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!

2 files changed, 1912 insertions, 0 deletions

diff --git a/net/packet/Makefile b/net/packet/Makefile
new file mode 100644
index 000000000000..81183eabfdec
--- /dev/null
+++ b/net/packet/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the packet AF.
+#
+
+obj-$(CONFIG_PACKET) += af_packet.o
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
new file mode 100644
index 000000000000..64acea0adaae
--- /dev/null
+++ b/net/packet/af_packet.c
@@ -0,0 +1,1907 @@
+/*
+ * 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.
+ *
+ *		PACKET - implements raw packet sockets.
+ *
+ * Version:	$Id: af_packet.c,v 1.61 2002/02/08 03:57:19 davem Exp $
+ *
+ * Authors:	Ross Biro, <bir7@leland.Stanford.Edu>
+ *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *		Alan Cox, <gw4pts@gw4pts.ampr.org>
+ *
+ * Fixes:	
+ *		Alan Cox	:	verify_area() now used correctly
+ *		Alan Cox	:	new skbuff lists, look ma no backlogs!
+ *		Alan Cox	:	tidied skbuff lists.
+ *		Alan Cox	:	Now uses generic datagram routines I
+ *					added. Also fixed the peek/read crash
+ *					from all old Linux datagram code.
+ *		Alan Cox	:	Uses the improved datagram code.
+ *		Alan Cox	:	Added NULL's for socket options.
+ *		Alan Cox	:	Re-commented the code.
+ *		Alan Cox	:	Use new kernel side addressing
+ *		Rob Janssen	:	Correct MTU usage.
+ *		Dave Platt	:	Counter leaks caused by incorrect
+ *					interrupt locking and some slightly
+ *					dubious gcc output. Can you read
+ *					compiler: it said _VOLATILE_
+ *	Richard Kooijman	:	Timestamp fixes.
+ *		Alan Cox	:	New buffers. Use sk->mac.raw.
+ *		Alan Cox	:	sendmsg/recvmsg support.
+ *		Alan Cox	:	Protocol setting support
+ *	Alexey Kuznetsov	:	Untied from IPv4 stack.
+ *	Cyrus Durgin		:	Fixed kerneld for kmod.
+ *	Michal Ostrowski        :       Module initialization cleanup.
+ *         Ulises Alonso        :       Frame number limit removal and 
+ *                                      packet_set_ring memory leak.
+ *
+ *		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/types.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/fcntl.h>
+#include <linux/socket.h>
+#include <linux/in.h>
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <linux/if_packet.h>
+#include <linux/wireless.h>
+#include <linux/kmod.h>
+#include <net/ip.h>
+#include <net/protocol.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <linux/errno.h>
+#include <linux/timer.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/ioctls.h>
+#include <asm/page.h>
+#include <asm/io.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/poll.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#ifdef CONFIG_INET
+#include <net/inet_common.h>
+#endif
+
+#define CONFIG_SOCK_PACKET	1
+
+/*
+   Proposed replacement for SIOC{ADD,DEL}MULTI and
+   IFF_PROMISC, IFF_ALLMULTI flags.
+
+   It is more expensive, but I believe,
+   it is really correct solution: reentereble, safe and fault tolerant.
+
+   IFF_PROMISC/IFF_ALLMULTI/SIOC{ADD/DEL}MULTI are faked by keeping
+   reference count and global flag, so that real status is
+   (gflag|(count != 0)), so that we can use obsolete faulty interface
+   not harming clever users.
+ */
+#define CONFIG_PACKET_MULTICAST	1
+
+/*
+   Assumptions:
+   - if device has no dev->hard_header routine, it adds and removes ll header
+     inside itself. In this case ll header is invisible outside of device,
+     but higher levels still should reserve dev->hard_header_len.
+     Some devices are enough clever to reallocate skb, when header
+     will not fit to reserved space (tunnel), another ones are silly
+     (PPP).
+   - packet socket receives packets with pulled ll header,
+     so that SOCK_RAW should push it back.
+
+On receive:
+-----------
+
+Incoming, dev->hard_header!=NULL
+   mac.raw -> ll header
+   data    -> data
+
+Outgoing, dev->hard_header!=NULL
+   mac.raw -> ll header
+   data    -> ll header
+
+Incoming, dev->hard_header==NULL
+   mac.raw -> UNKNOWN position. It is very likely, that it points to ll header.
+              PPP makes it, that is wrong, because introduce assymetry
+	      between rx and tx paths.
+   data    -> data
+
+Outgoing, dev->hard_header==NULL
+   mac.raw -> data. ll header is still not built!
+   data    -> data
+
+Resume
+  If dev->hard_header==NULL we are unlikely to restore sensible ll header.
