + iface->status |= ATIF_PROBE_FAIL; + + iface->address.s_net = htons(sa->sat_addr.s_net); + iface->address.s_node = sa->sat_addr.s_node; + } +} + + +void aarp_probe_network(struct atalk_iface *atif) +{ + if (atif->dev->type == ARPHRD_LOCALTLK || + atif->dev->type == ARPHRD_PPP) + aarp_send_probe_phase1(atif); + else { + unsigned int count; + + for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) { + aarp_send_probe(atif->dev, &atif->address); + + /* Defer 1/10th */ + current->state = TASK_INTERRUPTIBLE; + schedule_timeout(HZ / 10); + + if (atif->status & ATIF_PROBE_FAIL) + break; + } + } +} + +int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa) +{ + int hash, retval = -EPROTONOSUPPORT; + struct aarp_entry *entry; + unsigned int count; + + /* + * we don't currently support LocalTalk or PPP for proxy AARP; + * if someone wants to try and add it, have fun + */ + if (atif->dev->type == ARPHRD_LOCALTLK || + atif->dev->type == ARPHRD_PPP) + goto out; + + /* + * create a new AARP entry with the flags set to be published -- + * we need this one to hang around even if it's in use + */ + entry = aarp_alloc(); + retval = -ENOMEM; + if (!entry) + goto out; + + entry->expires_at = -1; + entry->status = ATIF_PROBE; + entry->target_addr.s_node = sa->s_node; + entry->target_addr.s_net = sa->s_net; + entry->dev = atif->dev; + + write_lock_bh(&aarp_lock); + + hash = sa->s_node % (AARP_HASH_SIZE - 1); + entry->next = proxies[hash]; + proxies[hash] = entry; + + for (count = 0; count < AARP_RETRANSMIT_LIMIT; count++) { + aarp_send_probe(atif->dev, sa); + + /* Defer 1/10th */ + current->state = TASK_INTERRUPTIBLE; + write_unlock_bh(&aarp_lock); + schedule_timeout(HZ / 10); + write_lock_bh(&aarp_lock); + + if (entry->status & ATIF_PROBE_FAIL) + break; + } + + if (entry->status & ATIF_PROBE_FAIL) { + entry->expires_at = jiffies - 1; /* free the entry */ + retval = -EADDRINUSE; /* return network full */ + } else { /* clear the probing flag */ + entry->status &= ~ATIF_PROBE; + retval = 1; + } + + write_unlock_bh(&aarp_lock); +out: + return retval; +} + +/* Send a DDP frame */ +int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb, + struct atalk_addr *sa, void *hwaddr) +{ + static char ddp_eth_multicast[ETH_ALEN] = + { 0x09, 0x00, 0x07, 0xFF, 0xFF, 0xFF }; + int hash; + struct aarp_entry *a; + + skb->nh.raw = skb->data; + + /* Check for LocalTalk first */ + if (dev->type == ARPHRD_LOCALTLK) { + struct atalk_addr *at = atalk_find_dev_addr(dev); + struct ddpehdr *ddp = (struct ddpehdr *)skb->data; + int ft = 2; + + /* + * Compressible ? + * + * IFF: src_net == dest_net == device_net + * (zero matches anything) + */ + + if ((!ddp->deh_snet || at->s_net == ddp->deh_snet) && + (!ddp->deh_dnet || at->s_net == ddp->deh_dnet)) { + skb_pull(skb, sizeof(*ddp) - 4); + + /* + * The upper two remaining bytes are the port + * numbers we just happen to need. Now put the + * length in the lower two. + */ + *((__u16 *)skb->data) = htons(skb->len); + ft = 1; + } + /* + * Nice and easy. No AARP type protocols occur here so we can + * just shovel it out with a 3 byte LLAP header + */ + + skb_push(skb, 3); + skb->data[0] = sa->s_node; + skb->data[1] = at->s_node; + skb->data[2] = ft; + skb->dev = dev; + goto sendit; + } + + /* On a PPP link we neither compress nor aarp. */ + if (dev->type == ARPHRD_PPP) { + skb->protocol = htons(ETH_P_PPPTALK); + skb->dev = dev; + goto sendit; + } + + /* Non ELAP we cannot do. */ + if (dev->type != ARPHRD_ETHER) + return -1; + + skb->dev = dev; + skb->protocol = htons(ETH_P_ATALK); + hash = sa->s_node % (AARP_HASH_SIZE - 1); + + /* Do we have a resolved entry? */ + if (sa->s_node == ATADDR_BCAST) { + /* Send it */ + ddp_dl->request(ddp_dl, skb, ddp_eth_multicast); + goto sent; + } + + write_lock_bh(&aarp_lock); + a = __aarp_find_entry(resolved[hash], dev, sa); + + if (a) { /* Return 1 and fill in the address */ + a->expires_at = jiffies + (sysctl_aarp_expiry_time * 10); + ddp_dl->request(ddp_dl, skb, a->hwaddr); + write_unlock_bh(&aarp_lock); + goto sent; + } + + /* Do we have an unresolved entry: This is the less common path */ + a = __aarp_find_entry(unresolved[hash], dev, sa); + if (a) { /* Queue onto the unresolved queue */ + skb_queue_tail(&a->packet_queue, skb); + goto out_unlock; + } + + /* Allocate a new entry */ + a = aarp_alloc(); + if (!a) { + /* Whoops slipped... good job it's an unreliable protocol 8) */ + write_unlock_bh(&aarp_lock); + return -1; + } + + /* Set up the queue */ + skb_queue_tail(&a->packet_queue, skb); + a->expires_at = jiffies + sysctl_aarp_resolve_time; + a->dev = dev; + a->next = unresolved[hash]; + a->target_addr = *sa; + a->xmit_count = 0; + unresolved[hash] = a; + unresolved_count++; + + /* Send an initial request for the address */ + __aarp_send_query(a); + + /* + * Switch to fast timer if needed (That is if this is the first + * unresolved entry to get added) + */ + + if (unresolved_count == 1) + mod_timer(&aarp_timer, jiffies + sysctl_aarp_tick_time); + + /* Now finally, it is safe to drop the lock. */ +out_unlock: + write_unlock_bh(&aarp_lock); + + /* Tell the ddp layer we have taken over for this frame. */ + return 0; + +sendit: + if (skb->sk) + skb->priority = skb->sk->sk_priority; + dev_queue_xmit(skb); +sent: + return 1; +} + +/* + * An entry in the aarp unresolved queue has become resolved. Send + * all the frames queued under it. + * + * Must run under aarp_lock. + */ +static void __aarp_resolved(struct aarp_entry **list, struct aarp_entry *a, + int hash) +{ + struct sk_buff *skb; + + while (*list) + if (*list == a) { + unresolved_count--; + *list = a->next; + + /* Move into the resolved list */ + a->next = resolved[hash]; + resolved[hash] = a; + + /* Kick frames off */ + while ((skb = skb_dequeue(&a->packet_queue)) != NULL) { + a->expires_at = jiffies + + sysctl_aarp_expiry_time * 10; + ddp_dl->request(ddp_dl, skb, a->hwaddr); + } + } else + list = &((*list)->next); +} + +/* + * This is called by the SNAP driver whenever we see an AARP SNAP + * frame. We currently only support Ethernet. + */ +static int aarp_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + struct elapaarp *ea = aarp_hdr(skb); + int hash, ret = 0; + __u16 function; + struct aarp_entry *a; + struct atalk_addr sa, *ma, da; + struct atalk_iface *ifa; + + /* We only do Ethernet SNAP AARP. */ + if (dev->type != ARPHRD_ETHER) + goto out0; + + /* Frame size ok? */ + if (!skb_pull(skb, sizeof(*ea))) + goto out0; + + function = ntohs(ea->function); + + /* Sanity check fields. */ + if (function < AARP_REQUEST || function > AARP_PROBE || + ea->hw_len != ETH_ALEN || ea->pa_len != AARP_PA_ALEN || + ea->pa_src_zero || ea->pa_dst_zero) + goto out0; + + /* Looks good. */ + hash = ea->pa_src_node % (AARP_HASH_SIZE - 1); + + /* Build an address. */ + sa.s_node = ea->pa_src_node; + sa.s_net = ea->pa_src_net; + + /* Process the packet. Check for replies of me. */ + ifa = atalk_find_dev(dev); + if (!ifa) + goto out1; + + if (ifa->status & ATIF_PROBE && + ifa->address.s_node == ea->pa_dst_node && + ifa->address.s_net == ea->pa_dst_net) { + ifa->status |= ATIF_PROBE_FAIL; /* Fail the probe (in use) */ + goto out1; + } + + /* Check for replies of proxy AARP entries */ + da.s_node = ea->pa_dst_node; + da.s_net = ea->pa_dst_net; + + write_lock_bh(&aarp_lock); + a = __aarp_find_entry(proxies[hash], dev, &da); + + if (a && a->status & ATIF_PROBE) { + a->status |= ATIF_PROBE_FAIL; + /* + * we do not respond to probe or request packets for + * this address while we are probing this address + */ + goto unlock; + } + + switch (function) { + case AARP_REPLY: + if (!unresolved_count) /* Speed up */ + break; + + /* Find the entry. */ + a = __aarp_find_entry(unresolved[hash], dev, &sa); + if (!a || dev != a->dev) + break; + + /* We can fill one in - this is good. */ + memcpy(a->hwaddr, ea->hw_src, ETH_ALEN); + __aarp_resolved(&unresolved[hash], a, hash); + if (!unresolved_count) + mod_timer(&aarp_timer, + jiffies + sysctl_aarp_expiry_time); + break; + + case AARP_REQUEST: + case AARP_PROBE: + + /* + * If it is my address set ma to my address and reply. + * We can treat probe and request the same. Probe + * simply means we shouldn't cache the querying host, + * as in a probe they are proposing an address not + * using one. + * + * Support for proxy-AARP added. We check if the + * address is one of our proxies before we toss the + * packet out. + */ + + sa.s_node = ea->pa_dst_node; + sa.s_net = ea->pa_dst_net; + + /* See if we have a matching proxy. */ + ma = __aarp_proxy_find(dev, &sa); + if (!ma) + ma = &ifa->address; + else { /* We need to make a copy of the entry. */ + da.s_node = sa.s_node; + da.s_net = da.s_net; + ma = &da; + } + + if (function == AARP_PROBE) { + /* + * A probe implies someone trying to get an + * address. So as a precaution flush any + * entries we have for this address. + */ + struct aarp_entry *a; + + a = __aarp_find_entry(resolved[sa.s_node % + (AARP_HASH_SIZE - 1)], + skb->dev, &sa); + + /* + * Make it expire next tick - that avoids us + * getting into a probe/flush/learn/probe/ + * flush/learn cycle during probing of a slow + * to respond host addr. + */ + if (a) { + a->expires_at = jiffies - 1; + mod_timer(&aarp_timer, jiffies + + sysctl_aarp_tick_time); + } + } + + if (sa.s_node != ma->s_node) + break; + + if (sa.s_net && ma->s_net && sa.s_net != ma->s_net) + break; + + sa.s_node = ea->pa_src_node; + sa.s_net = ea->pa_src_net; + + /* aarp_my_address has found the address to use for us. + */ + aarp_send_reply(dev, ma, &sa, ea->hw_src); + break; + } + +unlock: + write_unlock_bh(&aarp_lock); +out1: + ret = 1; +out0: + kfree_skb(skb); + return ret; +} + +static struct notifier_block aarp_notifier = { + .notifier_call = aarp_device_event, +}; + +static unsigned char aarp_snap_id[] = { 0x00, 0x00, 0x00, 0x80, 0xF3 }; + +void __init aarp_proto_init(void) +{ + aarp_dl = register_snap_client(aarp_snap_id, aarp_rcv); + if (!aarp_dl) + printk(KERN_CRIT "Unable to register AARP with SNAP.\n"); + init_timer(&aarp_timer); + aarp_timer.function = aarp_expire_timeout; + aarp_timer.data = 0; + aarp_timer.expires = jiffies + sysctl_aarp_expiry_time; + add_timer(&aarp_timer); + register_netdevice_notifier(&aarp_notifier); +} + +/* Remove the AARP entries associated with a device. */ +void aarp_device_down(struct net_device *dev) +{ + int ct; + + write_lock_bh(&aarp_lock); + + for (ct = 0; ct < AARP_HASH_SIZE; ct++) { + __aarp_expire_device(&resolved[ct], dev); + __aarp_expire_device(&unresolved[ct], dev); + __aarp_expire_device(&proxies[ct], dev); + } + + write_unlock_bh(&aarp_lock); +} + +#ifdef CONFIG_PROC_FS +struct aarp_iter_state { + int bucket; + struct aarp_entry **table; +}; + +/* + * Get the aarp entry that is in the chain described + * by the iterator. + * If pos is set then skip till that index. + * pos = 1 is the first entry + */ +static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos) +{ + int ct = iter->bucket; + struct aarp_entry **table = iter->table; + loff_t off = 0; + struct aarp_entry *entry; + + rescan: + while(ct < AARP_HASH_SIZE) { + for (entry = table[ct]; entry; entry = entry->next) { + if (!pos || ++off == *pos) { + iter->table = table; + iter->bucket = ct; + return entry; + } + } + ++ct; + } + + if (table == resolved) { + ct = 0; + table = unresolved; + goto rescan; + } + if (table == unresolved) { + ct = 0; + table = proxies; + goto rescan; + } + return NULL; +} + +static void *aarp_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct aarp_iter_state *iter = seq->private; + + read_lock_bh(&aarp_lock); + iter->table = resolved; + iter->bucket = 0; + + return *pos ? iter_next(iter, pos) : SEQ_START_TOKEN; +} + +static void *aarp_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct aarp_entry *entry = v; + struct aarp_iter_state *iter = seq->private; + + ++*pos; + + /* first line after header */ + if (v == SEQ_START_TOKEN) + entry = iter_next(iter, NULL); + + /* next entry in current bucket */ + else if (entry->next) + entry = entry->next; + + /* next bucket or table */ + else { + ++iter->bucket; + entry = iter_next(iter, NULL); + } + return entry; +} + +static void aarp_seq_stop(struct seq_file *seq, void *v) +{ + read_unlock_bh(&aarp_lock); +} + +static const char *dt2str(unsigned long ticks) +{ + static char buf[32]; + + sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ); + + return buf; +} + +static int aarp_seq_show(struct seq_file *seq, void *v) +{ + struct aarp_iter_state *iter = seq->private; + struct aarp_entry *entry = v; + unsigned long now = jiffies; + + if (v == SEQ_START_TOKEN) + seq_puts(seq, + "Address Interface Hardware Address" + " Expires LastSend Retry Status\n"); + else { + seq_printf(seq, "%04X:%02X %-12s", + ntohs(entry->target_addr.s_net), + (unsigned int) entry->target_addr.s_node, + entry->dev ? entry->dev->name : "????"); + seq_printf(seq, "%02X:%02X:%02X:%02X:%02X:%02X", + entry->hwaddr[0] & 0xFF, + entry->hwaddr[1] & 0xFF, + entry->hwaddr[2] & 0xFF, + entry->hwaddr[3] & 0xFF, + entry->hwaddr[4] & 0xFF, + entry->hwaddr[5] & 0xFF); + seq_printf(seq, " %8s", + dt2str((long)entry->expires_at - (long)now)); + if (iter->table == unresolved) + seq_printf(seq, " %8s %6hu", + dt2str(now - entry->last_sent), + entry->xmit_count); + else + seq_puts(seq, " "); + seq_printf(seq, " %s\n", + (iter->table == resolved) ? "resolved" + : (iter->table == unresolved) ? "unresolved" + : (iter->table == proxies) ? "proxies" + : "unknown"); + } + return 0; +} + +static struct seq_operations aarp_seq_ops = { + .start = aarp_seq_start, + .next = aarp_seq_next, + .stop = aarp_seq_stop, + .show = aarp_seq_show, +}; + +static int aarp_seq_open(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int rc = -ENOMEM; + struct aarp_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); + + if (!s) + goto out; + + rc = seq_open(file, &aarp_seq_ops); + if (rc) + goto out_kfree; + + seq = file->private_data; + seq->private = s; + memset(s, 0, sizeof(*s)); +out: + return rc; +out_kfree: + kfree(s); + goto out; +} + +struct file_operations atalk_seq_arp_fops = { + .owner = THIS_MODULE, + .open = aarp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; +#endif + +/* General module cleanup. Called from cleanup_module() in ddp.c. */ +void aarp_cleanup_module(void) +{ + del_timer_sync(&aarp_timer); + unregister_netdevice_notifier(&aarp_notifier); + unregister_snap_client(aarp_dl); + aarp_purge(); +} diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c new file mode 100644 index 000000000000..dc4048dd98c1 --- /dev/null +++ b/net/appletalk/atalk_proc.c @@ -0,0 +1,321 @@ +/* + * atalk_proc.c - proc support for Appletalk + * + * Copyright(c) Arnaldo Carvalho de Melo <acme@conectiva.com.br> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation, version 2. + */ + +#include <linux/config.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <net/sock.h> +#include <linux/atalk.h> + + +static __inline__ struct atalk_iface *atalk_get_interface_idx(loff_t pos) +{ + struct atalk_iface *i; + + for (i = atalk_interfaces; pos && i; i = i->next) + --pos; + + return i; +} + +static void *atalk_seq_interface_start(struct seq_file *seq, loff_t *pos) +{ + loff_t l = *pos; + + read_lock_bh(&atalk_interfaces_lock); + return l ? atalk_get_interface_idx(--l) : SEQ_START_TOKEN; +} + +static void *atalk_seq_interface_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct atalk_iface *i; + + ++*pos; + if (v == SEQ_START_TOKEN) { + i = NULL; + if (atalk_interfaces) + i = atalk_interfaces; + goto out; + } + i = v; + i = i->next; +out: + return i; +} + +static void atalk_seq_interface_stop(struct seq_file *seq, void *v) +{ + read_unlock_bh(&atalk_interfaces_lock); +} + +static int atalk_seq_interface_show(struct seq_file *seq, void *v) +{ + struct atalk_iface *iface; + + if (v == SEQ_START_TOKEN) { + seq_puts(seq, "Interface Address Networks " + "Status\n"); + goto out; + } + + iface = v; + seq_printf(seq, "%-16s %04X:%02X %04X-%04X %d\n", + iface->dev->name, ntohs(iface->address.s_net), + iface->address.s_node, ntohs(iface->nets.nr_firstnet), + ntohs(iface->nets.nr_lastnet), iface->status); +out: + return 0; +} + +static __inline__ struct atalk_route *atalk_get_route_idx(loff_t pos) +{ + struct atalk_route *r; + + for (r = atalk_routes; pos && r; r = r->next) + --pos; + + return r; +} + +static void *atalk_seq_route_start(struct seq_file *seq, loff_t *pos) +{ + loff_t l = *pos; + + read_lock_bh(&atalk_routes_lock); + return l ? atalk_get_route_idx(--l) : SEQ_START_TOKEN; +} + +static void *atalk_seq_route_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct atalk_route *r; + + ++*pos; + if (v == SEQ_START_TOKEN) { + r = NULL; + if (atalk_routes) + r = atalk_routes; + goto out; + } + r = v; + r = r->next; +out: + return r; +} + +static void atalk_seq_route_stop(struct seq_file *seq, void *v) +{ + read_unlock_bh(&atalk_routes_lock); +} + +static int atalk_seq_route_show(struct seq_file *seq, void *v) +{ + struct atalk_route *rt; + + if (v == SEQ_START_TOKEN) { + seq_puts(seq, "Target Router Flags Dev\n"); + goto out; + } + + if (atrtr_default.dev) { + rt = &atrtr_default; + seq_printf(seq, "Default %04X:%02X %-4d %s\n", + ntohs(rt->gateway.s_net), rt->gateway.s_node, + rt->flags, rt->dev->name); + } + + rt = v; + seq_printf(seq, "%04X:%02X %04X:%02X %-4d %s\n", + ntohs(rt->target.s_net), rt->target.s_node, + ntohs(rt->gateway.s_net), rt->gateway.s_node, + rt->flags, rt->dev->name); +out: + return 0; +} + +static __inline__ struct sock *atalk_get_socket_idx(loff_t pos) +{ + struct sock *s; + struct hlist_node *node; + + sk_for_each(s, node, &atalk_sockets) + if (!pos--) + goto found; + s = NULL; +found: + return s; +} + +static void *atalk_seq_socket_start(struct seq_file *seq, loff_t *pos) +{ + loff_t l = *pos; + + read_lock_bh(&atalk_sockets_lock); + return l ? atalk_get_socket_idx(--l) : SEQ_START_TOKEN; +} + +static void *atalk_seq_socket_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct sock *i; + + ++*pos; + if (v == SEQ_START_TOKEN) { + i = sk_head(&atalk_sockets); + goto out; + } + i = sk_next(v); +out: + return i; +} + +static void atalk_seq_socket_stop(struct seq_file *seq, void *v) +{ + read_unlock_bh(&atalk_sockets_lock); +} + +static int atalk_seq_socket_show(struct seq_file *seq, void *v) +{ + struct sock *s; + struct atalk_sock *at; + + if (v == SEQ_START_TOKEN) { + seq_printf(seq, "Type Local_addr Remote_addr Tx_queue " + "Rx_queue St UID\n"); + goto out; + } + + s = v; + at = at_sk(s); + + seq_printf(seq, "%02X %04X:%02X:%02X %04X:%02X:%02X %08X:%08X " + "%02X %d\n", + s->sk_type, ntohs(at->src_net), at->src_node, at->src_port, + ntohs(at->dest_net), at->dest_node, at->dest_port, + atomic_read(&s->sk_wmem_alloc), + atomic_read(&s->sk_rmem_alloc), + s->sk_state, SOCK_INODE(s->sk_socket)->i_uid); +out: + return 0; +} + +static struct seq_operations atalk_seq_interface_ops = { + .start = atalk_seq_interface_start, + .next = atalk_seq_interface_next, + .stop = atalk_seq_interface_stop, + .show = atalk_seq_interface_show, +}; + +static struct seq_operations atalk_seq_route_ops = { + .start = atalk_seq_route_start, + .next = atalk_seq_route_next, + .stop = atalk_seq_route_stop, + .show = atalk_seq_route_show, +}; + +static struct seq_operations atalk_seq_socket_ops = { + .start = atalk_seq_socket_start, + .next = atalk_seq_socket_next, + .stop = atalk_seq_socket_stop, + .show = atalk_seq_socket_show, +}; + +static int atalk_seq_interface_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &atalk_seq_interface_ops); +} + +static int atalk_seq_route_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &atalk_seq_route_ops); +} + +static int atalk_seq_socket_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &atalk_seq_socket_ops); +} + +static struct file_operations atalk_seq_interface_fops = { + .owner = THIS_MODULE, + .open = atalk_seq_interface_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static struct file_operations atalk_seq_route_fops = { + .owner = THIS_MODULE, + .open = atalk_seq_route_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static struct file_operations atalk_seq_socket_fops = { + .owner = THIS_MODULE, + .open = atalk_seq_socket_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static struct proc_dir_entry *atalk_proc_dir; + +int __init atalk_proc_init(void) +{ + struct proc_dir_entry *p; + int rc = -ENOMEM; + + atalk_proc_dir = proc_mkdir("atalk", proc_net); + if (!atalk_proc_dir) + goto out; + atalk_proc_dir->owner = THIS_MODULE; + + p = create_proc_entry("interface", S_IRUGO, atalk_proc_dir); + if (!p) + goto out_interface; + p->proc_fops = &atalk_seq_interface_fops; + + p = create_proc_entry("route", S_IRUGO, atalk_proc_dir); + if (!p) + goto out_route; + p->proc_fops = &atalk_seq_route_fops; + + p = create_proc_entry("socket", S_IRUGO, atalk_proc_dir); + if (!p) + goto out_socket; + p->proc_fops = &atalk_seq_socket_fops; + + p = create_proc_entry("arp", S_IRUGO, atalk_proc_dir); + if (!p) + goto out_arp; + p->proc_fops = &atalk_seq_arp_fops; + + rc = 0; +out: + return rc; +out_arp: + remove_proc_entry("socket", atalk_proc_dir); +out_socket: + remove_proc_entry("route", atalk_proc_dir); +out_route: + remove_proc_entry("interface", atalk_proc_dir); +out_interface: + remove_proc_entry("atalk", proc_net); + goto out; +} + +void __exit atalk_proc_exit(void) +{ + remove_proc_entry("interface", atalk_proc_dir); + remove_proc_entry("route", atalk_proc_dir); + remove_proc_entry("socket", atalk_proc_dir); + remove_proc_entry("arp", atalk_proc_dir); + remove_proc_entry("atalk", proc_net); +} diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c new file mode 100644 index 000000000000..d1fea5c3dda1 --- /dev/null +++ b/net/appletalk/ddp.c @@ -0,0 +1,1931 @@ +/* + * DDP: An implementation of the AppleTalk DDP protocol for + * Ethernet 'ELAP'. + * + * Alan Cox <Alan.Cox@linux.org> + * + * With more than a little assistance from + * + * Wesley Craig <netatalk@umich.edu> + * + * Fixes: + * Neil Horman : Added missing device ioctls + * Michael Callahan : Made routing work + * Wesley Craig : Fix probing to listen to a + * passed node id. + * Alan Cox : Added send/recvmsg support + * Alan Cox : Moved at. to protinfo in + * socket. + * Alan Cox : Added firewall hooks. + * Alan Cox : Supports new ARPHRD_LOOPBACK + * Christer Weinigel : Routing and /proc fixes. + * Bradford Johnson : LocalTalk. + * Tom Dyas : Module support. + * Alan Cox : Hooks for PPP (based on the + * LocalTalk hook). + * Alan Cox : Posix bits + * Alan Cox/Mike Freeman : Possible fix to NBP problems + * Bradford Johnson : IP-over-DDP (experimental) + * Jay Schulist : Moved IP-over-DDP to its own + * driver file. (ipddp.c & ipddp.h) + * Jay Schulist : Made work as module with + * AppleTalk drivers, cleaned it. + * Rob Newberry : Added proxy AARP and AARP + * procfs, moved probing to AARP + * module. + * Adrian Sun/ + * Michael Zuelsdorff : fix for net.0 packets. don't + * allow illegal ether/tokentalk + * port assignment. we lose a + * valid localtalk port as a + * result. + * Arnaldo C. de Melo : Cleanup, in preparation for + * shared skb support 8) + * Arnaldo C. de Melo : Move proc stuff to atalk_proc.c, + * use seq_file + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/tcp.h> +#include <linux/if_arp.h> +#include <linux/termios.h> /* For TIOCOUTQ/INQ */ +#include <net/datalink.h> +#include <net/psnap.h> +#include <net/sock.h> +#include <net/route.h> +#include <linux/atalk.h> + +struct datalink_proto *ddp_dl, *aarp_dl; +static struct proto_ops atalk_dgram_ops; + +/**************************************************************************\ +* * +* Handlers for the socket list. * +* * +\**************************************************************************/ + +HLIST_HEAD(atalk_sockets); +DEFINE_RWLOCK(atalk_sockets_lock); + +static inline void __atalk_insert_socket(struct sock *sk) +{ + sk_add_node(sk, &atalk_sockets); +} + +static inline void atalk_remove_socket(struct sock *sk) +{ + write_lock_bh(&atalk_sockets_lock); + sk_del_node_init(sk); + write_unlock_bh(&atalk_sockets_lock); +} + +static struct sock *atalk_search_socket(struct sockaddr_at *to, + struct atalk_iface *atif) +{ + struct sock *s; + struct hlist_node *node; + + read_lock_bh(&atalk_sockets_lock); + sk_for_each(s, node, &atalk_sockets) { + struct atalk_sock *at = at_sk(s); + + if (to->sat_port != at->src_port) + continue; + + if (to->sat_addr.s_net == ATADDR_ANYNET && + to->sat_addr.s_node == ATADDR_BCAST && + at->src_net == atif->address.s_net) + goto found; + + if (to->sat_addr.s_net == at->src_net && + (to->sat_addr.s_node == at->src_node || + to->sat_addr.s_node == ATADDR_BCAST || + to->sat_addr.s_node == ATADDR_ANYNODE)) + goto found; + + /* XXXX.0 -- we got a request for this router. make sure + * that the node is appropriately set. */ + if (to->sat_addr.s_node == ATADDR_ANYNODE && + to->sat_addr.s_net != ATADDR_ANYNET && + atif->address.s_node == at->src_node) { + to->sat_addr.s_node = atif->address.s_node; + goto found; + } + } + s = NULL; +found: + read_unlock_bh(&atalk_sockets_lock); + return s; +} + +/** + * atalk_find_or_insert_socket - Try to find a socket matching ADDR + * @sk - socket to insert in the list if it is not there already + * @sat - address to search for + * + * Try to find a socket matching ADDR in the socket list, if found then return + * it. If not, insert SK into the socket list. + * + * This entire operation must execute atomically. + */ +static struct sock *atalk_find_or_insert_socket(struct sock *sk, + struct sockaddr_at *sat) +{ + struct sock *s; + struct hlist_node *node; + struct atalk_sock *at; + + write_lock_bh(&atalk_sockets_lock); + sk_for_each(s, node, &atalk_sockets) { + at = at_sk(s); + + if (at->src_net == sat->sat_addr.s_net && + at->src_node == sat->sat_addr.s_node && + at->src_port == sat->sat_port) + goto found; + } + s = NULL; + __atalk_insert_socket(sk); /* Wheee, it's free, assign and insert. */ +found: + write_unlock_bh(&atalk_sockets_lock); + return s; +} + +static void atalk_destroy_timer(unsigned long data) +{ + struct sock *sk = (struct sock *)data; + + if (atomic_read(&sk->sk_wmem_alloc) || + atomic_read(&sk->sk_rmem_alloc)) { + sk->sk_timer.expires = jiffies + SOCK_DESTROY_TIME; + add_timer(&sk->sk_timer); + } else + sock_put(sk); +} + +static inline void atalk_destroy_socket(struct sock *sk) +{ + atalk_remove_socket(sk); + skb_queue_purge(&sk->sk_receive_queue); + + if (atomic_read(&sk->sk_wmem_alloc) || + atomic_read(&sk->sk_rmem_alloc)) { + init_timer(&sk->sk_timer); + sk->sk_timer.expires = jiffies + SOCK_DESTROY_TIME; + sk->sk_timer.function = atalk_destroy_timer; + sk->sk_timer.data = (unsigned long)sk; + add_timer(&sk->sk_timer); + } else + sock_put(sk); +} + +/**************************************************************************\ +* * +* Routing tables for the AppleTalk socket layer. * +* * +\**************************************************************************/ + +/* Anti-deadlock ordering is atalk_routes_lock --> iface_lock -DaveM */ +struct atalk_route *atalk_routes; +DEFINE_RWLOCK(atalk_routes_lock); + +struct atalk_iface *atalk_interfaces; +DEFINE_RWLOCK(atalk_interfaces_lock); + +/* For probing devices or in a routerless network */ +struct atalk_route atrtr_default; + +/* AppleTalk interface control */ +/* + * Drop a device. Doesn't drop any of its routes - that is the caller's + * problem. Called when we down the interface or delete the address. + */ +static void atif_drop_device(struct net_device *dev) +{ + struct atalk_iface **iface = &atalk_interfaces; + struct atalk_iface *tmp; + + write_lock_bh(&atalk_interfaces_lock); + while ((tmp = *iface) != NULL) { + if (tmp->dev == dev) { + *iface = tmp->next; + dev_put(dev); + kfree(tmp); + dev->atalk_ptr = NULL; + } else + iface = &tmp->next; + } + write_unlock_bh(&atalk_interfaces_lock); +} + +static struct atalk_iface *atif_add_device(struct net_device *dev, + struct atalk_addr *sa) +{ + struct atalk_iface *iface = kmalloc(sizeof(*iface), GFP_KERNEL); + + if (!iface) + goto out; + + memset(iface, 0, sizeof(*iface)); + dev_hold(dev); + iface->dev = dev; + dev->atalk_ptr = iface; + iface->address = *sa; + iface->status = 0; + + write_lock_bh(&atalk_interfaces_lock); + iface->next = atalk_interfaces; + atalk_interfaces = iface; + write_unlock_bh(&atalk_interfaces_lock); +out: + return iface; +} + +/* Perform phase 2 AARP probing on our tentative address */ +static int atif_probe_device(struct atalk_iface *atif) +{ + int netrange = ntohs(atif->nets.nr_lastnet) - + ntohs(atif->nets.nr_firstnet) + 1; + int probe_net = ntohs(atif->address.s_net); + int probe_node = atif->address.s_node; + int netct, nodect; + + /* Offset the network we start probing with */ + if (probe_net == ATADDR_ANYNET) { + probe_net = ntohs(atif->nets.nr_firstnet); + if (netrange) + probe_net += jiffies % netrange; + } + if (probe_node == ATADDR_ANYNODE) + probe_node = jiffies & 0xFF; + + /* Scan the networks */ + atif->status |= ATIF_PROBE; + for (netct = 0; netct <= netrange; netct++) { + /* Sweep the available nodes from a given start */ + atif->address.s_net = htons(probe_net); + for (nodect = 0; nodect < 256; nodect++) { + atif->address.s_node = (nodect + probe_node) & 0xFF; + if (atif->address.s_node > 0 && + atif->address.s_node < 254) { + /* Probe a proposed address */ + aarp_probe_network(atif); + + if (!