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/core |
Linux-2.6.12-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/core')
-rw-r--r-- | net/core/Makefile | 17 | ||||
-rw-r--r-- | net/core/datagram.c | 482 | ||||
-rw-r--r-- | net/core/dev.c | 3359 | ||||
-rw-r--r-- | net/core/dev_mcast.c | 299 | ||||
-rw-r--r-- | net/core/dst.c | 276 | ||||
-rw-r--r-- | net/core/dv.c | 548 | ||||
-rw-r--r-- | net/core/ethtool.c | 819 | ||||
-rw-r--r-- | net/core/filter.c | 432 | ||||
-rw-r--r-- | net/core/flow.c | 371 | ||||
-rw-r--r-- | net/core/gen_estimator.c | 250 | ||||
-rw-r--r-- | net/core/gen_stats.c | 239 | ||||
-rw-r--r-- | net/core/iovec.c | 239 | ||||
-rw-r--r-- | net/core/link_watch.c | 137 | ||||
-rw-r--r-- | net/core/neighbour.c | 2362 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 461 | ||||
-rw-r--r-- | net/core/netfilter.c | 799 | ||||
-rw-r--r-- | net/core/netpoll.c | 735 | ||||
-rw-r--r-- | net/core/pktgen.c | 3132 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 711 | ||||
-rw-r--r-- | net/core/scm.c | 291 | ||||
-rw-r--r-- | net/core/skbuff.c | 1460 | ||||
-rw-r--r-- | net/core/sock.c | 1565 | ||||
-rw-r--r-- | net/core/stream.c | 287 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 182 | ||||
-rw-r--r-- | net/core/utils.c | 155 | ||||
-rw-r--r-- | net/core/wireless.c | 1459 |
26 files changed, 21067 insertions, 0 deletions
diff --git a/net/core/Makefile b/net/core/Makefile new file mode 100644 index 000000000000..81f03243fe2f --- /dev/null +++ b/net/core/Makefile @@ -0,0 +1,17 @@ +# +# Makefile for the Linux networking core. +# + +obj-y := sock.o skbuff.o iovec.o datagram.o stream.o scm.o gen_stats.o gen_estimator.o + +obj-$(CONFIG_SYSCTL) += sysctl_net_core.o + +obj-y += flow.o dev.o ethtool.o dev_mcast.o dst.o \ + neighbour.o rtnetlink.o utils.o link_watch.o filter.o + +obj-$(CONFIG_SYSFS) += net-sysfs.o +obj-$(CONFIG_NETFILTER) += netfilter.o +obj-$(CONFIG_NET_DIVERT) += dv.o +obj-$(CONFIG_NET_PKTGEN) += pktgen.o +obj-$(CONFIG_NET_RADIO) += wireless.o +obj-$(CONFIG_NETPOLL) += netpoll.o diff --git a/net/core/datagram.c b/net/core/datagram.c new file mode 100644 index 000000000000..d1bfd279cc1a --- /dev/null +++ b/net/core/datagram.c @@ -0,0 +1,482 @@ +/* + * SUCS NET3: + * + * Generic datagram handling routines. These are generic for all + * protocols. Possibly a generic IP version on top of these would + * make sense. Not tonight however 8-). + * This is used because UDP, RAW, PACKET, DDP, IPX, AX.25 and + * NetROM layer all have identical poll code and mostly + * identical recvmsg() code. So we share it here. The poll was + * shared before but buried in udp.c so I moved it. + * + * Authors: Alan Cox <alan@redhat.com>. (datagram_poll() from old + * udp.c code) + * + * Fixes: + * Alan Cox : NULL return from skb_peek_copy() + * understood + * Alan Cox : Rewrote skb_read_datagram to avoid the + * skb_peek_copy stuff. + * Alan Cox : Added support for SOCK_SEQPACKET. + * IPX can no longer use the SO_TYPE hack + * but AX.25 now works right, and SPX is + * feasible. + * Alan Cox : Fixed write poll of non IP protocol + * crash. + * Florian La Roche: Changed for my new skbuff handling. + * Darryl Miles : Fixed non-blocking SOCK_SEQPACKET. + * Linus Torvalds : BSD semantic fixes. + * Alan Cox : Datagram iovec handling + * Darryl Miles : Fixed non-blocking SOCK_STREAM. + * Alan Cox : POSIXisms + * Pete Wyckoff : Unconnected accept() fix. + * + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <asm/uaccess.h> +#include <asm/system.h> +#include <linux/mm.h> +#include <linux/interrupt.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/inet.h> +#include <linux/tcp.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/poll.h> +#include <linux/highmem.h> + +#include <net/protocol.