+
+
+On transmit:
+------------
+
+dev->hard_header != NULL
+   mac.raw -> ll header
+   data    -> ll header
+
+dev->hard_header == NULL (ll header is added by device, we cannot control it)
+   mac.raw -> data
+   data -> data
+
+   We should set nh.raw on output to correct posistion,
+   packet classifier depends on it.
+ */
+
+/* List of all packet sockets. */
+static HLIST_HEAD(packet_sklist);
+static DEFINE_RWLOCK(packet_sklist_lock);
+
+static atomic_t packet_socks_nr;
+
+
+/* Private packet socket structures. */
+
+#ifdef CONFIG_PACKET_MULTICAST
+struct packet_mclist
+{
+	struct packet_mclist	*next;
+	int			ifindex;
+	int			count;
+	unsigned short		type;
+	unsigned short		alen;
+	unsigned char		addr[8];
+};
+#endif
+#ifdef CONFIG_PACKET_MMAP
+static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing);
+#endif
+
+static void packet_flush_mclist(struct sock *sk);
+
+struct packet_sock {
+	/* struct sock has to be the first member of packet_sock */
+	struct sock		sk;
+	struct tpacket_stats	stats;
+#ifdef CONFIG_PACKET_MMAP
+	char *			*pg_vec;
+	unsigned int		head;
+	unsigned int            frames_per_block;
+	unsigned int		frame_size;
+	unsigned int		frame_max;
+	int			copy_thresh;
+#endif
+	struct packet_type	prot_hook;
+	spinlock_t		bind_lock;
+	char			running;	/* prot_hook is attached*/
+	int			ifindex;	/* bound device		*/
+	unsigned short		num;
+#ifdef CONFIG_PACKET_MULTICAST
+	struct packet_mclist	*mclist;
+#endif
+#ifdef CONFIG_PACKET_MMAP
+	atomic_t		mapped;
+	unsigned int            pg_vec_order;
+	unsigned int		pg_vec_pages;
+	unsigned int		pg_vec_len;
+#endif
+};
+
+#ifdef CONFIG_PACKET_MMAP
+
+static inline char *packet_lookup_frame(struct packet_sock *po, unsigned int position)
+{
+	unsigned int pg_vec_pos, frame_offset;
+	char *frame;
+
+	pg_vec_pos = position / po->frames_per_block;
+	frame_offset = position % po->frames_per_block;
+
+	frame = po->pg_vec[pg_vec_pos] + (frame_offset * po->frame_size);
+	
+	return frame;
+}
+#endif
+
+static inline struct packet_sock *pkt_sk(struct sock *sk)
+{
+	return (struct packet_sock *)sk;
+}
+
+static void packet_sock_destruct(struct sock *sk)
+{
+	BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
+	BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
+
+	if (!sock_flag(sk, SOCK_DEAD)) {
+		printk("Attempt to release alive packet socket: %p\n", sk);
+		return;
+	}
+
+	atomic_dec(&packet_socks_nr);
+#ifdef PACKET_REFCNT_DEBUG
+	printk(KERN_DEBUG "PACKET socket %p is free, %d are alive\n", sk, atomic_read(&packet_socks_nr));
+#endif
+}
+
+
+static struct proto_ops packet_ops;
+
+#ifdef CONFIG_SOCK_PACKET
+static struct proto_ops packet_ops_spkt;
+
+static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev,  struct packet_type *pt)
+{
+	struct sock *sk;
+	struct sockaddr_pkt *spkt;
+
+	/*
+	 *	When we registered the protocol we saved the socket in the data
+	 *	field for just this event.
+	 */
+
+	sk = pt->af_packet_priv;
+	
+	/*
+	 *	Yank back the headers [hope the device set this
+	 *	right or kerboom...]
+	 *
+	 *	Incoming packets have ll header pulled,
+	 *	push it back.
+	 *
+	 *	For outgoing ones skb->data == skb->mac.raw
+	 *	so that this procedure is noop.
+	 */
+
+	if (skb->pkt_type == PACKET_LOOPBACK)
+		goto out;
+
+	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
+		goto oom;
+
+	/* drop any routing info */
+	dst_release(skb->dst);
+	skb->dst = NULL;
+
+	spkt = (struct sockaddr_pkt*)skb->cb;
+
+	skb_push(skb, skb->data-skb->mac.raw);
+
+	/*
+	 *	The SOCK_PACKET socket receives _all_ frames.
+	 */
+
+	spkt->spkt_family = dev->type;
+	strlcpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device));
+	spkt->spkt_protocol = skb->protocol;
+
+	/*
+	 *	Charge the memory to the socket. This is done specifically
+	 *	to prevent sockets using all the memory up.