(atif->status & ATIF_PROBE_FAIL)) { + atif->status &= ~ATIF_PROBE; + return 0; + } + } + atif->status &= ~ATIF_PROBE_FAIL; + } + probe_net++; + if (probe_net > ntohs(atif->nets.nr_lastnet)) + probe_net = ntohs(atif->nets.nr_firstnet); + } + atif->status &= ~ATIF_PROBE; + + return -EADDRINUSE; /* Network is full... */ +} + + +/* Perform AARP probing for a proxy address */ +static int atif_proxy_probe_device(struct atalk_iface *atif, + struct atalk_addr* proxy_addr) +{ + int netrange = ntohs(atif->nets.nr_lastnet) - + ntohs(atif->nets.nr_firstnet) + 1; + /* we probe the interface's network */ + int probe_net = ntohs(atif->address.s_net); + int probe_node = ATADDR_ANYNODE; /* we'll take anything */ + int netct, nodect; + + /* Offset the network we start probing with */ + if (probe_net == ATADDR_ANYNET) { + probe_net = ntohs(atif->nets.nr_firstnet); + if (netrange) + probe_net += jiffies % netrange; + } + + if (probe_node == ATADDR_ANYNODE) + probe_node = jiffies & 0xFF; + + /* Scan the networks */ + for (netct = 0; netct <= netrange; netct++) { + /* Sweep the available nodes from a given start */ + proxy_addr->s_net = htons(probe_net); + for (nodect = 0; nodect < 256; nodect++) { + proxy_addr->s_node = (nodect + probe_node) & 0xFF; + if (proxy_addr->s_node > 0 && + proxy_addr->s_node < 254) { + /* Tell AARP to probe a proposed address */ + int ret = aarp_proxy_probe_network(atif, + proxy_addr); + + if (ret != -EADDRINUSE) + return ret; + } + } + probe_net++; + if (probe_net > ntohs(atif->nets.nr_lastnet)) + probe_net = ntohs(atif->nets.nr_firstnet); + } + + return -EADDRINUSE; /* Network is full... */ +} + + +struct atalk_addr *atalk_find_dev_addr(struct net_device *dev) +{ + struct atalk_iface *iface = dev->atalk_ptr; + return iface ? &iface->address : NULL; +} + +static struct atalk_addr *atalk_find_primary(void) +{ + struct atalk_iface *fiface = NULL; + struct atalk_addr *retval; + struct atalk_iface *iface; + + /* + * Return a point-to-point interface only if + * there is no non-ptp interface available. + */ + read_lock_bh(&atalk_interfaces_lock); + for (iface = atalk_interfaces; iface; iface = iface->next) { + if (!fiface && !(iface->dev->flags & IFF_LOOPBACK)) + fiface = iface; + if (!(iface->dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))) { + retval = &iface->address; + goto out; + } + } + + if (fiface) + retval = &fiface->address; + else if (atalk_interfaces) + retval = &atalk_interfaces->address; + else + retval = NULL; +out: + read_unlock_bh(&atalk_interfaces_lock); + return retval; +} + +/* + * Find a match for 'any network' - ie any of our interfaces with that + * node number will do just nicely. + */ +static struct atalk_iface *atalk_find_anynet(int node, struct net_device *dev) +{ + struct atalk_iface *iface = dev->atalk_ptr; + + if (!iface || iface->status & ATIF_PROBE) + goto out_err; + + if (node != ATADDR_BCAST && + iface->address.s_node != node && + node != ATADDR_ANYNODE) + goto out_err; +out: + return iface; +out_err: + iface = NULL; + goto out; +} + +/* Find a match for a specific network:node pair */ +static struct atalk_iface *atalk_find_interface(int net, int node) +{ + struct atalk_iface *iface; + + read_lock_bh(&atalk_interfaces_lock); + for (iface = atalk_interfaces; iface; iface = iface->next) { + if ((node == ATADDR_BCAST || + node == ATADDR_ANYNODE || + iface->address.s_node == node) && + iface->address.s_net == net && + !(iface->status & ATIF_PROBE)) + break; + + /* XXXX.0 -- net.0 returns the iface associated with net */ + if (node == ATADDR_ANYNODE && net != ATADDR_ANYNET && + ntohs(iface->nets.nr_firstnet) <= ntohs(net) && + ntohs(net) <= ntohs(iface->nets.nr_lastnet)) + break; + } + read_unlock_bh(&atalk_interfaces_lock); + return iface; +} + + +/* + * Find a route for an AppleTalk packet. This ought to get cached in + * the socket (later on...). We know about host routes and the fact + * that a route must be direct to broadcast. + */ +static struct atalk_route *atrtr_find(struct atalk_addr *target) +{ + /* + * we must search through all routes unless we find a + * host route, because some host routes might overlap + * network routes + */ + struct atalk_route *net_route = NULL; + struct atalk_route *r; + + read_lock_bh(&atalk_routes_lock); + for (r = atalk_routes; r; r = r->next) { + if (!(r->flags & RTF_UP)) + continue; + + if (r->target.s_net == target->s_net) { + if (r->flags & RTF_HOST) { + /* + * if this host route is for the target, + * the we're done + */ + if (r->target.s_node == target->s_node) + goto out; + } else + /* + * this route will work if there isn't a + * direct host route, so cache it + */ + net_route = r; + } + } + + /* + * if we found a network route but not a direct host + * route, then return it + */ + if (net_route) + r = net_route; + else if (atrtr_default.dev) + r = &atrtr_default; + else /* No route can be found */ + r = NULL; +out: + read_unlock_bh(&atalk_routes_lock); + return r; +} + + +/* + * Given an AppleTalk network, find the device to use. This can be + * a simple lookup. + */ +struct net_device *atrtr_get_dev(struct atalk_addr *sa) +{ + struct atalk_route *atr = atrtr_find(sa); + return atr ? atr->dev : NULL; +} + +/* Set up a default router */ +static void atrtr_set_default(struct net_device *dev) +{ + atrtr_default.dev = dev; + atrtr_default.flags = RTF_UP; + atrtr_default.gateway.s_net = htons(0); + atrtr_default.gateway.s_node = 0; +} + +/* + * Add a router. Basically make sure it looks valid and stuff the + * entry in the list. While it uses netranges we always set them to one + * entry to work like netatalk. + */ +static int atrtr_create(struct rtentry *r, struct net_device *devhint) +{ + struct sockaddr_at *ta = (struct sockaddr_at *)&r->rt_dst; + struct sockaddr_at *ga = (struct sockaddr_at *)&r->rt_gateway; + struct atalk_route *rt; + struct atalk_iface *iface, *riface; + int retval = -EINVAL; + + /* + * Fixme: Raise/Lower a routing change semaphore for these + * operations. + */ + + /* Validate the request */ + if (ta->sat_family != AF_APPLETALK || + (!devhint && ga->sat_family != AF_APPLETALK)) + goto out; + + /* Now walk the routing table and make our decisions */ + write_lock_bh(&atalk_routes_lock); + for (rt = atalk_routes; rt; rt = rt->next) { + if (r->rt_flags != rt->flags) + continue; + + if (ta->sat_addr.s_net == rt->target.s_net) { + if (!(rt->flags & RTF_HOST)) + break; + if (ta->sat_addr.s_node == rt->target.s_node) + break; + } + } + + if (!devhint) { + riface = NULL; + + read_lock_bh(&atalk_interfaces_lock); + for (iface = atalk_interfaces; iface; iface = iface->next) { + if (!riface && + ntohs(ga->sat_addr.s_net) >= + ntohs(iface->nets.nr_firstnet) && + ntohs(ga->sat_addr.s_net) <= + ntohs(iface->nets.nr_lastnet)) + riface = iface; + + if (ga->sat_addr.s_net == iface->address.s_net && + ga->sat_addr.s_node == iface->address.s_node) + riface = iface; + } + read_unlock_bh(&atalk_interfaces_lock); + + retval = -ENETUNREACH; + if (!riface) + goto out_unlock; + + devhint = riface->dev; + } + + if (!rt) { + rt = kmalloc(sizeof(*rt), GFP_ATOMIC); + + retval = -ENOBUFS; + if (!rt) + goto out_unlock; + memset(rt, 0, sizeof(*rt)); + + rt->next = atalk_routes; + atalk_routes = rt; + } + + /* Fill in the routing entry */ + rt->target = ta->sat_addr; + rt->dev = devhint; + rt->flags = r->rt_flags; + rt->gateway = ga->sat_addr; + + retval = 0; +out_unlock: + write_unlock_bh(&atalk_routes_lock); +out: + return retval; +} + +/* Delete a route. Find it and discard it */ +static int atrtr_delete(struct atalk_addr * addr) +{ + struct atalk_route **r = &atalk_routes; + int retval = 0; + struct atalk_route *tmp; + + write_lock_bh(&atalk_routes_lock); + while ((tmp = *r) != NULL) { + if (tmp->target.s_net == addr->s_net && + (!(tmp->flags&RTF_GATEWAY) || + tmp->target.s_node == addr->s_node)) { + *r = tmp->next; + dev_put(tmp->dev); + kfree(tmp); + goto out; + } + r = &tmp->next; + } + retval = -ENOENT; +out: + write_unlock_bh(&atalk_routes_lock); + return retval; +} + +/* + * Called when a device is downed. Just throw away any routes + * via it. + */ +static void atrtr_device_down(struct net_device *dev) +{ + struct atalk_route **r = &atalk_routes; + struct atalk_route *tmp; + + write_lock_bh(&atalk_routes_lock); + while ((tmp = *r) != NULL) { + if (tmp->dev == dev) { + *r = tmp->next; + dev_put(dev); + kfree(tmp); + } else + r = &tmp->next; + } + write_unlock_bh(&atalk_routes_lock); + + if (atrtr_default.dev == dev) + atrtr_set_default(NULL); +} + +/* Actually down the interface */ +static inline void atalk_dev_down(struct net_device *dev) +{ + atrtr_device_down(dev); /* Remove all routes for the device */ + aarp_device_down(dev); /* Remove AARP entries for the device */ + atif_drop_device(dev); /* Remove the device */ +} + +/* + * A device event has occurred. Watch for devices going down and + * delete our use of them (iface and route). + */ +static int ddp_device_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + if (event == NETDEV_DOWN) + /* Discard any use of this */ + atalk_dev_down(ptr); + + return NOTIFY_DONE; +} + +/* ioctl calls. Shouldn't even need touching */ +/* Device configuration ioctl calls */ +static int atif_ioctl(int cmd, void __user *arg) +{ + static char aarp_mcast[6] = { 0x09, 0x00, 0x00, 0xFF, 0xFF, 0xFF }; + struct ifreq atreq; + struct atalk_netrange *nr; + struct sockaddr_at *sa; + struct net_device *dev; + struct atalk_iface *atif; + int ct; + int limit; + struct rtentry rtdef; + int add_route; + + if (copy_from_user(&atreq, arg, sizeof(atreq))) + return -EFAULT; + + dev = __dev_get_by_name(atreq.ifr_name); + if (!dev) + return -ENODEV; + + sa = (struct sockaddr_at *)&atreq.ifr_addr; + atif = atalk_find_dev(dev); + + switch (cmd) { + case SIOCSIFADDR: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (sa->sat_family != AF_APPLETALK) + return -EINVAL; + if (dev->type != ARPHRD_ETHER && + dev->type != ARPHRD_LOOPBACK && + dev->type != ARPHRD_LOCALTLK && + dev->type != ARPHRD_PPP) + return -EPROTONOSUPPORT; + + nr = (struct atalk_netrange *)&sa->sat_zero[0]; + add_route = 1; + + /* + * if this is a point-to-point iface, and we already + * have an iface for this AppleTalk address, then we + * should not add a route + */ + if ((dev->flags & IFF_POINTOPOINT) && + atalk_find_interface(sa->sat_addr.s_net, + sa->sat_addr.s_node)) { + printk(KERN_DEBUG "AppleTalk: point-to-point " + "interface added with " + "existing address\n"); + add_route = 0; + } + + /* + * Phase 1 is fine on LocalTalk but we don't do + * EtherTalk phase 1. Anyone wanting to add it go ahead. + */ + if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) + return -EPROTONOSUPPORT; + if (sa->sat_addr.s_node == ATADDR_BCAST || + sa->sat_addr.s_node == 254) + return -EINVAL; + if (atif) { + /* Already setting address */ + if (atif->status & ATIF_PROBE) + return -EBUSY; + + atif->address.s_net = sa->sat_addr.s_net; + atif->address.s_node = sa->sat_addr.s_node; + atrtr_device_down(dev); /* Flush old routes */ + } else { + atif = atif_add_device(dev, &sa->sat_addr); + if (!atif) + return -ENOMEM; + } + atif->nets = *nr; + + /* + * Check if the chosen address is used. If so we + * error and atalkd will try another. + */ + + if (!(dev->flags & IFF_LOOPBACK) && + !(dev->flags & IFF_POINTOPOINT) && + atif_probe_device(atif) < 0) { + atif_drop_device(dev); + return -EADDRINUSE; + } + + /* Hey it worked - add the direct routes */ + sa = (struct sockaddr_at *)&rtdef.rt_gateway; + sa->sat_family = AF_APPLETALK; + sa->sat_addr.s_net = atif->address.s_net; + sa->sat_addr.s_node = atif->address.s_node; + sa = (struct sockaddr_at *)&rtdef.rt_dst; + rtdef.rt_flags = RTF_UP; + sa->sat_family = AF_APPLETALK; + sa->sat_addr.s_node = ATADDR_ANYNODE; + if (dev->flags & IFF_LOOPBACK || + dev->flags & IFF_POINTOPOINT) + rtdef.rt_flags |= RTF_HOST; + + /* Routerless initial state */ + if (nr->nr_firstnet == htons(0) && + nr->nr_lastnet == htons(0xFFFE)) { + sa->sat_addr.s_net = atif->address.s_net; + atrtr_create(&rtdef, dev); + atrtr_set_default(dev); + } else { + limit = ntohs(nr->nr_lastnet); + if (limit - ntohs(nr->nr_firstnet) > 4096) { + printk(KERN_WARNING "Too many routes/" + "iface.\n"); + return -EINVAL; + } + if (add_route) + for (ct = ntohs(nr->nr_firstnet); + ct <= limit; ct++) { + sa->sat_addr.s_net = htons(ct); + atrtr_create(&rtdef, dev); + } + } + dev_mc_add(dev, aarp_mcast, 6, 1); + return 0; + + case SIOCGIFADDR: + if (!atif) + return -EADDRNOTAVAIL; + + sa->sat_family = AF_APPLETALK; + sa->sat_addr = atif->address; + break; + + case SIOCGIFBRDADDR: + if (!atif) + return -EADDRNOTAVAIL; + + sa->sat_family = AF_APPLETALK; + sa->sat_addr.s_net = atif->address.s_net; + sa->sat_addr.s_node = ATADDR_BCAST; + break; + + case SIOCATALKDIFADDR: + case SIOCDIFADDR: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (sa->sat_family != AF_APPLETALK) + return -EINVAL; + atalk_dev_down(dev); + break; + + case SIOCSARP: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (sa->sat_family != AF_APPLETALK) + return -EINVAL; + if (!atif) + return -EADDRNOTAVAIL; + + /* + * for now, we only support proxy AARP on ELAP; + * we should be able to do it for LocalTalk, too. + */ + if (dev->type != ARPHRD_ETHER) + return -EPROTONOSUPPORT; + + /* + * atif points to the current interface on this network; + * we aren't concerned about its current status (at + * least for now), but it has all the settings about + * the network we're going to probe. Consequently, it + * must exist. + */ + if (!atif) + return -EADDRNOTAVAIL; + + nr = (struct atalk_netrange *)&(atif->nets); + /* + * Phase 1 is fine on Localtalk but we don't do + * Ethertalk phase 1. Anyone wanting to add it go ahead. + */ + if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) + return -EPROTONOSUPPORT; + + if (sa->sat_addr.s_node == ATADDR_BCAST || + sa->sat_addr.s_node == 254) + return -EINVAL; + + /* + * Check if the chosen address is used. If so we + * error and ATCP will try another. + */ + if (atif_proxy_probe_device(atif, &(sa->sat_addr)) < 0) + return -EADDRINUSE; + + /* + * We now have an address on the local network, and + * the AARP code will defend it for us until we take it + * down. We don't set up any routes right now, because + * ATCP will install them manually via SIOCADDRT. + */ + break; + + case SIOCDARP: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (sa->sat_family != AF_APPLETALK) + return -EINVAL; + if (!atif) + return -EADDRNOTAVAIL; + + /* give to aarp module to remove proxy entry */ + aarp_proxy_remove(atif->dev, &(sa->sat_addr)); + return 0; + } + + return copy_to_user(arg, &atreq, sizeof(atreq)) ? -EFAULT : 0; +} + +/* Routing ioctl() calls */ +static int atrtr_ioctl(unsigned int cmd, void __user *arg) +{ + struct rtentry rt; + + if (copy_from_user(&rt, arg, sizeof(rt))) + return -EFAULT; + + switch (cmd) { + case SIOCDELRT: + if (rt.rt_dst.sa_family != AF_APPLETALK) + return -EINVAL; + return atrtr_delete(&((struct sockaddr_at *) + &rt.rt_dst)->sat_addr); + + case SIOCADDRT: { + struct net_device *dev = NULL; + if (rt.rt_dev) { + char name[IFNAMSIZ]; + if (copy_from_user(name, rt.rt_dev, IFNAMSIZ-1)) + return -EFAULT; + name[IFNAMSIZ-1] = '\0'; + dev = __dev_get_by_name(name); + if (!dev) + return -ENODEV; + } + return atrtr_create(&rt, dev); + } + } + return -EINVAL; +} + +/**************************************************************************\ +* * +* Handling for system calls applied via the various interfaces to an * +* AppleTalk socket object. * +* * +\**************************************************************************/ + +/* + * Checksum: This is 'optional'. It's quite likely also a good + * candidate for assembler hackery 8) + */ +static unsigned long atalk_sum_partial(const unsigned char *data, + int len, unsigned long sum) +{ + /* This ought to be unwrapped neatly. I'll trust gcc for now */ + while (len--) { + sum += *data; + sum <<= 1; + if (sum & 0x10000) { + sum++; + sum &= 0xffff; + } + data++; + } + return sum; +} + +/* Checksum skb data -- similar to skb_checksum */ +static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, + int len, unsigned long sum) +{ + int start = skb_headlen(skb); + int i, copy; + + /* checksum stuff in header space */ + if ( (copy = start - offset) > 0) { + if (copy > len) + copy = len; + sum = atalk_sum_partial(skb->data + offset, copy, sum); + if ( (len -= copy) == 0) + return sum; + + offset += copy; + } + + /* checksum stuff in frags */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + + BUG_TRAP(start <= offset + len); + + end = start + skb_shinfo(skb)->frags[i].size; + if ((copy = end - offset) > 0) { + u8 *vaddr; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + if (copy > len) + copy = len; + vaddr = kmap_skb_frag(frag); + sum = atalk_sum_partial(vaddr + frag->page_offset + + offset - start, copy, sum); + kunmap_skb_frag(vaddr); + + if (!(len -= copy)) + return sum; + offset += copy; + } + start = end; + } + + if (skb_shinfo(skb)->frag_list) { + struct sk_buff *list = skb_shinfo(skb)->frag_list; + + for (; list; list = list->next) { + int end; + + BUG_TRAP(start <= offset + len); + + end = start + list->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + sum = atalk_sum_skb(list, offset - start, + copy, sum); + if ((len -= copy) == 0) + return sum; + offset += copy; + } + start = end; + } + } + + BUG_ON(len > 0); + + return sum; +} + +static unsigned short atalk_checksum(const struct sk_buff *skb, int len) +{ + unsigned long sum; + + /* skip header 4 bytes */ + sum = atalk_sum_skb(skb, 4, len-4, 0); + + /* Use 0xFFFF for 0. 0 itself means none */ + return sum ? htons((unsigned short)sum) : 0xFFFF; +} + +static struct proto ddp_proto = { + .name = "DDP", + .owner = THIS_MODULE, + .obj_size = sizeof(struct atalk_sock), +}; + +/* + * Create a socket. Initialise the socket, blank the addresses + * set the state. + */ +static int atalk_create(struct socket *sock, int protocol) +{ + struct sock *sk; + int rc = -ESOCKTNOSUPPORT; + + /* + * We permit SOCK_DGRAM and RAW is an extension. It is trivial to do + * and gives you the full ELAP frame. Should be handy for CAP 8) + */ + if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) + goto out; + rc = -ENOMEM; + sk = sk_alloc(PF_APPLETALK, GFP_KERNEL, &ddp_proto, 1); + if (!sk) + goto out; + rc = 0; + sock->ops = &atalk_dgram_ops; + sock_init_data(sock, sk); + + /* Checksums on by default */ + sock_set_flag(sk, SOCK_ZAPPED); +out: + return rc; +} + +/* Free a socket. No work needed */ +static int atalk_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + + if (sk) { + sock_orphan(sk); + sock->sk = NULL; + atalk_destroy_socket(sk); + } + return 0; +} + +/** + * atalk_pick_and_bind_port - Pick a source port when one is not given + * @sk - socket to insert into the tables + * @sat - address to search for + * + * Pick a source port when one is not given. If we can find a suitable free + * one, we insert the socket into the tables using it. + * + * This whole operation must be atomic. + */ +static int atalk_pick_and_bind_port(struct sock *sk, struct sockaddr_at *sat) +{ + int retval; + + write_lock_bh(&atalk_sockets_lock); + + for (sat->sat_port = ATPORT_RESERVED; + sat->sat_port < ATPORT_LAST; + sat->sat_port++) { + struct sock *s; + struct hlist_node *node; + + sk_for_each(s, node, &atalk_sockets) { + struct atalk_sock *at = at_sk(s); + + if (at->src_net == sat->sat_addr.s_net && + at->src_node == sat->sat_addr.s_node && + at->src_port == sat->sat_port) + goto try_next_port; + } + + /* Wheee, it's free, assign and insert. */ + __atalk_insert_socket(sk); + at_sk(sk)->src_port = sat->sat_port; + retval = 0; + goto out; + +try_next_port:; + } + + retval = -EBUSY; +out: + write_unlock_bh(&atalk_sockets_lock); + return retval; +} + +static int atalk_autobind(struct sock *sk) +{ + struct atalk_sock *at = at_sk(sk); + struct sockaddr_at sat; + struct atalk_addr *ap = atalk_find_primary(); + int n = -EADDRNOTAVAIL; + + if (!ap || ap->s_net == htons(ATADDR_ANYNET)) + goto out; + + at->src_net = sat.sat_addr.s_net = ap->s_net; + at->src_node = sat.sat_addr.s_node = ap->s_node; + + n = atalk_pick_and_bind_port(sk, &sat); + if (!n) + sock_reset_flag(sk, SOCK_ZAPPED); +out: + return n; +} + +/* Set the address 'our end' of the connection */ +static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +{ + struct sockaddr_at *addr = (struct sockaddr_at *)uaddr; + struct sock *sk = sock->sk; + struct atalk_sock *at = at_sk(sk); + + if (!sock_flag(sk, SOCK_ZAPPED) || + addr_len != sizeof(struct sockaddr_at)) + return -EINVAL; + + if (addr->sat_family != AF_APPLETALK) + return -EAFNOSUPPORT; + + if (addr->sat_addr.s_net == htons(ATADDR_ANYNET)) { + struct atalk_addr *ap = atalk_find_primary(); + + if (!ap) + return -EADDRNOTAVAIL; + + at->src_net = addr->sat_addr.s_net = ap->s_net; + at->src_node = addr->sat_addr.s_node= ap->s_node; + } else { + if (!atalk_find_interface(addr->sat_addr.s_net, + addr->sat_addr.s_node)) + return -EADDRNOTAVAIL; + + at->src_net = addr->sat_addr.s_net; + at->src_node = addr->sat_addr.s_node; + } + + if (addr->sat_port == ATADDR_ANYPORT) { + int n = atalk_pick_and_bind_port(sk, addr); + + if (n < 0) + return n; + } else { + at->src_port = addr->sat_port; + + if (atalk_find_or_insert_socket(sk, addr)) + return -EADDRINUSE; + } + + sock_reset_flag(sk, SOCK_ZAPPED); + return 0; +} + +/* Set the address we talk to */ +static int atalk_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags) +{ + struct sock *sk = sock->sk; + struct atalk_sock *at = at_sk(sk); + struct sockaddr_at *addr; + + sk->sk_state = TCP_CLOSE; + sock->state = SS_UNCONNECTED; + + if (addr_len != sizeof(*addr)) + return -EINVAL; + + addr = (struct sockaddr_at *)uaddr; + + if (addr->sat_family != AF_APPLETALK) + return -EAFNOSUPPORT; + + if (addr->sat_addr.s_node == ATADDR_BCAST && + !sock_flag(sk, SOCK_BROADCAST)) { +#if 1 + printk(KERN_WARNING "%s is broken and did not set " + "SO_BROADCAST. It will break when 2.2 is " + "released.\n", + current->comm); +#else + return -EACCES; +#endif + } + + if (sock_flag(sk, SOCK_ZAPPED)) + if (atalk_autobind(sk) < 0) + return -EBUSY; + + if (!atrtr_get_dev(&addr->sat_addr)) + return -ENETUNREACH; + + at->dest_port = addr->sat_port; + at->dest_net = addr->sat_addr.s_net; + at->dest_node = addr->sat_addr.s_node; + + sock->state = SS_CONNECTED; + sk->sk_state = TCP_ESTABLISHED; + return 0; +} + +/* + * Find the name of an AppleTalk socket. Just copy the right + * fields into the sockaddr. + */ +static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, + int *uaddr_len, int peer) +{ + struct sockaddr_at sat; + struct sock *sk = sock->sk; + struct atalk_sock *at = at_sk(sk); + + if (sock_flag(sk, SOCK_ZAPPED)) + if (atalk_autobind(sk) < 0) + return -ENOBUFS; + + *uaddr_len = sizeof(struct sockaddr_at); + + if (peer) { + if (sk->sk_state != TCP_ESTABLISHED) + return -ENOTCONN; + + sat.sat_addr.s_net = at->dest_net; + sat.sat_addr.s_node = at->dest_node; + sat.sat_port = at->dest_port; + } else { + sat.sat_addr.s_net = at->src_net; + sat.sat_addr.s_node = at->src_node; + sat.sat_port = at->src_port; + } + + sat.sat_family = AF_APPLETALK; + memcpy(uaddr, &sat, sizeof(sat)); + return 0; +} + +#if defined(CONFIG_IPDDP) || defined(CONFIG_IPDDP_MODULE) +static __inline__ int is_ip_over_ddp(struct sk_buff *skb) +{ + return skb->data[12] == 22; +} + +static int handle_ip_over_ddp(struct sk_buff *skb) +{ + struct net_device *dev = __dev_get_by_name("ipddp0"); + struct net_device_stats *stats; + + /* This needs to be able to handle ipddp"N" devices */ + if (!dev) + return -ENODEV; + + skb->protocol = htons(ETH_P_IP); + skb_pull(skb, 13); + skb->dev = dev; + skb->h.raw = skb->data; + + stats = dev->priv; + stats->rx_packets++; + stats->rx_bytes += skb->len + 13; + netif_rx(skb); /* Send the SKB up to a higher place. */ + return 0; +} +#else +/* make it easy for gcc to optimize this test out, i.e. kill the code */ +#define is_ip_over_ddp(skb) 0 +#define handle_ip_over_ddp(skb) 0 +#endif + +static void atalk_route_packet(struct sk_buff *skb, struct net_device *dev, + struct ddpehdr *ddp, struct ddpebits *ddphv, + int origlen) +{ + struct atalk_route *rt; + struct atalk_addr ta; + + /* + * Don't route multicast, etc., packets, or packets sent to "this + * network" + */ + if (skb->pkt_type != PACKET_HOST || !ddp->deh_dnet) { + /* + * FIXME: + * + * Can it ever happen that a packet is from a PPP iface and + * needs to be broadcast onto the default network? + */ + if (dev->type == ARPHRD_PPP) + printk(KERN_DEBUG "AppleTalk: didn't forward broadcast " + "packet received from PPP iface\n"); + goto free_it; + } + + ta.s_net = ddp->deh_dnet; + ta.s_node = ddp->deh_dnode; + + /* Route the packet */ + rt = atrtr_find(&ta); + if (!rt || ddphv->deh_hops == DDP_MAXHOPS) + goto free_it; + /* FIXME: use skb->cb to be able to use shared skbs */ + ddphv->deh_hops++; + + /* + * Route goes through another gateway, so set the target to the + * gateway instead. + */ + + if (rt->flags & RTF_GATEWAY) { + ta.s_net = rt->gateway.s_net; + ta.s_node = rt->gateway.s_node; + } + + /* Fix up skb->len field */ + skb_trim(skb, min_t(unsigned int, origlen, + (rt->dev->hard_header_len + + ddp_dl->header_length + ddphv->deh_len))); + + /* Mend the byte order */ + /* FIXME: use skb->cb to be able to use shared skbs */ + *((__u16 *)ddp) = ntohs(*((__u16 *)ddphv)); + + /* + * Send the buffer onwards + * + * Now we must always be careful. If it's come from LocalTalk to + * EtherTalk it might not fit + * + * Order matters here: If a packet has to be copied to make a new + * headroom (rare hopefully) then it won't need unsharing. + * + * Note. ddp-> becomes invalid at the realloc. + */ + if (skb_headroom(skb) < 22) { + /* 22 bytes - 12 ether, 2 len, 3 802.2 5 snap */ + struct sk_buff *nskb = skb_realloc_headroom(skb, 32); + kfree_skb(skb); + if (!nskb) + goto out; + skb = nskb; + } else + skb = skb_unshare(skb, GFP_ATOMIC); + + /* + * If the buffer didn't vanish into the lack of space bitbucket we can + * send it. + */ + if (skb && aarp_send_ddp(rt->dev, skb, &ta, NULL) == -1) + goto free_it; +out: + return; +free_it: + kfree_skb(skb); +} + +/** + * atalk_rcv - Receive a packet (in skb) from device dev + * @skb - packet received + * @dev - network device where the packet comes from + * @pt - packet type + * + * Receive a packet (in skb) from device dev. This has come from the SNAP + * decoder, and on entry skb->h.raw is the DDP header, skb->len is the DDP + * header, skb->len is the DDP length. The physical headers have been + * extracted. PPP should probably pass frames marked as for this layer. + * [ie ARPHRD_ETHERTALK] + */ +static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + struct ddpehdr *ddp; + struct sock *sock; + struct atalk_iface *atif; + struct sockaddr_at tosat; + int origlen; + struct ddpebits ddphv; + + /* Don't mangle buffer if shared */ + if (!(skb = skb_share_check(skb, GFP_ATOMIC))) + goto out; + + /* Size check and make sure header is contiguous */ + if (!pskb_may_pull(skb, sizeof(*ddp))) + goto freeit; + + ddp = ddp_hdr(skb); + + /* + * Fix up the length field [Ok this is horrible but otherwise + * I end up with unions of bit fields and messy bit field order + * compiler/endian dependencies..] + */ + *((__u16 *)&ddphv) = ntohs(*((__u16 *)ddp)); + + /* Trim buffer in case of stray trailing data */ + origlen = skb->len; + skb_trim(skb, min_t(unsigned int, skb->len, ddphv.deh_len)); + + /* + * Size check to see if ddp->deh_len was crap + * (Otherwise we'll detonate most spectacularly + * in the middle of recvmsg()). + */ + if (skb->len < sizeof(*ddp)) + goto freeit; + + /* + * Any checksums. Note we don't do htons() on this == is assumed to be + * valid for net byte orders all over the networking code... + */ + if (ddp->deh_sum && + atalk_checksum(skb, ddphv.deh_len) != ddp->deh_sum) + /* Not a valid AppleTalk frame - dustbin time */ + goto freeit; + + /* Check the packet is aimed at us */ + if (!ddp->deh_dnet) /* Net 0 is 'this network' */ + atif = atalk_find_anynet(ddp->deh_dnode, dev); + else + atif = atalk_find_interface(ddp->deh_dnet, ddp->deh_dnode); + + /* Not ours, so we route the packet via the correct AppleTalk iface */ + if (!atif) { + atalk_route_packet(skb, dev, ddp, &ddphv, origlen); + goto out; + } + + /* if IP over DDP is not selected this code will be optimized out */ + if (is_ip_over_ddp(skb)) + return handle_ip_over_ddp(skb); + /* + * Which socket - atalk_search_socket() looks for a *full match* + * of the <net, node, port> tuple. + */ + tosat.sat_addr.s_net = ddp->deh_dnet; + tosat.sat_addr.s_node = ddp->deh_dnode; + tosat.sat_port = ddp->deh_dport; + + sock = atalk_search_socket(&tosat, atif); + if (!sock) /* But not one of our sockets */ + goto freeit; + + /* Queue packet (standard) */ + skb->sk = sock; + + if (sock_queue_rcv_skb(sock, skb) < 0) + goto freeit; +out: + return 0; +freeit: + kfree_skb(skb); + goto out; +} + +/* + * Receive a LocalTalk frame. We make some demands on the caller here. + * Caller must provide enough headroom on the packet to pull the short + * header and append a long one. + */ +static int ltalk_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + /* Expand any short form frames */ + if (skb->mac.raw[2] == 1) { + struct ddpehdr *ddp; + /* Find our address */ + struct atalk_addr *ap = atalk_find_dev_addr(dev); + + if (!ap || skb->len < sizeof(struct ddpshdr)) + goto freeit; + + /* Don't mangle buffer if shared */ + if (!