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <net/checksum.h> + + +/* + * Is a socket 'connection oriented' ? + */ +static inline int connection_based(struct sock *sk) +{ + return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM; +} + +/* + * Wait for a packet.. + */ +static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) +{ + int error; + DEFINE_WAIT(wait); + + prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + + /* Socket errors? */ + error = sock_error(sk); + if (error) + goto out_err; + + if (!skb_queue_empty(&sk->sk_receive_queue)) + goto out; + + /* Socket shut down? */ + if (sk->sk_shutdown & RCV_SHUTDOWN) + goto out_noerr; + + /* Sequenced packets can come disconnected. + * If so we report the problem + */ + error = -ENOTCONN; + if (connection_based(sk) && + !(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_LISTEN)) + goto out_err; + + /* handle signals */ + if (signal_pending(current)) + goto interrupted; + + error = 0; + *timeo_p = schedule_timeout(*timeo_p); +out: + finish_wait(sk->sk_sleep, &wait); + return error; +interrupted: + error = sock_intr_errno(*timeo_p); +out_err: + *err = error; + goto out; +out_noerr: + *err = 0; + error = 1; + goto out; +} + +/** + * skb_recv_datagram - Receive a datagram skbuff + * @sk - socket + * @flags - MSG_ flags + * @noblock - blocking operation? + * @err - error code returned + * + * Get a datagram skbuff, understands the peeking, nonblocking wakeups + * and possible races. This replaces identical code in packet, raw and + * udp, as well as the IPX AX.25 and Appletalk. It also finally fixes + * the long standing peek and read race for datagram sockets. If you + * alter this routine remember it must be re-entrant. + * + * This function will lock the socket if a skb is returned, so the caller + * needs to unlock the socket in that case (usually by calling + * skb_free_datagram) + * + * * It does not lock socket since today. This function is + * * free of race conditions. This measure should/can improve + * * significantly datagram socket latencies at high loads, + * * when data copying to user space takes lots of time. + * * (BTW I've just killed the last cli() in IP/IPv6/core/netlink/packet + * * 8) Great win.) + * * --ANK (980729) + * + * The order of the tests when we find no data waiting are specified + * quite explicitly by POSIX 1003.1g, don't change them without having + * the standard around please. + */ +struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, + int noblock, int *err) +{ + struct sk_buff *skb; + long timeo; + /* + * Caller is allowed not to check sk->sk_err before skb_recv_datagram() + */ + int error = sock_error(sk); + + if (error) + goto no_packet; + + timeo = sock_rcvtimeo(sk, noblock); + + do { + /* Again only user level code calls this function, so nothing + * interrupt level will suddenly eat the receive_queue. + * + * Look at current nfs client by the way... + * However, this function was corrent in any case. 8) + */ + if (flags & MSG_PEEK) { + unsigned long cpu_flags; + + spin_lock_irqsave(&sk->sk_receive_queue.lock, + cpu_flags); + skb = skb_peek(&sk->sk_receive_queue); + if (skb) + atomic_inc(&skb->users); + spin_unlock_irqrestore(&sk->sk_receive_queue.lock, + cpu_flags); + } else + skb = skb_dequeue(&sk->sk_receive_queue); + + if (skb) + return skb; + + /* User doesn't want to wait */ + error = -EAGAIN; + if (!timeo) + goto no_packet; + + } while (!wait_for_packet(sk, err, &timeo)); + + return NULL; + +no_packet: + *err = error; + return NULL; +} + +void skb_free_datagram(struct sock *sk, struct sk_buff *skb) +{ + kfree_skb(skb); +} + +/** + * skb_copy_datagram_iovec - Copy a datagram to an iovec. + * @skb - buffer to copy + * @offset - offset in the buffer to start copying from + * @iovec - io vector to copy to + * @len - amount of data to