+	 */
+
+	if (sock_queue_rcv_skb(sk,skb) == 0)
+		return 0;
+
+out:
+	kfree_skb(skb);
+oom:
+	return 0;
+}
+
+
+/*
+ *	Output a raw packet to a device layer. This bypasses all the other
+ *	protocol layers and you must therefore supply it with a complete frame
+ */
+ 
+static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock,
+			       struct msghdr *msg, size_t len)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_pkt *saddr=(struct sockaddr_pkt *)msg->msg_name;
+	struct sk_buff *skb;
+	struct net_device *dev;
+	unsigned short proto=0;
+	int err;
+	
+	/*
+	 *	Get and verify the address. 
+	 */
+
+	if (saddr)
+	{
+		if (msg->msg_namelen < sizeof(struct sockaddr))
+			return(-EINVAL);
+		if (msg->msg_namelen==sizeof(struct sockaddr_pkt))
+			proto=saddr->spkt_protocol;
+	}
+	else
+		return(-ENOTCONN);	/* SOCK_PACKET must be sent giving an address */
+
+	/*
+	 *	Find the device first to size check it 
+	 */
+
+	saddr->spkt_device[13] = 0;
+	dev = dev_get_by_name(saddr->spkt_device);
+	err = -ENODEV;
+	if (dev == NULL)
+		goto out_unlock;
+	
+	/*
+	 *	You may not queue a frame bigger than the mtu. This is the lowest level
+	 *	raw protocol and you must do your own fragmentation at this level.
+	 */
+	 
+	err = -EMSGSIZE;
+ 	if(len>dev->mtu+dev->hard_header_len)
+		goto out_unlock;
+
+	err = -ENOBUFS;
+	skb = sock_wmalloc(sk, len + LL_RESERVED_SPACE(dev), 0, GFP_KERNEL);
+
+	/*
+	 *	If the write buffer is full, then tough. At this level the user gets to
+	 *	deal with the problem - do your own algorithmic backoffs. That's far
+	 *	more flexible.
+	 */
+	 
+	if (skb == NULL) 
+		goto out_unlock;
+
+	/*
+	 *	Fill it in 
+	 */
+	 
+	/* FIXME: Save some space for broken drivers that write a
+	 * hard header at transmission time by themselves. PPP is the
+	 * notable one here. This should really be fixed at the driver level.
+	 */
+	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb->nh.raw = skb->data;
+
+	/* Try to align data part correctly */
+	if (dev->hard_header) {
+		skb->data -= dev->hard_header_len;
+		skb->tail -= dev->hard_header_len;
+		if (len < dev->hard_header_len)
+			skb->nh.raw = skb->data;
+	}
+
+	/* Returns -EFAULT on error */
+	err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len);
+	skb->protocol = proto;
+	skb->dev = dev;
+	skb->priority = sk->sk_priority;
+	if (err)
+		goto out_free;
+
+	err = -ENETDOWN;
+	if (!(dev->flags & IFF_UP))
+		goto out_free;
+
+	/*
+	 *	Now send it
+	 */
+
+	dev_queue_xmit(skb);
+	dev_put(dev);
+	return(len);
+
+out_free:
+	kfree_skb(skb);
+out_unlock:
+	if (dev)
+		dev_put(dev);
+	return err;
+}
+#endif
+
+static inline unsigned run_filter(struct sk_buff *skb, struct sock *sk, unsigned res)
+{
+	struct sk_filter *filter;
+
+	bh_lock_sock(sk);
+	filter = sk->sk_filter;
+	/*
+	 * Our caller already checked that filter != NULL but we need to
+	 * verify that under bh_lock_sock() to be safe
+	 */
+	if (likely(filter != NULL))
+		res = sk_run_filter(skb, filter->insns, filter->len);
+	bh_unlock_sock(sk);
+
+	return res;
+}
+
+/*
+   This function makes lazy skb cloning in hope that most of packets
+   are discarded by BPF.
+
+   Note tricky part: we DO mangle shared skb! skb->data, skb->len
+   and skb->cb are mangled. It works because (and until) packets
+   falling here are owned by current CPU. Output packets are cloned
+   by dev_queue_xmit_nit(), input packets are processed by net_bh
+   sequencially, so that if we return skb to original state on exit,
+   we will not harm anyone.
+ */
+
+static int packet_rcv(struct sk_buff *skb, struct net_device *dev,  struct packet_type *pt)
+{
+	struct sock *sk;
+	struct sockaddr_ll *sll;
+	struct packet_sock *po;
+	u8 * skb_head = skb->data;
+	int skb_len = skb->len;
+	unsigned snaplen;
+
+	if (skb->pkt_type == PACKET_LOOPBACK)
+		goto drop;
+
+	sk = pt->af_packet_priv;
+	po = pkt_sk(sk);
+
+	skb->dev = dev;
+
+	if (dev->hard_header) {
+		/* The device has an explicit notion of ll header,
+		   exported to higher levels.