(skb = skb_share_check(skb, GFP_ATOMIC))) + return 0; + + /* + * The push leaves us with a ddephdr not an shdr, and + * handily the port bytes in the right place preset. + */ + ddp = (struct ddpehdr *) skb_push(skb, sizeof(*ddp) - 4); + + /* Now fill in the long header */ + + /* + * These two first. The mac overlays the new source/dest + * network information so we MUST copy these before + * we write the network numbers ! + */ + + ddp->deh_dnode = skb->mac.raw[0]; /* From physical header */ + ddp->deh_snode = skb->mac.raw[1]; /* From physical header */ + + ddp->deh_dnet = ap->s_net; /* Network number */ + ddp->deh_snet = ap->s_net; + ddp->deh_sum = 0; /* No checksum */ + /* + * Not sure about this bit... + */ + ddp->deh_len = skb->len; + ddp->deh_hops = DDP_MAXHOPS; /* Non routable, so force a drop + if we slip up later */ + /* Mend the byte order */ + *((__u16 *)ddp) = htons(*((__u16 *)ddp)); + } + skb->h.raw = skb->data; + + return atalk_rcv(skb, dev, pt); +freeit: + kfree_skb(skb); + return 0; +} + +static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, + size_t len) +{ + struct sock *sk = sock->sk; + struct atalk_sock *at = at_sk(sk); + struct sockaddr_at *usat = (struct sockaddr_at *)msg->msg_name; + int flags = msg->msg_flags; + int loopback = 0; + struct sockaddr_at local_satalk, gsat; + struct sk_buff *skb; + struct net_device *dev; + struct ddpehdr *ddp; + int size; + struct atalk_route *rt; + int err; + + if (flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT)) + return -EINVAL; + + if (len > DDP_MAXSZ) + return -EMSGSIZE; + + if (usat) { + if (sock_flag(sk, SOCK_ZAPPED)) + if (atalk_autobind(sk) < 0) + return -EBUSY; + + if (msg->msg_namelen < sizeof(*usat) || + usat->sat_family != AF_APPLETALK) + return -EINVAL; + + /* netatalk doesn't implement this check */ + if (usat->sat_addr.s_node == ATADDR_BCAST && + !sock_flag(sk, SOCK_BROADCAST)) { + printk(KERN_INFO "SO_BROADCAST: Fix your netatalk as " + "it will break before 2.2\n"); +#if 0 + return -EPERM; +#endif + } + } else { + if (sk->sk_state != TCP_ESTABLISHED) + return -ENOTCONN; + usat = &local_satalk; + usat->sat_family = AF_APPLETALK; + usat->sat_port = at->dest_port; + usat->sat_addr.s_node = at->dest_node; + usat->sat_addr.s_net = at->dest_net; + } + + /* Build a packet */ + SOCK_DEBUG(sk, "SK %p: Got address.\n", sk); + + /* For headers */ + size = sizeof(struct ddpehdr) + len + ddp_dl->header_length; + + if (usat->sat_addr.s_net || usat->sat_addr.s_node == ATADDR_ANYNODE) { + rt = atrtr_find(&usat->sat_addr); + if (!rt) + return -ENETUNREACH; + + dev = rt->dev; + } else { + struct atalk_addr at_hint; + + at_hint.s_node = 0; + at_hint.s_net = at->src_net; + + rt = atrtr_find(&at_hint); + if (!rt) + return -ENETUNREACH; + + dev = rt->dev; + } + + SOCK_DEBUG(sk, "SK %p: Size needed %d, device %s\n", + sk, size, dev->name); + + size += dev->hard_header_len; + skb = sock_alloc_send_skb(sk, size, (flags & MSG_DONTWAIT), &err); + if (!skb) + return err; + + skb->sk = sk; + skb_reserve(skb, ddp_dl->header_length); + skb_reserve(skb, dev->hard_header_len); + skb->dev = dev; + + SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk); + + ddp = (struct ddpehdr *)skb_put(skb, sizeof(struct ddpehdr)); + ddp->deh_pad = 0; + ddp->deh_hops = 0; + ddp->deh_len = len + sizeof(*ddp); + /* + * Fix up the length field [Ok this is horrible but otherwise + * I end up with unions of bit fields and messy bit field order + * compiler/endian dependencies.. + */ + *((__u16 *)ddp) = ntohs(*((__u16 *)ddp)); + + ddp->deh_dnet = usat->sat_addr.s_net; + ddp->deh_snet = at->src_net; + ddp->deh_dnode = usat->sat_addr.s_node; + ddp->deh_snode = at->src_node; + ddp->deh_dport = usat->sat_port; + ddp->deh_sport = at->src_port; + + SOCK_DEBUG(sk, "SK %p: Copy user data (%Zd bytes).\n", sk, len); + + err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); + if (err) { + kfree_skb(skb); + return -EFAULT; + } + + if (sk->sk_no_check == 1) + ddp->deh_sum = 0; + else + ddp->deh_sum = atalk_checksum(skb, len + sizeof(*ddp)); + + /* + * Loopback broadcast packets to non gateway targets (ie routes + * to group we are in) + */ + if (ddp->deh_dnode == ATADDR_BCAST && + !(rt->flags & RTF_GATEWAY) && !(dev->flags & IFF_LOOPBACK)) { + struct sk_buff *skb2 = skb_copy(skb, GFP_KERNEL); + + if (skb2) { + loopback = 1; + SOCK_DEBUG(sk, "SK %p: send out(copy).\n", sk); + if (aarp_send_ddp(dev, skb2, + &usat->sat_addr, NULL) == -1) + kfree_skb(skb2); + /* else queued/sent above in the aarp queue */ + } + } + + if (dev->flags & IFF_LOOPBACK || loopback) { + SOCK_DEBUG(sk, "SK %p: Loop back.\n", sk); + /* loop back */ + skb_orphan(skb); + ddp_dl->request(ddp_dl, skb, dev->dev_addr); + } else { + SOCK_DEBUG(sk, "SK %p: send out.\n", sk); + if (rt->flags & RTF_GATEWAY) { + gsat.sat_addr = rt->gateway; + usat = &gsat; + } + + if (aarp_send_ddp(dev, skb, &usat->sat_addr, NULL) == -1) + kfree_skb(skb); + /* else queued/sent above in the aarp queue */ + } + SOCK_DEBUG(sk, "SK %p: Done write (%Zd).\n", sk, len); + + return len; +} + +static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, + size_t size, int flags) +{ + struct sock *sk = sock->sk; + struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name; + struct ddpehdr *ddp; + int copied = 0; + int err = 0; + struct ddpebits ddphv; + struct sk_buff *skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, + flags & MSG_DONTWAIT, &err); + if (!skb) + return err; + + /* FIXME: use skb->cb to be able to use shared skbs */ + ddp = ddp_hdr(skb); + *((__u16 *)&ddphv) = ntohs(*((__u16 *)ddp)); + + if (sk->sk_type == SOCK_RAW) { + copied = ddphv.deh_len; + if (copied > size) { + copied = size; + msg->msg_flags |= MSG_TRUNC; + } + + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + } else { + copied = ddphv.deh_len - sizeof(*ddp); + if (copied > size) { + copied = size; + msg->msg_flags |= MSG_TRUNC; + } + err = skb_copy_datagram_iovec(skb, sizeof(*ddp), + msg->msg_iov, copied); + } + + if (!err) { + if (sat) { + sat->sat_family = AF_APPLETALK; + sat->sat_port = ddp->deh_sport; + sat->sat_addr.s_node = ddp->deh_snode; + sat->sat_addr.s_net = ddp->deh_snet; + } + msg->msg_namelen = sizeof(*sat); + } + + skb_free_datagram(sk, skb); /* Free the datagram. */ + return err ? : copied; +} + + +/* + * AppleTalk ioctl calls. + */ +static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + int rc = -EINVAL; + struct sock *sk = sock->sk; + void __user *argp = (void __user *)arg; + + switch (cmd) { + /* Protocol layer */ + case TIOCOUTQ: { + long amount = sk->sk_sndbuf - + atomic_read(&sk->sk_wmem_alloc); + + if (amount < 0) + amount = 0; + rc = put_user(amount, (int __user *)argp); + break; + } + case TIOCINQ: { + /* + * These two are safe on a single CPU system as only + * user tasks fiddle here + */ + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + long amount = 0; + + if (skb) + amount = skb->len - sizeof(struct ddpehdr); + rc = put_user(amount, (int __user *)argp); + break; + } + case SIOCGSTAMP: + rc = sock_get_timestamp(sk, argp); + break; + /* Routing */ + case SIOCADDRT: + case SIOCDELRT: + rc = -EPERM; + if (capable(CAP_NET_ADMIN)) + rc = atrtr_ioctl(cmd, argp); + break; + /* Interface */ + case SIOCGIFADDR: + case SIOCSIFADDR: + case SIOCGIFBRDADDR: + case SIOCATALKDIFADDR: + case SIOCDIFADDR: + case SIOCSARP: /* proxy AARP */ + case SIOCDARP: /* proxy AARP */ + rtnl_lock(); + rc = atif_ioctl(cmd, argp); + rtnl_unlock(); + break; + /* Physical layer ioctl calls */ + case SIOCSIFLINK: + case SIOCGIFHWADDR: + case SIOCSIFHWADDR: + case SIOCGIFFLAGS: + case SIOCSIFFLAGS: + case SIOCGIFTXQLEN: + case SIOCSIFTXQLEN: + case SIOCGIFMTU: + case SIOCGIFCONF: + case SIOCADDMULTI: + case SIOCDELMULTI: + case SIOCGIFCOUNT: + case SIOCGIFINDEX: + case SIOCGIFNAME: + rc = dev_ioctl(cmd, argp); + break; + } + + return rc; +} + +static struct net_proto_family atalk_family_ops = { + .family = PF_APPLETALK, + .create = atalk_create, + .owner = THIS_MODULE, +}; + +static struct proto_ops SOCKOPS_WRAPPED(atalk_dgram_ops) = { + .family = PF_APPLETALK, + .owner = THIS_MODULE, + .release = atalk_release, + .bind = atalk_bind, + .connect = atalk_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = atalk_getname, + .poll = datagram_poll, + .ioctl = atalk_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = sock_no_setsockopt, + .getsockopt = sock_no_getsockopt, + .sendmsg = atalk_sendmsg, + .recvmsg = atalk_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +#include <linux/smp_lock.h> +SOCKOPS_WRAP(atalk_dgram, PF_APPLETALK); + +static struct notifier_block ddp_notifier = { + .notifier_call = ddp_device_event, +}; + +static struct packet_type ltalk_packet_type = { + .type = __constant_htons(ETH_P_LOCALTALK), + .func = ltalk_rcv, +}; + +static struct packet_type ppptalk_packet_type = { + .type = __constant_htons(ETH_P_PPPTALK), + .func = atalk_rcv, +}; + +static unsigned char ddp_snap_id[] = { 0x08, 0x00, 0x07, 0x80, 0x9B }; + +/* Export symbols for use by drivers when AppleTalk is a module */ +EXPORT_SYMBOL(aarp_send_ddp); +EXPORT_SYMBOL(atrtr_get_dev); +EXPORT_SYMBOL(atalk_find_dev_addr); + +static char atalk_err_snap[] __initdata = + KERN_CRIT "Unable to register DDP with SNAP.\n"; + +/* Called by proto.c on kernel start up */ +static int __init atalk_init(void) +{ + int rc = proto_register(&ddp_proto, 0); + + if (rc != 0) + goto out; + + (void)sock_register(&atalk_family_ops); + ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv); + if (!ddp_dl) + printk(atalk_err_snap); + + dev_add_pack(<alk_packet_type); + dev_add_pack(&ppptalk_packet_type); + + register_netdevice_notifier(&ddp_notifier); + aarp_proto_init(); + atalk_proc_init(); + atalk_register_sysctl(); +out: + return rc; +} +module_init(atalk_init); + +/* + * No explicit module reference count manipulation is needed in the + * protocol. Socket layer sets module reference count for us + * and interfaces reference counting is done + * by the network device layer. + * + * Ergo, before the AppleTalk module can be removed, all AppleTalk + * sockets be closed from user space. + */ +static void __exit atalk_exit(void) +{ +#ifdef CONFIG_SYSCTL + atalk_unregister_sysctl(); +#endif /* CONFIG_SYSCTL */ + atalk_proc_exit(); + aarp_cleanup_module(); /* General aarp clean-up. */ + unregister_netdevice_notifier(&ddp_notifier); + dev_remove_pack(<alk_packet_type); + dev_remove_pack(&ppptalk_packet_type); + unregister_snap_client(ddp_dl); + sock_unregister(PF_APPLETALK); + proto_unregister(&ddp_proto); +} +module_exit(atalk_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Alan Cox <Alan.Cox@linux.org>"); +MODULE_DESCRIPTION("AppleTalk 0.20\n"); +MODULE_ALIAS_NETPROTO(PF_APPLETALK); diff --git a/net/appletalk/dev.c b/net/appletalk/dev.c new file mode 100644 index 000000000000..76598445d84b --- /dev/null +++ b/net/appletalk/dev.c @@ -0,0 +1,43 @@ +/* + * Moved here from drivers/net/net_init.c, which is: + * Written 1993,1994,1995 by Donald Becker. + */ + +#include <linux/errno.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/if_arp.h> +#include <linux/if_ltalk.h> + +static int ltalk_change_mtu(struct net_device *dev, int mtu) +{ + return -EINVAL; +} + +static int ltalk_mac_addr(struct net_device *dev, void *addr) +{ + return -EINVAL; +} + +void ltalk_setup(struct net_device *dev) +{ + /* Fill in the fields of the device structure with localtalk-generic values. */ + + dev->change_mtu = ltalk_change_mtu; + dev->hard_header = NULL; + dev->rebuild_header = NULL; + dev->set_mac_address = ltalk_mac_addr; + dev->hard_header_cache = NULL; + dev->header_cache_update= NULL; + + dev->type = ARPHRD_LOCALTLK; + dev->hard_header_len = LTALK_HLEN; + dev->mtu = LTALK_MTU; + dev->addr_len = LTALK_ALEN; + dev->tx_queue_len = 10; + + dev->broadcast[0] = 0xFF; + + dev->flags = IFF_BROADCAST|IFF_MULTICAST|IFF_NOARP; +} +EXPORT_SYMBOL(ltalk_setup); diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c new file mode 100644 index 000000000000..af7f0604395d --- /dev/null +++ b/net/appletalk/sysctl_net_atalk.c @@ -0,0 +1,83 @@ +/* + * sysctl_net_atalk.c: sysctl interface to net AppleTalk subsystem. + * + * Begun April 1, 1996, Mike Shaver. + * Added /proc/sys/net/atalk directory entry (empty =) ). [MS] + * Dynamic registration, added aarp entries. (5/30/97 Chris Horn) + */ + +#include <linux/config.h> +#include <linux/sysctl.h> +#include <net/sock.h> +#include <linux/atalk.h> + +static struct ctl_table atalk_table[] = { + { + .ctl_name = NET_ATALK_AARP_EXPIRY_TIME, + .procname = "aarp-expiry-time", + .data = &sysctl_aarp_expiry_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, + }, + { + .ctl_name = NET_ATALK_AARP_TICK_TIME, + .procname = "aarp-tick-time", + .data = &sysctl_aarp_tick_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, + }, + { + .ctl_name = NET_ATALK_AARP_RETRANSMIT_LIMIT, + .procname = "aarp-retransmit-limit", + .data = &sysctl_aarp_retransmit_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = NET_ATALK_AARP_RESOLVE_TIME, + .procname = "aarp-resolve-time", + .data = &sysctl_aarp_resolve_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, + }, + { 0 }, +}; + +static struct ctl_table atalk_dir_table[] = { + { + .ctl_name = NET_ATALK, + .procname = "appletalk", + .mode = 0555, + .child = atalk_table, + }, + { 0 }, +}; + +static struct ctl_table atalk_root_table[] = { + { + .ctl_name = CTL_NET, + .procname = "net", + .mode = 0555, + .child = atalk_dir_table, + }, + { 0 }, +}; + +static struct ctl_table_header *atalk_table_header; + +void atalk_register_sysctl(void) +{ + atalk_table_header = register_sysctl_table(atalk_root_table, 1); +} + +void atalk_unregister_sysctl(void) +{ + unregister_sysctl_table(atalk_table_header); +} diff --git a/net/atm/Makefile b/net/atm/Makefile new file mode 100644 index 000000000000..d5818751f6ba --- /dev/null +++ b/net/atm/Makefile @@ -0,0 +1,18 @@ +# +# Makefile for the ATM Protocol Families. +# + +atm-y := addr.o pvc.o signaling.o svc.o ioctl.o common.o atm_misc.o raw.o resources.o +mpoa-objs := mpc.o mpoa_caches.o mpoa_proc.o + +obj-$(CONFIG_ATM) += atm.o +obj-$(CONFIG_ATM_CLIP) += clip.o +atm-$(subst m,y,$(CONFIG_ATM_CLIP)) += ipcommon.o +obj-$(CONFIG_ATM_BR2684) += br2684.o +atm-$(subst m,y,$(CONFIG_ATM_BR2684)) += ipcommon.o +atm-$(subst m,y,$(CONFIG_NET_SCH_ATM)) += ipcommon.o +atm-$(CONFIG_PROC_FS) += proc.o + +obj-$(CONFIG_ATM_LANE) += lec.o +obj-$(CONFIG_ATM_MPOA) += mpoa.o +obj-$(CONFIG_PPPOATM) += pppoatm.o diff --git a/net/atm/addr.c b/net/atm/addr.c new file mode 100644 index 000000000000..1c8867f7f54a --- /dev/null +++ b/net/atm/addr.c @@ -0,0 +1,134 @@ +/* net/atm/addr.c - Local ATM address registry */ + +/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ + +#include <linux/atm.h> +#include <linux/atmdev.h> +#include <linux/sched.h> +#include <asm/uaccess.h> + +#include "signaling.h" +#include "addr.h" + +static int check_addr(struct sockaddr_atmsvc *addr) +{ + int i; + + if (addr->sas_family != AF_ATMSVC) + return -EAFNOSUPPORT; + if (!*addr->sas_addr.pub) + return *addr->sas_addr.prv ? 0 : -EINVAL; + for (i = 1; i < ATM_E164_LEN + 1; i++) /* make sure it's \0-terminated */ + if (!addr->sas_addr.pub[i]) + return 0; + return -EINVAL; +} + +static int identical(struct sockaddr_atmsvc *a, struct sockaddr_atmsvc *b) +{ + if (*a->sas_addr.prv) + if (memcmp(a->sas_addr.prv, b->sas_addr.prv, ATM_ESA_LEN)) + return 0; + if (!*a->sas_addr.pub) + return !*b->sas_addr.pub; + if (!*b->sas_addr.pub) + return 0; + return !strcmp(a->sas_addr.pub, b->sas_addr.pub); +} + +static void notify_sigd(struct atm_dev *dev) +{ + struct sockaddr_atmpvc pvc; + + pvc.sap_addr.itf = dev->number; + sigd_enq(NULL, as_itf_notify, NULL, &pvc, NULL); +} + +void atm_reset_addr(struct atm_dev *dev) +{ + unsigned long flags; + struct atm_dev_addr *this, *p; + + spin_lock_irqsave(&dev->lock, flags); + list_for_each_entry_safe(this, p, &dev->local, entry) + kfree(this); + spin_unlock_irqrestore(&dev->lock, flags); + notify_sigd(dev); +} + +int atm_add_addr(struct atm_dev *dev, struct sockaddr_atmsvc *addr) +{ + unsigned long flags; + struct atm_dev_addr *this; + int error; + + error = check_addr(addr); + if (error) + return error; + spin_lock_irqsave(&dev->lock, flags); + list_for_each_entry(this, &dev->local, entry) { + if (identical(&this->addr, addr)) { + spin_unlock_irqrestore(&dev->lock, flags); + return -EEXIST; + } + } + this = kmalloc(sizeof(struct atm_dev_addr), GFP_ATOMIC); + if (!this) { + spin_unlock_irqrestore(&dev->lock, flags); + return -ENOMEM; + } + this->addr = *addr; + list_add(&this->entry, &dev->local); + spin_unlock_irqrestore(&dev->lock, flags); + notify_sigd(dev); + return 0; +} + +int atm_del_addr(struct atm_dev *dev, struct sockaddr_atmsvc *addr) +{ + unsigned long flags; + struct atm_dev_addr *this; + int error; + + error = check_addr(addr); + if (error) + return error; + spin_lock_irqsave(&dev->lock, flags); + list_for_each_entry(this, &dev->local, entry) { + if (identical(&this->addr, addr)) { + list_del(&this->entry); + spin_unlock_irqrestore(&dev->lock, flags); + kfree(this); + notify_sigd(dev); + return 0; + } + } + spin_unlock_irqrestore(&dev->lock, flags); + return -ENOENT; +} + +int atm_get_addr(struct atm_dev *dev, struct sockaddr_atmsvc __user * buf, + size_t size) +{ + unsigned long flags; + struct atm_dev_addr *this; + int total = 0, error; + struct sockaddr_atmsvc *tmp_buf, *tmp_bufp; + + spin_lock_irqsave(&dev->lock, flags); + list_for_each_entry(this, &dev->local, entry) + total += sizeof(struct sockaddr_atmsvc); + tmp_buf = tmp_bufp = kmalloc(total, GFP_ATOMIC); + if (!tmp_buf) { + spin_unlock_irqrestore(&dev->lock, flags); + return -ENOMEM; + } + list_for_each_entry(this, &dev->local, entry) + memcpy(tmp_bufp++, &this->addr, sizeof(struct sockaddr_atmsvc)); + spin_unlock_irqrestore(&dev->lock, flags); + error = total > size ? -E2BIG : total; + if (copy_to_user(buf, tmp_buf, total < size ? total : size)) + error = -EFAULT; + kfree(tmp_buf); + return error; +} diff --git a/net/atm/addr.h b/net/atm/addr.h new file mode 100644 index 000000000000..3099d21feeaa --- /dev/null +++ b/net/atm/addr.h @@ -0,0 +1,18 @@ +/* net/atm/addr.h - Local ATM address registry */ + +/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ + + +#ifndef NET_ATM_ADDR_H +#define NET_ATM_ADDR_H + +#include <linux/atm.h> +#include <linux/atmdev.h> + + +void atm_reset_addr(struct atm_dev *dev); +int atm_add_addr(struct atm_dev *dev,struct sockaddr_atmsvc *addr); +int atm_del_addr(struct atm_dev *dev,struct sockaddr_atmsvc *addr); +int atm_get_addr(struct atm_dev *dev,struct sockaddr_atmsvc __user *buf,size_t size); + +#endif diff --git a/net/atm/atm_misc.c b/net/atm/atm_misc.c new file mode 100644 index 000000000000..b2113c3454ae --- /dev/null +++ b/net/atm/atm_misc.c @@ -0,0 +1,106 @@ +/* net/atm/atm_misc.c - Various functions for use by ATM drivers */ + +/* Written 1995-2000 by Werner Almesberger, EPFL ICA */ + + +#include <linux/module.h> +#include <linux/atm.h> +#include <linux/atmdev.h> +#include <linux/skbuff.h> +#include <linux/sonet.h> +#include <linux/bitops.h> +#include <asm/atomic.h> +#include <asm/errno.h> + + +int atm_charge(struct atm_vcc *vcc,int truesize) +{ + atm_force_charge(vcc,truesize); + if (atomic_read(&sk_atm(vcc)->sk_rmem_alloc) <= sk_atm(vcc)->sk_rcvbuf) + return 1; + atm_return(vcc,truesize); + atomic_inc(&vcc->stats->rx_drop); + return 0; +} + + +struct sk_buff *atm_alloc_charge(struct atm_vcc *vcc,int pdu_size, + int gfp_flags) +{ + struct sock *sk = sk_atm(vcc); + int guess = atm_guess_pdu2truesize(pdu_size); + + atm_force_charge(vcc,guess); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { + struct sk_buff *skb = alloc_skb(pdu_size,gfp_flags); + + if (skb) { + atomic_add(skb->truesize-guess, + &sk->sk_rmem_alloc); + return skb; + } + } + atm_return(vcc,guess); + atomic_inc(&vcc->stats->rx_drop); + return NULL; +} + + +/* + * atm_pcr_goal returns the positive PCR if it should be rounded up, the + * negative PCR if it should be rounded down, and zero if the maximum available + * bandwidth should be used. + * + * The rules are as follows (* = maximum, - = absent (0), x = value "x", + * (x+ = x or next value above x, x- = x or next value below): + * + * min max pcr result min max pcr result + * - - - * (UBR only) x - - x+ + * - - * * x - * * + * - - z z- x - z z- + * - * - * x * - x+ + * - * * * x * * * + * - * z z- x * z z- + * - y - y- x y - x+ + * - y * y- x y * y- + * - y z z- x y z z- + * + * All non-error cases can be converted with the following simple set of rules: + * + * if pcr == z then z- + * else if min == x && pcr == - then x+ + * else if max == y then y- + * else * + */ + + +int atm_pcr_goal(struct atm_trafprm *tp) +{ + if (tp->pcr && tp->pcr != ATM_MAX_PCR) return -tp->pcr; + if (tp->min_pcr && !tp->pcr) return tp->min_pcr; + if (tp->max_pcr != ATM_MAX_PCR) return -tp->max_pcr; + return 0; +} + + +void sonet_copy_stats(struct k_sonet_stats *from,struct sonet_stats *to) +{ +#define __HANDLE_ITEM(i) to->i = atomic_read(&from->i) + __SONET_ITEMS +#undef __HANDLE_ITEM +} + + +void sonet_subtract_stats(struct k_sonet_stats *from,struct sonet_stats *to) +{ +#define __HANDLE_ITEM(i) atomic_sub(to->i,&from->i) + __SONET_ITEMS +#undef __HANDLE_ITEM +} + + +EXPORT_SYMBOL(atm_charge); +EXPORT_SYMBOL(atm_alloc_charge); +EXPORT_SYMBOL(atm_pcr_goal); +EXPORT_SYMBOL(sonet_copy_stats); +EXPORT_SYMBOL(sonet_subtract_stats); diff --git a/net/atm/br2684.c b/net/atm/br2684.c new file mode 100644 index 000000000000..e6954cf1459d --- /dev/null +++ b/net/atm/br2684.c @@ -0,0 +1,824 @@ +/* +Experimental ethernet netdevice using ATM AAL5 as underlying carrier +(RFC1483 obsoleted by RFC2684) for Linux 2.4 +Author: Marcell GAL, 2000, XDSL Ltd, Hungary +*/ + +#include <linux/module.h> +#include <linux/config.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/ip.h> +#include <asm/uaccess.h> +#include <net/arp.h> +#include <linux/atm.h> +#include <linux/atmdev.h> +#include <linux/seq_file.h> + +#include <linux/atmbr2684.h> + +#include "common.h" +#include "ipcommon.h" + +/* + * Define this to use a version of the code which interacts with the higher + * layers in a more intellegent way, by always reserving enough space for + * our header at the begining of the packet. However, there may still be + * some problems with programs like tcpdump. In 2.5 we'll sort out what + * we need to do to get this perfect. For now we just will copy the packet + * if we need space for the header + */ +/* #define FASTER_VERSION */ + +#ifdef DEBUG +#define DPRINTK(format, args...) printk(KERN_DEBUG "br2684: " format, ##args) +#else +#define DPRINTK(format, args...) +#endif + +#ifdef SKB_DEBUG +static void skb_debug(const struct sk_buff *skb) +{ +#define NUM2PRINT 50 + char buf[NUM2PRINT * 3 + 1]; /* 3 chars per byte */ + int i = 0; + for (i = 0; i < skb->len && i < NUM2PRINT; i++) { + sprintf(buf + i * 3, "%2.2x ", 0xff & skb->data[i]); + } + printk(KERN_DEBUG "br2684: skb: %s\n", buf); +} +#else +#define skb_debug(skb) do {} while (0) +#endif + +static unsigned char llc_oui_pid_pad[] = + { 0xAA, 0xAA, 0x03, 0x00, 0x80, 0xC2, 0x00, 0x07, 0x00, 0x00 }; +#define PADLEN (2) + +enum br2684_encaps { + e_vc = BR2684_ENCAPS_VC, + e_llc = BR2684_ENCAPS_LLC, +}; + +struct br2684_vcc { + struct atm_vcc *atmvcc; + struct net_device *device; + /* keep old push,pop functions for chaining */ + void (*old_push)(struct atm_vcc *vcc,struct sk_buff *skb); + /* void (*old_pop)(struct atm_vcc *vcc,struct sk_buff *skb); */ + enum br2684_encaps encaps; + struct list_head brvccs; +#ifdef CONFIG_ATM_BR2684_IPFILTER + struct br2684_filter filter; +#endif /* CONFIG_ATM_BR2684_IPFILTER */ +#ifndef FASTER_VERSION + unsigned copies_needed, copies_failed; +#endif /* FASTER_VERSION */ +}; + +struct br2684_dev { + struct net_device *net_dev; + struct list_head br2684_devs; + int number; + struct list_head brvccs; /* one device <=> one vcc (before xmas) */ + struct net_device_stats stats; + int mac_was_set; +}; + +/* + * This lock should be held for writing any time the list of devices or + * their attached vcc's could be altered. It should be held for reading + * any time these are being queried. Note that we sometimes need to + * do read-locking under interrupt context, so write locking must block + * the current CPU's interrupts + */ +static DEFINE_RWLOCK(devs_lock); + +static LIST_HEAD(br2684_devs); + +static inline struct br2684_dev *BRPRIV(const struct net_device *net_dev) +{ + return (struct br2684_dev *) net_dev->priv; +} + +static inline struct net_device *list_entry_brdev(const struct list_head *le) +{ + return list_entry(le, struct br2684_dev, br2684_devs)->net_dev; +} + +static inline struct br2684_vcc *BR2684_VCC(const struct atm_vcc *atmvcc) +{ + return (struct br2684_vcc *) (atmvcc->user_back); +} + +static inline struct br2684_vcc *list_entry_brvcc(const struct list_head *le) +{ + return list_entry(le, struct br2684_vcc, brvccs); +} + +/* Caller should hold read_lock(&devs_lock) */ +static struct net_device *br2684_find_dev(const struct br2684_if_spec *s) +{ + struct list_head *lh; + struct net_device *net_dev; + switch (s->method) { + case BR2684_FIND_BYNUM: + list_for_each(lh, &br2684_devs) { + net_dev = list_entry_brdev(lh); + if (BRPRIV(net_dev)->number == s->spec.devnum) + return net_dev; + } + break; + case BR2684_FIND_BYIFNAME: + list_for_each(lh, &br2684_devs) { + net_dev = list_entry_brdev(lh); + if (!strncmp(net_dev->name, s->spec.ifname, IFNAMSIZ)) + return net_dev; + } + break; + } + return NULL; +} + +/* + * Send a packet out a particular vcc. Not to useful right now, but paves + * the way for multiple vcc's per itf. Returns true if we can send, + * otherwise false + */ +static int br2684_xmit_vcc(struct sk_buff *skb, struct br2684_dev *brdev, + struct br2684_vcc *brvcc) +{ + struct atm_vcc *atmvcc; +#ifdef FASTER_VERSION + if (brvcc->encaps == e_llc) + memcpy(skb_push(skb, 8), llc_oui_pid_pad, 8); + /* last 2 bytes of llc_oui_pid_pad are managed by header routines; + yes, you got it: 8 + 2 = sizeof(llc_oui_pid_pad) + */ +#else + int minheadroom = (brvcc->encaps == e_llc) ? 