copy from buffer to iovec + * + * Note: the iovec is modified during the copy. + */ +int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, + struct iovec *to, int len) +{ + int start = skb_headlen(skb); + int i, copy = start - offset; + + /* Copy header. */ + if (copy > 0) { + if (copy > len) + copy = len; + if (memcpy_toiovec(to, skb->data + offset, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } + + /* Copy paged appendix. Hmm... why does this look so complicated? */ + 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) { + int err; + u8 *vaddr; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = frag->page; + + if (copy > len) + copy = len; + vaddr = kmap(page); + err = memcpy_toiovec(to, vaddr + frag->page_offset + + offset - start, copy); + kunmap(page); + if (err) + goto fault; + if (!(len -= copy)) + return 0; + 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; + if (skb_copy_datagram_iovec(list, + offset - start, + to, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } + start = end; + } + } + if (!len) + return 0; + +fault: + return -EFAULT; +} + +static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, + u8 __user *to, int len, + unsigned int *csump) +{ + int start = skb_headlen(skb); + int pos = 0; + int i, copy = start - offset; + + /* Copy header. */ + if (copy > 0) { + int err = 0; + if (copy > len) + copy = len; + *csump = csum_and_copy_to_user(skb->data + offset, to, copy, + *csump, &err); + if (err) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + to += copy; + pos = copy; + } + + 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) { + unsigned int csum2; + int err = 0; + u8 *vaddr; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = frag->page; + + if (copy > len) + copy = len; + vaddr = kmap(page); + csum2 = csum_and_copy_to_user(vaddr + + frag->page_offset + + offset - start, + to, copy, 0, &err); + kunmap(page); + if (err) + goto fault; + *csump = csum_block_add(*csump, csum2, pos); + if (!(len -= copy)) + return 0; + offset += copy; + to += copy; + pos += 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) { + unsigned int csum2 = 0; + if (copy > len) + copy = len; + if (skb_copy_and_csum_datagram(list, + offset - start, + to, copy, + &csum2)) + goto fault; + *csump = csum_block_add(*csump, csum2, pos); + if ((len -= copy) == 0) + return 0; + offset += copy; + to += copy; + pos += copy; + } + start = end; + } + } + if (!len) + return 0; + +fault: + return -EFAULT; +} + +/** + * skb_copy_and_csum_datagram_iovec - Copy and checkum skb to user iovec. + * @skb - skbuff + * @hlen - hardware length + * @iovec - io vector + * + * Caller _must_ check that skb will fit to this iovec. + * + * Returns: 0 - success. + * -EINVAL - checksum failure. + * -EFAULT - fault during copy. Beware, in this case iovec + * can be modified! + */ +int skb_copy_and_csum_datagram_iovec(const struct sk_buff *skb, + int hlen, struct iovec *iov) +{ + unsigned int csum; + int chunk = skb->len - hlen; + + /* Skip filled elements. + * Pretty silly, look at memcpy_toiovec, though 8) + */ + while (!iov->iov_len) + iov++; + + if (iov->iov_len < chunk) { + if ((unsigned short)csum_fold(skb_checksum(skb, 0, chunk + hlen, + skb->csum))) + goto csum_error; + if (skb_copy_datagram_iovec(skb, hlen, iov, chunk)) + goto fault; + } else { + csum = csum_partial(skb->data, hlen, skb->csum); + if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base, + chunk, &csum)) + goto fault; + if ((unsigned short)csum_fold(csum)) + goto csum_error; + iov->iov_len -= chunk; + iov->iov_base += chunk; + } + return 0; +csum_error: + return -EINVAL; +fault: + return -EFAULT; +} + +/** + * datagram_poll - generic datagram poll + * @file - file struct + * @sock - socket + * @wait - poll table + * + * Datagram poll: Again totally generic. This