+
+		   Otherwise, the device hides datails of it frame
+		   structure, so that corresponding packet head
+		   never delivered to user.
+		 */
+		if (sk->sk_type != SOCK_DGRAM)
+			skb_push(skb, skb->data - skb->mac.raw);
+		else if (skb->pkt_type == PACKET_OUTGOING) {
+			/* Special case: outgoing packets have ll header at head */
+			skb_pull(skb, skb->nh.raw - skb->data);
+		}
+	}
+
+	snaplen = skb->len;
+
+	if (sk->sk_filter) {
+		unsigned res = run_filter(skb, sk, snaplen);
+		if (res == 0)
+			goto drop_n_restore;
+		if (snaplen > res)
+			snaplen = res;
+	}
+
+	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
+	    (unsigned)sk->sk_rcvbuf)
+		goto drop_n_acct;
+
+	if (skb_shared(skb)) {
+		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+		if (nskb == NULL)
+			goto drop_n_acct;
+
+		if (skb_head != skb->data) {
+			skb->data = skb_head;
+			skb->len = skb_len;
+		}
+		kfree_skb(skb);
+		skb = nskb;
+	}
+
+	sll = (struct sockaddr_ll*)skb->cb;
+	sll->sll_family = AF_PACKET;
+	sll->sll_hatype = dev->type;
+	sll->sll_protocol = skb->protocol;
+	sll->sll_pkttype = skb->pkt_type;
+	sll->sll_ifindex = dev->ifindex;
+	sll->sll_halen = 0;
+
+	if (dev->hard_header_parse)
+		sll->sll_halen = dev->hard_header_parse(skb, sll->sll_addr);
+
+	if (pskb_trim(skb, snaplen))
+		goto drop_n_acct;
+
+	skb_set_owner_r(skb, sk);
+	skb->dev = NULL;
+	dst_release(skb->dst);
+	skb->dst = NULL;
+
+	spin_lock(&sk->sk_receive_queue.lock);
+	po->stats.tp_packets++;
+	__skb_queue_tail(&sk->sk_receive_queue, skb);
+	spin_unlock(&sk->sk_receive_queue.lock);
+	sk->sk_data_ready(sk, skb->len);
+	return 0;
+
+drop_n_acct:
+	spin_lock(&sk->sk_receive_queue.lock);
+	po->stats.tp_drops++;
+	spin_unlock(&sk->sk_receive_queue.lock);
+
+drop_n_restore:
+	if (skb_head != skb->data && skb_shared(skb)) {
+		skb->data = skb_head;
+		skb->len = skb_len;
+	}
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+
+#ifdef CONFIG_PACKET_MMAP
+static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,  struct packet_type *pt)
+{
+	struct sock *sk;
+	struct packet_sock *po;
+	struct sockaddr_ll *sll;
+	struct tpacket_hdr *h;
+	u8 * skb_head = skb->data;
+	int skb_len = skb->len;
+	unsigned snaplen;
+	unsigned long status = TP_STATUS_LOSING|TP_STATUS_USER;
+	unsigned short macoff, netoff;
+	struct sk_buff *copy_skb = NULL;
+
+	if (skb->pkt_type == PACKET_LOOPBACK)
+		goto drop;
+
+	sk = pt->af_packet_priv;
+	po = pkt_sk(sk);
+
+	if (dev->hard_header) {
+		if (sk->sk_type != SOCK_DGRAM)
+			skb_push(skb, skb->data - skb->mac.raw);
+		else if (skb->pkt_type == PACKET_OUTGOING) {
+			/* Special case: outgoing packets have ll header at head */
+			skb_pull(skb, skb->nh.raw - skb->data);
+			if (skb->ip_summed == CHECKSUM_HW)
+				status |= TP_STATUS_CSUMNOTREADY;
+		}
+	}
+
+	snaplen = skb->len;
+
+	if (sk->sk_filter) {
+		unsigned res = run_filter(skb, sk, snaplen);
+		if (res == 0)
+			goto drop_n_restore;
+		if (snaplen > res)