10 : 2; + if (skb_headroom(skb) < minheadroom) { + struct sk_buff *skb2 = skb_realloc_headroom(skb, minheadroom); + brvcc->copies_needed++; + dev_kfree_skb(skb); + if (skb2 == NULL) { + brvcc->copies_failed++; + return 0; + } + skb = skb2; + } + skb_push(skb, minheadroom); + if (brvcc->encaps == e_llc) + memcpy(skb->data, llc_oui_pid_pad, 10); + else + memset(skb->data, 0, 2); +#endif /* FASTER_VERSION */ + skb_debug(skb); + + ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; + DPRINTK("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); + if (!atm_may_send(atmvcc, skb->truesize)) { + /* we free this here for now, because we cannot know in a higher + layer whether the skb point it supplied wasn't freed yet. + now, it always is. + */ + dev_kfree_skb(skb); + return 0; + } + atomic_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); + ATM_SKB(skb)->atm_options = atmvcc->atm_options; + brdev->stats.tx_packets++; + brdev->stats.tx_bytes += skb->len; + atmvcc->send(atmvcc, skb); + return 1; +} + +static inline struct br2684_vcc *pick_outgoing_vcc(struct sk_buff *skb, + struct br2684_dev *brdev) +{ + return list_empty(&brdev->brvccs) ? NULL : + list_entry_brvcc(brdev->brvccs.next); /* 1 vcc/dev right now */ +} + +static int br2684_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct br2684_dev *brdev = BRPRIV(dev); + struct br2684_vcc *brvcc; + + DPRINTK("br2684_start_xmit, skb->dst=%p\n", skb->dst); + read_lock(&devs_lock); + brvcc = pick_outgoing_vcc(skb, brdev); + if (brvcc == NULL) { + DPRINTK("no vcc attached to dev %s\n", dev->name); + brdev->stats.tx_errors++; + brdev->stats.tx_carrier_errors++; + /* netif_stop_queue(dev); */ + dev_kfree_skb(skb); + read_unlock(&devs_lock); + return -EUNATCH; + } + if (!br2684_xmit_vcc(skb, brdev, brvcc)) { + /* + * We should probably use netif_*_queue() here, but that + * involves added complication. We need to walk before + * we can run + */ + /* don't free here! this pointer might be no longer valid! + dev_kfree_skb(skb); + */ + brdev->stats.tx_errors++; + brdev->stats.tx_fifo_errors++; + } + read_unlock(&devs_lock); + return 0; +} + +static struct net_device_stats *br2684_get_stats(struct net_device *dev) +{ + DPRINTK("br2684_get_stats\n"); + return &BRPRIV(dev)->stats; +} + +#ifdef FASTER_VERSION +/* + * These mirror eth_header and eth_header_cache. They are not usually + * exported for use in modules, so we grab them from net_device + * after ether_setup() is done with it. Bit of a hack. + */ +static int (*my_eth_header)(struct sk_buff *, struct net_device *, + unsigned short, void *, void *, unsigned); +static int (*my_eth_header_cache)(struct neighbour *, struct hh_cache *); + +static int +br2684_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, void *daddr, void *saddr, unsigned len) +{ + u16 *pad_before_eth; + int t = my_eth_header(skb, dev, type, daddr, saddr, len); + if (t > 0) { + pad_before_eth = (u16 *) skb_push(skb, 2); + *pad_before_eth = 0; + return dev->hard_header_len; /* or return 16; ? */ + } else + return t; +} + +static int +br2684_header_cache(struct neighbour *neigh, struct hh_cache *hh) +{ +/* hh_data is 16 bytes long. if encaps is ether-llc we need 24, so +xmit will add the additional header part in that case */ + u16 *pad_before_eth = (u16 *)(hh->hh_data); + int t = my_eth_header_cache(neigh, hh); + DPRINTK("br2684_header_cache, neigh=%p, hh_cache=%p\n", neigh, hh); + if (t < 0) + return t; + else { + *pad_before_eth = 0; + hh->hh_len = PADLEN + ETH_HLEN; + } + return 0; +} + +/* + * This is similar to eth_type_trans, which cannot be used because of + * our dev->hard_header_len + */ +static inline unsigned short br_type_trans(struct sk_buff *skb, + struct net_device *dev) +{ + struct ethhdr *eth; + unsigned char *rawp; + eth = eth_hdr(skb); + + if (*eth->h_dest & 1) { + if (memcmp(eth->h_dest, dev->broadcast, ETH_ALEN) == 0) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } + + else if (memcmp(eth->h_dest, dev->dev_addr, ETH_ALEN)) + skb->pkt_type = PACKET_OTHERHOST; + + if (ntohs(eth->h_proto) >= 1536) + return eth->h_proto; + + rawp = skb->data; + + /* + * This is a magic hack to spot IPX packets. Older Novell breaks + * the protocol design and runs IPX over 802.3 without an 802.2 LLC + * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This + * won't work for fault tolerant netware but does for the rest. + */ + if (*(unsigned short *) rawp == 0xFFFF) + return htons(ETH_P_802_3); + + /* + * Real 802.2 LLC + */ + return htons(ETH_P_802_2); +} +#endif /* FASTER_VERSION */ + +/* + * We remember when the MAC gets set, so we don't override it later with + * the ESI of the ATM card of the first VC + */ +static int (*my_eth_mac_addr)(struct net_device *, void *); +static int br2684_mac_addr(struct net_device *dev, void *p) +{ + int err = my_eth_mac_addr(dev, p); + if (!err) + BRPRIV(dev)->mac_was_set = 1; + return err; +} + +#ifdef CONFIG_ATM_BR2684_IPFILTER +/* this IOCTL is experimental. */ +static int br2684_setfilt(struct atm_vcc *atmvcc, void __user *arg) +{ + struct br2684_vcc *brvcc; + struct br2684_filter_set fs; + + if (copy_from_user(&fs, arg, sizeof fs)) + return -EFAULT; + if (fs.ifspec.method != BR2684_FIND_BYNOTHING) { + /* + * This is really a per-vcc thing, but we can also search + * by device + */ + struct br2684_dev *brdev; + read_lock(&devs_lock); + brdev = BRPRIV(br2684_find_dev(&fs.ifspec)); + if (brdev == NULL || list_empty(&brdev->brvccs) || + brdev->brvccs.next != brdev->brvccs.prev) /* >1 VCC */ + brvcc = NULL; + else + brvcc = list_entry_brvcc(brdev->brvccs.next); + read_unlock(&devs_lock); + if (brvcc == NULL) + return -ESRCH; + } else + brvcc = BR2684_VCC(atmvcc); + memcpy(&brvcc->filter, &fs.filter, sizeof(brvcc->filter)); + return 0; +} + +/* Returns 1 if packet should be dropped */ +static inline int +packet_fails_filter(u16 type, struct br2684_vcc *brvcc, struct sk_buff *skb) +{ + if (brvcc->filter.netmask == 0) + return 0; /* no filter in place */ + if (type == __constant_htons(ETH_P_IP) && + (((struct iphdr *) (skb->data))->daddr & brvcc->filter. + netmask) == brvcc->filter.prefix) + return 0; + if (type == __constant_htons(ETH_P_ARP)) + return 0; + /* TODO: we should probably filter ARPs too.. don't want to have + * them returning values that don't make sense, or is that ok? + */ + return 1; /* drop */ +} +#endif /* CONFIG_ATM_BR2684_IPFILTER */ + +static void br2684_close_vcc(struct br2684_vcc *brvcc) +{ + DPRINTK("removing VCC %p from dev %p\n", brvcc, brvcc->device); + write_lock_irq(&devs_lock); + list_del(&brvcc->brvccs); + write_unlock_irq(&devs_lock); + brvcc->atmvcc->user_back = NULL; /* what about vcc->recvq ??? */ + brvcc->old_push(brvcc->atmvcc, NULL); /* pass on the bad news */ + kfree(brvcc); + module_put(THIS_MODULE); +} + +/* when AAL5 PDU comes in: */ +static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb) +{ + struct br2684_vcc *brvcc = BR2684_VCC(atmvcc); + struct net_device *net_dev = brvcc->device; + struct br2684_dev *brdev = BRPRIV(net_dev); + int plen = sizeof(llc_oui_pid_pad) + ETH_HLEN; + + DPRINTK("br2684_push\n"); + + if (unlikely(skb == NULL)) { + /* skb==NULL means VCC is being destroyed */ + br2684_close_vcc(brvcc); + if (list_empty(&brdev->brvccs)) { + read_lock(&devs_lock); + list_del(&brdev->br2684_devs); + read_unlock(&devs_lock); + unregister_netdev(net_dev); + free_netdev(net_dev); + } + return; + } + + skb_debug(skb); + atm_return(atmvcc, skb->truesize); + DPRINTK("skb from brdev %p\n", brdev); + if (brvcc->encaps == e_llc) { + /* let us waste some time for checking the encapsulation. + Note, that only 7 char is checked so frames with a valid FCS + are also accepted (but FCS is not checked of course) */ + if (memcmp(skb->data, llc_oui_pid_pad, 7)) { + brdev->stats.rx_errors++; + dev_kfree_skb(skb); + return; + } + + /* Strip FCS if present */ + if (skb->len > 7 && skb->data[7] == 0x01) + __skb_trim(skb, skb->len - 4); + } else { + plen = PADLEN + ETH_HLEN; /* pad, dstmac,srcmac, ethtype */ + /* first 2 chars should be 0 */ + if (*((u16 *) (skb->data)) != 0) { + brdev->stats.rx_errors++; + dev_kfree_skb(skb); + return; + } + } + if (skb->len < plen) { + brdev->stats.rx_errors++; + dev_kfree_skb(skb); /* dev_ not needed? */ + return; + } + +#ifdef FASTER_VERSION + /* FIXME: tcpdump shows that pointer to mac header is 2 bytes earlier, + than should be. What else should I set? */ + skb_pull(skb, plen); + skb->mac.raw = ((char *) (skb->data)) - ETH_HLEN; + skb->pkt_type = PACKET_HOST; +#ifdef CONFIG_BR2684_FAST_TRANS + skb->protocol = ((u16 *) skb->data)[-1]; +#else /* some protocols might require this: */ + skb->protocol = br_type_trans(skb, net_dev); +#endif /* CONFIG_BR2684_FAST_TRANS */ +#else + skb_pull(skb, plen - ETH_HLEN); + skb->protocol = eth_type_trans(skb, net_dev); +#endif /* FASTER_VERSION */ +#ifdef CONFIG_ATM_BR2684_IPFILTER + if (unlikely(packet_fails_filter(skb->protocol, brvcc, skb))) { + brdev->stats.rx_dropped++; + dev_kfree_skb(skb); + return; + } +#endif /* CONFIG_ATM_BR2684_IPFILTER */ + skb->dev = net_dev; + ATM_SKB(skb)->vcc = atmvcc; /* needed ? */ + DPRINTK("received packet's protocol: %x\n", ntohs(skb->protocol)); + skb_debug(skb); + if (unlikely(!(net_dev->flags & IFF_UP))) { + /* sigh, interface is down */ + brdev->stats.rx_dropped++; + dev_kfree_skb(skb); + return; + } + brdev->stats.rx_packets++; + brdev->stats.rx_bytes += skb->len; + memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data)); + netif_rx(skb); +} + +static int br2684_regvcc(struct atm_vcc *atmvcc, void __user *arg) +{ +/* assign a vcc to a dev +Note: we do not have explicit unassign, but look at _push() +*/ + int err; + struct br2684_vcc *brvcc; + struct sk_buff_head copy; + struct sk_buff *skb; + struct br2684_dev *brdev; + struct net_device *net_dev; + struct atm_backend_br2684 be; + + if (copy_from_user(&be, arg, sizeof be)) + return -EFAULT; + brvcc = kmalloc(sizeof(struct br2684_vcc), GFP_KERNEL); + if (!brvcc) + return -ENOMEM; + memset(brvcc, 0, sizeof(struct br2684_vcc)); + write_lock_irq(&devs_lock); + net_dev = br2684_find_dev(&be.ifspec); + if (net_dev == NULL) { + printk(KERN_ERR + "br2684: tried to attach to non-existant device\n"); + err = -ENXIO; + goto error; + } + brdev = BRPRIV(net_dev); + if (atmvcc->push == NULL) { + err = -EBADFD; + goto error; + } + if (!list_empty(&brdev->brvccs)) { + /* Only 1 VCC/dev right now */ + err = -EEXIST; + goto error; + } + if (be.fcs_in != BR2684_FCSIN_NO || be.fcs_out != BR2684_FCSOUT_NO || + be.fcs_auto || be.has_vpiid || be.send_padding || (be.encaps != + BR2684_ENCAPS_VC && be.encaps != BR2684_ENCAPS_LLC) || + be.min_size != 0) { + err = -EINVAL; + goto error; + } + DPRINTK("br2684_regvcc vcc=%p, encaps=%d, brvcc=%p\n", atmvcc, be.encaps, + brvcc); + if (list_empty(&brdev->brvccs) && !brdev->mac_was_set) { + unsigned char *esi = atmvcc->dev->esi; + if (esi[0] | esi[1] | esi[2] | esi[3] | esi[4] | esi[5]) + memcpy(net_dev->dev_addr, esi, net_dev->addr_len); + else + net_dev->dev_addr[2] = 1; + } + list_add(&brvcc->brvccs, &brdev->brvccs); + write_unlock_irq(&devs_lock); + brvcc->device = net_dev; + brvcc->atmvcc = atmvcc; + atmvcc->user_back = brvcc; + brvcc->encaps = (enum br2684_encaps) be.encaps; + brvcc->old_push = atmvcc->push; + barrier(); + atmvcc->push = br2684_push; + skb_queue_head_init(©); + skb_migrate(&sk_atm(atmvcc)->sk_receive_queue, ©); + while ((skb = skb_dequeue(©)) != NULL) { + BRPRIV(skb->dev)->stats.rx_bytes -= skb->len; + BRPRIV(skb->dev)->stats.rx_packets--; + br2684_push(atmvcc, skb); + } + __module_get(THIS_MODULE); + return 0; + error: + write_unlock_irq(&devs_lock); + kfree(brvcc); + return err; +} + +static void br2684_setup(struct net_device *netdev) +{ + struct br2684_dev *brdev = BRPRIV(netdev); + + ether_setup(netdev); + brdev->net_dev = netdev; + +#ifdef FASTER_VERSION + my_eth_header = netdev->hard_header; + netdev->hard_header = br2684_header; + my_eth_header_cache = netdev->hard_header_cache; + netdev->hard_header_cache = br2684_header_cache; + netdev->hard_header_len = sizeof(llc_oui_pid_pad) + ETH_HLEN; /* 10 + 14 */ +#endif + my_eth_mac_addr = netdev->set_mac_address; + netdev->set_mac_address = br2684_mac_addr; + netdev->hard_start_xmit = br2684_start_xmit; + netdev->get_stats = br2684_get_stats; + + INIT_LIST_HEAD(&brdev->brvccs); +} + +static int br2684_create(void __user *arg) +{ + int err; + struct net_device *netdev; + struct br2684_dev *brdev; + struct atm_newif_br2684 ni; + + DPRINTK("br2684_create\n"); + + if (copy_from_user(&ni, arg, sizeof ni)) { + return -EFAULT; + } + if (ni.media != BR2684_MEDIA_ETHERNET || ni.mtu != 1500) { + return -EINVAL; + } + + netdev = alloc_netdev(sizeof(struct br2684_dev), + ni.ifname[0] ? ni.ifname : "nas%d", + br2684_setup); + if (!netdev) + return -ENOMEM; + + brdev = BRPRIV(netdev); + + DPRINTK("registered netdev %s\n", netdev->name); + /* open, stop, do_ioctl ? */ + err = register_netdev(netdev); + if (err < 0) { + printk(KERN_ERR "br2684_create: register_netdev failed\n"); + free_netdev(netdev); + return err; + } + + write_lock_irq(&devs_lock); + brdev->number = list_empty(&br2684_devs) ? 1 : + BRPRIV(list_entry_brdev(br2684_devs.prev))->number + 1; + list_add_tail(&brdev->br2684_devs, &br2684_devs); + write_unlock_irq(&devs_lock); + return 0; +} + +/* + * This handles ioctls actually performed on our vcc - we must return + * -ENOIOCTLCMD for any unrecognized ioctl + */ +static int br2684_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + struct atm_vcc *atmvcc = ATM_SD(sock); + void __user *argp = (void __user *)arg; + + int err; + switch(cmd) { + case ATM_SETBACKEND: + case ATM_NEWBACKENDIF: { + atm_backend_t b; + err = get_user(b, (atm_backend_t __user *) argp); + if (err) + return -EFAULT; + if (b != ATM_BACKEND_BR2684) + return -ENOIOCTLCMD; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (cmd == ATM_SETBACKEND) + return br2684_regvcc(atmvcc, argp); + else + return br2684_create(argp); + } +#ifdef CONFIG_ATM_BR2684_IPFILTER + case BR2684_SETFILT: + if (atmvcc->push != br2684_push) + return -ENOIOCTLCMD; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + err = br2684_setfilt(atmvcc, argp); + return err; +#endif /* CONFIG_ATM_BR2684_IPFILTER */ + } + return -ENOIOCTLCMD; +} + +static struct atm_ioctl br2684_ioctl_ops = { + .owner = THIS_MODULE, + .ioctl = br2684_ioctl, +}; + + +#ifdef CONFIG_PROC_FS +static void *br2684_seq_start(struct seq_file *seq, loff_t *pos) +{ + loff_t offs = 0; + struct br2684_dev *brd; + + read_lock(&devs_lock); + + list_for_each_entry(brd, &br2684_devs, br2684_devs) { + if (offs == *pos) + return brd; + ++offs; + } + return NULL; +} + +static void *br2684_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct br2684_dev *brd = v; + + ++*pos; + + brd = list_entry(brd->br2684_devs.next, + struct br2684_dev, br2684_devs); + return (&brd->br2684_devs != &br2684_devs) ? brd : NULL; +} + +static void br2684_seq_stop(struct seq_file *seq, void *v) +{ + read_unlock(&devs_lock); +} + +static int br2684_seq_show(struct seq_file *seq, void *v) +{ + const struct br2684_dev *brdev = v; + const struct net_device *net_dev = brdev->net_dev; + const struct br2684_vcc *brvcc; + + seq_printf(seq, "dev %.16s: num=%d, mac=%02X:%02X:" + "%02X:%02X:%02X:%02X (%s)\n", net_dev->name, + brdev->number, + net_dev->dev_addr[0], + net_dev->dev_addr[1], + net_dev->dev_addr[2], + net_dev->dev_addr[3], + net_dev->dev_addr[4], + net_dev->dev_addr[5], + brdev->mac_was_set ? "set" : "auto"); + + list_for_each_entry(brvcc, &brdev->brvccs, brvccs) { + seq_printf(seq, " vcc %d.%d.%d: encaps=%s" +#ifndef FASTER_VERSION + ", failed copies %u/%u" +#endif /* FASTER_VERSION */ + "\n", brvcc->atmvcc->dev->number, + brvcc->atmvcc->vpi, brvcc->atmvcc->vci, + (brvcc->encaps == e_llc) ? "LLC" : "VC" +#ifndef FASTER_VERSION + , brvcc->copies_failed + , brvcc->copies_needed +#endif /* FASTER_VERSION */ + ); +#ifdef CONFIG_ATM_BR2684_IPFILTER +#define b1(var, byte) ((u8 *) &brvcc->filter.var)[byte] +#define bs(var) b1(var, 0), b1(var, 1), b1(var, 2), b1(var, 3) + if (brvcc->filter.netmask != 0) + seq_printf(seq, " filter=%d.%d.%d.%d/" + "%d.%d.%d.%d\n", + bs(prefix), bs(netmask)); +#undef bs +#undef b1 +#endif /* CONFIG_ATM_BR2684_IPFILTER */ + } + return 0; +} + +static struct seq_operations br2684_seq_ops = { + .start = br2684_seq_start, + .next = br2684_seq_next, + .stop = br2684_seq_stop, + .show = br2684_seq_show, +}; + +static int br2684_proc_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &br2684_seq_ops); +} + +static struct file_operations br2684_proc_ops = { + .owner = THIS_MODULE, + .open = br2684_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +extern struct proc_dir_entry *atm_proc_root; /* from proc.c */ +#endif + +static int __init br2684_init(void) +{ +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *p; + if ((p = create_proc_entry("br2684", 0, atm_proc_root)) == NULL) + return -ENOMEM; + p->proc_fops = &br2684_proc_ops; +#endif + register_atm_ioctl(&br2684_ioctl_ops); + return 0; +} + +static void __exit br2684_exit(void) +{ + struct net_device *net_dev; + struct br2684_dev *brdev; + struct br2684_vcc *brvcc; + deregister_atm_ioctl(&br2684_ioctl_ops); + +#ifdef CONFIG_PROC_FS + remove_proc_entry("br2684", atm_proc_root); +#endif + + while (!list_empty(&br2684_devs)) { + net_dev = list_entry_brdev(br2684_devs.next); + brdev = BRPRIV(net_dev); + while (!list_empty(&brdev->brvccs)) { + brvcc = list_entry_brvcc(brdev->brvccs.next); + br2684_close_vcc(brvcc); + } + + list_del(&brdev->br2684_devs); + unregister_netdev(net_dev); + free_netdev(net_dev); + } +} + +module_init(br2684_init); +module_exit(br2684_exit); + +MODULE_AUTHOR("Marcell GAL"); +MODULE_DESCRIPTION("RFC2684 bridged protocols over ATM/AAL5"); +MODULE_LICENSE("GPL"); diff --git a/net/atm/clip.c b/net/atm/clip.c new file mode 100644 index 000000000000..28dab55a4387 --- /dev/null +++ b/net/atm/clip.c @@ -0,0 +1,1045 @@ +/* net/atm/clip.c - RFC1577 Classical IP over ATM */ + +/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ + + +#include <linux/config.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/kernel.h> /* for UINT_MAX */ +#include <linux/module.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/wait.h> +#include <linux/timer.h> +#include <linux/if_arp.h> /* for some manifest constants */ +#include <linux/notifier.h> +#include <linux/atm.h> +#include <linux/atmdev.h> +#include <linux/atmclip.h> +#include <linux/atmarp.h> +#include <linux/ip.h> /* for net/route.h */ +#include <linux/in.h> /* for struct sockaddr_in */ +#include <linux/if.h> /* for IFF_UP */ +#include <linux/inetdevice.h> +#include <linux/bitops.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/rcupdate.h> +#include <linux/jhash.h> +#include <net/route.h> /* for struct rtable and routing */ +#include <net/icmp.h> /* icmp_send */ +#include <asm/param.h> /* for HZ */ +#include <asm/byteorder.h> /* for htons etc. */ +#include <asm/system.h> /* save/restore_flags */ +#include <asm/uaccess.h> +#include <asm/atomic.h> + +#include "common.h" +#include "resources.h" +#include "ipcommon.h" +#include <net/atmclip.h> + + +#if 0 +#define DPRINTK(format,args...) printk(format,##args) +#else +#define DPRINTK(format,args...) +#endif + + +static struct net_device *clip_devs; +static struct atm_vcc *atmarpd; +static struct neigh_table clip_tbl; +static struct timer_list idle_timer; +static int start_timer = 1; + + +static int to_atmarpd(enum atmarp_ctrl_type type,int itf,unsigned long ip) +{ + struct sock *sk; + struct atmarp_ctrl *ctrl; + struct sk_buff *skb; + + DPRINTK("to_atmarpd(%d)\n",type); + if (!atmarpd) return -EUNATCH; + skb = alloc_skb(sizeof(struct atmarp_ctrl),GFP_ATOMIC); + if (!skb) return -ENOMEM; + ctrl = (struct atmarp_ctrl *) skb_put(skb,sizeof(struct atmarp_ctrl)); + ctrl->type = type; + ctrl->itf_num = itf; + ctrl->ip = ip; + atm_force_charge(atmarpd,skb->truesize); + + sk = sk_atm(atmarpd); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); + return 0; +} + + +static void link_vcc(struct clip_vcc *clip_vcc,struct atmarp_entry *entry) +{ + DPRINTK("link_vcc %p to entry %p (neigh %p)\n",clip_vcc,entry, + entry->neigh); + clip_vcc->entry = entry; + clip_vcc->xoff = 0; /* @@@ may overrun buffer by one packet */ + clip_vcc->next = entry->vccs; + entry->vccs = clip_vcc; + entry->neigh->used = jiffies; +} + + +static void unlink_clip_vcc(struct clip_vcc *clip_vcc) +{ + struct atmarp_entry *entry = clip_vcc->entry; + struct clip_vcc **walk; + + if (!entry) { + printk(KERN_CRIT "!clip_vcc->entry (clip_vcc %p)\n",clip_vcc); + return; + } + spin_lock_bh(&entry->neigh->dev->xmit_lock); /* block clip_start_xmit() */ + entry->neigh->used = jiffies; + for (walk = &entry->vccs; *walk; walk = &(*walk)->next) + if (*walk == clip_vcc) { + int error; + + *walk = clip_vcc->next; /* atomic */ + clip_vcc->entry = NULL; + if (clip_vcc->xoff) + netif_wake_queue(entry->neigh->dev); + if (entry->vccs) + goto out; + entry->expires = jiffies-1; + /* force resolution or expiration */ + error = neigh_update(entry->neigh, NULL, NUD_NONE, + NEIGH_UPDATE_F_ADMIN); + if (error) + printk(KERN_CRIT "unlink_clip_vcc: " + "neigh_update failed with %d\n",error); + goto out; + } + printk(KERN_CRIT "ATMARP: unlink_clip_vcc failed (entry %p, vcc " + "0x%p)\n",entry,clip_vcc); +out: + spin_unlock_bh(&entry->neigh->dev->xmit_lock); +} + +/* The neighbour entry n->lock is held. */ +static int neigh_check_cb(struct neighbour *n) +{ + struct atmarp_entry *entry = NEIGH2ENTRY(n); + struct clip_vcc *cv; + + for (cv = entry->vccs; cv; cv = cv->next) { + unsigned long exp = cv->last_use + cv->idle_timeout; + + if (cv->idle_timeout && time_after(jiffies, exp)) { + DPRINTK("releasing vcc %p->%p of entry %p\n", + cv, cv->vcc, entry); + vcc_release_async(cv->vcc, -ETIMEDOUT); + } + } + + if (entry->vccs || time_before(jiffies, entry->expires)) + return 0; + + if (atomic_read(&n->refcnt) > 1) { + struct sk_buff *skb; + + DPRINTK("destruction postponed with ref %d\n", + atomic_read(&n->refcnt)); + + while ((skb = skb_dequeue(&n->arp_queue)) != NULL) + dev_kfree_skb(skb); + + return 0; + } + + DPRINTK("expired neigh %p\n",n); + return 1; +} + +static void idle_timer_check(unsigned long dummy) +{ + write_lock(&clip_tbl.lock); + __neigh_for_each_release(&clip_tbl, neigh_check_cb); + mod_timer(&idle_timer, jiffies+CLIP_CHECK_INTERVAL*HZ); + write_unlock(&clip_tbl.lock); +} + +static int clip_arp_rcv(struct sk_buff *skb) +{ + struct atm_vcc *vcc; + + DPRINTK("clip_arp_rcv\n"); + vcc = ATM_SKB(skb)->vcc; + if (!vcc || !atm_charge(vcc,skb->truesize)) { + dev_kfree_skb_any(skb); + return 0; + } + DPRINTK("pushing to %p\n",vcc); + DPRINTK("using %p\n",CLIP_VCC(vcc)->old_push); + CLIP_VCC(vcc)->old_push(vcc,skb); + return 0; +} + +static const unsigned char llc_oui[] = { + 0xaa, /* DSAP: non-ISO */ + 0xaa, /* SSAP: non-ISO */ + 0x03, /* Ctrl: Unnumbered Information Command PDU */ + 0x00, /* OUI: EtherType */ + 0x00, + 0x00 }; + +static void clip_push(struct atm_vcc *vcc,struct sk_buff *skb) +{ + struct clip_vcc *clip_vcc = CLIP_VCC(vcc); + + DPRINTK("clip push\n"); + if (!skb) { + DPRINTK("removing VCC %p\n",clip_vcc); + if (clip_vcc->entry) unlink_clip_vcc(clip_vcc); + clip_vcc->old_push(vcc,NULL); /* pass on the bad news */ + kfree(clip_vcc); + return; + } + atm_return(vcc,skb->truesize); + skb->dev = clip_vcc->entry ? clip_vcc->entry->neigh->dev : clip_devs; + /* clip_vcc->entry == NULL if we don't have an IP address yet */ + if (!skb->dev) { + dev_kfree_skb_any(skb); + return; + } + ATM_SKB(skb)->vcc = vcc; + skb->mac.raw = skb->data; + if (!clip_vcc->encap || skb->len < RFC1483LLC_LEN || memcmp(skb->data, + llc_oui,sizeof(llc_oui))) skb->protocol = htons(ETH_P_IP); + else { + skb->protocol = ((u16 *) skb->data)[3]; + skb_pull(skb,RFC1483LLC_LEN); + if (skb->protocol == htons(ETH_P_ARP)) { + PRIV(skb->dev)->stats.rx_packets++; + PRIV(skb->dev)->stats.rx_bytes += skb->len; + clip_arp_rcv(skb); + return; + } + } + clip_vcc->last_use = jiffies; + PRIV(skb->dev)->stats.rx_packets++; + PRIV(skb->dev)->stats.rx_bytes += skb->len; + memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data)); + netif_rx(skb); +} + + +/* + * Note: these spinlocks _must_not_ block on non-SMP. The only goal is that + * clip_pop is atomic with respect to the critical section in clip_start_xmit. + */ + + +static void clip_pop(struct atm_vcc *vcc,struct sk_buff *skb) +{ + struct clip_vcc *clip_vcc = CLIP_VCC(vcc); + struct net_device *dev = skb->dev; + int old; + unsigned long flags; + + DPRINTK("clip_pop(vcc %p)\n",vcc); + clip_vcc->old_pop(vcc,skb); + /* skb->dev == NULL in outbound ARP packets */ + if (!dev) return; + spin_lock_irqsave(&PRIV(dev)->xoff_lock,flags); + if (atm_may_send(vcc,0)) { + old = xchg(&clip_vcc->xoff,0); + if (old) netif_wake_queue(dev); + } + spin_unlock_irqrestore(&PRIV(dev)->xoff_lock,flags); +} + + +static void clip_neigh_destroy(struct neighbour *neigh) +{ + DPRINTK("clip_neigh_destroy (neigh %p)\n",neigh); + if (NEIGH2ENTRY(neigh)->vccs) + printk(KERN_CRIT "clip_neigh_destroy: vccs != NULL !!!\n"); + NEIGH2ENTRY(neigh)->vccs = (void *) 0xdeadbeef; +} + + +static void clip_neigh_solicit(struct neighbour *neigh,struct sk_buff *skb) +{ + DPRINTK("clip_neigh_solicit (neigh %p, skb %p)\n",neigh,skb); + to_atmarpd(act_need,PRIV(neigh->dev)->number,NEIGH2ENTRY(neigh)->ip); +} + + +static void clip_neigh_error(struct neighbour *neigh,struct sk_buff *skb) +{ +#ifndef CONFIG_ATM_CLIP_NO_ICMP + icmp_send(skb,ICMP_DEST_UNREACH,ICMP_HOST_UNREACH,0); +#endif + kfree_skb(skb); +} + + +static struct neigh_ops clip_neigh_ops = { + .family = AF_INET, + .destructor = clip_neigh_destroy, + .solicit = clip_neigh_solicit, + .error_report = clip_neigh_error, + .output = dev_queue_xmit, + .connected_output = dev_queue_xmit, + .hh_output = dev_queue_xmit, + .queue_xmit = dev_queue_xmit, +}; + + +static int clip_constructor(struct neighbour *neigh) +{ + struct atmarp_entry *entry = NEIGH2ENTRY(neigh); + struct net_device *dev = neigh->dev; + struct in_device *in_dev; + struct neigh_parms *parms; + + DPRINTK("clip_constructor (neigh %p, entry %p)\n",neigh,entry); + neigh->type = inet_addr_type(entry->ip); + if (neigh->type != RTN_UNICAST) return -EINVAL; + + rcu_read_lock(); + in_dev = rcu_dereference(__in_dev_get(dev)); + if (!in_dev) { + rcu_read_unlock(); + return -EINVAL; + } + + parms = in_dev->arp_parms; + __neigh_parms_put(neigh->parms); + neigh->parms = neigh_parms_clone(parms); + rcu_read_unlock(); + + neigh->ops = &clip_neigh_ops; + neigh->output = neigh->nud_state & NUD_VALID ? + neigh->ops->connected_output : neigh->ops->output; + entry->neigh = neigh; + entry->vccs = NULL; + entry->expires = jiffies-1; + return 0; +} + +static u32 clip_hash(const void *pkey, const struct net_device *dev) +{ + return jhash_2words(*(u32 *)pkey, dev->ifindex, clip_tbl.hash_rnd); +} + +static struct neigh_table clip_tbl = { + .family = AF_INET, + .entry_size = sizeof(struct neighbour)+sizeof(struct atmarp_entry), + .key_len = 4, + .hash = clip_hash, + .constructor = clip_constructor, + .id = "clip_arp_cache", + + /* parameters are copied from ARP ... */ + .parms = { + .tbl = &clip_tbl, + .base_reachable_time = 30 * HZ, + .retrans_time = 1 * HZ, + .gc_staletime = 60 * HZ, + .reachable_time = 30 * HZ, + .delay_probe_time = 5 * HZ, + .queue_len = 3, + .ucast_probes = 3, + .mcast_probes = 3, + .anycast_delay = 1 * HZ, + .proxy_delay = (8 * HZ) / 10, + .proxy_qlen = 64, + .locktime = 1 * HZ, + }, + .gc_interval = 30 * HZ, + .gc_thresh1 = 128, + .gc_thresh2 = 512, + .gc_thresh3 = 1024, +}; + + +/* @@@ copy bh locking from arp.c -- need to bh-enable atm code before */ + +/* + * We play with the resolve flag: 0 and 1 have the usual meaning, but -1 means + * to allocate the neighbour entry but not to ask atmarpd for resolution. Also, + * don't increment the usage count. This is used to create entries in + * clip_setentry. + */ + + +static int clip_encap(struct atm_vcc *vcc,int mode) +{ + CLIP_VCC(vcc)->encap = mode; + return 0; +} + + +static int clip_start_xmit(struct sk_buff *skb,struct net_device *dev) +{ + struct clip_priv *clip_priv = PRIV(dev); + struct atmarp_entry *entry; + struct atm_vcc *vcc; + int old; + unsigned long flags; + + DPRINTK("clip_start_xmit (skb %p)\n",skb); + if (!skb->dst) { + printk(KERN_ERR "clip_start_xmit: skb->dst == NULL\n"); + dev_kfree_skb(skb); + clip_priv->stats.tx_dropped++; + return 0; + } + if (!skb->dst->neighbour) { +#if 0 + skb->dst->neighbour = clip_find_neighbour(skb->dst,1); + if (!skb->dst->neighbour) { + dev_kfree_skb(skb); /* lost that one */ + clip_priv->stats.tx_dropped++; + return 0; + } +#endif + printk(KERN_ERR "clip_start_xmit: NO NEIGHBOUR !\n"); + dev_kfree_skb(skb); + clip_priv->stats.tx_dropped++; + return 0; + } + entry = NEIGH2ENTRY(skb->dst->neighbour); + if (!entry->vccs) { + if (time_after(jiffies, entry->expires)) { + /* should be resolved */ + entry->expires = jiffies+ATMARP_RETRY_DELAY*HZ; + to_atmarpd(act_need,PRIV(dev)->number,entry->ip); + } + if (entry->neigh->arp_queue.qlen < ATMARP_MAX_UNRES_PACKETS) + skb_queue_tail(&entry->neigh->arp_queue,skb); + else { + dev_kfree_skb(skb); + clip_priv->stats.tx_dropped++; + } + return 0; + } + DPRINTK("neigh %p, vccs %p\n",entry,entry->vccs); + ATM_SKB(skb)->vcc = vcc = entry->vccs->vcc; + DPRINTK("using neighbour %p, vcc %p\n",skb->dst->neighbour,vcc); + if (entry->vccs->encap) { + void *here; + + here = skb_push(skb,RFC1483LLC_LEN); + memcpy(here,llc_oui,sizeof(llc_oui)); + ((u16 *) here)[3] = skb->protocol; + } + atomic_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + ATM_SKB(skb)->atm_options = vcc->atm_options; + entry->vccs->last_use = jiffies; + DPRINTK("atm_skb(%p)->vcc(%p)->dev(%p)\n",skb,vcc,vcc->dev); + old = xchg(&entry->vccs->xoff,1); /* assume XOFF ... */ + if (old) { + printk(KERN_WARNING "clip_start_xmit: XOFF->XOFF transition\n"); + return 0; + } + clip_priv->stats.tx_packets++; + clip_priv->stats.tx_bytes += skb->len; + (void) vcc->send(vcc,skb); + if (atm_may_send(vcc,0)) { + entry->vccs->xoff = 0; + return 0; + } + spin_lock_irqsave(&clip_priv->xoff_lock,flags); + netif_stop_queue(dev); /* XOFF -> throttle immediately */ + barrier(); + if (!entry->vccs->xoff) + netif_start_queue(dev); + /* Oh, we just raced with clip_pop. netif_start_queue should be + good enough, because nothing should really be asleep because + of the brief netif_stop_queue. If this isn't true or if it + changes, use netif_wake_queue instead. */ + spin_unlock_irqrestore(&clip_priv->xoff_lock,flags); + return 0; +} + + +static struct net_device_stats *clip_get_stats(struct net_device *dev) +{ + return &PRIV(dev)->stats; +} + + +static int clip_mkip(struct atm_vcc *vcc,int timeout) +{ + struct clip_vcc *clip_vcc; + struct sk_buff_head copy; + struct sk_buff *skb; + + if (!vcc->push) return -EBADFD; + clip_vcc = kmalloc(sizeof(struct clip_vcc),GFP_KERNEL); + if (!clip_vcc) return -ENOMEM; + DPRINTK("mkip clip_vcc %p vcc %p\n",clip_vcc,vcc); + clip_vcc->vcc = vcc; + vcc->user_back = clip_vcc; + set_bit(ATM_VF_IS_CLIP, &vcc->flags); + clip_vcc->entry = NULL; + clip_vcc->xoff = 0; + clip_vcc->encap = 1; + clip_vcc->last_use = jiffies; + clip_vcc->idle_timeout = timeout*HZ; + clip_vcc->old_push = vcc->push; + clip_vcc->old_pop = vcc->pop; + vcc->push = clip_push; + vcc->pop = clip_pop; + skb_queue_head_init(©); + skb_migrate(&sk_atm(vcc)->sk_receive_queue, ©); + /* re-process everything received between connection setup and MKIP */ + while ((skb = skb_dequeue(©)) != NULL) + if (!clip_devs) { + atm_return(vcc,skb->truesize); + kfree_skb(skb); + } + else { + unsigned int len = skb->len; + + clip_push(vcc,skb); + PRIV(skb->dev)->stats.rx_packets--; + PRIV(skb->dev)->stats.rx_bytes -= len; + } + return 0; +} + + +static int clip_setentry(struct atm_vcc *vcc,u32 ip) +{ + struct neighbour *neigh; + struct atmarp_entry *entry; + int error; + struct clip_vcc *clip_vcc; + struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ip, .tos = 1 } } }; + struct rtable *rt; + + if (vcc->push != clip_push) { + printk(KERN_WARNING "clip_setentry: non-CLIP VCC\n"); + return -EBADF; + } + clip_vcc = CLIP_VCC(vcc); + if (!ip) { + if (!clip_vcc->entry) { + printk(KERN_ERR "hiding hidden ATMARP entry\n"); + return 0; + } + DPRINTK("setentry: remove\n"); + unlink_clip_vcc(clip_vcc); + return 0; + } + error = ip_route_output_key(&rt,&fl); + if (error) return error; + neigh = __neigh_lookup(&clip_tbl,&ip,rt->u.dst.dev,1); + ip_rt_put(rt); + if (!neigh) + return -ENOMEM; + entry = NEIGH2ENTRY(neigh); + if (entry != clip_vcc->entry) { + if (!clip_vcc->entry) DPRINTK("setentry: add\n"); + else { + DPRINTK("setentry: update\n"); + unlink_clip_vcc(clip_vcc); + } + link_vcc(clip_vcc,entry); + } + error = neigh_update(neigh, llc_oui, NUD_PERMANENT, + NEIGH_UPDATE_F_OVERRIDE|NEIGH_UPDATE_F_ADMIN); + neigh_release(neigh); + return error; +} + + +static void clip_setup(struct net_device *dev) +{ + dev->hard_start_xmit = clip_start_xmit; + /* sg_xmit ... */ + dev->get_stats = clip_get_stats; + dev->type = ARPHRD_ATM; + dev->hard_header_len = RFC1483LLC_LEN; + dev->mtu = RFC1626_MTU; + dev->tx_queue_len = 100; /* "normal" queue (packets) */ + /* When using a "real" qdisc, the qdisc determines the queue */ + /* length. tx_queue_len is only used for the default case, */ + /* without any more elaborate queuing. 