also handles + * sequenced packet sockets providing the socket receive queue + * is only ever holding data ready to receive. + * + * Note: when you _don't_ use this routine for this protocol, + * and you use a different write policy from sock_writeable() + * then please supply your own write_space callback. + */ +unsigned int datagram_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + struct sock *sk = sock->sk; + unsigned int mask; + + poll_wait(file, sk->sk_sleep, wait); + mask = 0; + + /* exceptional events? */ + if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + mask |= POLLERR; + if (sk->sk_shutdown == SHUTDOWN_MASK) + mask |= POLLHUP; + + /* readable? */ + if (!skb_queue_empty(&sk->sk_receive_queue) || + (sk->sk_shutdown & RCV_SHUTDOWN)) + mask |= POLLIN | POLLRDNORM; + + /* Connection-based need to check for termination and startup */ + if (connection_based(sk)) { + if (sk->sk_state == TCP_CLOSE) + mask |= POLLHUP; + /* connection hasn't started yet? */ + if (sk->sk_state == TCP_SYN_SENT) + return mask; + } + + /* writable? */ + if (sock_writeable(sk)) + mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + else + set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + + return mask; +} + +EXPORT_SYMBOL(datagram_poll); +EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec); +EXPORT_SYMBOL(skb_copy_datagram_iovec); +EXPORT_SYMBOL(skb_free_datagram); +EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/core/dev.c b/net/core/dev.c new file mode 100644 index 000000000000..42344d903692 --- /dev/null +++ b/net/core/dev.c @@ -0,0 +1,3359 @@ +/* + * NET3 Protocol independent device support routines. + * + * 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. + * + * Derived from the non IP parts of dev.c 1.0.19 + * Authors: Ross Biro, <bir7@leland.Stanford.Edu> + * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> + * Mark Evans, <evansmp@uhura.aston.ac.uk> + * + * Additional Authors: + * Florian la Roche <rzsfl@rz.uni-sb.de> + * Alan Cox <gw4pts@gw4pts.ampr.org> + * David Hinds <dahinds@users.sourceforge.net> + * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> + * Adam Sulmicki <adam@cfar.umd.edu> + * Pekka Riikonen <priikone@poesidon.pspt.fi> + * + * Changes: + * D.J. Barrow : Fixed bug where dev->refcnt gets set + * to 2 if register_netdev gets called + * before net_dev_init & also removed a + * few lines of code in the process. + * Alan Cox : device private ioctl copies fields back. + * Alan Cox : Transmit queue code does relevant + * stunts to keep the queue safe. + * Alan Cox : Fixed double lock. + * Alan Cox : Fixed promisc NULL pointer trap + * ???????? : Support the full private ioctl range + * Alan Cox : Moved ioctl permission check into + * drivers + * Tim Kordas : SIOCADDMULTI/SIOCDELMULTI + * Alan Cox : 100 backlog just doesn't cut it when + * you start doing multicast video 8) + * Alan Cox : Rewrote net_bh and list manager. + * Alan Cox : Fix ETH_P_ALL echoback lengths. + * Alan Cox : Took out transmit every packet pass + * Saved a few bytes in the ioctl handler + * Alan Cox : Network driver sets packet type before + * calling netif_rx. Saves a function + * call a packet. + * Alan Cox : Hashed net_bh() + * Richard Kooijman: Timestamp fixes. + * Alan Cox : Wrong field in SIOCGIFDSTADDR + * Alan Cox : Device lock protection. + * Alan Cox : Fixed nasty side effect of device close + * changes. + * Rudi Cilibrasi : Pass the right thing to + * set_mac_address() + * Dave Miller : 32bit quantity for the device lock to + * make it work out on a Sparc. + * Bjorn Ekwall : Added KERNELD hack. + * Alan Cox : Cleaned up the backlog initialise. + * Craig Metz : SIOCGIFCONF fix if space for under + * 1 device. + * Thomas Bogendoerfer : Return ENODEV for dev_open, if there + * is no device open