+			snaplen = res;
+	}
+
+	if (sk->sk_type == SOCK_DGRAM) {
+		macoff = netoff = TPACKET_ALIGN(TPACKET_HDRLEN) + 16;
+	} else {
+		unsigned maclen = skb->nh.raw - skb->data;
+		netoff = TPACKET_ALIGN(TPACKET_HDRLEN + (maclen < 16 ? 16 : maclen));
+		macoff = netoff - maclen;
+	}
+
+	if (macoff + snaplen > po->frame_size) {
+		if (po->copy_thresh &&
+		    atomic_read(&sk->sk_rmem_alloc) + skb->truesize <
+		    (unsigned)sk->sk_rcvbuf) {
+			if (skb_shared(skb)) {
+				copy_skb = skb_clone(skb, GFP_ATOMIC);
+			} else {
+				copy_skb = skb_get(skb);
+				skb_head = skb->data;
+			}
+			if (copy_skb)
+				skb_set_owner_r(copy_skb, sk);
+		}
+		snaplen = po->frame_size - macoff;
+		if ((int)snaplen < 0)
+			snaplen = 0;
+	}
+	if (snaplen > skb->len-skb->data_len)
+		snaplen = skb->len-skb->data_len;
+
+	spin_lock(&sk->sk_receive_queue.lock);
+	h = (struct tpacket_hdr *)packet_lookup_frame(po, po->head);
+	
+	if (h->tp_status)
+		goto ring_is_full;
+	po->head = po->head != po->frame_max ? po->head+1 : 0;
+	po->stats.tp_packets++;
+	if (copy_skb) {
+		status |= TP_STATUS_COPY;
+		__skb_queue_tail(&sk->sk_receive_queue, copy_skb);
+	}
+	if (!po->stats.tp_drops)
+		status &= ~TP_STATUS_LOSING;
+	spin_unlock(&sk->sk_receive_queue.lock);
+
+	memcpy((u8*)h + macoff, skb->data, snaplen);
+
+	h->tp_len = skb->len;
+	h->tp_snaplen = snaplen;
+	h->tp_mac = macoff;
+	h->tp_net = netoff;
+	if (skb->stamp.tv_sec == 0) { 
+		do_gettimeofday(&skb->stamp);
+		sock_enable_timestamp(sk);
+	}
+	h->tp_sec = skb->stamp.tv_sec;
+	h->tp_usec = skb->stamp.tv_usec;
+
+	sll = (struct sockaddr_ll*)((u8*)h + TPACKET_ALIGN(sizeof(*h)));
+	sll->sll_halen = 0;
+	if (dev->hard_header_parse)
+		sll->sll_halen = dev->hard_header_parse(skb, sll->sll_addr);
+	sll->sll_family = AF_PACKET;
+	sll->sll_hatype = dev->type;
+	sll->sll_protocol = skb->protocol;
+	sll->sll_pkttype = skb->pkt_type;
+	sll->sll_ifindex = dev->ifindex;
+
+	h->tp_status = status;
+	mb();
+
+	{
+		struct page *p_start, *p_end;
+		u8 *h_end = (u8 *)h + macoff + snaplen - 1;
+
+		p_start = virt_to_page(h);
+		p_end = virt_to_page(h_end);
+		while (p_start <= p_end) {
+			flush_dcache_page(p_start);
+			p_start++;
+		}
+	}
+
+	sk->sk_data_ready(sk, 0);
+
+drop_n_restore:
+	if (skb_head != skb->data && skb_shared(skb)) {
+		skb->data = skb_head;
+		skb->len = skb_len;
+	}
+drop:
+        kfree_skb(skb);
+	return 0;
+
+ring_is_full:
+	po->stats.tp_drops++;
+	spin_unlock(&sk->sk_receive_queue.lock);
+
+	sk->sk_data_ready(sk, 0);
+	if (copy_skb)
+		kfree_skb(copy_skb);
+	goto drop_n_restore;
+}
+
+#endif
+
+
+static int packet_sendmsg(struct kiocb *iocb, struct socket *sock,
+			  struct msghdr *msg, size_t len)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_ll *saddr=(struct sockaddr_ll *)msg->msg_name;
+	struct sk_buff *skb;
+	struct net_device *dev;
+	unsigned short proto;
+	unsigned char *addr;
+	int ifindex, err, reserve = 0;
+
+	/*
+	 *	Get and verify the address. 