100 is a reasonable */ + /* compromise between decent burst-tolerance and protection */ + /* against memory hogs. */ +} + + +static int clip_create(int number) +{ + struct net_device *dev; + struct clip_priv *clip_priv; + int error; + + if (number != -1) { + for (dev = clip_devs; dev; dev = PRIV(dev)->next) + if (PRIV(dev)->number == number) return -EEXIST; + } + else { + number = 0; + for (dev = clip_devs; dev; dev = PRIV(dev)->next) + if (PRIV(dev)->number >= number) + number = PRIV(dev)->number+1; + } + dev = alloc_netdev(sizeof(struct clip_priv), "", clip_setup); + if (!dev) + return -ENOMEM; + clip_priv = PRIV(dev); + sprintf(dev->name,"atm%d",number); + spin_lock_init(&clip_priv->xoff_lock); + clip_priv->number = number; + error = register_netdev(dev); + if (error) { + free_netdev(dev); + return error; + } + clip_priv->next = clip_devs; + clip_devs = dev; + DPRINTK("registered (net:%s)\n",dev->name); + return number; +} + + +static int clip_device_event(struct notifier_block *this,unsigned long event, + void *dev) +{ + /* ignore non-CLIP devices */ + if (((struct net_device *) dev)->type != ARPHRD_ATM || + ((struct net_device *) dev)->hard_start_xmit != clip_start_xmit) + return NOTIFY_DONE; + switch (event) { + case NETDEV_UP: + DPRINTK("clip_device_event NETDEV_UP\n"); + (void) to_atmarpd(act_up,PRIV(dev)->number,0); + break; + case NETDEV_GOING_DOWN: + DPRINTK("clip_device_event NETDEV_DOWN\n"); + (void) to_atmarpd(act_down,PRIV(dev)->number,0); + break; + case NETDEV_CHANGE: + case NETDEV_CHANGEMTU: + DPRINTK("clip_device_event NETDEV_CHANGE*\n"); + (void) to_atmarpd(act_change,PRIV(dev)->number,0); + break; + case NETDEV_REBOOT: + case NETDEV_REGISTER: + case NETDEV_DOWN: + DPRINTK("clip_device_event %ld\n",event); + /* ignore */ + break; + default: + printk(KERN_WARNING "clip_device_event: unknown event " + "%ld\n",event); + break; + } + return NOTIFY_DONE; +} + + +static int clip_inet_event(struct notifier_block *this,unsigned long event, + void *ifa) +{ + struct in_device *in_dev; + + in_dev = ((struct in_ifaddr *) ifa)->ifa_dev; + if (!in_dev || !in_dev->dev) { + printk(KERN_WARNING "clip_inet_event: no device\n"); + return NOTIFY_DONE; + } + /* + * Transitions are of the down-change-up type, so it's sufficient to + * handle the change on up. + */ + if (event != NETDEV_UP) return NOTIFY_DONE; + return clip_device_event(this,NETDEV_CHANGE,in_dev->dev); +} + + +static struct notifier_block clip_dev_notifier = { + clip_device_event, + NULL, + 0 +}; + + + +static struct notifier_block clip_inet_notifier = { + clip_inet_event, + NULL, + 0 +}; + + + +static void atmarpd_close(struct atm_vcc *vcc) +{ + DPRINTK("atmarpd_close\n"); + atmarpd = NULL; /* assumed to be atomic */ + barrier(); + unregister_inetaddr_notifier(&clip_inet_notifier); + unregister_netdevice_notifier(&clip_dev_notifier); + if (skb_peek(&sk_atm(vcc)->sk_receive_queue)) + printk(KERN_ERR "atmarpd_close: closing with requests " + "pending\n"); + skb_queue_purge(&sk_atm(vcc)->sk_receive_queue); + DPRINTK("(done)\n"); + module_put(THIS_MODULE); +} + + +static struct atmdev_ops atmarpd_dev_ops = { + .close = atmarpd_close +}; + + +static struct atm_dev atmarpd_dev = { + .ops = &atmarpd_dev_ops, + .type = "arpd", + .number = 999, + .lock = SPIN_LOCK_UNLOCKED +}; + + +static int atm_init_atmarp(struct atm_vcc *vcc) +{ + if (atmarpd) return -EADDRINUSE; + if (start_timer) { + start_timer = 0; + init_timer(&idle_timer); + idle_timer.expires = jiffies+CLIP_CHECK_INTERVAL*HZ; + idle_timer.function = idle_timer_check; + add_timer(&idle_timer); + } + atmarpd = vcc; + set_bit(ATM_VF_META,&vcc->flags); + set_bit(ATM_VF_READY,&vcc->flags); + /* allow replies and avoid getting closed if signaling dies */ + vcc->dev = &atmarpd_dev; + vcc_insert_socket(sk_atm(vcc)); + vcc->push = NULL; + vcc->pop = NULL; /* crash */ + vcc->push_oam = NULL; /* crash */ + if (register_netdevice_notifier(&clip_dev_notifier)) + printk(KERN_ERR "register_netdevice_notifier failed\n"); + if (register_inetaddr_notifier(&clip_inet_notifier)) + printk(KERN_ERR "register_inetaddr_notifier failed\n"); + return 0; +} + +static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + struct atm_vcc *vcc = ATM_SD(sock); + int err = 0; + + switch (cmd) { + case SIOCMKCLIP: + case ATMARPD_CTRL: + case ATMARP_MKIP: + case ATMARP_SETENTRY: + case ATMARP_ENCAP: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + break; + default: + return -ENOIOCTLCMD; + } + + switch (cmd) { + case SIOCMKCLIP: + err = clip_create(arg); + break; + case ATMARPD_CTRL: + err = atm_init_atmarp(vcc); + if (!err) { + sock->state = SS_CONNECTED; + __module_get(THIS_MODULE); + } + break; + case ATMARP_MKIP: + err = clip_mkip(vcc ,arg); + break; + case ATMARP_SETENTRY: + err = clip_setentry(vcc, arg); + break; + case ATMARP_ENCAP: + err = clip_encap(vcc, arg); + break; + } + return err; +} + +static struct atm_ioctl clip_ioctl_ops = { + .owner = THIS_MODULE, + .ioctl = clip_ioctl, +}; + +#ifdef CONFIG_PROC_FS + +static void svc_addr(struct seq_file *seq, struct sockaddr_atmsvc *addr) +{ + static int code[] = { 1,2,10,6,1,0 }; + static int e164[] = { 1,8,4,6,1,0 }; + + if (*addr->sas_addr.pub) { + seq_printf(seq, "%s", addr->sas_addr.pub); + if (*addr->sas_addr.prv) + seq_putc(seq, '+'); + } else if (!*addr->sas_addr.prv) { + seq_printf(seq, "%s", "(none)"); + return; + } + if (*addr->sas_addr.prv) { + unsigned char *prv = addr->sas_addr.prv; + int *fields; + int i, j; + + fields = *prv == ATM_AFI_E164 ? e164 : code; + for (i = 0; fields[i]; i++) { + for (j = fields[i]; j; j--) + seq_printf(seq, "%02X", *prv++); + if (fields[i+1]) + seq_putc(seq, '.'); + } + } +} + +/* This means the neighbour entry has no attached VCC objects. */ +#define SEQ_NO_VCC_TOKEN ((void *) 2) + +static void atmarp_info(struct seq_file *seq, struct net_device *dev, + struct atmarp_entry *entry, struct clip_vcc *clip_vcc) +{ + unsigned long exp; + char buf[17]; + int svc, llc, off; + + svc = ((clip_vcc == SEQ_NO_VCC_TOKEN) || + (sk_atm(clip_vcc->vcc)->sk_family == AF_ATMSVC)); + + llc = ((clip_vcc == SEQ_NO_VCC_TOKEN) || + clip_vcc->encap); + + if (clip_vcc == SEQ_NO_VCC_TOKEN) + exp = entry->neigh->used; + else + exp = clip_vcc->last_use; + + exp = (jiffies - exp) / HZ; + + seq_printf(seq, "%-6s%-4s%-4s%5ld ", + dev->name, + svc ? "SVC" : "PVC", + llc ? "LLC" : "NULL", + exp); + + off = scnprintf(buf, sizeof(buf) - 1, "%d.%d.%d.%d", + NIPQUAD(entry->ip)); + while (off < 16) + buf[off++] = ' '; + buf[off] = '\0'; + seq_printf(seq, "%s", buf); + + if (clip_vcc == SEQ_NO_VCC_TOKEN) { + if (time_before(jiffies, entry->expires)) + seq_printf(seq, "(resolving)\n"); + else + seq_printf(seq, "(expired, ref %d)\n", + atomic_read(&entry->neigh->refcnt)); + } else if (!svc) { + seq_printf(seq, "%d.%d.%d\n", + clip_vcc->vcc->dev->number, + clip_vcc->vcc->vpi, + clip_vcc->vcc->vci); + } else { + svc_addr(seq, &clip_vcc->vcc->remote); + seq_putc(seq, '\n'); + } +} + +struct clip_seq_state { + /* This member must be first. */ + struct neigh_seq_state ns; + + /* Local to clip specific iteration. */ + struct clip_vcc *vcc; +}; + +static struct clip_vcc *clip_seq_next_vcc(struct atmarp_entry *e, + struct clip_vcc *curr) +{ + if (!curr) { + curr = e->vccs; + if (!curr) + return SEQ_NO_VCC_TOKEN; + return curr; + } + if (curr == SEQ_NO_VCC_TOKEN) + return NULL; + + curr = curr->next; + + return curr; +} + +static void *clip_seq_vcc_walk(struct clip_seq_state *state, + struct atmarp_entry *e, loff_t *pos) +{ + struct clip_vcc *vcc = state->vcc; + + vcc = clip_seq_next_vcc(e, vcc); + if (vcc && pos != NULL) { + while (*pos) { + vcc = clip_seq_next_vcc(e, vcc); + if (!vcc) + break; + --(*pos); + } + } + state->vcc = vcc; + + return vcc; +} + +static void *clip_seq_sub_iter(struct neigh_seq_state *_state, + struct neighbour *n, loff_t *pos) +{ + struct clip_seq_state *state = (struct clip_seq_state *) _state; + + return clip_seq_vcc_walk(state, NEIGH2ENTRY(n), pos); +} + +static void *clip_seq_start(struct seq_file *seq, loff_t *pos) +{ + return neigh_seq_start(seq, pos, &clip_tbl, NEIGH_SEQ_NEIGH_ONLY); +} + +static int clip_seq_show(struct seq_file *seq, void *v) +{ + static char atm_arp_banner[] = + "IPitf TypeEncp Idle IP address ATM address\n"; + + if (v == SEQ_START_TOKEN) { + seq_puts(seq, atm_arp_banner); + } else { + struct clip_seq_state *state = seq->private; + struct neighbour *n = v; + struct clip_vcc *vcc = state->vcc; + + atmarp_info(seq, n->dev, NEIGH2ENTRY(n), vcc); + } + return 0; +} + +static struct seq_operations arp_seq_ops = { + .start = clip_seq_start, + .next = neigh_seq_next, + .stop = neigh_seq_stop, + .show = clip_seq_show, +}; + +static int arp_seq_open(struct inode *inode, struct file *file) +{ + struct clip_seq_state *state; + struct seq_file *seq; + int rc = -EAGAIN; + + state = kmalloc(sizeof(*state), GFP_KERNEL); + if (!state) { + rc = -ENOMEM; + goto out_kfree; + } + memset(state, 0, sizeof(*state)); + state->ns.neigh_sub_iter = clip_seq_sub_iter; + + rc = seq_open(file, &arp_seq_ops); + if (rc) + goto out_kfree; + + seq = file->private_data; + seq->private = state; +out: + return rc; + +out_kfree: + kfree(state); + goto out; +} + +static struct file_operations arp_seq_fops = { + .open = arp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, + .owner = THIS_MODULE +}; +#endif + +static int __init atm_clip_init(void) +{ + neigh_table_init(&clip_tbl); + + clip_tbl_hook = &clip_tbl; + register_atm_ioctl(&clip_ioctl_ops); + +#ifdef CONFIG_PROC_FS +{ + struct proc_dir_entry *p; + + p = create_proc_entry("arp", S_IRUGO, atm_proc_root); + if (p) + p->proc_fops = &arp_seq_fops; +} +#endif + + return 0; +} + +static void __exit atm_clip_exit(void) +{ + struct net_device *dev, *next; + + remove_proc_entry("arp", atm_proc_root); + + deregister_atm_ioctl(&clip_ioctl_ops); + + /* First, stop the idle timer, so it stops banging + * on the table. + */ + if (start_timer == 0) + del_timer(&idle_timer); + + /* Next, purge the table, so that the device + * unregister loop below does not hang due to + * device references remaining in the table. + */ + neigh_ifdown(&clip_tbl, NULL); + + dev = clip_devs; + while (dev) { + next = PRIV(dev)->next; + unregister_netdev(dev); + free_netdev(dev); + dev = next; + } + + /* Now it is safe to fully shutdown whole table. */ + neigh_table_clear(&clip_tbl); + + clip_tbl_hook = NULL; +} + +module_init(atm_clip_init); +module_exit(atm_clip_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/atm/common.c b/net/atm/common.c new file mode 100644 index 000000000000..6d16be334ea0 --- /dev/null +++ b/net/atm/common.c @@ -0,0 +1,804 @@ +/* net/atm/common.c - ATM sockets (common part for PVC and SVC) */ + +/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ + + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/kmod.h> +#include <linux/net.h> /* struct socket, struct proto_ops */ +#include <linux/atm.h> /* ATM stuff */ +#include <linux/atmdev.h> +#include <linux/socket.h> /* SOL_SOCKET */ +#include <linux/errno.h> /* error codes */ +#include <linux/capability.h> +#include <linux/mm.h> /* verify_area */ +#include <linux/sched.h> +#include <linux/time.h> /* struct timeval */ +#include <linux/skbuff.h> +#include <linux/bitops.h> +#include <linux/init.h> +#include <net/sock.h> /* struct sock */ + +#include <asm/uaccess.h> +#include <asm/atomic.h> +#include <asm/poll.h> + + +#include "resources.h" /* atm_find_dev */ +#include "common.h" /* prototypes */ +#include "protocols.h" /* atm_init_<transport> */ +#include "addr.h" /* address registry */ +#include "signaling.h" /* for WAITING and sigd_attach */ + + +#if 0 +#define DPRINTK(format,args...) printk(KERN_DEBUG format,##args) +#else +#define DPRINTK(format,args...) +#endif + +struct hlist_head vcc_hash[VCC_HTABLE_SIZE]; +DEFINE_RWLOCK(vcc_sklist_lock); + +static void __vcc_insert_socket(struct sock *sk) +{ + struct atm_vcc *vcc = atm_sk(sk); + struct hlist_head *head = &vcc_hash[vcc->vci & + (VCC_HTABLE_SIZE - 1)]; + sk->sk_hashent = vcc->vci & (VCC_HTABLE_SIZE - 1); + sk_add_node(sk, head); +} + +void vcc_insert_socket(struct sock *sk) +{ + write_lock_irq(&vcc_sklist_lock); + __vcc_insert_socket(sk); + write_unlock_irq(&vcc_sklist_lock); +} + +static void vcc_remove_socket(struct sock *sk) +{ + write_lock_irq(&vcc_sklist_lock); + sk_del_node_init(sk); + write_unlock_irq(&vcc_sklist_lock); +} + + +static struct sk_buff *alloc_tx(struct atm_vcc *vcc,unsigned int size) +{ + struct sk_buff *skb; + struct sock *sk = sk_atm(vcc); + + if (atomic_read(&sk->sk_wmem_alloc) && !atm_may_send(vcc, size)) { + DPRINTK("Sorry: wmem_alloc = %d, size = %d, sndbuf = %d\n", + atomic_read(&sk->sk_wmem_alloc), size, + sk->sk_sndbuf); + return NULL; + } + while (!(skb = alloc_skb(size,GFP_KERNEL))) schedule(); + DPRINTK("AlTx %d += %d\n", atomic_read(&sk->sk_wmem_alloc), + skb->truesize); + atomic_add(skb->truesize, &sk->sk_wmem_alloc); + return skb; +} + + +EXPORT_SYMBOL(vcc_hash); +EXPORT_SYMBOL(vcc_sklist_lock); +EXPORT_SYMBOL(vcc_insert_socket); + +static void vcc_sock_destruct(struct sock *sk) +{ + if (atomic_read(&sk->sk_rmem_alloc)) + printk(KERN_DEBUG "vcc_sock_destruct: rmem leakage (%d bytes) detected.\n", atomic_read(&sk->sk_rmem_alloc)); + + if (atomic_read(&sk->sk_wmem_alloc)) + printk(KERN_DEBUG "vcc_sock_destruct: wmem leakage (%d bytes) detected.\n", atomic_read(&sk->sk_wmem_alloc)); +} + +static void vcc_def_wakeup(struct sock *sk) +{ + read_lock(&sk->sk_callback_lock); + if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + wake_up(sk->sk_sleep); + read_unlock(&sk->sk_callback_lock); +} + +static inline int vcc_writable(struct sock *sk) +{ + struct atm_vcc *vcc = atm_sk(sk); + + return (vcc->qos.txtp.max_sdu + + atomic_read(&sk->sk_wmem_alloc)) <= sk->sk_sndbuf; +} + +static void vcc_write_space(struct sock *sk) +{ + read_lock(&sk->sk_callback_lock); + + if (vcc_writable(sk)) { + if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + wake_up_interruptible(sk->sk_sleep); + + sk_wake_async(sk, 2, POLL_OUT); + } + + read_unlock(&sk->sk_callback_lock); +} + +static struct proto vcc_proto = { + .name = "VCC", + .owner = THIS_MODULE, + .obj_size = sizeof(struct atm_vcc), +}; + +int vcc_create(struct socket *sock, int protocol, int family) +{ + struct sock *sk; + struct atm_vcc *vcc; + + sock->sk = NULL; + if (sock->type == SOCK_STREAM) + return -EINVAL; + sk = sk_alloc(family, GFP_KERNEL, &vcc_proto, 1); + if (!sk) + return -ENOMEM; + sock_init_data(sock, sk); + sk->sk_state_change = vcc_def_wakeup; + sk->sk_write_space = vcc_write_space; + + vcc = atm_sk(sk); + vcc->dev = NULL; + memset(&vcc->local,0,sizeof(struct sockaddr_atmsvc)); + memset(&vcc->remote,0,sizeof(struct sockaddr_atmsvc)); + vcc->qos.txtp.max_sdu = 1 << 16; /* for meta VCs */ + atomic_set(&sk->sk_wmem_alloc, 0); + atomic_set(&sk->sk_rmem_alloc, 0); + vcc->push = NULL; + vcc->pop = NULL; + vcc->push_oam = NULL; + vcc->vpi = vcc->vci = 0; /* no VCI/VPI yet */ + vcc->atm_options = vcc->aal_options = 0; + sk->sk_destruct = vcc_sock_destruct; + return 0; +} + + +static void vcc_destroy_socket(struct sock *sk) +{ + struct atm_vcc *vcc = atm_sk(sk); + struct sk_buff *skb; + + set_bit(ATM_VF_CLOSE, &vcc->flags); + clear_bit(ATM_VF_READY, &vcc->flags); + if (vcc->dev) { + if (vcc->dev->ops->close) + vcc->dev->ops->close(vcc); + if (vcc->push) + vcc->push(vcc, NULL); /* atmarpd has no push */ + + vcc_remove_socket(sk); /* no more receive */ + + while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { + atm_return(vcc,skb->truesize); + kfree_skb(skb); + } + + module_put(vcc->dev->ops->owner); + atm_dev_put(vcc->dev); + } +} + + +int vcc_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + + if (sk) { + lock_sock(sk); + vcc_destroy_socket(sock->sk); + release_sock(sk); + sock_put(sk); + } + + return 0; +} + + +void vcc_release_async(struct atm_vcc *vcc, int reply) +{ + struct sock *sk = sk_atm(vcc); + + set_bit(ATM_VF_CLOSE, &vcc->flags); + sk->sk_shutdown |= RCV_SHUTDOWN; + sk->sk_err = -reply; + clear_bit(ATM_VF_WAITING, &vcc->flags); + sk->sk_state_change(sk); +} + + +EXPORT_SYMBOL(vcc_release_async); + + +static int adjust_tp(struct atm_trafprm *tp,unsigned char aal) +{ + int max_sdu; + + if (!tp->traffic_class) return 0; + switch (aal) { + case ATM_AAL0: + max_sdu = ATM_CELL_SIZE-1; + break; + case ATM_AAL34: + max_sdu = ATM_MAX_AAL34_PDU; + break; + default: + printk(KERN_WARNING "ATM: AAL problems ... " + "(%d)\n",aal); + /* fall through */ + case ATM_AAL5: + max_sdu = ATM_MAX_AAL5_PDU; + } + if (!tp->max_sdu) tp->max_sdu = max_sdu; + else if (tp->max_sdu > max_sdu) return -EINVAL; + if (!tp->max_cdv) tp->max_cdv = ATM_MAX_CDV; + return 0; +} + + +static int check_ci(struct atm_vcc *vcc, short vpi, int vci) +{ + struct hlist_head *head = &vcc_hash[vci & + (VCC_HTABLE_SIZE - 1)]; + struct hlist_node *node; + struct sock *s; + struct atm_vcc *walk; + + sk_for_each(s, node, head) { + walk = atm_sk(s); + if (walk->dev != vcc->dev) + continue; + if (test_bit(ATM_VF_ADDR, &walk->flags) && walk->vpi == vpi && + walk->vci == vci && ((walk->qos.txtp.traffic_class != + ATM_NONE && vcc->qos.txtp.traffic_class != ATM_NONE) || + (walk->qos.rxtp.traffic_class != ATM_NONE && + vcc->qos.rxtp.traffic_class != ATM_NONE))) + return -EADDRINUSE; + } + + /* allow VCCs with same VPI/VCI iff they don't collide on + TX/RX (but we may refuse such sharing for other reasons, + e.g. if protocol requires to have both channels) */ + + return 0; +} + + +static int find_ci(struct atm_vcc *vcc, short *vpi, int *vci) +{ + static short p; /* poor man's per-device cache */ + static int c; + short old_p; + int old_c; + int err; + + if (*vpi != ATM_VPI_ANY && *vci != ATM_VCI_ANY) { + err = check_ci(vcc, *vpi, *vci); + return err; + } + /* last scan may have left values out of bounds for current device */ + if (*vpi != ATM_VPI_ANY) + p = *vpi; + else if (p >= 1 << vcc->dev->ci_range.vpi_bits) + p = 0; + if (*vci != ATM_VCI_ANY) + c = *vci; + else if (c < ATM_NOT_RSV_VCI || c >= 1 << vcc->dev->ci_range.vci_bits) + c = ATM_NOT_RSV_VCI; + old_p = p; + old_c = c; + do { + if (!check_ci(vcc, p, c)) { + *vpi = p; + *vci = c; + return 0; + } + if (*vci == ATM_VCI_ANY) { + c++; + if (c >= 1 << vcc->dev->ci_range.vci_bits) + c = ATM_NOT_RSV_VCI; + } + if ((c == ATM_NOT_RSV_VCI || *vci != ATM_VCI_ANY) && + *vpi == ATM_VPI_ANY) { + p++; + if (p >= 1 << vcc->dev->ci_range.vpi_bits) p = 0; + } + } + while (old_p != p || old_c != c); + return -EADDRINUSE; +} + + +static int __vcc_connect(struct atm_vcc *vcc, struct atm_dev *dev, short vpi, + int vci) +{ + struct sock *sk = sk_atm(vcc); + int error; + + if ((vpi != ATM_VPI_UNSPEC && vpi != ATM_VPI_ANY && + vpi >> dev->ci_range.vpi_bits) || (vci != ATM_VCI_UNSPEC && + vci != ATM_VCI_ANY && vci >> dev->ci_range.vci_bits)) + return -EINVAL; + if (vci > 0 && vci < ATM_NOT_RSV_VCI && !capable(CAP_NET_BIND_SERVICE)) + return -EPERM; + error = 0; + if (!try_module_get(dev->ops->owner)) + return -ENODEV; + vcc->dev = dev; + write_lock_irq(&vcc_sklist_lock); + if ((error = find_ci(vcc, &vpi, &vci))) { + write_unlock_irq(&vcc_sklist_lock); + goto fail_module_put; + } + vcc->vpi = vpi; + vcc->vci = vci; + __vcc_insert_socket(sk); + write_unlock_irq(&vcc_sklist_lock); + switch (vcc->qos.aal) { + case ATM_AAL0: + error = atm_init_aal0(vcc); + vcc->stats = &dev->stats.aal0; + break; + case ATM_AAL34: + error = atm_init_aal34(vcc); + vcc->stats = &dev->stats.aal34; + break; + case ATM_NO_AAL: + /* ATM_AAL5 is also used in the "0 for default" case */ + vcc->qos.aal = ATM_AAL5; + /* fall through */ + case ATM_AAL5: + error = atm_init_aal5(vcc); + vcc->stats = &dev->stats.aal5; + break; + default: + error = -EPROTOTYPE; + } + if (!error) error = adjust_tp(&vcc->qos.txtp,vcc->qos.aal); + if (!error) error = adjust_tp(&vcc->qos.rxtp,vcc->qos.aal); + if (error) + goto fail; + DPRINTK("VCC %d.%d, AAL %d\n",vpi,vci,vcc->qos.aal); + DPRINTK(" TX: %d, PCR %d..%d, SDU %d\n",vcc->qos.txtp.traffic_class, + vcc->qos.txtp.min_pcr,vcc->qos.txtp.max_pcr,vcc->qos.txtp.max_sdu); + DPRINTK(" RX: %d, PCR %d..%d, SDU %d\n",vcc->qos.rxtp.traffic_class, + vcc->qos.rxtp.min_pcr,vcc->qos.rxtp.max_pcr,vcc->qos.rxtp.max_sdu); + + if (dev->ops->open) { + if ((error = dev->ops->open(vcc))) + goto fail; + } + return 0; + +fail: + vcc_remove_socket(sk); +fail_module_put: + module_put(dev->ops->owner); + /* ensure we get dev module ref count correct */ + vcc->dev = NULL; + return error; +} + + +int vcc_connect(struct socket *sock, int itf, short vpi, int vci) +{ + struct atm_dev *dev; + struct atm_vcc *vcc = ATM_SD(sock); + int error; + + DPRINTK("vcc_connect (vpi %d, vci %d)\n",vpi,vci); + if (sock->state == SS_CONNECTED) + return -EISCONN; + if (sock->state != SS_UNCONNECTED) + return -EINVAL; + if (!(vpi || vci)) + return -EINVAL; + + if (vpi != ATM_VPI_UNSPEC && vci != ATM_VCI_UNSPEC) + clear_bit(ATM_VF_PARTIAL,&vcc->flags); + else + if (test_bit(ATM_VF_PARTIAL,&vcc->flags)) + return -EINVAL; + DPRINTK("vcc_connect (TX: cl %d,bw %d-%d,sdu %d; " + "RX: cl %d,bw %d-%d,sdu %d,AAL %s%d)\n", + vcc->qos.txtp.traffic_class,vcc->qos.txtp.min_pcr, + vcc->qos.txtp.max_pcr,vcc->qos.txtp.max_sdu, + vcc->qos.rxtp.traffic_class,vcc->qos.rxtp.min_pcr, + vcc->qos.rxtp.max_pcr,vcc->qos.rxtp.max_sdu, + vcc->qos.aal == ATM_AAL5 ? "" : vcc->qos.aal == ATM_AAL0 ? "" : + " ??? code ",vcc->qos.aal == ATM_AAL0 ? 0 : vcc->qos.aal); + if (!test_bit(ATM_VF_HASQOS, &vcc->flags)) + return -EBADFD; + if (vcc->qos.txtp.traffic_class == ATM_ANYCLASS || + vcc->qos.rxtp.traffic_class == ATM_ANYCLASS) + return -EINVAL; + if (itf != ATM_ITF_ANY) { + dev = atm_dev_lookup(itf); + if (!dev) + return -ENODEV; + error = __vcc_connect(vcc, dev, vpi, vci); + if (error) { + atm_dev_put(dev); + return error; + } + } else { + struct list_head *p, *next; + + dev = NULL; + spin_lock(&atm_dev_lock); + list_for_each_safe(p, next, &atm_devs) { + dev = list_entry(p, struct atm_dev, dev_list); + atm_dev_hold(dev); + spin_unlock(&atm_dev_lock); + if (!__vcc_connect(vcc, dev, vpi, vci)) + break; + atm_dev_put(dev); + dev = NULL; + spin_lock(&atm_dev_lock); + } + spin_unlock(&atm_dev_lock); + if (!dev) + return -ENODEV; + } + if (vpi == ATM_VPI_UNSPEC || vci == ATM_VCI_UNSPEC) + set_bit(ATM_VF_PARTIAL,&vcc->flags); + if (test_bit(ATM_VF_READY,&ATM_SD(sock)->flags)) + sock->state = SS_CONNECTED; + return 0; +} + + +int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, + size_t size, int flags) +{ + struct sock *sk = sock->sk; + struct atm_vcc *vcc; + struct sk_buff *skb; + int copied, error = -EINVAL; + + if (sock->state != SS_CONNECTED) + return -ENOTCONN; + if (flags & ~MSG_DONTWAIT) /* only handle MSG_DONTWAIT */ + return -EOPNOTSUPP; + vcc = ATM_SD(sock); + if (test_bit(ATM_VF_RELEASED,&vcc->flags) || + test_bit(ATM_VF_CLOSE,&vcc->flags) || + !test_bit(ATM_VF_READY, &vcc->flags)) + return 0; + + skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &error); + if (!skb) + return error; + + copied = skb->len; + if (copied > size) { + copied = size; + msg->msg_flags |= MSG_TRUNC; + } + + error = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (error) + return error; + sock_recv_timestamp(msg, sk, skb); + DPRINTK("RcvM %d -= %d\n", atomic_read(&sk->rmem_alloc), skb->truesize); + atm_return(vcc, skb->truesize); + skb_free_datagram(sk, skb); + return copied; +} + + +int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, + size_t total_len) +{ + struct sock *sk = sock->sk; + DEFINE_WAIT(wait); + struct atm_vcc *vcc; + struct sk_buff *skb; + int eff,error; + const void __user *buff; + int size; + + lock_sock(sk); + if (sock->state != SS_CONNECTED) { + error = -ENOTCONN; + goto out; + } + if (m->msg_name) { + error = -EISCONN; + goto out; + } + if (m->msg_iovlen != 1) { + error = -ENOSYS; /* fix this later @@@ */ + goto out; + } + buff = m->msg_iov->iov_base; + size = m->msg_iov->iov_len; + vcc = ATM_SD(sock); + if (test_bit(ATM_VF_RELEASED, &vcc->flags) || + test_bit(ATM_VF_CLOSE, &vcc->flags) || + !test_bit(ATM_VF_READY, &vcc->flags)) { + error = -EPIPE; + send_sig(SIGPIPE, current, 0); + goto out; + } + if (!size) { + error = 0; + goto out; + } + if (size < 0 || size > vcc->qos.txtp.max_sdu) { + error = -EMSGSIZE; + goto out; + } + /* verify_area is done by net/socket.c */ + eff = (size+3) & ~3; /* align to word boundary */ + prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + error = 0; + while (!(skb = alloc_tx(vcc,eff))) { + if (m->msg_flags & MSG_DONTWAIT) { + error = -EAGAIN; + break; + } + schedule(); + if (signal_pending(current)) { + error = -ERESTARTSYS; + break; + } + if (test_bit(ATM_VF_RELEASED,&vcc->flags) || + test_bit(ATM_VF_CLOSE,&vcc->flags) || + !test_bit(ATM_VF_READY,&vcc->flags)) { + error = -EPIPE; + send_sig(SIGPIPE, current, 0); + break; + } + prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + } + finish_wait(sk->sk_sleep, &wait); + if (error) + goto out; + skb->dev = NULL; /* for paths shared with net_device interfaces */ + ATM_SKB(skb)->atm_options = vcc->atm_options; + if (copy_from_user(skb_put(skb,size),buff,size)) { + kfree_skb(skb); + error = -EFAULT; + goto out; + } + if (eff != size) memset(skb->data+size,0,eff-size); + error = vcc->dev->ops->send(vcc,skb); + error = error ? error : size; +out: + release_sock(sk); + return error; +} + + +unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait) +{ + struct sock *sk = sock->sk; + struct atm_vcc *vcc; + unsigned int mask; + + poll_wait(file, sk->sk_sleep, wait); + mask = 0; + + vcc = ATM_SD(sock); + + /* exceptional events */ + if (sk->sk_err) + mask = POLLERR; + + if (test_bit(ATM_VF_RELEASED, &vcc->flags) || + test_bit(ATM_VF_CLOSE, &vcc->flags)) + mask |= POLLHUP; + + /* readable? */ + if (!skb_queue_empty(&sk->sk_receive_queue)) + mask |= POLLIN | POLLRDNORM; + + /* writable? */ + if (sock->state == SS_CONNECTING && + test_bit(ATM_VF_WAITING, &vcc->flags)) + return mask; + + if (vcc->qos.txtp.traffic_class != ATM_NONE && + vcc_writable(sk)) + mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + + return mask; +} + + +static int atm_change_qos(struct atm_vcc *vcc,struct atm_qos *qos) +{ + int error; + + /* + * Don't let the QoS change the already connected AAL type nor the + * traffic class. + */ + if (qos->aal != vcc->qos.aal || + qos->rxtp.traffic_class != vcc->qos.rxtp.traffic_class || + qos->txtp.traffic_class != vcc->qos.txtp.traffic_class) + return -EINVAL; + error = adjust_tp(&qos->txtp,qos->aal); + if (!error) error = adjust_tp(&qos->rxtp,qos->aal); + if (error) return error; + if (!vcc->dev->ops->change_qos) return -EOPNOTSUPP; + if (sk_atm(vcc)->sk_family == AF_ATMPVC) + return vcc->dev->ops->change_qos(vcc,qos,ATM_MF_SET); + return svc_change_qos(vcc,qos); +} + + +static int check_tp(struct atm_trafprm *tp) +{ + /* @@@ Should be merged with adjust_tp */ + if (!tp->traffic_class || tp->traffic_class == ATM_ANYCLASS) return 0; + if (tp->traffic_class != ATM_UBR && !tp->min_pcr && !tp->pcr && + !tp->max_pcr) return -EINVAL; + if (tp->min_pcr == ATM_MAX_PCR) return -EINVAL; + if (tp->min_pcr && tp->max_pcr && tp->max_pcr != ATM_MAX_PCR && + tp->min_pcr > tp->max_pcr) return -EINVAL; + /* + * We allow pcr to be outside [min_pcr,max_pcr], because later + * adjustment may still push it in the valid range. + */ + return 0; +} + + +static int check_qos(struct atm_qos *qos) +{ + int error; + + if (!qos->txtp.traffic_class && !qos->rxtp.traffic_class) + return -EINVAL; + if (qos->txtp.traffic_class != qos->rxtp.traffic_class && + qos->txtp.traffic_class && qos->rxtp.traffic_class && + qos->txtp.traffic_class != ATM_ANYCLASS && + qos->rxtp.traffic_class != ATM_ANYCLASS) return -EINVAL; + error = check_tp(&qos->txtp); + if (error) return error; + return check_tp(&qos->rxtp); +} + +int vcc_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, int optlen) +{ + struct atm_vcc *vcc; + unsigned long value; + int error; + + if (__SO_LEVEL_MATCH(optname, level) && optlen != __SO_SIZE(optname)) + return -EINVAL; + + vcc = ATM_SD(sock); + switch (optname) { + case SO_ATMQOS: + { + struct atm_qos qos; + + if (copy_from_user(&qos,optval,sizeof(qos))) + return -EFAULT; + error = check_qos(&qos); + if (error) return error; + if (sock->state == SS_CONNECTED) + return atm_change_qos(vcc,&qos); + if (sock->state != SS_UNCONNECTED) + return -EBADFD; + vcc->qos = qos; + set_bit(ATM_VF_HASQOS,&vcc->flags); + return 0; + } + case SO_SETCLP: + if (get_user(value,(unsigned long __user *)optval)) + return -EFAULT; + if (value) vcc->atm_options |= ATM_ATMOPT_CLP; + else vcc->atm_options &= ~ATM_ATMOPT_CLP; + return 0; + default: + if (level == SOL_SOCKET) return -EINVAL; + break; + } + if (!vcc->dev || !vcc->dev->ops->setsockopt) return -EINVAL; + return vcc->dev->ops->setsockopt(vcc,level,optname,optval,optlen); +} + + +int vcc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct atm_vcc *vcc; + int len; + + if (get_user(len, optlen)) + return -EFAULT; + if (__SO_LEVEL_MATCH(optname, level) && len != __SO_SIZE(optname)) + return -EINVAL; + + vcc = ATM_SD(sock); + switch (optname) { + case SO_ATMQOS: + if (!test_bit(ATM_VF_HASQOS,&vcc->flags)) + return -EINVAL; + return copy_to_user(optval,&vcc->qos,sizeof(vcc->qos)) ? + -EFAULT : 0; + case SO_SETCLP: + return put_user(vcc->atm_options & ATM_ATMOPT_CLP ? 