function. + * Andi Kleen : Fix error reporting for SIOCGIFCONF + * Michael Chastain : Fix signed/unsigned for SIOCGIFCONF + * Cyrus Durgin : Cleaned for KMOD + * Adam Sulmicki : Bug Fix : Network Device Unload + * A network device unload needs to purge + * the backlog queue. + * Paul Rusty Russell : SIOCSIFNAME + * Pekka Riikonen : Netdev boot-time settings code + * Andrew Morton : Make unregister_netdevice wait + * indefinitely on dev->refcnt + * J Hadi Salim : - Backlog queue sampling + * - netif_rx() feedback + */ + +#include <asm/uaccess.h> +#include <asm/system.h> +#include <linux/bitops.h> +#include <linux/config.h> +#include <linux/cpu.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/sockios.h> +#include <linux/errno.h> +#include <linux/interrupt.h> +#include <linux/if_ether.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/notifier.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <linux/rtnetlink.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/stat.h> +#include <linux/if_bridge.h> +#include <linux/divert.h> +#include <net/dst.h> +#include <net/pkt_sched.h> +#include <net/checksum.h> +#include <linux/highmem.h> +#include <linux/init.h> +#include <linux/kmod.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/netpoll.h> +#include <linux/rcupdate.h> +#include <linux/delay.h> +#ifdef CONFIG_NET_RADIO +#include <linux/wireless.h> /* Note : will define WIRELESS_EXT */ +#include <net/iw_handler.h> +#endif /* CONFIG_NET_RADIO */ +#include <asm/current.h> + +/* This define, if set, will randomly drop a packet when congestion + * is more than moderate. It helps fairness in the multi-interface + * case when one of them is a hog, but it kills performance for the + * single interface case so it is off now by default. + */ +#undef RAND_LIE + +/* Setting this will sample the queue lengths and thus congestion + * via a timer instead of as each packet is received. + */ +#undef OFFLINE_SAMPLE + +/* + * The list of packet types we will receive (as opposed to discard) + * and the routines to invoke. + * + * Why 16. Because with 16 the only overlap we get on a hash of the + * low nibble of the protocol value is RARP/SNAP/X.25. + * + * NOTE: That is no longer true with the addition of VLAN tags. Not + * sure which should go first, but I bet it won't make much + * difference if we are running VLANs. The good news is that + * this protocol won't be in the list unless compiled in, so + * the average user (w/out VLANs) will not be adversly affected. + * --BLG + * + * 0800 IP + * 8100 802.1Q VLAN + * 0001 802.3 + * 0002 AX.25 + * 0004 802.2 + * 8035 RARP + * 0005 SNAP + * 0805 X.25 + * 0806 ARP + * 8137 IPX + * 0009 Localtalk + * 86DD IPv6 + */ + +static DEFINE_SPINLOCK(ptype_lock); +static struct list_head ptype_base[16]; /* 16 way hashed list */ +static struct list_head ptype_all; /* Taps */ + +#ifdef OFFLINE_SAMPLE +static void sample_queue(unsigned long dummy); +static struct timer_list samp_timer = TIMER_INITIALIZER(sample_queue, 0, 0); +#endif + +/* + * The @dev_base list is protected by @dev_base_lock and the rtln + * semaphore. + * + * Pure readers hold dev_base_lock for reading. + * + * Writers must hold the rtnl semaphore while they loop through the + * dev_base list, and hold dev_base_lock for writing when they do the + * actual updates. This allows pure readers to access the list even + * while a writer is preparing to update it. + * + * To put it another way, dev_base_lock is held for writing only to + * protect against pure readers; the rtnl semaphore provides the + * protection against other writers. + * + * See, for example usages, register_netdevice() and + * unregister_netdevice(), which must be called with the rtnl + * semaphore held. + */ +struct net_device *dev_base; +static struct net_device **dev_tail = &dev_base; +DEFINE_RWLOCK(dev_base_lock); + +EXPORT_SYMBOL(dev_base); +EXPORT_SYMBOL(dev_base_lock); + +#define NETDEV_HASHBITS 8 +static struct hlist_head dev_name_head[1<<NETDEV_HASHBITS]; +static struct hlist_head dev_index_head[1<<NETDEV_HASHBITS]; + +static inline struct hlist_head *dev_name_hash(const char *name) +{ + unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); + return &dev_name_head[hash & ((1<<NETDEV_HASHBITS)-1)]; +} + +static inline struct hlist_head *dev_index_hash(int ifindex) +{ + return &dev_index_head[ifindex & ((1<<NETDEV_HASHBITS)-1)]; +} + +/* + * Our notifier list + */ + +static struct notifier_block *netdev_chain; + +/* + * Device drivers call our routines to queue packets here. We empty the + * queue in the local softnet handler. + */ +DEFINE_PER_CPU(struct softnet_data, softnet_data) = { 0, }; + +#ifdef CONFIG_SYSFS +extern int netdev_sysfs_init(void); +extern int netdev_register_sysfs(struct net_device *); +extern void netdev_unregister_sysfs(struct net_device *); +#else +#define netdev_sysfs_init() (0) +#define netdev_register_sysfs(dev) (0) +#define netdev_unregister_sysfs(dev) do { } while(0) +#endif + + +/******************************************************************************* + + Protocol management and registration routines + +*******************************************************************************/ + +/* + * For efficiency + */ + +int netdev_nit; + +/* + * Add a protocol ID to the list. Now that the input handler is + * smarter we can dispense with all the messy stuff that used to be + * here. + * + * BEWARE!!! Protocol handlers, mangling input packets, + * MUST BE last in hash buckets and checking protocol handlers + * MUST start from promiscuous ptype_all chain in net_bh. + * It is true now, do not change it. + * Explanation follows: if protocol handler, mangling packet, will + * be the first on list, it is not able to sense, that packet + * is cloned and should be copied-on-write, so that it will + * change it and subsequent readers will get broken packet. + * --ANK (980803) + */ + +/** + * dev_add_pack - add packet handler + * @pt: packet type declaration + * + * Add a protocol handler to the networking stack. The passed &packet_type + * is linked into kernel lists and may not be freed until it has been + * removed from the kernel lists. + * + * This call does not sleep therefore it can not + * guarantee all CPU's that are in middle of receiving packets + * will see the new packet type (until the next received packet). + */ + +void dev_add_pack(struct packet_type *pt) +{ + int hash; + + spin_lock_bh(&ptype_lock); + if (pt->type == htons(ETH_P_ALL)) { + netdev_nit++; + list_add_rcu(&pt->list, &ptype_all); + } else { + hash = ntohs(pt->type) & 15; + list_add_rcu(&pt->list, &ptype_base[hash]); + } + spin_unlock_bh(&ptype_lock); +} + +extern void linkwatch_run_queue(void); + + + +/** + * __dev_remove_pack - remove packet handler + * @pt: packet type declaration + * + * Remove a protocol handler that was previously added to the kernel + * protocol handlers by dev_add_pack(). The passed &packet_type is removed + * from the kernel lists and can be freed or reused once this function + * returns. + * + * The packet type might still be in use by receivers + * and must not be freed until after all the CPU's have gone + * through a quiescent state. + */ +void __dev_remove_pack(struct packet_type *pt) +{ + struct list_head *head; + struct packet_type *pt1; + + spin_lock_bh(&ptype_lock); + + if (pt->type == htons(ETH_P_ALL)) { + netdev_nit--; + head = &ptype_all; + } else + head = &ptype_base[ntohs(pt->type) & 15]; + + list_for_each_entry(pt1, head, list) { + if (pt == pt1) { + list_del_rcu(&pt->list); + goto out; + } + } + + printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt); +out: + spin_unlock_bh(&ptype_lock); +} +/** + * dev_remove_pack - remove packet handler + * @pt: packet type declaration + * + * Remove a protocol handler that was previously added to the kernel + * protocol handlers by dev_add_pack(). The passed &packet_type is removed + * from the kernel lists and can be freed or reused once this function + * returns. + * + * This call sleeps to guarantee that no CPU is looking at the packet + * type after return. + */ +void dev_remove_pack(struct packet_type *pt) +{ + __dev_remove_pack(pt); + + synchronize_net(); +} + +/****************************************************************************** + + Device Boot-time Settings Routines + +*******************************************************************************/ + +/* Boot time configuration table */ +static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX]; + +/** + * netdev_boot_setup_add - add new setup entry + * @name: name of the device + * @map: configured settings for the device + * + * Adds new setup entry to the dev_boot_setup list. The function + * returns 0 on error and 1 on success. This is a generic routine to + * all netdevices. + */ +static int netdev_boot_setup_add(char *name, struct ifmap *map) +{ + struct netdev_boot_setup *s; + int i; + + s = dev_boot_setup; + for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { + if (s[i].name[0] == '\0' || s[i].name[0] == ' ') { + memset(s[i].name, 0, sizeof(s[i].name)); + strcpy(s[i].name, name); + memcpy(&s[i].map, map, sizeof(s[i].map)); + break; + } + } + + return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1; +} + +/** + * netdev_boot_setup_check - check boot time settings + * @dev: the netdevice + * + * Check boot time settings for the device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found, 1 if they are. + */ +int netdev_boot_setup_check(struct net_device *dev) +{ + struct netdev_boot_setup *s = dev_boot_setup; + int i; + + for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { + if (s[i].name[0] != '\0' && s[i].name[0] != ' ' && + !strncmp(dev->name, s[i].name, strlen(s[i].name))) { + dev->irq = s[i].map.irq; + dev->base_addr = s[i].map.base_addr; + dev->mem_start = s[i].map.mem_start; + dev->mem_end = s[i].map.mem_end; + return 1; + } + } + return 0; +} + + +/** + * netdev_boot_base - get address from boot time settings + * @prefix: prefix for network device + * @unit: id for network device + * + * Check boot time settings for the base address of device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found. + */ +unsigned long netdev_boot_base(const char *prefix, int unit) +{ + const struct netdev_boot_setup *s = dev_boot_setup; + char name[IFNAMSIZ]; + int i; + + sprintf(name, "%s%d", prefix, unit); + + /* + * If device already registered then return base of 1 + * to indicate not to probe for this interface + */ + if (__dev_get_by_name(name)) + return 1; + + for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) + if (!strcmp(name, s[i].name)) + return s[i].map.base_addr; + return 0; +} + +/* + * Saves at boot time configured settings for any netdevice. + */ +int __init netdev_boot_setup(char *str) +{ + int ints[5]; + struct ifmap map; + + str = get_options(str, ARRAY_SIZE(ints), ints); + if (!str || !*str) + return 0; + + /* Save settings */ + memset(&map, 0, sizeof(map)); + if (ints[0] > 0) + map.irq = ints[1]; + if (ints[0] > 1) + map.base_addr = ints[2]; + if (ints[0] > 2) + map.mem_start = ints[3]; + if (ints[0] > 3) + map.mem_end = ints[4]; + + /* Add new entry to the list */ + return netdev_boot_setup_add(str, &map); +} + +__setup("netdev=", netdev_boot_setup); + +/******************************************************************************* + + Device Interface Subroutines + +******************************************************* |