+	 */
+	 
+	if (saddr == NULL) {
+		struct packet_sock *po = pkt_sk(sk);
+
+		ifindex	= po->ifindex;
+		proto	= po->num;
+		addr	= NULL;
+	} else {
+		err = -EINVAL;
+		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
+			goto out;
+		ifindex	= saddr->sll_ifindex;
+		proto	= saddr->sll_protocol;
+		addr	= saddr->sll_addr;
+	}
+
+
+	dev = dev_get_by_index(ifindex);
+	err = -ENXIO;
+	if (dev == NULL)
+		goto out_unlock;
+	if (sock->type == SOCK_RAW)
+		reserve = dev->hard_header_len;
+
+	err = -EMSGSIZE;
+	if (len > dev->mtu+reserve)
+		goto out_unlock;
+
+	skb = sock_alloc_send_skb(sk, len + LL_RESERVED_SPACE(dev),
+				msg->msg_flags & MSG_DONTWAIT, &err);
+	if (skb==NULL)
+		goto out_unlock;
+
+	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb->nh.raw = skb->data;
+
+	if (dev->hard_header) {
+		int res;
+		err = -EINVAL;
+		res = dev->hard_header(skb, dev, ntohs(proto), addr, NULL, len);
+		if (sock->type != SOCK_DGRAM) {
+			skb->tail = skb->data;
+			skb->len = 0;
+		} else if (res < 0)
+			goto out_free;
+	}
+
+	/* Returns -EFAULT on error */
+	err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len);
+	if (err)
+		goto out_free;
+
+	skb->protocol = proto;
+	skb->dev = dev;
+	skb->priority = sk->sk_priority;
+
+	err = -ENETDOWN;
+	if (!(dev->flags & IFF_UP))
+		goto out_free;
+
+	/*
+	 *	Now send it
+	 */
+
+	err = dev_queue_xmit(skb);
+	if (err > 0 && (err = net_xmit_errno(err)) != 0)
+		goto out_unlock;
+
+	dev_put(dev);
+
+	return(len);
+
+out_free:
+	kfree_skb(skb);
+out_unlock:
+	if (dev)
+		dev_put(dev);
+out:
+	return err;
+}
+
+/*
+ *	Close a PACKET socket. This is fairly simple. We immediately go
+ *	to 'closed' state and remove our protocol entry in the device list.
+ */
+
+static int packet_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct packet_sock *po;
+
+	if (!sk)
+		return 0;
+
+	po = pkt_sk(sk);
+
+	write_lock_bh(&packet_sklist_lock);
+	sk_del_node_init(sk);
+	write_unlock_bh(&packet_sklist_lock);
+
+	/*
+	 *	Unhook packet receive handler.
+	 */
+
+	if (po->running) {
+		/*
+		 *	Remove the protocol hook
+		 */
+		dev_remove_pack(&po->prot_hook);
+		po->running = 0;
+		po->num = 0;
+		__sock_put(sk);
+	}
+
+#ifdef CONFIG_PACKET_MULTICAST
+	packet_flush_mclist(sk);
+#endif
+
+#ifdef CONFIG_PACKET_MMAP
+	if (po->pg_vec) {
+		struct tpacket_req req;
+		memset(&req, 0, sizeof(req));
+		packet_set_ring(sk, &req, 1);
+	}
+#endif
+
+	/*
+	 *	Now the socket is dead. No more input will appear.
+	 */
+
+	sock_orphan(sk);
+	sock->sk = NULL;
+
+	/* Purge queues */
+
+	skb_queue_purge(&sk->sk_receive_queue);
+
+	sock_put(sk);
+	return 0;
+}
+
+/*
+ *	Attach a packet hook.
+ */
+
+static int packet_do_bind(struct sock *sk, struct net_device *dev, int protocol)
+{
+	struct packet_sock *po = pkt_sk(sk);
+	/*
+	 *	Detach an existing hook if present.
+	 */
+
+	lock_sock(sk);
+
+	spin_lock(&po->bind_lock);
+	if (po->running) {
+		__sock_put(sk);
+		po->running = 0;
+		po->num = 0;
+		spin_unlock(&po->bind_lock);
+		dev_remove_pack(&po->prot_hook);
+		spin_lock(&po->bind_lock);
+	}
+
+	po->num = protocol;
+	po->prot_hook.type = protocol;
+	po->prot_hook.dev = dev;
+
+	po->ifindex = dev ? dev->ifindex : 0;
+
+	if (protocol == 0)
+		goto out_unlock;
+
+	if (dev) {
+		if (dev->flags&IFF_UP) {
+			dev_add_pack(&po->prot_hook);
+			sock_hold(sk);
+			po->running = 1;
+		} else {
+			sk->sk_err = ENETDOWN;
+			if (!sock_flag(sk, SOCK_DEAD))
+				sk->sk_error_report(sk);
+		}
+	} else {
+		dev_add_pack(&po->prot_hook);
+		sock_hold(sk);
+		po->running = 1;
+	}
+
+out_unlock:
+	spin_unlock(&po->bind_lock);
+	release_sock(sk);
+	return 0;
+}
+
+/*
+ *	Bind a packet socket to a device
+ */
+
+#ifdef CONFIG_SOCK_PACKET
+
+static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+	struct sock *sk=sock->sk;
+	char name[15];
+	struct net_device *dev;
+	int err = -ENODEV;
+	
+	/*
+	 *	Check legality
+	 */
+	 
+	if(addr_len!=sizeof(struct sockaddr))
+		return -EINVAL;
+	strlcpy(name,uaddr->sa_data,sizeof(name));
+
+	dev = dev_get_by_name(name);
+	if (dev) {
+		err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
+		dev_put(dev);
+	}
+	return err;
+}
+#endif
+
+static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+	struct sockaddr_ll *sll = (struct sockaddr_ll*)uaddr;
+	struct sock *sk=sock->sk;
+	struct net_device *dev = NULL;
+	int err;
+
+
+	/*
+	 *	Check legality
+	 */
+	 
+	if (addr_len < sizeof(struct sockaddr_ll))
+		return -EINVAL;
+	if (sll->sll_family != AF_PACKET)
+		return -EINVAL;
+
+	if (sll->sll_ifindex) {
+		err = -ENODEV;
+		dev = dev_get_by_index(sll->sll_ifindex);
+		if (dev == NULL)
+			goto out;
+	}
+	err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
+	if (dev)
+		dev_put(dev);
+
+out:
+	return err;
+}
+
+static struct proto packet_proto = {
+	.name	  = "PACKET",
+	.owner	  = THIS_MODULE,
+	.obj_size = sizeof(struct packet_sock),
+};
+
+/*
+ *	Create a packet of type SOCK_PACKET. 