1 : + 0,(unsigned long __user *)optval) ? -EFAULT : 0; + case SO_ATMPVC: + { + struct sockaddr_atmpvc pvc; + + if (!vcc->dev || + !test_bit(ATM_VF_ADDR,&vcc->flags)) + return -ENOTCONN; + pvc.sap_family = AF_ATMPVC; + pvc.sap_addr.itf = vcc->dev->number; + pvc.sap_addr.vpi = vcc->vpi; + pvc.sap_addr.vci = vcc->vci; + return copy_to_user(optval,&pvc,sizeof(pvc)) ? + -EFAULT : 0; + } + default: + if (level == SOL_SOCKET) return -EINVAL; + break; + } + if (!vcc->dev || !vcc->dev->ops->getsockopt) return -EINVAL; + return vcc->dev->ops->getsockopt(vcc, level, optname, optval, len); +} + +static int __init atm_init(void) +{ + int error; + + if ((error = proto_register(&vcc_proto, 0)) < 0) + goto out; + + if ((error = atmpvc_init()) < 0) { + printk(KERN_ERR "atmpvc_init() failed with %d\n", error); + goto out_unregister_vcc_proto; + } + if ((error = atmsvc_init()) < 0) { + printk(KERN_ERR "atmsvc_init() failed with %d\n", error); + goto out_atmpvc_exit; + } + if ((error = atm_proc_init()) < 0) { + printk(KERN_ERR "atm_proc_init() failed with %d\n",error); + goto out_atmsvc_exit; + } +out: + return error; +out_atmsvc_exit: + atmsvc_exit(); +out_atmpvc_exit: + atmsvc_exit(); +out_unregister_vcc_proto: + proto_unregister(&vcc_proto); + goto out; +} + +static void __exit atm_exit(void) +{ + atm_proc_exit(); + atmsvc_exit(); + atmpvc_exit(); + proto_unregister(&vcc_proto); +} + +module_init(atm_init); +module_exit(atm_exit); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETPROTO(PF_ATMPVC); +MODULE_ALIAS_NETPROTO(PF_ATMSVC); diff --git a/net/atm/common.h b/net/atm/common.h new file mode 100644 index 000000000000..e49ed41c0e33 --- /dev/null +++ b/net/atm/common.h @@ -0,0 +1,50 @@ +/* net/atm/common.h - ATM sockets (common part for PVC and SVC) */ + +/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ + + +#ifndef NET_ATM_COMMON_H +#define NET_ATM_COMMON_H + +#include <linux/net.h> +#include <linux/poll.h> /* for poll_table */ + + +int vcc_create(struct socket *sock, int protocol, int family); +int vcc_release(struct socket *sock); +int vcc_connect(struct socket *sock, int itf, short vpi, int vci); +int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, + size_t size, int flags); +int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, + size_t total_len); +unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait); +int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); +int vcc_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, int optlen); +int vcc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen); + +int atmpvc_init(void); +void atmpvc_exit(void); +int atmsvc_init(void); +void atmsvc_exit(void); + +#ifdef CONFIG_PROC_FS +int atm_proc_init(void); +void atm_proc_exit(void); +#else +static inline int atm_proc_init(void) +{ + return 0; +} + +static inline void atm_proc_exit(void) +{ + /* nothing */ +} +#endif /* CONFIG_PROC_FS */ + +/* SVC */ +int svc_change_qos(struct atm_vcc *vcc,struct atm_qos *qos); + +#endif diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c new file mode 100644 index 000000000000..4dbb5af34a5e --- /dev/null +++ b/net/atm/ioctl.c @@ -0,0 +1,139 @@ +/* ATM ioctl handling */ + +/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ +/* 2003 John Levon <levon@movementarian.org> */ + + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/kmod.h> +#include <linux/net.h> /* struct socket, struct proto_ops */ +#include <linux/atm.h> /* ATM stuff */ +#include <linux/atmdev.h> +#include <linux/atmclip.h> /* CLIP_*ENCAP */ +#include <linux/atmarp.h> /* manifest constants */ +#include <linux/sonet.h> /* for ioctls */ +#include <linux/atmsvc.h> +#include <linux/atmmpc.h> +#include <net/atmclip.h> +#include <linux/atmlec.h> +#include <asm/ioctls.h> + +#include "resources.h" +#include "signaling.h" /* for WAITING and sigd_attach */ + + +static DECLARE_MUTEX(ioctl_mutex); +static LIST_HEAD(ioctl_list); + + +void register_atm_ioctl(struct atm_ioctl *ioctl) +{ + down(&ioctl_mutex); + list_add_tail(&ioctl->list, &ioctl_list); + up(&ioctl_mutex); +} + +void deregister_atm_ioctl(struct atm_ioctl *ioctl) +{ + down(&ioctl_mutex); + list_del(&ioctl->list); + up(&ioctl_mutex); +} + +EXPORT_SYMBOL(register_atm_ioctl); +EXPORT_SYMBOL(deregister_atm_ioctl); + +int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + struct sock *sk = sock->sk; + struct atm_vcc *vcc; + int error; + struct list_head * pos; + void __user *argp = (void __user *)arg; + + vcc = ATM_SD(sock); + switch (cmd) { + case SIOCOUTQ: + if (sock->state != SS_CONNECTED || + !test_bit(ATM_VF_READY, &vcc->flags)) { + error = -EINVAL; + goto done; + } + error = put_user(sk->sk_sndbuf - + atomic_read(&sk->sk_wmem_alloc), + (int __user *) argp) ? -EFAULT : 0; + goto done; + case SIOCINQ: + { + struct sk_buff *skb; + + if (sock->state != SS_CONNECTED) { + error = -EINVAL; + goto done; + } + skb = skb_peek(&sk->sk_receive_queue); + error = put_user(skb ? skb->len : 0, + (int __user *)argp) ? -EFAULT : 0; + goto done; + } + case SIOCGSTAMP: /* borrowed from IP */ + error = sock_get_timestamp(sk, argp); + goto done; + case ATM_SETSC: + printk(KERN_WARNING "ATM_SETSC is obsolete\n"); + error = 0; + goto done; + case ATMSIGD_CTRL: + if (!capable(CAP_NET_ADMIN)) { + error = -EPERM; + goto done; + } + /* + * The user/kernel protocol for exchanging signalling + * info uses kernel pointers as opaque references, + * so the holder of the file descriptor can scribble + * on the kernel... so we should make sure that we + * have the same privledges that /proc/kcore needs + */ + if (!capable(CAP_SYS_RAWIO)) { + error = -EPERM; + goto done; + } + error = sigd_attach(vcc); + if (!error) + sock->state = SS_CONNECTED; + goto done; + default: + break; + } + + if (cmd == ATMMPC_CTRL || cmd == ATMMPC_DATA) + request_module("mpoa"); + if (cmd == ATMARPD_CTRL) + request_module("clip"); + if (cmd == ATMLEC_CTRL) + request_module("lec"); + + error = -ENOIOCTLCMD; + + down(&ioctl_mutex); + list_for_each(pos, &ioctl_list) { + struct atm_ioctl * ic = list_entry(pos, struct atm_ioctl, list); + if (try_module_get(ic->owner)) { + error = ic->ioctl(sock, cmd, arg); + module_put(ic->owner); + if (error != -ENOIOCTLCMD) + break; + } + } + up(&ioctl_mutex); + + if (error != -ENOIOCTLCMD) + goto done; + + error = atm_dev_ioctl(cmd, argp); + +done: + return error; +} diff --git a/net/atm/ipcommon.c b/net/atm/ipcommon.c new file mode 100644 index 000000000000..181a3002d8ad --- /dev/null +++ b/net/atm/ipcommon.c @@ -0,0 +1,61 @@ +/* net/atm/ipcommon.c - Common items for all ways of doing IP over ATM */ + +/* Written 1996-2000 by Werner Almesberger, EPFL LRC/ICA */ + + +#include <linux/module.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/in.h> +#include <linux/atmdev.h> +#include <linux/atmclip.h> + +#include "common.h" +#include "ipcommon.h" + + +#if 0 +#define DPRINTK(format,args...) printk(KERN_DEBUG format,##args) +#else +#define DPRINTK(format,args...) +#endif + + +/* + * skb_migrate appends the list at "from" to "to", emptying "from" in the + * process. skb_migrate is atomic with respect to all other skb operations on + * "from" and "to". Note that it locks both lists at the same time, so beware + * of potential deadlocks. + * + * This function should live in skbuff.c or skbuff.h. + */ + + +void skb_migrate(struct sk_buff_head *from,struct sk_buff_head *to) +{ + struct sk_buff *skb; + unsigned long flags; + struct sk_buff *skb_from = (struct sk_buff *) from; + struct sk_buff *skb_to = (struct sk_buff *) to; + struct sk_buff *prev; + + spin_lock_irqsave(&from->lock,flags); + spin_lock(&to->lock); + prev = from->prev; + from->next->prev = to->prev; + prev->next = skb_to; + to->prev->next = from->next; + to->prev = from->prev; + for (skb = from->next; skb != skb_to; skb = skb->next) + skb->list = to; + to->qlen += from->qlen; + spin_unlock(&to->lock); + from->prev = skb_from; + from->next = skb_from; + from->qlen = 0; + spin_unlock_irqrestore(&from->lock,flags); +} + + +EXPORT_SYMBOL(skb_migrate); diff --git a/net/atm/ipcommon.h b/net/atm/ipcommon.h new file mode 100644 index 000000000000..d72165f60939 --- /dev/null +++ b/net/atm/ipcommon.h @@ -0,0 +1,22 @@ +/* net/atm/ipcommon.h - Common items for all ways of doing IP over ATM */ + +/* Written 1996-2000 by Werner Almesberger, EPFL LRC/ICA */ + + +#ifndef NET_ATM_IPCOMMON_H +#define NET_ATM_IPCOMMON_H + + +#include <linux/string.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/atmdev.h> + +/* + * Appends all skbs from "from" to "to". The operation is atomic with respect + * to all other skb operations on "from" or "to". + */ + +void skb_migrate(struct sk_buff_head *from,struct sk_buff_head *to); + +#endif diff --git a/net/atm/lec.c b/net/atm/lec.c new file mode 100644 index 000000000000..a0752487026d --- /dev/null +++ b/net/atm/lec.c @@ -0,0 +1,2538 @@ +/* + * lec.c: Lan Emulation driver + * Marko Kiiskila mkiiskila@yahoo.com + * + */ + +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/bitops.h> + +/* We are ethernet device */ +#include <linux/if_ether.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <net/sock.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <asm/byteorder.h> +#include <asm/uaccess.h> +#include <net/arp.h> +#include <net/dst.h> +#include <linux/proc_fs.h> +#include <linux/spinlock.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +/* TokenRing if needed */ +#ifdef CONFIG_TR +#include <linux/trdevice.h> +#endif + +/* And atm device */ +#include <linux/atmdev.h> +#include <linux/atmlec.h> + +/* Proxy LEC knows about bridging */ +#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) +#include <linux/if_bridge.h> +#include "../bridge/br_private.h" + +static unsigned char bridge_ula_lec[] = {0x01, 0x80, 0xc2, 0x00, 0x00}; +#endif + +/* Modular too */ +#include <linux/module.h> +#include <linux/init.h> + +#include "lec.h" +#include "lec_arpc.h" +#include "resources.h" + +#if 0 +#define DPRINTK printk +#else +#define DPRINTK(format,args...) +#endif + +#define DUMP_PACKETS 0 /* 0 = None, + * 1 = 30 first bytes + * 2 = Whole packet + */ + +#define LEC_UNRES_QUE_LEN 8 /* number of tx packets to queue for a + single destination while waiting for SVC */ + +static int lec_open(struct net_device *dev); +static int lec_start_xmit(struct sk_buff *skb, struct net_device *dev); +static int lec_close(struct net_device *dev); +static struct net_device_stats *lec_get_stats(struct net_device *dev); +static void lec_init(struct net_device *dev); +static struct lec_arp_table* lec_arp_find(struct lec_priv *priv, + unsigned char *mac_addr); +static int lec_arp_remove(struct lec_priv *priv, + struct lec_arp_table *to_remove); +/* LANE2 functions */ +static void lane2_associate_ind (struct net_device *dev, u8 *mac_address, + u8 *tlvs, u32 sizeoftlvs); +static int lane2_resolve(struct net_device *dev, u8 *dst_mac, int force, + u8 **tlvs, u32 *sizeoftlvs); +static int lane2_associate_req (struct net_device *dev, u8 *lan_dst, + u8 *tlvs, u32 sizeoftlvs); + +static int lec_addr_delete(struct lec_priv *priv, unsigned char *atm_addr, + unsigned long permanent); +static void lec_arp_check_empties(struct lec_priv *priv, + struct atm_vcc *vcc, struct sk_buff *skb); +static void lec_arp_destroy(struct lec_priv *priv); +static void lec_arp_init(struct lec_priv *priv); +static struct atm_vcc* lec_arp_resolve(struct lec_priv *priv, + unsigned char *mac_to_find, + int is_rdesc, + struct lec_arp_table **ret_entry); +static void lec_arp_update(struct lec_priv *priv, unsigned char *mac_addr, + unsigned char *atm_addr, unsigned long remoteflag, + unsigned int targetless_le_arp); +static void lec_flush_complete(struct lec_priv *priv, unsigned long tran_id); +static int lec_mcast_make(struct lec_priv *priv, struct atm_vcc *vcc); +static void lec_set_flush_tran_id(struct lec_priv *priv, + unsigned char *atm_addr, + unsigned long tran_id); +static void lec_vcc_added(struct lec_priv *priv, struct atmlec_ioc *ioc_data, + struct atm_vcc *vcc, + void (*old_push)(struct atm_vcc *vcc, struct sk_buff *skb)); +static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc); + +static struct lane2_ops lane2_ops = { + lane2_resolve, /* resolve, spec 3.1.3 */ + lane2_associate_req, /* associate_req, spec 3.1.4 */ + NULL /* associate indicator, spec 3.1.5 */ +}; + +static unsigned char bus_mac[ETH_ALEN] = {0xff,0xff,0xff,0xff,0xff,0xff}; + +/* Device structures */ +static struct net_device *dev_lec[MAX_LEC_ITF]; + +#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) +static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) +{ + struct ethhdr *eth; + char *buff; + struct lec_priv *priv; + + /* Check if this is a BPDU. If so, ask zeppelin to send + * LE_TOPOLOGY_REQUEST with the same value of Topology Change bit + * as the Config BPDU has */ + eth = (struct ethhdr *)skb->data; + buff = skb->data + skb->dev->hard_header_len; + if (*buff++ == 0x42 && *buff++ == 0x42 && *buff++ == 0x03) { + struct sock *sk; + struct sk_buff *skb2; + struct atmlec_msg *mesg; + + skb2 = alloc_skb(sizeof(struct atmlec_msg), GFP_ATOMIC); + if (skb2 == NULL) return; + skb2->len = sizeof(struct atmlec_msg); + mesg = (struct atmlec_msg *)skb2->data; + mesg->type = l_topology_change; + buff += 4; + mesg->content.normal.flag = *buff & 0x01; /* 0x01 is topology change */ + + priv = (struct lec_priv *)dev->priv; + atm_force_charge(priv->lecd, skb2->truesize); + sk = sk_atm(priv->lecd); + skb_queue_tail(&sk->sk_receive_queue, skb2); + sk->sk_data_ready(sk, skb2->len); + } + + return; +} +#endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ + +/* + * Modelled after tr_type_trans + * All multicast and ARE or STE frames go to BUS. + * Non source routed frames go by destination address. + * Last hop source routed frames go by destination address. + * Not last hop source routed frames go by _next_ route descriptor. + * Returns pointer to destination MAC address or fills in rdesc + * and returns NULL. + */ +#ifdef CONFIG_TR +static unsigned char *get_tr_dst(unsigned char *packet, unsigned char *rdesc) +{ + struct trh_hdr *trh; + int riflen, num_rdsc; + + trh = (struct trh_hdr *)packet; + if (trh->daddr[0] & (uint8_t)0x80) + return bus_mac; /* multicast */ + + if (trh->saddr[0] & TR_RII) { + riflen = (ntohs(trh->rcf) & TR_RCF_LEN_MASK) >> 8; + if ((ntohs(trh->rcf) >> 13) != 0) + return bus_mac; /* ARE or STE */ + } + else + return trh->daddr; /* not source routed */ + + if (riflen < 6) + return trh->daddr; /* last hop, source routed */ + + /* riflen is 6 or more, packet has more than one route descriptor */ + num_rdsc = (riflen/2) - 1; + memset(rdesc, 0, ETH_ALEN); + /* offset 4 comes from LAN destination field in LE control frames */ + if (trh->rcf & htons((uint16_t)TR_RCF_DIR_BIT)) + memcpy(&rdesc[4], &trh->rseg[num_rdsc-2], sizeof(uint16_t)); + else { + memcpy(&rdesc[4], &trh->rseg[1], sizeof(uint16_t)); + rdesc[5] = ((ntohs(trh->rseg[0]) & 0x000f) | (rdesc[5] & 0xf0)); + } + + return NULL; +} +#endif /* CONFIG_TR */ + +/* + * Open/initialize the netdevice. This is called (in the current kernel) + * sometime after booting when the 'ifconfig' program is run. + * + * This routine should set everything up anew at each open, even + * registers that "should" only need to be set once at boot, so that + * there is non-reboot way to recover if something goes wrong. + */ + +static int +lec_open(struct net_device *dev) +{ + struct lec_priv *priv = (struct lec_priv *)dev->priv; + + netif_start_queue(dev); + memset(&priv->stats,0,sizeof(struct net_device_stats)); + + return 0; +} + +static __inline__ void +lec_send(struct atm_vcc *vcc, struct sk_buff *skb, struct lec_priv *priv) +{ + ATM_SKB(skb)->vcc = vcc; + ATM_SKB(skb)->atm_options = vcc->atm_options; + + atomic_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + if (vcc->send(vcc, skb) < 0) { + priv->stats.tx_dropped++; + return; + } + + priv->stats.tx_packets++; + priv->stats.tx_bytes += skb->len; +} + +static void +lec_tx_timeout(struct net_device *dev) +{ + printk(KERN_INFO "%s: tx timeout\n", dev->name); + dev->trans_start = jiffies; + netif_wake_queue(dev); +} + +static int +lec_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct sk_buff *skb2; + struct lec_priv *priv = (struct lec_priv *)dev->priv; + struct lecdatahdr_8023 *lec_h; + struct atm_vcc *vcc; + struct lec_arp_table *entry; + unsigned char *dst; + int min_frame_size; +#ifdef CONFIG_TR + unsigned char rdesc[ETH_ALEN]; /* Token Ring route descriptor */ +#endif + int is_rdesc; +#if DUMP_PACKETS > 0 + char buf[300]; + int i=0; +#endif /* DUMP_PACKETS >0 */ + + DPRINTK("lec_start_xmit called\n"); + if (!priv->lecd) { + printk("%s:No lecd attached\n",dev->name); + priv->stats.tx_errors++; + netif_stop_queue(dev); + return -EUNATCH; + } + + DPRINTK("skbuff head:%lx data:%lx tail:%lx end:%lx\n", + (long)skb->head, (long)skb->data, (long)skb->tail, + (long)skb->end); +#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) + if (memcmp(skb->data, bridge_ula_lec, sizeof(bridge_ula_lec)) == 0) + lec_handle_bridge(skb, dev); +#endif + + /* Make sure we have room for lec_id */ + if (skb_headroom(skb) < 2) { + + DPRINTK("lec_start_xmit: reallocating skb\n"); + skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); + kfree_skb(skb); + if (skb2 == NULL) return 0; + skb = skb2; + } + skb_push(skb, 2); + + /* Put le header to place, works for TokenRing too */ + lec_h = (struct lecdatahdr_8023*)skb->data; + lec_h->le_header = htons(priv->lecid); + +#ifdef CONFIG_TR + /* Ugly. Use this to realign Token Ring packets for + * e.g. PCA-200E driver. */ + if (priv->is_trdev) { + skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); + kfree_skb(skb); + if (skb2 == NULL) return 0; + skb = skb2; + } +#endif + +#if DUMP_PACKETS > 0 + printk("%s: send datalen:%ld lecid:%4.4x\n", dev->name, + skb->len, priv->lecid); +#if DUMP_PACKETS >= 2 + for(i=0;i<skb->len && i <99;i++) { + sprintf(buf+i*3,"%2.2x ",0xff&skb->data[i]); + } +#elif DUMP_PACKETS >= 1 + for(i=0;i<skb->len && i < 30;i++) { + sprintf(buf+i*3,"%2.2x ", 0xff&skb->data[i]); + } +#endif /* DUMP_PACKETS >= 1 */ + if (i==skb->len) + printk("%s\n",buf); + else + printk("%s...\n",buf); +#endif /* DUMP_PACKETS > 0 */ + + /* Minimum ethernet-frame size */ +#ifdef CONFIG_TR + if (priv->is_trdev) + min_frame_size = LEC_MINIMUM_8025_SIZE; + else +#endif + min_frame_size = LEC_MINIMUM_8023_SIZE; + if (skb->len < min_frame_size) { + if ((skb->len + skb_tailroom(skb)) < min_frame_size) { + skb2 = skb_copy_expand(skb, 0, + min_frame_size - skb->truesize, GFP_ATOMIC); + dev_kfree_skb(skb); + if (skb2 == NULL) { + priv->stats.tx_dropped++; + return 0; + } + skb = skb2; + } + skb_put(skb, min_frame_size - skb->len); + } + + /* Send to right vcc */ + is_rdesc = 0; + dst = lec_h->h_dest; +#ifdef CONFIG_TR + if (priv->is_trdev) { + dst = get_tr_dst(skb->data+2, rdesc); + if (dst == NULL) { + dst = rdesc; + is_rdesc = 1; + } + } +#endif + entry = NULL; + vcc = lec_arp_resolve(priv, dst, is_rdesc, &entry); + DPRINTK("%s:vcc:%p vcc_flags:%x, entry:%p\n", dev->name, + vcc, vcc?vcc->flags:0, entry); + if (!vcc || !test_bit(ATM_VF_READY,&vcc->flags)) { + if (entry && (entry->tx_wait.qlen < LEC_UNRES_QUE_LEN)) { + DPRINTK("%s:lec_start_xmit: queuing packet, ", dev->name); + DPRINTK("MAC address 0x%02x:%02x:%02x:%02x:%02x:%02x\n", + lec_h->h_dest[0], lec_h->h_dest[1], lec_h->h_dest[2], + lec_h->h_dest[3], lec_h->h_dest[4], lec_h->h_dest[5]); + skb_queue_tail(&entry->tx_wait, skb); + } else { + DPRINTK("%s:lec_start_xmit: tx queue full or no arp entry, dropping, ", dev->name); + DPRINTK("MAC address 0x%02x:%02x:%02x:%02x:%02x:%02x\n", + lec_h->h_dest[0], lec_h->h_dest[1], lec_h->h_dest[2], + lec_h->h_dest[3], lec_h->h_dest[4], lec_h->h_dest[5]); + priv->stats.tx_dropped++; + dev_kfree_skb(skb); + } + return 0; + } + +#if DUMP_PACKETS > 0 + printk("%s:sending to vpi:%d vci:%d\n", dev->name, + vcc->vpi, vcc->vci); +#endif /* DUMP_PACKETS > 0 */ + + while (entry && (skb2 = skb_dequeue(&entry->tx_wait))) { + DPRINTK("lec.c: emptying tx queue, "); + DPRINTK("MAC address 0x%02x:%02x:%02x:%02x:%02x:%02x\n", + lec_h->h_dest[0], lec_h->h_dest[1], lec_h->h_dest[2], + lec_h->h_dest[3], lec_h->h_dest[4], lec_h->h_dest[5]); + lec_send(vcc, skb2, priv); + } + + lec_send(vcc, skb, priv); + + if (!atm_may_send(vcc, 0)) { + struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); + + vpriv->xoff = 1; + netif_stop_queue(dev); + + /* + * vcc->pop() might have occurred in between, making + * the vcc usuable again. Since xmit is serialized, + * this is the only situation we have to re-test. + */ + + if (atm_may_send(vcc, 0)) + netif_wake_queue(dev); + } + + dev->trans_start = jiffies; + return 0; +} + +/* The inverse routine to net_open(). */ +static int +lec_close(struct net_device *dev) +{ + netif_stop_queue(dev); + return 0; +} + +/* + * Get the current statistics. + * This may be called with the card open or closed. + */ +static struct net_device_stats * +lec_get_stats(struct net_device *dev) +{ + return &((struct lec_priv *)dev->priv)->stats; +} + +static int +lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) +{ + unsigned long flags; + struct net_device *dev = (struct net_device*)vcc->proto_data; + struct lec_priv *priv = (struct lec_priv*)dev->priv; + struct atmlec_msg *mesg; + struct lec_arp_table *entry; + int i; + char *tmp; /* FIXME */ + + atomic_sub(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + mesg = (struct atmlec_msg *)skb->data; + tmp = skb->data; + tmp += sizeof(struct atmlec_msg); + DPRINTK("%s: msg from zeppelin:%d\n", dev->name, mesg->type); + switch(mesg->type) { + case l_set_mac_addr: + for (i=0;i<6;i++) { + dev->dev_addr[i] = mesg->content.normal.mac_addr[i]; + } + break; + case l_del_mac_addr: + for(i=0;i<6;i++) { + dev->dev_addr[i] = 0; + } + break; + case l_addr_delete: + lec_addr_delete(priv, mesg->content.normal.atm_addr, + mesg->content.normal.flag); + break; + case l_topology_change: + priv->topology_change = mesg->content.normal.flag; + break; + case l_flush_complete: + lec_flush_complete(priv, mesg->content.normal.flag); + break; + case l_narp_req: /* LANE2: see 7.1.35 in the lane2 spec */ + spin_lock_irqsave(&priv->lec_arp_lock, flags); + entry = lec_arp_find(priv, mesg->content.normal.mac_addr); + lec_arp_remove(priv, entry); + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + + if (mesg->content.normal.no_source_le_narp) + break; + /* FALL THROUGH */ + case l_arp_update: + lec_arp_update(priv, mesg->content.normal.mac_addr, + mesg->content.normal.atm_addr, + mesg->content.normal.flag, + mesg->content.normal.targetless_le_arp); + DPRINTK("lec: in l_arp_update\n"); + if (mesg->sizeoftlvs != 0) { /* LANE2 3.1.5 */ + DPRINTK("lec: LANE2 3.1.5, got tlvs, size %d\n", mesg->sizeoftlvs); + lane2_associate_ind(dev, + mesg->content.normal.mac_addr, + tmp, mesg->sizeoftlvs); + } + break; + case l_config: + priv->maximum_unknown_frame_count = + mesg->content.config.maximum_unknown_frame_count; + priv->max_unknown_frame_time = + (mesg->content.config.max_unknown_frame_time*HZ); + priv->max_retry_count = + mesg->content.config.max_retry_count; + priv->aging_time = (mesg->content.config.aging_time*HZ); + priv->forward_delay_time = + (mesg->content.config.forward_delay_time*HZ); + priv->arp_response_time = + (mesg->content.config.arp_response_time*HZ); + priv->flush_timeout = (mesg->content.config.flush_timeout*HZ); + priv->path_switching_delay = + (mesg->content.config.path_switching_delay*HZ); + priv->lane_version = mesg->content.config.lane_version; /* LANE2 */ + priv->lane2_ops = NULL; + if (priv->lane_version > 1) + priv->lane2_ops = &lane2_ops; + if (dev->change_mtu(dev, mesg->content.config.mtu)) + printk("%s: change_mtu to %d failed\n", dev->name, + mesg->content.config.mtu); + priv->is_proxy = mesg->content.config.is_proxy; + break; + case l_flush_tran_id: + lec_set_flush_tran_id(priv, mesg->content.normal.atm_addr, + mesg->content.normal.flag); + break; + case l_set_lecid: + priv->lecid=(unsigned short)(0xffff&mesg->content.normal.flag); + break; + case l_should_bridge: { +#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) + struct net_bridge_fdb_entry *f; + + DPRINTK("%s: bridge zeppelin asks about 0x%02x:%02x:%02x:%02x:%02x:%02x\n", + dev->name, + mesg->content.proxy.mac_addr[0], mesg->content.proxy.mac_addr[1], + mesg->content.proxy.mac_addr[2], mesg->content.proxy.mac_addr[3], + mesg->content.proxy.mac_addr[4], mesg->content.proxy.mac_addr[5]); + + if (br_fdb_get_hook == NULL || dev->br_port == NULL) + break; + + f = br_fdb_get_hook(dev->br_port->br, mesg->content.proxy.mac_addr); + if (f != NULL && + f->dst->dev != dev && + f->dst->state == BR_STATE_FORWARDING) { + /* hit from bridge table, send LE_ARP_RESPONSE */ + struct sk_buff *skb2; + struct sock *sk; + + DPRINTK("%s: entry found, responding to zeppelin\n", dev->name); + skb2 = alloc_skb(sizeof(struct atmlec_msg), GFP_ATOMIC); + if (skb2 == NULL) { + br_fdb_put_hook(f); + break; + } + skb2->len = sizeof(struct atmlec_msg); + memcpy(skb2->data, mesg, sizeof(struct atmlec_msg)); + atm_force_charge(priv->lecd, skb2->truesize); + sk = sk_atm(priv->lecd); + skb_queue_tail(&sk->sk_receive_queue, skb2); + sk->sk_data_ready(sk, skb2->len); + } + if (f != NULL) br_fdb_put_hook(f); +#endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ + } + break; + default: + printk("%s: Unknown message type %d\n", dev->name, mesg->type); + dev_kfree_skb(skb); + return -EINVAL; + } + dev_kfree_skb(skb); + return 0; +} + +static void +lec_atm_close(struct atm_vcc *vcc) +{ + struct sk_buff *skb; + struct net_device *dev = (struct net_device *)vcc->proto_data; + struct lec_priv *priv = (struct lec_priv *)dev->priv; + + priv->lecd = NULL; + /* Do something needful? */ + + netif_stop_queue(dev); + lec_arp_destroy(priv); + + if (skb_peek(&sk_atm(vcc)->sk_receive_queue)) + printk("%s lec_atm_close: closing with messages pending\n", + dev->name); + while ((skb = skb_dequeue(&sk_atm(vcc)->sk_receive_queue)) != NULL) { + atm_return(vcc, skb->truesize); + dev_kfree_skb(skb); + } + + printk("%s: Shut down!\n", dev->name); + module_put(THIS_MODULE); +} + +static struct atmdev_ops lecdev_ops = { + .close = lec_atm_close, + .send = lec_atm_send +}; + +static struct atm_dev lecatm_dev = { + .ops = &lecdev_ops, + .type = "lec", + .number = 999, /* dummy device number */ + .lock = SPIN_LOCK_UNLOCKED +}; + +/* + * LANE2: new argument struct sk_buff *data contains + * the LE_ARP based TLVs introduced in the LANE2 spec + */ +static int +send_to_lecd(struct lec_priv *priv, atmlec_msg_type type, + unsigned char *mac_addr, unsigned char *atm_addr, + struct sk_buff *data) +{ + struct sock *sk; + struct sk_buff *skb; + struct atmlec_msg *mesg; + + if (!priv || !priv->lecd) { + return -1; + } + skb = alloc_skb(sizeof(struct atmlec_msg), GFP_ATOMIC); + if (!skb) + return -1; + skb->len = sizeof(struct atmlec_msg); + mesg = (struct atmlec_msg *)skb->data; + memset(mesg, 0, sizeof(struct atmlec_msg)); + mesg->type = type; + if (data != NULL) + mesg->sizeoftlvs = data->len; + if (mac_addr) + memcpy(&mesg->content.normal.mac_addr, mac_addr, ETH_ALEN); + else + mesg->content.normal.targetless_le_arp = 1; + if (atm_addr) + memcpy(&mesg->content.normal.atm_addr, atm_addr, ATM_ESA_LEN); + + atm_force_charge(priv->lecd, skb->truesize); + sk = sk_atm(priv->lecd); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); + + if (data != NULL) { + DPRINTK("lec: about to send %d bytes of data\n", data->len); + atm_force_charge(priv->lecd, data->truesize); + skb_queue_tail(&sk->sk_receive_queue, data); + sk->sk_data_ready(sk, skb->len); + } + + return 0; +} + +/* shamelessly stolen from drivers/net/net_init.c */ +static int lec_change_mtu(struct net_device *dev, int new_mtu) +{ + if ((new_mtu < 68) || (new_mtu > 18190)) + return -EINVAL; + dev->mtu = new_mtu; + return 0; +} + +static void lec_set_multicast_list(struct net_device *dev) +{ + /* by default, all multicast frames arrive over the bus. + * eventually support selective multicast service + */ + return; +} + +static void +lec_init(struct net_device *dev) +{ + dev->change_mtu = lec_change_mtu; + dev->open = lec_open; + dev->stop = lec_close; + dev->hard_start_xmit = lec_start_xmit; + dev->tx_timeout = lec_tx_timeout; + + dev->get_stats = lec_get_stats; + dev->set_multicast_list = lec_set_multicast_list; + dev->do_ioctl = NULL; + printk("%s: Initialized!\n",dev->name); + return; +} + +static unsigned char lec_ctrl_magic[] = { + 0xff, + 0x00, + 0x01, + 0x01 }; + +static void +lec_push(struct atm_vcc *vcc, struct sk_buff *skb) +{ + struct net_device *dev = (struct net_device *)vcc->proto_data; + struct lec_priv *priv = (struct lec_priv *)dev->priv; + +#if DUMP_PACKETS >0 + int i=0; + char buf[300]; + + printk("%s: lec_push vcc vpi:%d vci:%d\n", dev->name, + vcc->vpi, vcc->vci); +#endif + if (!skb) { + DPRINTK("%s: null skb\n",dev->name); + lec_vcc_close(priv, vcc); + return; + } +#if DUMP_PACKETS > 0 + printk("%s: rcv datalen:%ld lecid:%4.4x\n", dev->name, + skb->len, priv->lecid); +#if DUMP_PACKETS >= 2 + for(i=0;i<skb->len && i <99;i++) { + sprintf(buf+i*3,"%2.2x ",0xff&skb->data[i]); + } +#elif DUMP_PACKETS >= 1 + for(i=0;i<skb->len && i < 30;i++) { + sprintf(buf+i*3,"%2.2x ", 0xff&skb->data[i]); + } +#endif /* DUMP_PACKETS >= 1 */ + if (i==skb->len) + printk("%s\n",buf); + else + printk("%s...\n",buf); +#endif /* DUMP_PACKETS > 0 */ + if (memcmp(skb->data, lec_ctrl_magic, 4) ==0) { /* Control frame, to daemon*/ + struct sock *sk = sk_atm(vcc); + + DPRINTK("%s: To daemon\n",dev->name); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); + } else { /* Data frame, queue to protocol handlers */ + unsigned char *dst; + + atm_return(vcc,skb->truesize); + if (*(uint16_t *)skb->data == htons(priv->lecid) || + !priv->lecd || + !