+ */
+
+static int packet_create(struct socket *sock, int protocol)
+{
+	struct sock *sk;
+	struct packet_sock *po;
+	int err;
+
+	if (!capable(CAP_NET_RAW))
+		return -EPERM;
+	if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW
+#ifdef CONFIG_SOCK_PACKET
+	    && sock->type != SOCK_PACKET
+#endif
+	    )
+		return -ESOCKTNOSUPPORT;
+
+	sock->state = SS_UNCONNECTED;
+
+	err = -ENOBUFS;
+	sk = sk_alloc(PF_PACKET, GFP_KERNEL, &packet_proto, 1);
+	if (sk == NULL)
+		goto out;
+
+	sock->ops = &packet_ops;
+#ifdef CONFIG_SOCK_PACKET
+	if (sock->type == SOCK_PACKET)
+		sock->ops = &packet_ops_spkt;
+#endif
+	sock_init_data(sock, sk);
+
+	po = pkt_sk(sk);
+	sk->sk_family = PF_PACKET;
+	po->num = protocol;
+
+	sk->sk_destruct = packet_sock_destruct;
+	atomic_inc(&packet_socks_nr);
+
+	/*
+	 *	Attach a protocol block
+	 */
+
+	spin_lock_init(&po->bind_lock);
+	po->prot_hook.func = packet_rcv;
+#ifdef CONFIG_SOCK_PACKET
+	if (sock->type == SOCK_PACKET)
+		po->prot_hook.func = packet_rcv_spkt;
+#endif
+	po->prot_hook.af_packet_priv = sk;
+
+	if (protocol) {
+		po->prot_hook.type = protocol;
+		dev_add_pack(&po->prot_hook);
+		sock_hold(sk);
+		po->running = 1;
+	}
+
+	write_lock_bh(&packet_sklist_lock);
+	sk_add_node(sk, &packet_sklist);
+	write_unlock_bh(&packet_sklist_lock);
+	return(0);
+out:
+	return err;
+}
+
+/*
+ *	Pull a packet from our receive queue and hand it to the user.
+ *	If necessary we block.
+ */
+
+static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
+			  struct msghdr *msg, size_t len, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sk_buff *skb;
+	int copied, err;
+
+	err = -EINVAL;
+	if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
+		goto out;
+
+#if 0
+	/* What error should we return now? EUNATTACH? */
+	if (pkt_sk(sk)->ifindex < 0)
+		return -ENODEV;
+#endif
+
+	/*
+	 *	If the address length field is there to be filled in, we fill
+	 *	it in now.
+	 */
+
+	if (sock->type == SOCK_PACKET)
+		msg->msg_namelen = sizeof(struct sockaddr_pkt);
+	else
+		msg->msg_namelen = sizeof(struct sockaddr_ll);
+
+	/*
+	 *	Call the generic datagram receiver. This handles all sorts
+	 *	of horrible races and re-entrancy so we can forget about it
+	 *	in the protocol layers.
+	 *
+	 *	Now it will return ENETDOWN, if device have just gone down,
+	 *	but then it will block.
+	 */
+
+	skb=skb_recv_datagram(sk,flags,flags&MSG_DONTWAIT,&err);
+
+	/*
+	 *	An error occurred so return it. Because skb_recv_datagram() 
+	 *	handles the blocking we don't see and worry about blocking
+	 *	retries.
+	 */
+
+	if(skb==NULL)
+		goto out;
+
+	/*
+	 *	You lose any data beyond the buffer you gave. If it worries a
+	 *	user program they can ask the device for its MTU anyway.
+	 */
+
+	copied = skb->len;
+	if (copied > len)
+	{
+		copied=len;
+		msg->msg_flags|=MSG_TRUNC;
+	}
+
+	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	if (err)
+		goto out_free;
+
+	sock_recv_timestamp(msg, sk, skb);
+
+	if (msg->msg_name)
+		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
+
+	/*
+	 *	Free or return the buffer as appropriate. Again this
+	 *	hides all the races and re-entrancy issues from us.
+	 */
+	err = (flags&MSG_TRUNC) ? skb->len : copied;
+
+out_free:
+	skb_free_datagram(sk, skb);
+out:
+	return err;
+}
+
+#ifdef CONFIG_SOCK_PACKET
+static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
+			       int *uaddr_len, int peer)
+{
+	struct net_device *dev;
+	struct sock *sk	= sock->sk;
+
+	if (peer)
+		return -EOPNOTSUPP;
+
+	uaddr->sa_family = AF_PACKET;
+	dev = dev_get_by_index(pkt_sk(sk)->ifindex);
+	if (dev) {
+		strlcpy(uaddr->sa_data, dev->name, 15);
+		dev_put(dev);
+	} else
+		memset(uaddr->sa_data, 0, 14);
+	*uaddr_len = sizeof(*uaddr);
+
+	return 0;
+}
+#endif
+
+static int packet_getname(struct socket *sock, struct sockaddr *uaddr,
+			  int *uaddr_len, int peer)
+{
+	struct net_device *dev;
+	struct sock *sk = sock->sk;
+	struct packet_sock *po = pkt_sk(sk);
+	struct sockaddr_ll *sll = (struct sockaddr_ll*)uaddr;
+
+	if (peer)
+		return -EOPNOTSUPP;
+
+	sll->sll_family = AF_PACKET;
+	sll->sll_ifindex = po->ifindex;
+	sll->sll_protocol = po->num;
+	dev = dev_get_by_index(po->ifindex);
+	if (dev) {
+		sll->sll_hatype = dev->type;
+		sll->sll_halen = dev->addr_len;
+		memcpy(sll->sll_addr, dev->dev_addr, dev->addr_len);
+		dev_put(dev);
+	} else {
+		sll->sll_hatype = 0;	/* Bad: we have no ARPHRD_UNSPEC */
+		sll->sll_halen = 0;
+	}
+	*uaddr_len = sizeof(*sll);
+
+	return 0;
+}
+
+#ifdef CONFIG_PACKET_MULTICAST
+static void packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what)
+{
+	switch (i->type) {
+	case PACKET_MR_MULTICAST:
+		if (what > 0)
+			dev_mc_add(dev, i->addr, i->alen, 0);
+		else
+			dev_mc_delete(dev, i->addr, i->alen, 0);
+		break;
+	case PACKET_MR_PROMISC:
+		dev_set_promiscuity(dev, what);
+		break;
+	case PACKET_MR_ALLMULTI:
+		dev_set_allmulti(dev, what);
+		break;
+	default:;
+	}
+}
+
+static void packet_dev_mclist(struct net_device *dev, struct packet_mclist *i, int what)
+{
+	for ( ; i; i=i->next) {
+		if (i->ifindex == dev->ifindex)
+			packet_dev_mc(dev, i, what);
+	}
+}
+
+static int packet_mc_add(struct sock *sk, struct packet_mreq *mreq)
+{
+	struct packet_sock *po = pkt_sk(sk);
+	struct packet_mclist *ml, *i;
+	struct net_device *dev;
+	int err;
+
+	rtnl_lock();
+
+	err = -ENODEV;
+	dev = __dev_get_by_index(mreq->mr_ifindex);
+	if (!dev)
+		goto done;
+
+	err = -EINVAL;
+	if (mreq->mr_alen > dev->addr_len)
+		goto done;
+
+	err = -ENOBUFS;
+	i = (struct packet_mclist *)kmalloc(sizeof(*i), GFP_KERNEL);
+	if (i == NULL)
+		goto done;
+
+	err = 0;
+	for (ml = po->mclist; ml; ml = ml->next) {
+		if (ml->ifindex == mreq->mr_ifindex &&
+		    ml->type == mreq->mr_type &&
+		    ml->alen == mreq->mr_alen &&
+		    memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) {
+			ml->count++;
+			/* Free the new element ... */
+			kfree(i);
+			goto done;
+		}
+	}
+
+	i->type = mreq->mr_type;
+	i->ifindex = mreq->mr_ifindex;
+	i->alen = mreq->mr_alen;
+	memcpy(i->addr, mreq->mr_address, i->alen);
+	i->count = 1;
+	i->next = po->mclist;
+	po->mclist = i;
+	packet