(dev->flags & IFF_UP)) { + /* Probably looping back, or if lecd is missing, + lecd has gone down */ + DPRINTK("Ignoring frame...\n"); + dev_kfree_skb(skb); + return; + } +#ifdef CONFIG_TR + if (priv->is_trdev) dst = ((struct lecdatahdr_8025 *)skb->data)->h_dest; + else +#endif + dst = ((struct lecdatahdr_8023 *)skb->data)->h_dest; + + if (!(dst[0]&0x01) && /* Never filter Multi/Broadcast */ + !priv->is_proxy && /* Proxy wants all the packets */ + memcmp(dst, dev->dev_addr, dev->addr_len)) { + dev_kfree_skb(skb); + return; + } + if (priv->lec_arp_empty_ones) { + lec_arp_check_empties(priv, vcc, skb); + } + skb->dev = dev; + skb_pull(skb, 2); /* skip lec_id */ +#ifdef CONFIG_TR + if (priv->is_trdev) skb->protocol = tr_type_trans(skb, dev); + else +#endif + skb->protocol = eth_type_trans(skb, dev); + priv->stats.rx_packets++; + priv->stats.rx_bytes += skb->len; + memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data)); + netif_rx(skb); + } +} + +static void +lec_pop(struct atm_vcc *vcc, struct sk_buff *skb) +{ + struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); + struct net_device *dev = skb->dev; + + if (vpriv == NULL) { + printk("lec_pop(): vpriv = NULL!?!?!?\n"); + return; + } + + vpriv->old_pop(vcc, skb); + + if (vpriv->xoff && atm_may_send(vcc, 0)) { + vpriv->xoff = 0; + if (netif_running(dev) && netif_queue_stopped(dev)) + netif_wake_queue(dev); + } +} + +static int +lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) +{ + struct lec_vcc_priv *vpriv; + int bytes_left; + struct atmlec_ioc ioc_data; + + /* Lecd must be up in this case */ + bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc)); + if (bytes_left != 0) { + printk("lec: lec_vcc_attach, copy from user failed for %d bytes\n", + bytes_left); + } + if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF || + !dev_lec[ioc_data.dev_num]) + return -EINVAL; + if (!(vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL))) + return -ENOMEM; + vpriv->xoff = 0; + vpriv->old_pop = vcc->pop; + vcc->user_back = vpriv; + vcc->pop = lec_pop; + lec_vcc_added(dev_lec[ioc_data.dev_num]->priv, + &ioc_data, vcc, vcc->push); + vcc->proto_data = dev_lec[ioc_data.dev_num]; + vcc->push = lec_push; + return 0; +} + +static int +lec_mcast_attach(struct atm_vcc *vcc, int arg) +{ + if (arg <0 || arg >= MAX_LEC_ITF || !dev_lec[arg]) + return -EINVAL; + vcc->proto_data = dev_lec[arg]; + return (lec_mcast_make((struct lec_priv*)dev_lec[arg]->priv, vcc)); +} + +/* Initialize device. */ +static int +lecd_attach(struct atm_vcc *vcc, int arg) +{ + int i; + struct lec_priv *priv; + + if (arg<0) + i = 0; + else + i = arg; +#ifdef CONFIG_TR + if (arg >= MAX_LEC_ITF) + return -EINVAL; +#else /* Reserve the top NUM_TR_DEVS for TR */ + if (arg >= (MAX_LEC_ITF-NUM_TR_DEVS)) + return -EINVAL; +#endif + if (!dev_lec[i]) { + int is_trdev, size; + + is_trdev = 0; + if (i >= (MAX_LEC_ITF - NUM_TR_DEVS)) + is_trdev = 1; + + size = sizeof(struct lec_priv); +#ifdef CONFIG_TR + if (is_trdev) + dev_lec[i] = alloc_trdev(size); + else +#endif + dev_lec[i] = alloc_etherdev(size); + if (!dev_lec[i]) + return -ENOMEM; + snprintf(dev_lec[i]->name, IFNAMSIZ, "lec%d", i); + if (register_netdev(dev_lec[i])) { + free_netdev(dev_lec[i]); + return -EINVAL; + } + + priv = dev_lec[i]->priv; + priv->is_trdev = is_trdev; + lec_init(dev_lec[i]); + } else { + priv = dev_lec[i]->priv; + if (priv->lecd) + return -EADDRINUSE; + } + lec_arp_init(priv); + priv->itfnum = i; /* LANE2 addition */ + priv->lecd = vcc; + vcc->dev = &lecatm_dev; + vcc_insert_socket(sk_atm(vcc)); + + vcc->proto_data = dev_lec[i]; + set_bit(ATM_VF_META,&vcc->flags); + set_bit(ATM_VF_READY,&vcc->flags); + + /* Set default values to these variables */ + priv->maximum_unknown_frame_count = 1; + priv->max_unknown_frame_time = (1*HZ); + priv->vcc_timeout_period = (1200*HZ); + priv->max_retry_count = 1; + priv->aging_time = (300*HZ); + priv->forward_delay_time = (15*HZ); + priv->topology_change = 0; + priv->arp_response_time = (1*HZ); + priv->flush_timeout = (4*HZ); + priv->path_switching_delay = (6*HZ); + + if (dev_lec[i]->flags & IFF_UP) { + netif_start_queue(dev_lec[i]); + } + __module_get(THIS_MODULE); + return i; +} + +#ifdef CONFIG_PROC_FS +static char* lec_arp_get_status_string(unsigned char status) +{ + static char *lec_arp_status_string[] = { + "ESI_UNKNOWN ", + "ESI_ARP_PENDING ", + "ESI_VC_PENDING ", + "<Undefined> ", + "ESI_FLUSH_PENDING ", + "ESI_FORWARD_DIRECT" + }; + + if (status > ESI_FORWARD_DIRECT) + status = 3; /* ESI_UNDEFINED */ + return lec_arp_status_string[status]; +} + +static void lec_info(struct seq_file *seq, struct lec_arp_table *entry) +{ + int i; + + for (i = 0; i < ETH_ALEN; i++) + seq_printf(seq, "%2.2x", entry->mac_addr[i] & 0xff); + seq_printf(seq, " "); + for (i = 0; i < ATM_ESA_LEN; i++) + seq_printf(seq, "%2.2x", entry->atm_addr[i] & 0xff); + seq_printf(seq, " %s %4.4x", lec_arp_get_status_string(entry->status), + entry->flags & 0xffff); + if (entry->vcc) + seq_printf(seq, "%3d %3d ", entry->vcc->vpi, entry->vcc->vci); + else + seq_printf(seq, " "); + if (entry->recv_vcc) { + seq_printf(seq, " %3d %3d", entry->recv_vcc->vpi, + entry->recv_vcc->vci); + } + seq_putc(seq, '\n'); +} + + +struct lec_state { + unsigned long flags; + struct lec_priv *locked; + struct lec_arp_table *entry; + struct net_device *dev; + int itf; + int arp_table; + int misc_table; +}; + +static void *lec_tbl_walk(struct lec_state *state, struct lec_arp_table *tbl, + loff_t *l) +{ + struct lec_arp_table *e = state->entry; + + if (!e) + e = tbl; + if (e == (void *)1) { + e = tbl; + --*l; + } + for (; e; e = e->next) { + if (--*l < 0) + break; + } + state->entry = e; + return (*l < 0) ? state : NULL; +} + +static void *lec_arp_walk(struct lec_state *state, loff_t *l, + struct lec_priv *priv) +{ + void *v = NULL; + int p; + + for (p = state->arp_table; p < LEC_ARP_TABLE_SIZE; p++) { + v = lec_tbl_walk(state, priv->lec_arp_tables[p], l); + if (v) + break; + } + state->arp_table = p; + return v; +} + +static void *lec_misc_walk(struct lec_state *state, loff_t *l, + struct lec_priv *priv) +{ + struct lec_arp_table *lec_misc_tables[] = { + priv->lec_arp_empty_ones, + priv->lec_no_forward, + priv->mcast_fwds + }; + void *v = NULL; + int q; + + for (q = state->misc_table; q < ARRAY_SIZE(lec_misc_tables); q++) { + v = lec_tbl_walk(state, lec_misc_tables[q], l); + if (v) + break; + } + state->misc_table = q; + return v; +} + +static void *lec_priv_walk(struct lec_state *state, loff_t *l, + struct lec_priv *priv) +{ + if (!state->locked) { + state->locked = priv; + spin_lock_irqsave(&priv->lec_arp_lock, state->flags); + } + if (!lec_arp_walk(state, l, priv) && + !lec_misc_walk(state, l, priv)) { + spin_unlock_irqrestore(&priv->lec_arp_lock, state->flags); + state->locked = NULL; + /* Partial state reset for the next time we get called */ + state->arp_table = state->misc_table = 0; + } + return state->locked; +} + +static void *lec_itf_walk(struct lec_state *state, loff_t *l) +{ + struct net_device *dev; + void *v; + + dev = state->dev ? state->dev : dev_lec[state->itf]; + v = (dev && dev->priv) ? lec_priv_walk(state, l, dev->priv) : NULL; + if (!v && dev) { + dev_put(dev); + /* Partial state reset for the next time we get called */ + dev = NULL; + } + state->dev = dev; + return v; +} + +static void *lec_get_idx(struct lec_state *state, loff_t l) +{ + void *v = NULL; + + for (; state->itf < MAX_LEC_ITF; state->itf++) { + v = lec_itf_walk(state, &l); + if (v) + break; + } + return v; +} + +static void *lec_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct lec_state *state = seq->private; + + state->itf = 0; + state->dev = NULL; + state->locked = NULL; + state->arp_table = 0; + state->misc_table = 0; + state->entry = (void *)1; + + return *pos ? lec_get_idx(state, *pos) : (void*)1; +} + +static void lec_seq_stop(struct seq_file *seq, void *v) +{ + struct lec_state *state = seq->private; + + if (state->dev) { + spin_unlock_irqrestore(&state->locked->lec_arp_lock, + state->flags); + dev_put(state->dev); + } +} + +static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct lec_state *state = seq->private; + + v = lec_get_idx(state, 1); + *pos += !!PTR_ERR(v); + return v; +} + +static int lec_seq_show(struct seq_file *seq, void *v) +{ + static char lec_banner[] = "Itf MAC ATM destination" + " Status Flags " + "VPI/VCI Recv VPI/VCI\n"; + + if (v == (void *)1) + seq_puts(seq, lec_banner); + else { + struct lec_state *state = seq->private; + struct net_device *dev = state->dev; + + seq_printf(seq, "%s ", dev->name); + lec_info(seq, state->entry); + } + return 0; +} + +static struct seq_operations lec_seq_ops = { + .start = lec_seq_start, + .next = lec_seq_next, + .stop = lec_seq_stop, + .show = lec_seq_show, +}; + +static int lec_seq_open(struct inode *inode, struct file *file) +{ + struct lec_state *state; + struct seq_file *seq; + int rc = -EAGAIN; + + state = kmalloc(sizeof(*state), GFP_KERNEL); + if (!state) { + rc = -ENOMEM; + goto out; + } + + rc = seq_open(file, &lec_seq_ops); + if (rc) + goto out_kfree; + seq = file->private_data; + seq->private = state; +out: + return rc; + +out_kfree: + kfree(state); + goto out; +} + +static int lec_seq_release(struct inode *inode, struct file *file) +{ + return seq_release_private(inode, file); +} + +static struct file_operations lec_seq_fops = { + .owner = THIS_MODULE, + .open = lec_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = lec_seq_release, +}; +#endif + +static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + struct atm_vcc *vcc = ATM_SD(sock); + int err = 0; + + switch (cmd) { + case ATMLEC_CTRL: + case ATMLEC_MCAST: + case ATMLEC_DATA: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + break; + default: + return -ENOIOCTLCMD; + } + + switch (cmd) { + case ATMLEC_CTRL: + err = lecd_attach(vcc, (int) arg); + if (err >= 0) + sock->state = SS_CONNECTED; + break; + case ATMLEC_MCAST: + err = lec_mcast_attach(vcc, (int) arg); + break; + case ATMLEC_DATA: + err = lec_vcc_attach(vcc, (void __user *) arg); + break; + } + + return err; +} + +static struct atm_ioctl lane_ioctl_ops = { + .owner = THIS_MODULE, + .ioctl = lane_ioctl, +}; + +static int __init lane_module_init(void) +{ +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *p; + + p = create_proc_entry("lec", S_IRUGO, atm_proc_root); + if (p) + p->proc_fops = &lec_seq_fops; +#endif + + register_atm_ioctl(&lane_ioctl_ops); + printk("lec.c: " __DATE__ " " __TIME__ " initialized\n"); + return 0; +} + +static void __exit lane_module_cleanup(void) +{ + int i; + struct lec_priv *priv; + + remove_proc_entry("lec", atm_proc_root); + + deregister_atm_ioctl(&lane_ioctl_ops); + + for (i = 0; i < MAX_LEC_ITF; i++) { + if (dev_lec[i] != NULL) { + priv = (struct lec_priv *)dev_lec[i]->priv; + unregister_netdev(dev_lec[i]); + free_netdev(dev_lec[i]); + dev_lec[i] = NULL; + } + } + + return; +} + +module_init(lane_module_init); +module_exit(lane_module_cleanup); + +/* + * LANE2: 3.1.3, LE_RESOLVE.request + * Non force allocates memory and fills in *tlvs, fills in *sizeoftlvs. + * If sizeoftlvs == NULL the default TLVs associated with with this + * lec will be used. + * If dst_mac == NULL, targetless LE_ARP will be sent + */ +static int lane2_resolve(struct net_device *dev, u8 *dst_mac, int force, + u8 **tlvs, u32 *sizeoftlvs) +{ + unsigned long flags; + struct lec_priv *priv = (struct lec_priv *)dev->priv; + struct lec_arp_table *table; + struct sk_buff *skb; + int retval; + + if (force == 0) { + spin_lock_irqsave(&priv->lec_arp_lock, flags); + table = lec_arp_find(priv, dst_mac); + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + if(table == NULL) + return -1; + + *tlvs = kmalloc(table->sizeoftlvs, GFP_ATOMIC); + if (*tlvs == NULL) + return -1; + + memcpy(*tlvs, table->tlvs, table->sizeoftlvs); + *sizeoftlvs = table->sizeoftlvs; + + return 0; + } + + if (sizeoftlvs == NULL) + retval = send_to_lecd(priv, l_arp_xmt, dst_mac, NULL, NULL); + + else { + skb = alloc_skb(*sizeoftlvs, GFP_ATOMIC); + if (skb == NULL) + return -1; + skb->len = *sizeoftlvs; + memcpy(skb->data, *tlvs, *sizeoftlvs); + retval = send_to_lecd(priv, l_arp_xmt, dst_mac, NULL, skb); + } + return retval; +} + + +/* + * LANE2: 3.1.4, LE_ASSOCIATE.request + * Associate the *tlvs with the *lan_dst address. + * Will overwrite any previous association + * Returns 1 for success, 0 for failure (out of memory) + * + */ +static int lane2_associate_req (struct net_device *dev, u8 *lan_dst, + u8 *tlvs, u32 sizeoftlvs) +{ + int retval; + struct sk_buff *skb; + struct lec_priv *priv = (struct lec_priv*)dev->priv; + + if ( memcmp(lan_dst, dev->dev_addr, ETH_ALEN) != 0 ) + return (0); /* not our mac address */ + + kfree(priv->tlvs); /* NULL if there was no previous association */ + + priv->tlvs = kmalloc(sizeoftlvs, GFP_KERNEL); + if (priv->tlvs == NULL) + return (0); + priv->sizeoftlvs = sizeoftlvs; + memcpy(priv->tlvs, tlvs, sizeoftlvs); + + skb = alloc_skb(sizeoftlvs, GFP_ATOMIC); + if (skb == NULL) + return 0; + skb->len = sizeoftlvs; + memcpy(skb->data, tlvs, sizeoftlvs); + retval = send_to_lecd(priv, l_associate_req, NULL, NULL, skb); + if (retval != 0) + printk("lec.c: lane2_associate_req() failed\n"); + /* If the previous association has changed we must + * somehow notify other LANE entities about the change + */ + return (1); +} + +/* + * LANE2: 3.1.5, LE_ASSOCIATE.indication + * + */ +static void lane2_associate_ind (struct net_device *dev, u8 *mac_addr, + u8 *tlvs, u32 sizeoftlvs) +{ +#if 0 + int i = 0; +#endif + struct lec_priv *priv = (struct lec_priv *)dev->priv; +#if 0 /* Why have the TLVs in LE_ARP entries since we do not use them? When you + uncomment this code, make sure the TLVs get freed when entry is killed */ + struct lec_arp_table *entry = lec_arp_find(priv, mac_addr); + + if (entry == NULL) + return; /* should not happen */ + + kfree(entry->tlvs); + + entry->tlvs = kmalloc(sizeoftlvs, GFP_KERNEL); + if (entry->tlvs == NULL) + return; + + entry->sizeoftlvs = sizeoftlvs; + memcpy(entry->tlvs, tlvs, sizeoftlvs); +#endif +#if 0 + printk("lec.c: lane2_associate_ind()\n"); + printk("dump of tlvs, sizeoftlvs=%d\n", sizeoftlvs); + while (i < sizeoftlvs) + printk("%02x ", tlvs[i++]); + + printk("\n"); +#endif + + /* tell MPOA about the TLVs we saw */ + if (priv->lane2_ops && priv->lane2_ops->associate_indicator) { + priv->lane2_ops->associate_indicator(dev, mac_addr, + tlvs, sizeoftlvs); + } + return; +} + +/* + * Here starts what used to lec_arpc.c + * + * lec_arpc.c was added here when making + * lane client modular. October 1997 + * + */ + +#include <linux/types.h> +#include <linux/sched.h> +#include <linux/timer.h> +#include <asm/param.h> +#include <asm/atomic.h> +#include <linux/inetdevice.h> +#include <net/route.h> + + +#if 0 +#define DPRINTK(format,args...) +/* +#define DPRINTK printk +*/ +#endif +#define DEBUG_ARP_TABLE 0 + +#define LEC_ARP_REFRESH_INTERVAL (3*HZ) + +static void lec_arp_check_expire(unsigned long data); +static void lec_arp_expire_arp(unsigned long data); + +/* + * Arp table funcs + */ + +#define HASH(ch) (ch & (LEC_ARP_TABLE_SIZE -1)) + +/* + * Initialization of arp-cache + */ +static void +lec_arp_init(struct lec_priv *priv) +{ + unsigned short i; + + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + priv->lec_arp_tables[i] = NULL; + } + spin_lock_init(&priv->lec_arp_lock); + init_timer(&priv->lec_arp_timer); + priv->lec_arp_timer.expires = jiffies + LEC_ARP_REFRESH_INTERVAL; + priv->lec_arp_timer.data = (unsigned long)priv; + priv->lec_arp_timer.function = lec_arp_check_expire; + add_timer(&priv->lec_arp_timer); +} + +static void +lec_arp_clear_vccs(struct lec_arp_table *entry) +{ + if (entry->vcc) { + struct atm_vcc *vcc = entry->vcc; + struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); + struct net_device *dev = (struct net_device*) vcc->proto_data; + + vcc->pop = vpriv->old_pop; + if (vpriv->xoff) + netif_wake_queue(dev); + kfree(vpriv); + vcc->user_back = NULL; + vcc->push = entry->old_push; + vcc_release_async(vcc, -EPIPE); + vcc = NULL; + } + if (entry->recv_vcc) { + entry->recv_vcc->push = entry->old_recv_push; + vcc_release_async(entry->recv_vcc, -EPIPE); + entry->recv_vcc = NULL; + } +} + +/* + * Insert entry to lec_arp_table + * LANE2: Add to the end of the list to satisfy 8.1.13 + */ +static inline void +lec_arp_add(struct lec_priv *priv, struct lec_arp_table *to_add) +{ + unsigned short place; + struct lec_arp_table *tmp; + + place = HASH(to_add->mac_addr[ETH_ALEN-1]); + tmp = priv->lec_arp_tables[place]; + to_add->next = NULL; + if (tmp == NULL) + priv->lec_arp_tables[place] = to_add; + + else { /* add to the end */ + while (tmp->next) + tmp = tmp->next; + tmp->next = to_add; + } + + DPRINTK("LEC_ARP: Added entry:%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", + 0xff&to_add->mac_addr[0], 0xff&to_add->mac_addr[1], + 0xff&to_add->mac_addr[2], 0xff&to_add->mac_addr[3], + 0xff&to_add->mac_addr[4], 0xff&to_add->mac_addr[5]); +} + +/* + * Remove entry from lec_arp_table + */ +static int +lec_arp_remove(struct lec_priv *priv, + struct lec_arp_table *to_remove) +{ + unsigned short place; + struct lec_arp_table *tmp; + int remove_vcc=1; + + if (!to_remove) { + return -1; + } + place = HASH(to_remove->mac_addr[ETH_ALEN-1]); + tmp = priv->lec_arp_tables[place]; + if (tmp == to_remove) { + priv->lec_arp_tables[place] = tmp->next; + } else { + while(tmp && tmp->next != to_remove) { + tmp = tmp->next; + } + if (!tmp) {/* Entry was not found */ + return -1; + } + } + tmp->next = to_remove->next; + del_timer(&to_remove->timer); + + /* If this is the only MAC connected to this VCC, also tear down + the VCC */ + if (to_remove->status >= ESI_FLUSH_PENDING) { + /* + * ESI_FLUSH_PENDING, ESI_FORWARD_DIRECT + */ + for(place = 0; place < LEC_ARP_TABLE_SIZE; place++) { + for(tmp = priv->lec_arp_tables[place]; tmp != NULL; tmp = tmp->next) { + if (memcmp(tmp->atm_addr, to_remove->atm_addr, + ATM_ESA_LEN)==0) { + remove_vcc=0; + break; + } + } + } + if (remove_vcc) + lec_arp_clear_vccs(to_remove); + } + skb_queue_purge(&to_remove->tx_wait); /* FIXME: good place for this? */ + + DPRINTK("LEC_ARP: Removed entry:%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", + 0xff&to_remove->mac_addr[0], 0xff&to_remove->mac_addr[1], + 0xff&to_remove->mac_addr[2], 0xff&to_remove->mac_addr[3], + 0xff&to_remove->mac_addr[4], 0xff&to_remove->mac_addr[5]); + return 0; +} + +#if DEBUG_ARP_TABLE +static char* +get_status_string(unsigned char st) +{ + switch(st) { + case ESI_UNKNOWN: + return "ESI_UNKNOWN"; + case ESI_ARP_PENDING: + return "ESI_ARP_PENDING"; + case ESI_VC_PENDING: + return "ESI_VC_PENDING"; + case ESI_FLUSH_PENDING: + return "ESI_FLUSH_PENDING"; + case ESI_FORWARD_DIRECT: + return "ESI_FORWARD_DIRECT"; + default: + return "<UNKNOWN>"; + } +} +#endif + +static void +dump_arp_table(struct lec_priv *priv) +{ +#if DEBUG_ARP_TABLE + int i,j, offset; + struct lec_arp_table *rulla; + char buf[1024]; + struct lec_arp_table **lec_arp_tables = + (struct lec_arp_table **)priv->lec_arp_tables; + struct lec_arp_table *lec_arp_empty_ones = + (struct lec_arp_table *)priv->lec_arp_empty_ones; + struct lec_arp_table *lec_no_forward = + (struct lec_arp_table *)priv->lec_no_forward; + struct lec_arp_table *mcast_fwds = priv->mcast_fwds; + + + printk("Dump %p:\n",priv); + for (i=0;i<LEC_ARP_TABLE_SIZE;i++) { + rulla = lec_arp_tables[i]; + offset = 0; + offset += sprintf(buf,"%d: %p\n",i, rulla); + while (rulla) { + offset += sprintf(buf+offset,"Mac:"); + for(j=0;j<ETH_ALEN;j++) { + offset+=sprintf(buf+offset, + "%2.2x ", + rulla->mac_addr[j]&0xff); + } + offset +=sprintf(buf+offset,"Atm:"); + for(j=0;j<ATM_ESA_LEN;j++) { + offset+=sprintf(buf+offset, + "%2.2x ", + rulla->atm_addr[j]&0xff); + } + offset+=sprintf(buf+offset, + "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", + rulla->vcc?rulla->vcc->vpi:0, + rulla->vcc?rulla->vcc->vci:0, + rulla->recv_vcc?rulla->recv_vcc->vpi:0, + rulla->recv_vcc?rulla->recv_vcc->vci:0, + rulla->last_used, + rulla->timestamp, rulla->no_tries); + offset+=sprintf(buf+offset, + "Flags:%x, Packets_flooded:%x, Status: %s ", + rulla->flags, rulla->packets_flooded, + get_status_string(rulla->status)); + offset+=sprintf(buf+offset,"->%p\n",rulla->next); + rulla = rulla->next; + } + printk("%s",buf); + } + rulla = lec_no_forward; + if (rulla) + printk("No forward\n"); + while(rulla) { + offset=0; + offset += sprintf(buf+offset,"Mac:"); + for(j=0;j<ETH_ALEN;j++) { + offset+=sprintf(buf+offset,"%2.2x ", + rulla->mac_addr[j]&0xff); + } + offset +=sprintf(buf+offset,"Atm:"); + for(j=0;j<ATM_ESA_LEN;j++) { + offset+=sprintf(buf+offset,"%2.2x ", + rulla->atm_addr[j]&0xff); + } + offset+=sprintf(buf+offset, + "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", + rulla->vcc?rulla->vcc->vpi:0, + rulla->vcc?rulla->vcc->vci:0, + rulla->recv_vcc?rulla->recv_vcc->vpi:0, + rulla->recv_vcc?rulla->recv_vcc->vci:0, + rulla->last_used, + rulla->timestamp, rulla->no_tries); + offset+=sprintf(buf+offset, + "Flags:%x, Packets_flooded:%x, Status: %s ", + rulla->flags, rulla->packets_flooded, + get_status_string(rulla->status)); + offset+=sprintf(buf+offset,"->%lx\n",(long)rulla->next); + rulla = rulla->next; + printk("%s",buf); + } + rulla = lec_arp_empty_ones; + if (rulla) + printk("Empty ones\n"); + while(rulla) { + offset=0; + offset += sprintf(buf+offset,"Mac:"); + for(j=0;j<ETH_ALEN;j++) { + offset+=sprintf(buf+offset,"%2.2x ", + rulla->mac_addr[j]&0xff); + } + offset +=sprintf(buf+offset,"Atm:"); + for(j=0;j<ATM_ESA_LEN;j++) { + offset+=sprintf(buf+offset,"%2.2x ", + rulla->atm_addr[j]&0xff); + } + offset+=sprintf(buf+offset, + "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", + rulla->vcc?rulla->vcc->vpi:0, + rulla->vcc?rulla->vcc->vci:0, + rulla->recv_vcc?rulla->recv_vcc->vpi:0, + rulla->recv_vcc?rulla->recv_vcc->vci:0, + rulla->last_used, + rulla->timestamp, rulla->no_tries); + offset+=sprintf(buf+offset, + "Flags:%x, Packets_flooded:%x, Status: %s ", + rulla->flags, rulla->packets_flooded, + get_status_string(rulla->status)); + offset+=sprintf(buf+offset,"->%lx\n",(long)rulla->next); + rulla = rulla->next; + printk("%s",buf); + } + + rulla = mcast_fwds; + if (rulla) + printk("Multicast Forward VCCs\n"); + while(rulla) { + offset=0; + offset += sprintf(buf+offset,"Mac:"); + for(j=0;j<ETH_ALEN;j++) { + offset+=sprintf(buf+offset,"%2.2x ", + rulla->mac_addr[j]&0xff); + } + offset +=sprintf(buf+offset,"Atm:"); + for(j=0;j<ATM_ESA_LEN;j++) { + offset+=sprintf(buf+offset,"%2.2x ", + rulla->atm_addr[j]&0xff); + } + offset+=sprintf(buf+offset, + "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", + rulla->vcc?rulla->vcc->vpi:0, + rulla->vcc?rulla->vcc->vci:0, + rulla->recv_vcc?rulla->recv_vcc->vpi:0, + rulla->recv_vcc?rulla->recv_vcc->vci:0, + rulla->last_used, + rulla->timestamp, rulla->no_tries); + offset+=sprintf(buf+offset, + "Flags:%x, Packets_flooded:%x, Status: %s ", + rulla->flags, rulla->packets_flooded, + get_status_string(rulla->status)); + offset+=sprintf(buf+offset,"->%lx\n",(long)rulla->next); + rulla = rulla->next; + printk("%s",buf); + } + +#endif +} + +/* + * Destruction of arp-cache + */ +static void +lec_arp_destroy(struct lec_priv *priv) +{ + unsigned long flags; + struct lec_arp_table *entry, *next; + int i; + + del_timer_sync(&priv->lec_arp_timer); + + /* + * Remove all entries + */ + + spin_lock_irqsave(&priv->lec_arp_lock, flags); + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + for(entry = priv->lec_arp_tables[i]; entry != NULL; entry=next) { + next = entry->next; + lec_arp_remove(priv, entry); + kfree(entry); + } + } + entry = priv->lec_arp_empty_ones; + while(entry) { + next = entry->next; + del_timer_sync(&entry->timer); + lec_arp_clear_vccs(entry); + kfree(entry); + entry = next; + } + priv->lec_arp_empty_ones = NULL; + entry = priv->lec_no_forward; + while(entry) { + next = entry->next; + del_timer_sync(&entry->timer); + lec_arp_clear_vccs(entry); + kfree(entry); + entry = next; + } + priv->lec_no_forward = NULL; + entry = priv->mcast_fwds; + while(entry) { + next = entry->next; + /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ + lec_arp_clear_vccs(entry); + kfree(entry); + entry = next; + } + priv->mcast_fwds = NULL; + priv->mcast_vcc = NULL; + memset(priv->lec_arp_tables, 0, + sizeof(struct lec_arp_table *) * LEC_ARP_TABLE_SIZE); + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); +} + + +/* + * Find entry by mac_address + */ +static struct lec_arp_table* +lec_arp_find(struct lec_priv *priv, + unsigned char *mac_addr) +{ + unsigned short place; + struct lec_arp_table *to_return; + + DPRINTK("LEC_ARP: lec_arp_find :%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", + mac_addr[0]&0xff, mac_addr[1]&0xff, mac_addr[2]&0xff, + mac_addr[3]&0xff, mac_addr[4]&0xff, mac_addr[5]&0xff); + place = HASH(mac_addr[ETH_ALEN-1]); + + to_return = priv->lec_arp_tables[place]; + while(to_return) { + if (memcmp(mac_addr, to_return->mac_addr, ETH_ALEN) == 0) { + return to_return; + } + to_return = to_return->next; + } + return NULL; +} + +static struct lec_arp_table* +make_entry(struct lec_priv *priv, unsigned char *mac_addr) +{ + struct lec_arp_table *to_return; + + to_return = (struct lec_arp_table *) kmalloc(sizeof(struct lec_arp_table), + GFP_ATOMIC); + if (!to_return) { + printk("LEC: Arp entry kmalloc failed\n"); + return NULL; + } + memset(to_return, 0, sizeof(struct lec_arp_table)); + memcpy(to_return->mac_addr, mac_addr, ETH_ALEN); + init_timer(&to_return->timer); + to_return->timer.function = lec_arp_expire_arp; + to_return->timer.data = (unsigned long) to_return; + to_return->last_used = jiffies; + to_return->priv = priv; + skb_queue_head_init(&to_return->tx_wait); + return to_return; +} + +/* + * + * Arp sent timer expired + * + */ +static void +lec_arp_expire_arp(unsigned long data) +{ + struct lec_arp_table *entry; + + entry = (struct lec_arp_table *)data; + + DPRINTK("lec_arp_expire_arp\n"); + if (entry->status == ESI_ARP_PENDING) { + if (entry->no_tries <= entry->priv->max_retry_count) { + if (entry->is_rdesc) + send_to_lecd(entry->priv, l_rdesc_arp_xmt, entry->mac_addr, NULL, NULL); + else + send_to_lecd(entry->priv, l_arp_xmt, entry->mac_addr, NULL, NULL); + entry->no_tries++; + } + mod_timer(&entry->timer, jiffies + (1*HZ)); + } +} + +/* + * + * Unknown/unused vcc expire, remove associated entry + * + */ +static void +lec_arp_expire_vcc(unsigned long data) +{ + unsigned long flags; + struct lec_arp_table *to_remove = (struct lec_arp_table*)data; + struct lec_priv *priv = (struct lec_priv *)to_remove->priv; + struct lec_arp_table *entry = NULL; + + del_timer(&to_remove->timer); + + DPRINTK("LEC_ARP %p %p: lec_arp_expire_vcc vpi:%d vci:%d\n", + to_remove, priv, + to_remove->vcc?to_remove->recv_vcc->vpi:0, + to_remove->vcc?to_remove->recv_vcc->vci:0); + DPRINTK("eo:%p nf:%p\n",priv->lec_arp_empty_ones,priv->lec_no_forward); + + spin_lock_irqsave(&priv->lec_arp_lock, flags); + if (to_remove == priv->lec_arp_empty_ones) + priv->lec_arp_empty_ones = to_remove->next; + else { + entry = priv->lec_arp_empty_ones; + while (entry && entry->next != to_remove) + entry = entry->next; + if (entry) + entry->next = to_remove->next; + } + if (!entry) { + if (to_remove == priv->lec_no_forward) { + priv->lec_no_forward = to_remove->next; + } else { + entry = priv->lec_no_forward; + while (entry && entry->next != to_remove) + entry = entry->next; + if (entry) + entry->next = to_remove->next; + } + } + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + + lec_arp_clear_vccs(to_remove); + kfree(to_remove); +} + +/* + * Expire entries. + * 1. Re-set timer + * 2. For each entry, delete entries that have aged past the age limit. + * 3. For each entry, depending on the status of the entry, perform + * the following maintenance. + * a. If status is ESI_VC_PENDING or ESI_ARP_PENDING then if the + * tick_count is above the max_unknown_frame_time, clear + * the tick_count to zero and clear the packets_flooded counter + * to zero. This supports the packet rate limit per address + * while flooding unknowns. + * b. If the status is ESI_FLUSH_PENDING and the tick_count is greater + * than or equal to the path_switching_delay, change the status + * to ESI_FORWARD_DIRECT. This causes the flush period to end + * regardless of the progress of the flush protocol. + */ +static void +lec_arp_check_expire(unsigned long data) +{ + unsigned long flags; + struct lec_priv *priv = (struct lec_priv *)data; + struct lec_arp_table *entry, *next; + unsigned long now; + unsigned long time_to_check; + int i; + + DPRINTK("lec_arp_check_expire %p\n",priv); + DPRINTK("expire: eo:%p nf:%p\n",priv->lec_arp_empty_ones, + priv->lec_no_forward); + now = jiffies; + spin_lock_irqsave(&priv->lec_arp_lock, flags); + for(i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + for(entry = priv->lec_arp_tables[i]; entry != NULL; ) { + if ((entry->flags) & LEC_REMOTE_FLAG && + priv->topology_change) + time_to_check = priv->forward_delay_time; + else + time_to_check = priv->aging_time; + + DPRINTK("About to expire: %lx - %lx > %lx\n", + now,entry->last_used, time_to_check); + if( time_after(now, entry->last_used+ + time_to_check) && + !(entry->flags & LEC_PERMANENT_FLAG) && + !(entry->mac_addr[0] & 0x01) ) { /* LANE2: 7.1.20 */ + /* Remove entry */ + DPRINTK("LEC:Entry timed out\n"); + next = entry->next; + lec_arp_remove(priv, entry); + kfree(entry); + entry = next; + } else { + /* Something else */ + if ((entry->status == ESI_VC_PENDING || + entry->status == ESI_ARP_PENDING) + && time_after_eq(now, + entry->timestamp + + priv->max_unknown_frame_time)) { + entry->timestamp = jiffies; + entry->packets_flooded = 0; + if (entry->status == ESI_VC_PENDING) + send_to_lecd(priv, l_svc_setup, entry->mac_addr, entry->atm_addr, NULL); + } + if (entry->status == ESI_FLUSH_PENDING + && + time_after_eq(now, entry->timestamp+ + priv->path_switching_delay)) { + struct sk_buff *skb; + + while ((skb = skb_dequeue(&entry->tx_wait)) != NULL) + lec_send(entry->vcc, skb, entry->priv); + entry->last_used = jiffies; + entry->status = + ESI_FORWARD_DIRECT; + } + entry = entry->next; + } + } + } + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + + mod_timer(&priv->lec_arp_timer, jiffies + LEC_ARP_REFRESH_INTERVAL); +} +/* + * Try to find vcc where mac_address is attached. + * + */ +static struct atm_vcc* +lec_arp_resolve(struct lec_priv *priv, unsigned char *mac_to_find, + int is_rdesc, struct lec_arp_table **ret_entry) +{ + unsigned long flags; + struct lec_arp_table *entry; + struct atm_vcc *found; + + if (mac_to_find[0] & 0x01) { + switch (priv->lane_version) { + case 1: + return priv->mcast_vcc; + break; + case 2: /* LANE2 wants arp for multicast addresses */ + if ( memcmp(mac_to_find, bus_mac, ETH_ALEN) == 0) + return priv->mcast_vcc; + break; + default: + break; + } + } + + spin_lock_irqsave(&priv->lec_arp_lock, flags); + entry = lec_arp_find(priv, mac_to_find); + + if (entry) { + if (entry->status == ESI_FORWARD_DIRECT) { + /* Connection Ok */ + entry->last_used = jiffies; + *ret_entry = entry; + found = entry->vcc; + goto out; + } + /* Data direct VC not yet set up, check to see if the unknown + frame count is greater than the limit. If the limit has + not been reached, allow the caller to send packet to + BUS. */ + if (entry->status != ESI_FLUSH_PENDING && + entry->packets_flooded<priv->maximum_unknown_frame_count) { + entry->packets_flooded++; + DPRINTK("LEC_ARP: Flooding..\n"); + found = priv->mcast_vcc; + goto out; + } + /* We got here because entry->status == ESI_FLUSH_PENDING + * or BUS flood limit was reached for an entry which is + * in ESI_ARP_PENDING or ESI_VC_PENDING state. + */ + *ret_entry = entry; + DPRINTK("lec: entry->status %d entry->vcc %p\n", entry->status, entry->vcc); + found = NULL; + } else { + /* No matching entry was found */ + entry = make_entry(priv, mac_to_find); + DPRINTK("LEC_ARP: Making entry\n"); + if (!entry) { + found = priv->mcast_vcc; + goto out; + } + lec_arp_add(priv, entry); + /* We want arp-request(s) to be sent */ + entry->packets_flooded =1; + entry->status = ESI_ARP_PENDING; + entry->no_tries = 1; + entry->last_used = entry->timestamp = jiffies; + entry->is_rdesc = is_rdesc; + if (entry->is_rdesc) + send_to_lecd(priv, l_rdesc_arp_xmt, mac_to_find, NULL, NULL); + else + send_to_lecd(priv, l_arp_xmt, mac_to_find, NULL, NULL); + entry->timer.expires = jiffies + (1*HZ); + entry->timer.function = lec_arp_expire_arp; + add_timer(&entry->timer); + found = priv->mcast_vcc; + } + +out: + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + return found; +} + +static int +lec_addr_delete(struct lec_priv *priv, unsigned char *atm_addr, + unsigned long permanent) +{ + unsigned long flags; + struct lec_arp_table *entry, *next; + int i; + + DPRINTK("lec_addr_delete\n"); + spin_lock_irqsave(&priv->lec_arp_lock, flags); + for(i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + for(entry = priv->lec_arp_tables[i]; entry != NULL; entry = next) { + next = entry->next; + if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN) + && (permanent || + !(entry->flags & LEC_PERMANENT_FLAG))) { + lec_arp_remove(priv, entry); + kfree(entry); + } + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + return 0; + } + } + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + return -1; +} + +/* + * Notifies: Response to arp_request (atm_addr != NULL) + */ +static void +lec_arp_update(struct lec_priv *priv, unsigned char *mac_addr, + unsigned char *atm_addr, unsigned long remoteflag, + unsigned int targetless_le_arp) +{ + unsigned long flags; + struct lec_arp_table *entry, *tmp; + int i; + + DPRINTK("lec:%s", (targetless_le_arp) ? "targetless ": " "); + DPRINTK("lec_arp_update mac:%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", + mac_addr[0],mac_addr[1],mac_addr[2],mac_addr[3], + mac_addr[4],mac_addr[5]); + + spin_lock_irqsave(&priv->lec_arp_lock, flags); + entry = lec_arp_find(priv, mac_addr); + if (entry == NULL && targetless_le_arp) + goto out; /* LANE2: ignore targetless LE_ARPs for which + * we have no entry in the cache. 7.1.30 + */ + if (priv->lec_arp_empty_ones) { + entry = priv->lec_arp_empty_ones; + if (!memcmp(entry->atm_addr, atm_addr, ATM_ESA_LEN)) { + priv->lec_arp_empty_ones = entry->next; + } else { + while(entry->next && memcmp(entry->next->atm_addr, + atm_addr, ATM_ESA_LEN)) + entry = entry->next; + if (entry->next) { + tmp = entry; + entry = entry->next; + tmp->next = entry->next; + } else + entry = NULL; + + } + if (entry) { + del_timer(&entry->timer); + tmp = lec_arp_find(priv, mac_addr); + if (tmp) { + del_timer(&tmp->timer); + tmp->status = ESI_FORWARD_DIRECT; + memcpy(tmp->atm_addr, atm_addr, ATM_ESA_LEN); + tmp->vcc = entry->vcc; + tmp->old_push = entry->old_push; + tmp->last_used = jiffies; + del_timer(&entry->timer); + kfree(entry); + entry=tmp; + } else { + entry->status = ESI_FORWARD_DIRECT; + memcpy(entry->mac_addr, mac_addr, ETH_ALEN); + entry->last_used = jiffies; + lec_arp_add(priv, entry); + } + if (remoteflag) + entry->flags|=LEC_REMOTE_FLAG; + else + entry->flags&=~LEC_REMOTE_FLAG; + DPRINTK("After update\n"); + dump_arp_table(priv); + goto out; + } + } + entry = lec_arp_find(priv, mac_addr); + if (!entry) { + entry = make_entry(priv, mac_addr); + if (!entry) + goto out; + entry->status = ESI_UNKNOWN; + lec_arp_add(priv, entry); + /* Temporary, changes before end of function */ + } + memcpy(entry->atm_addr, atm_addr, ATM_ESA_LEN); + del_timer(&entry->timer); + for(i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + for(tmp = priv->lec_arp_tables[i]; tmp; tmp=tmp->next) { + if (entry != tmp && + !memcmp(tmp->atm_addr, atm_addr, + ATM_ESA_LEN)) { + /* Vcc to this host exists */ + if (tmp->status > ESI_VC_PENDING) { + /* + * ESI_FLUSH_PENDING, + * ESI_FORWARD_DIRECT + */ + entry->vcc = tmp->vcc; + entry->old_push=tmp->old_push; + } + entry->status=tmp->status; + break; + } + } + } + if (remoteflag) + entry->flags|=LEC_REMOTE_FLAG; + else + entry->flags&=~LEC_REMOTE_FLAG; + if (entry->status == ESI_ARP_PENDING || + entry->status == ESI_UNKNOWN) { + entry->status = ESI_VC_PENDING; + send_to_lecd(priv, l_svc_setup, entry->mac_addr, atm_addr, NULL); + } + DPRINTK("After update2\n"); + dump_arp_table(priv); +out: + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); +} + +/* + * Notifies: Vcc setup ready + */ +static void +lec_vcc_added(struct lec_priv *priv, struct atmlec_ioc *ioc_data, + struct atm_vcc *vcc, + void (*old_push)(struct atm_vcc *vcc, struct sk_buff *skb)) +{ + unsigned long flags; + struct lec_arp_table *entry; + int i, found_entry=0; + + spin_lock_irqsave(&priv->lec_arp_lock, flags); + if (ioc_data->receive == 2) { + /* Vcc for Multicast Forward. No timer, LANEv2 7.1.20 and 2.3.5.3 */ + + DPRINTK("LEC_ARP: Attaching mcast forward\n"); +#if 0 + entry = lec_arp_find(priv, bus_mac); + if (!entry) { + printk("LEC_ARP: Multicast entry not found!\n"); + goto out; + } + memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); + entry->recv_vcc = vcc; + entry->old_recv_push = old_push; +#endif + entry = make_entry(priv, bus_mac); + if (entry == NULL) + goto out; + del_timer(&entry->timer); + memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); + entry->recv_vcc = vcc; + entry->old_recv_push = old_push; + entry->next = priv->mcast_fwds; + priv->mcast_fwds = entry; + goto out; + } else if (ioc_data->receive == 1) { + /* Vcc which we don't want to make default vcc, attach it + anyway. */ + DPRINTK("LEC_ARP:Attaching data direct, not default :%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", + ioc_data->atm_addr[0],ioc_data->atm_addr[1], + ioc_data->atm_addr[2],ioc_data->atm_addr[3], + ioc_data->atm_addr[4],ioc_data->atm_addr[5], + ioc_data->atm_addr[6],ioc_data->atm_addr[7], + ioc_data->atm_addr[8],ioc_data->atm_addr[9], + ioc_data->atm_addr[10],ioc_data->atm_addr[11], + ioc_data->atm_addr[12],ioc_data->atm_addr[13], + ioc_data->atm_addr[14],ioc_data->atm_addr[15], + ioc_data->atm_addr[16],ioc_data->atm_addr[17], + ioc_data->atm_addr[18],ioc_data->atm_addr[19]); + entry = make_entry(priv, bus_mac); + if (entry == NULL) + goto out; + memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); + memset(entry->mac_addr, 0, ETH_ALEN); + entry->recv_vcc = vcc; + entry->old_recv_push = old_push; + entry->status = ESI_UNKNOWN; + entry->timer.expires = jiffies + priv->vcc_timeout_period; + entry->timer.function = lec_arp_expire_vcc; + add_timer(&entry->timer); + entry->next = priv->lec_no_forward; + priv->lec_no_forward = entry; + dump_arp_table(priv); + goto out; + } + DPRINTK("LEC_ARP:Attaching data direct, default:%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", + ioc_data->atm_addr[0],ioc_data->atm_addr[1], + ioc_data->atm_addr[2],ioc_data->atm_addr[3], + ioc_data->atm_addr[4],ioc_data->atm_addr[5], + ioc_data->atm_addr[6],ioc_data->atm_addr[7], + ioc_data->atm_addr[8],ioc_data->atm_addr[9], + ioc_data->atm_addr[10],ioc_data->atm_addr[11], + ioc_data->atm_addr[12],ioc_data->atm_addr[13], + ioc_data->atm_addr[14],ioc_data->atm_addr[15], + ioc_data->atm_addr[16],ioc_data->atm_addr[17], + ioc_data->atm_addr[18],ioc_data->atm_addr[19]); + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + for (entry = priv->lec_arp_tables[i]; entry; entry=entry->next) { + if (memcmp(ioc_data->atm_addr, entry->atm_addr, + ATM_ESA_LEN)==0) { + DPRINTK("LEC_ARP: Attaching data direct\n"); + DPRINTK("Currently -> Vcc: %d, Rvcc:%d\n", + entry->vcc?entry->vcc->vci:0, + entry->recv_vcc?entry->recv_vcc->vci:0); + found_entry=1; + del_timer(&entry->timer); + entry->vcc = vcc; + entry->old_push = old_push; + if (entry->status == ESI_VC_PENDING) { + if(priv->maximum_unknown_frame_count + ==0) + entry->status = + ESI_FORWARD_DIRECT; + else { + entry->timestamp = jiffies; + entry->status = + ESI_FLUSH_PENDING; +#if 0 + send_to_lecd(priv,l_flush_xmt, + NULL, + entry->atm_addr, + NULL); +#endif + } + } else { + /* They were forming a connection + to us, and we to them. Our + ATM address is numerically lower + than theirs, so we make connection + we formed into default VCC (8.1.11). + Connection they made gets torn + down. This might confuse some + clients. Can be changed if + someone reports trouble... */ + ; + } + } + } + } + if (found_entry) { + DPRINTK("After vcc was added\n"); + dump_arp_table(priv); + goto out; + } + /* Not found, snatch address from first data packet that arrives from + this vcc */ + entry = make_entry(priv, bus_mac); + if (!entry) + goto out; + entry->vcc = vcc; + entry->old_push = old_push; + memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); + memset(entry->mac_addr, 0, ETH_ALEN); + entry->status = ESI_UNKNOWN; + entry->next = priv->lec_arp_empty_ones; + priv->lec_arp_empty_ones = entry; + entry->timer.expires = jiffies + priv->vcc_timeout_period; + entry->timer.function = lec_arp_expire_vcc; + add_timer(&entry->timer); + DPRINTK("After vcc was added\n"); + dump_arp_table(priv); +out: + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); +} + +static void +lec_flush_complete(struct lec_priv *priv, unsigned long tran_id) +{ + unsigned long flags; + struct lec_arp_table *entry; + int i; + + DPRINTK("LEC:lec_flush_complete %lx\n",tran_id); + spin_lock_irqsave(&priv->lec_arp_lock, flags); + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { + for (entry = priv->lec_arp_tables[i]; entry; entry=entry->next) { + if (entry->flush_tran_id == tran_id && + entry->status == ESI_FLUSH_PENDING) { + struct sk_buff *skb; + + while ((skb = skb_dequeue(&entry->tx_wait)) != NULL) + lec_send(entry->vcc, skb, entry->priv); + entry->status = ESI_FORWARD_DIRECT; + DPRINTK("LEC_ARP: Flushed\n"); + } + } + } + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + dump_arp_table(priv); +} + +static void +lec_set_flush_tran_id(struct lec_priv *priv, + unsigned char *atm_addr, unsigned long tran_id) +{ + unsigned long flags; + struct lec_arp_table *entry; + int i; + + spin_lock_irqsave(&priv->lec_arp_lock, flags); + for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) + for(entry = priv->lec_arp_tables[i]; entry; entry=entry->next) + if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN)) { + entry->flush_tran_id = tran_id; + DPRINTK("Set flush transaction id to %lx for %p\n",tran_id,entry); + } + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); +} + +static int +lec_mcast_make(struct lec_priv *priv, struct atm_vcc *vcc) +{ + unsigned long flags; + unsigned char mac_addr[] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; + struct lec_arp_table *to_add; + struct lec_vcc_priv *vpriv; + int err = 0; + + if (!(vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL))) + return -ENOMEM; + vpriv->xoff = 0; + vpriv->old_pop = vcc->pop; + vcc->user_back = vpriv; + vcc->pop = lec_pop; + spin_lock_irqsave(&priv->lec_arp_lock, flags); + to_add = make_entry(priv, mac_addr); + if (!to_add) { + vcc->pop = vpriv->old_pop; + kfree(vpriv); + err = -ENOMEM; + goto out; + } + memcpy(to_add->atm_addr, vcc->remote.sas_addr.prv, ATM_ESA_LEN); + to_add->status = ESI_FORWARD_DIRECT; + to_add->flags |= LEC_PERMANENT_FLAG; + to_add->vcc = vcc; + to_add->old_push = vcc->push; + vcc->push = lec_push; + priv->mcast_vcc = vcc; + lec_arp_add(priv, to_add); +out: + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + return err; +} + +static void +lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) +{ + unsigned long flags; + struct lec_arp_table *entry, *next; + int i; + + DPRINTK("LEC_ARP: lec_vcc_close vpi:%d vci:%d\n",vcc->vpi,vcc->vci); + dump_arp_table(priv); + spin_lock_irqsave(&priv->lec_arp_lock, flags); + for(i=0;i<LEC_ARP_TABLE_SIZE;i++) { + for(entry = priv->lec_arp_tables[i];entry; entry=next) { + next = entry->next; + if (vcc == entry->vcc) { + lec_arp_remove(priv, entry); + kfree(entry); + if (priv->mcast_vcc == vcc) { + priv->mcast_vcc = NULL; + } + } + } + } + + entry = priv->lec_arp_empty_ones; + priv->lec_arp_empty_ones = NULL; + while (entry != NULL) { + next = entry->next; + if (entry->vcc == vcc) { /* leave it out from the list */ + lec_arp_clear_vccs(entry); + del_timer(&entry->timer); + kfree(entry); + } + else { /* put it back to the list */ + entry->next = priv->lec_arp_empty_ones; + priv->lec_arp_empty_ones = entry; + } + entry = next; + } + + entry = priv->lec_no_forward; + priv->lec_no_forward = NULL; + while (entry != NULL) { + next = entry->next; + if (entry->recv_vcc == vcc) { + lec_arp_clear_vccs(entry); + del_timer(&entry->timer); + kfree(entry); + } + else { + entry->next = priv->lec_no_forward; + priv->lec_no_forward = entry; + } + entry = next; + } + + entry = priv->mcast_fwds; + priv->mcast_fwds = NULL; + while (entry != NULL) { + next = entry->next; + if (entry->recv_vcc == vcc) { + lec_arp_clear_vccs(entry); + /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ + kfree(entry); + } + else { + entry->next = priv->mcast_fwds; + priv->mcast_fwds = entry; + } + entry = next; + } + + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); + dump_arp_table(priv); +} + +static void +lec_arp_check_empties(struct lec_priv *priv, + struct atm_vcc *vcc, struct sk_buff *skb) +{ + unsigned long flags; + struct lec_arp_table *entry, *prev; + struct lecdatahdr_8023 *hdr = (struct lecdatahdr_8023 *)skb->data; + unsigned char *src; +#ifdef CONFIG_TR + struct lecdatahdr_8025 *tr_hdr = (struct lecdatahdr_8025 *)skb->data; + + if (priv->is_trdev) src = tr_hdr->h_source; + else +#endif + src = hdr->h_source; + + spin_lock_irqsave(&priv->lec_arp_lock, flags); + entry = priv->lec_arp_empty_ones; + if (vcc == entry->vcc) { + del_timer(&entry->timer); + memcpy(entry->mac_addr, src, ETH_ALEN); + entry->status = ESI_FORWARD_DIRECT; + entry->last_used = jiffies; + priv->lec_arp_empty_ones = entry->next; + /* We might have got an entry */ + if ((prev = lec_arp_find(priv,src))) { + lec_arp_remove(priv, prev); + kfree(prev); + } + lec_arp_add(priv, entry); + goto out; + } + prev = entry; + entry = entry->next; + while (entry && entry->vcc != vcc) { + prev= entry; + entry = entry->next; + } + if (!entry) { + DPRINTK("LEC_ARP: Arp_check_empties: entry not found!\n"); + goto out; + } + del_timer(&entry->timer); + memcpy(entry->mac_addr, src, ETH_ALEN); + entry->status = ESI_FORWARD_DIRECT; + entry->last_used = jiffies; + prev->next = entry->next; + if ((prev = lec_arp_find(priv, src))) { + lec_arp_remove(priv, prev); + kfree(prev); + } + lec_arp_add(priv, entry); +out: + spin_unlock_irqrestore(&priv->lec_arp_lock, flags); +} +MODULE_LICENSE("GPL"); diff --git a/net/atm/lec.h b/net/atm/lec.h new file mode 100644 index 000000000000..6606082b29a8 --- /dev/null +++ b/net/atm/lec.h @@ -0,0 +1,142 @@ +/* + * + * Lan Emulation client header file + * + * Marko Kiiskila mkiiskila@yahoo.com + * + */ + +#ifndef _LEC_H_ +#define _LEC_H_ + +#include <linux/config.h> +#include <linux/atmdev.h> +#include <linux/netdevice.h> +#include <linux/atmlec.h> + +#define LEC_HEADER_LEN 16 + +struct lecdatahdr_8023 { + unsigned short le_header; + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + unsigned short h_type; +}; + +struct lecdatahdr_8025 { + unsigned short le_header; + unsigned char ac_pad; + unsigned char fc; + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; +}; + +#define LEC_MINIMUM_8023_SIZE 62 +#define LEC_MINIMUM_8025_SIZE 16 + +/* + * Operations that LANE2 capable device can do. Two first functions + * are used to make the device do things. See spec 3.1.3 and 3.1.4. + * + * The third function is intented for the MPOA component sitting on + * top of the LANE device. The MPOA component assigns it's own function + * to (*associate_indicator)() and the LANE device will use that + * function to tell about TLVs it sees floating through. + * + */ +struct lane2_ops { + int (*resolve)(struct net_device *dev, u8 *dst_mac, int force, + u8 **tlvs, u32 *sizeoftlvs); + int (*associate_req)(struct net_device *dev, u8 *lan_dst, + u8 *tlvs, u32 sizeoftlvs); + void (*associate_indicator)(struct net_device *dev, u8 *mac_addr, + u8 *tlvs, u32 sizeoftlvs); +}; + +/* + * ATM LAN Emulation supports both LLC & Dix Ethernet EtherType + * frames. + * 1. Dix Ethernet EtherType frames encoded by placing EtherType + * field in h_type field. Data follows immediatelly after header. + * 2. LLC Data frames whose total length, including LLC field and data, + * but not padding required to meet the minimum data frame length, + * is less than 1536(0x0600) MUST be encoded by placing that length + * in the h_type field. The LLC field follows header immediatelly. + * 3. LLC data frames longer than this maximum MUST be encoded by placing + * the value 0 in the h_type field. + * + */ + +/* Hash table size */ +#define LEC_ARP_TABLE_SIZE 16 + +struct lec_priv { + struct net_device_stats stats; + unsigned short lecid; /* Lecid of this client */ + struct lec_arp_table *lec_arp_empty_ones; + /* Used for storing VCC's that don't have a MAC address attached yet */ + struct lec_arp_table *lec_arp_tables[LEC_ARP_TABLE_SIZE]; + /* Actual LE ARP table */ + struct lec_arp_table *lec_no_forward; + /* Used for storing VCC's (and forward packets from) which are to + age out by not using them to forward packets. + This is because to some LE clients there will be 2 VCCs. Only + one of them gets used. */ + struct lec_arp_table *mcast_fwds; + /* With LANEv2 it is possible that BUS (or a special multicast server) + establishes multiple Multicast Forward VCCs to us. This list + collects all those VCCs. LANEv1 client has only one item in this + list. These entries are not aged out. */ + spinlock_t lec_arp_lock; + struct atm_vcc *mcast_vcc; /* Default Multicast Send VCC */ + struct atm_vcc *lecd; + struct timer_list lec_arp_timer; + /* C10 */ + unsigned int maximum_unknown_frame_count; +/* Within the period of time defined by this variable, the client will send + no more than C10 frames to BUS for a given unicast destination. (C11) */ + unsigned long max_unknown_frame_time; +/* If no traffic has been sent in this vcc for this period of time, + vcc will be torn down (C12)*/ + unsigned long vcc_timeout_period; +/* An LE Client MUST not retry an LE_ARP_REQUEST for a + given frame's LAN Destination more than maximum retry count times, + after the first LEC_ARP_REQUEST (C13)*/ + unsigned short max_retry_count; +/* Max time the client will maintain an entry in its arp cache in + absence of a verification of that relationship (C17)*/ + unsigned long aging_time; +/* Max time the client will maintain an entry in cache when + topology change flag is true (C18) */ + unsigned long forward_delay_time; +/* Topology change flag (C19)*/ + int topology_change; +/* Max time the client expects an LE_ARP_REQUEST/LE_ARP_RESPONSE + cycle to take (C20)*/ + unsigned long arp_response_time; +/* Time limit ot wait to receive an LE_FLUSH_RESPONSE after the + LE_FLUSH_REQUEST has been sent before taking recover action. (C21)*/ + unsigned long flush_timeout; +/* The time since sending a frame to the bus after which the + LE Client may assume that the frame has been either discarded or + delivered to the recipient (C22) */ + unsigned long path_switching_delay; + + u8 *tlvs; /* LANE2: TLVs are new */ + u32 sizeoftlvs; /* The size of the tlv array in bytes */ + int lane_version; /* LANE2 */ + int itfnum; /* e.g. 2 for lec2, 5 for lec5 */ + struct lane2_ops *lane2_ops; /* can be NULL for LANE v1 */ + int is_proxy; /* bridge between ATM and Ethernet */ + int is_trdev; /* Device type, 0 = Ethernet, 1 = TokenRing */ +}; + +struct lec_vcc_priv { + void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb); + int xoff; +}; + +#define LEC_VCC_PRIV(vcc) ((struct lec_vcc_priv *)((vcc)->user_back)) + +#endif /* _LEC_H_ */ + diff --git a/net/atm/lec_arpc.h b/net/atm/lec_arpc.h new file mode 100644 index 000000000000..397448094648 --- /dev/null +++ b/net/atm/lec_arpc.h @@ -0,0 +1,92 @@ +/* + * Lec arp cache + * Marko Kiiskila mkiiskila@yahoo.com + * + */ +#ifndef _LEC_ARP_H +#define _LEC_ARP_H +#include <linux/atm.h> +#include <linux/atmdev.h> +#include <linux/if_ether.h> +#include <linux/atmlec.h> + +struct lec_arp_table { + struct lec_arp_table *next; /* Linked entry list */ + unsigned char atm_addr[ATM_ESA_LEN]; /* Atm address */ + unsigned char mac_addr[ETH_ALEN]; /* Mac address */ + int is_rdesc; /* Mac address is a route descriptor */ + struct atm_vcc *vcc; /* Vcc this entry is attached */ + struct atm_vcc *recv_vcc; /* Vcc we receive data from */ + void (*old_push)(struct atm_vcc *vcc,struct sk_buff *skb); + /* Push that leads to daemon */ + void (*old_recv_push)(struct atm_vcc *vcc, struct sk_buff *skb); + /* Push that leads to daemon */ + void (*old_close)(struct atm_vcc *vcc); + /* We want to see when this + * vcc gets closed */ + unsigned long last_used; /* For expiry */ + unsigned long timestamp; /* Used for various timestamping + * things: + * 1. FLUSH started + * (status=ESI_FLUSH_PENDING) + * 2. Counting to + * max_unknown_frame_time + * (status=ESI_ARP_PENDING|| + * status=ESI_VC_PENDING) + */ + unsigned char no_tries; /* No of times arp retry has been + tried */ + unsigned char status; /* Status of this entry */ + unsigned short flags; /* Flags for this entry */ + unsigned short packets_flooded; /* Data packets flooded */ + unsigned long flush_tran_id; /* Transaction id in flush protocol */ + struct timer_list timer; /* Arping timer */ + struct lec_priv *priv; /* Pointer back */ + + u8 *tlvs; /* LANE2: Each MAC address can have TLVs */ + u32 sizeoftlvs; /* associated with it. sizeoftlvs tells the */ + /* the length of the tlvs array */ + struct sk_buff_head tx_wait; /* wait queue for outgoing packets */ +}; + +struct tlv { /* LANE2: Template tlv struct for accessing */ + /* the tlvs in the lec_arp_table->tlvs array*/ + u32 type; + u8 length; + u8 value[255]; +}; + +/* Status fields */ +#define ESI_UNKNOWN 0 /* + * Next packet sent to this mac address + * causes ARP-request to be sent + */ +#define ESI_ARP_PENDING 1 /* + * There is no ATM address associated with this + * 48-bit address. The LE-ARP protocol is in + * progress. + */ +#define ESI_VC_PENDING 2 /* + * There is a valid ATM address associated with + * this 48-bit address but there is no VC set + * up to that ATM address. The signaling + * protocol is in process. + */ +#define ESI_FLUSH_PENDING 4 /* + * The LEC has been notified of the FLUSH_START + * status and it is assumed that the flush + * protocol is in process. + */ +#define ESI_FORWARD_DIRECT 5 /* + * Either the Path Switching Delay (C22) has + * elapsed or the LEC has notified the Mapping + * that the flush protocol has completed. In + * either case, it is safe to forward packets + * to this address via the data direct VC. + */ + +/* Flag values */ +#define LEC_REMOTE_FLAG 0x0001 +#define LEC_PERMANENT_FLAG 0x0002 + +#endif diff --git a/net/atm/mpc.c b/net/atm/mpc.c new file mode 100644 index 000000000000..17a81ebe7e6e --- /dev/null +++ b/net/atm/mpc.c @@ -0,0 +1,1514 @@ +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/timer.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/seq_file.h> + +/* We are an ethernet device */ +#include <linux/if_ether.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <net/sock.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <asm/byteorder.h> +#include <asm/uaccess.h> +#include <net/checksum.h> /* for ip_fast_csum() */ +#include <net/arp.h> +#include <net/dst.h> +#include <linux/proc_fs.h> + +/* And atm device */ +#include <linux/atmdev.h> +#include <linux/atmlec.h> +#include <linux/atmmpc.h> +/* Modular too */ +#include <linux/config.h> +#include <linux/module.h> + +#include "lec.h" +#include "mpc.h" +#include "resources.h" + +/* + * mpc.c: Implementation of MPOA client kernel part + */ + +#if 0 +#define dprintk printk /* debug */ +#else +#define dprintk(format,args...) +#endif + +#if 0 +#define ddprintk printk /* more debug */ +#else +#define ddprintk(format,args...) +#endif + + + +#define MPOA_TAG_LEN 4 + +/* mpc_daemon -> kernel */ +static void MPOA_trigger_rcvd (struct k_message *msg, struct mpoa_client *mpc); +static void MPOA_res_reply_rcvd(struct k_message *msg, struct mpoa_client *mpc); +static void ingress_purge_rcvd(struct k_message *msg, struct mpoa_client *mpc); +static void egress_purge_rcvd(struct k_message *msg, struct mpoa_client *mpc); +static void mps_death(struct k_message *msg, struct mpoa_client *mpc); +static void clean_up(struct k_message *msg, struct mpoa_client *mpc, int action); +static void MPOA_cache_impos_rcvd(struct k_message *msg, struct mpoa_client *mpc); +static void set_mpc_ctrl_addr_rcvd(struct k_message *mesg, struct mpoa_client *mpc); +static void set_mps_mac_addr_rcvd(struct k_message *mesg, struct mpoa_client *mpc); + +static uint8_t *copy_macs(struct mpoa_client *mpc, uint8_t *router_mac, + uint8_t *tlvs, uint8_t mps_macs, uint8_t device_type); +static void purge_egress_shortcut(struct atm_vcc *vcc, eg_cache_entry *entry); + +static void send_set_mps_ctrl_addr(char *addr, struct mpoa_client *mpc); +static void mpoad_close(struct atm_vcc *vcc); +static int msg_from_mpoad(struct atm_vcc *vcc, struct sk_buff *skb); + +static void mpc_push(struct atm_vcc *vcc, struct sk_buff *skb); +static int mpc_send_packet(struct sk_buff *skb, struct net_device *dev); +static int mpoa_event_listener(struct notifier_block *mpoa_notifier, unsigned long event, void *dev); +static void mpc_timer_refresh(void); +static void mpc_cache_check( unsigned long checking_time ); + +static struct llc_snap_hdr llc_snap_mpoa_ctrl = { + 0xaa, 0xaa, 0x03, + {0x00, 0x00, 0x5e}, + {0x00, 0x03} /* For MPOA control PDUs */ +}; +static struct llc_snap_hdr llc_snap_mpoa_data = { + 0xaa, 0xaa, 0x03, + {0x00, 0x00, 0x00}, + {0x08, 0x00} /* This is for IP PDUs only */ +}; +static struct llc_snap_hdr llc_snap_mpoa_data_tagged = { + 0xaa, 0xaa, 0x03, + {0x00, 0x00, 0x00}, + {0x88, 0x4c} /* This is for tagged data PDUs */ +}; + +static struct notifier_block mpoa_notifier = { + mpoa_event_listener, + NULL, + 0 +}; + +#ifdef CONFIG_PROC_FS +extern int mpc_proc_init(void); +extern void mpc_proc_clean(void); +#endif + +struct mpoa_client *mpcs = NULL; /* FIXME */ +static struct atm_mpoa_qos *qos_head = NULL; +static struct timer_list mpc_timer = TIMER_INITIALIZER(NULL, 0, 0); + + +static struct mpoa_client *find_mpc_by_itfnum(int itf) +{ + struct mpoa_client *mpc; + + mpc = mpcs; /* our global linked list */ + while (mpc != NULL) { + if (mpc->dev_num == itf) + return mpc; + mpc = mpc->next; + } + + return NULL; /* not found */ +} + +static struct mpoa_client *find_mpc_by_vcc(struct atm_vcc *vcc) +{ + struct mpoa_client *mpc; + + mpc = mpcs; /* our global linked list */ + while (mpc != NULL) { + if (mpc->mpoad_vcc == vcc) + return mpc; + mpc = mpc->next; + } + + return NULL; /* not found */ +} + +static struct mpoa_client *find_mpc_by_lec(struct net_device *dev) +{ + struct mpoa_client *mpc; + + mpc = mpcs; /* our global linked list */ + while (mpc != NULL) { + if (mpc->dev == dev) |