qi-hardware/openwrt-xburst
1
0
Fork 0
mirror of git://projects.qi-hardware.com/openwrt-xburst.git synced 2024-12-02 17:42:50 +02:00
Code
aa14640dab
openwrt-xburst/openwrt/target/linux/linux-2.6/patches/generic/104-pf_ring.patch

5300 lines
135 KiB
Diff
Raw Normal View History

add pf_ring patches for kernel and libpcap git-svn-id: svn://svn.openwrt.org/openwrt/trunk@2266 3c298f89-4303-0410-b956-a3cf2f4a3e73
2005-10-23 01:03:56 +03:00
diff --unified --recursive --new-file linux-2.6.12.5/include/linux/ring.h linux-2.6.12.5-1-686-smp-ring3/include/linux/ring.h
--- linux-2.6.12.5/include/linux/ring.h 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.12.5-1-686-smp-ring3/include/linux/ring.h 2005-10-22 23:50:44.951445250 +0200
@@ -0,0 +1,108 @@
+/*
+ * Definitions for packet ring
+ *
+ * 2004 - Luca Deri <deri@ntop.org>
+ */
+#ifndef __RING_H
+#define __RING_H
+
+
+#define INCLUDE_MAC_INFO
+
+#ifdef INCLUDE_MAC_INFO
+#define SKB_DISPLACEMENT 14 /* Include MAC address information */
+#else
+#define SKB_DISPLACEMENT 0 /* Do NOT include MAC address information */
+#endif
+
+#define RING_MAGIC
+#define RING_MAGIC_VALUE 0x88
+#define RING_FLOWSLOT_VERSION 5
+#define RING_VERSION "3.0"
+
+#define SO_ADD_TO_CLUSTER 99
+#define SO_REMOVE_FROM_CLUSTER 100
+#define SO_SET_REFLECTOR 101
+
+/* *********************************** */
+
+#ifndef HAVE_PCAP
+struct pcap_pkthdr {
+ struct timeval ts; /* time stamp */
+ u_int32_t caplen; /* length of portion present */
+ u_int32_t len; /* length this packet (off wire) */
+};
+#endif
+
+/* *********************************** */
+
+enum cluster_type {
+ cluster_per_flow = 0,
+ cluster_round_robin
+};
+
+/* *********************************** */
+
+#define RING_MIN_SLOT_SIZE (60+sizeof(struct pcap_pkthdr))
+#define RING_MAX_SLOT_SIZE (1514+sizeof(struct pcap_pkthdr))
+
+/* *********************************** */
+
+typedef struct flowSlotInfo {
+ u_int16_t version, sample_rate;
+ u_int32_t tot_slots, slot_len, tot_mem;
+
+ u_int64_t tot_pkts, tot_lost;
+ u_int64_t tot_insert, tot_read;
+ u_int16_t insert_idx;
+ u_int16_t remove_idx;
+} FlowSlotInfo;
+
+/* *********************************** */
+
+typedef struct flowSlot {
+#ifdef RING_MAGIC
+ u_char magic; /* It must alwasy be zero */
+#endif
+ u_char slot_state; /* 0=empty, 1=full */
+ u_char bucket; /* bucket[bucketLen] */
+} FlowSlot;
+
+/* *********************************** */
+
+#ifdef __KERNEL__
+
+FlowSlotInfo* getRingPtr(void);
+int allocateRing(char *deviceName, u_int numSlots,
+ u_int bucketLen, u_int sampleRate);
+unsigned int pollRing(struct file *fp, struct poll_table_struct * wait);
+void deallocateRing(void);
+
+/* ************************* */
+
+typedef int (*handle_ring_skb)(struct sk_buff *skb,
+ u_char recv_packet, u_char real_skb);
+extern handle_ring_skb get_skb_ring_handler(void);
+extern void set_skb_ring_handler(handle_ring_skb the_handler);
+extern void do_skb_ring_handler(struct sk_buff *skb,
+ u_char recv_packet, u_char real_skb);
+
+typedef int (*handle_ring_buffer)(struct net_device *dev,
+ char *data, int len);
+extern handle_ring_buffer get_buffer_ring_handler(void);
+extern void set_buffer_ring_handler(handle_ring_buffer the_handler);
+extern int do_buffer_ring_handler(struct net_device *dev,
+ char *data, int len);
+#endif /* __KERNEL__ */
+
+/* *********************************** */
+
+#define PF_RING 27 /* Packet Ring */
+#define SOCK_RING PF_RING
+
+/* ioctl() */
+#define SIORINGPOLL 0x8888
+
+/* *********************************** */
+
+#endif /* __RING_H */
diff --unified --recursive --new-file linux-2.6.12.5/net/Kconfig linux-2.6.12.5-1-686-smp-ring3/net/Kconfig
--- linux-2.6.12.5/net/Kconfig 2005-08-15 02:20:18.000000000 +0200
+++ linux-2.6.12.5-1-686-smp-ring3/net/Kconfig 2005-10-22 23:50:45.535481750 +0200
@@ -72,6 +72,7 @@
Say Y unless you know what you are doing.
+source "net/ring/Kconfig"
config INET
bool "TCP/IP networking"
---help---
diff --unified --recursive --new-file linux-2.6.12.5/net/Makefile linux-2.6.12.5-1-686-smp-ring3/net/Makefile
--- linux-2.6.12.5/net/Makefile 2005-08-15 02:20:18.000000000 +0200
+++ linux-2.6.12.5-1-686-smp-ring3/net/Makefile 2005-10-22 23:50:45.491479000 +0200
@@ -41,6 +41,7 @@
obj-$(CONFIG_DECNET) += decnet/
obj-$(CONFIG_ECONET) += econet/
obj-$(CONFIG_VLAN_8021Q) += 8021q/
+obj-$(CONFIG_RING) += ring/
obj-$(CONFIG_IP_SCTP) += sctp/
ifeq ($(CONFIG_NET),y)
diff --unified --recursive --new-file linux-2.6.12.5/net/Makefile.ORG linux-2.6.12.5-1-686-smp-ring3/net/Makefile.ORG
--- linux-2.6.12.5/net/Makefile.ORG 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.12.5-1-686-smp-ring3/net/Makefile.ORG 2005-10-22 23:50:45.483478500 +0200
@@ -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 --unified --recursive --new-file linux-2.6.12.5/net/core/dev.c linux-2.6.12.5-1-686-smp-ring3/net/core/dev.c
--- linux-2.6.12.5/net/core/dev.c 2005-08-15 02:20:18.000000000 +0200
+++ linux-2.6.12.5-1-686-smp-ring3/net/core/dev.c 2005-10-22 23:50:45.479478250 +0200
@@ -115,6 +115,56 @@
#endif /* CONFIG_NET_RADIO */
#include <asm/current.h>
+#if defined (CONFIG_RING) || defined(CONFIG_RING_MODULE)
+
+/* #define RING_DEBUG */
+
+#include <linux/ring.h>
+#include <linux/version.h>
+
+static handle_ring_skb ring_handler = NULL;
+
+handle_ring_skb get_skb_ring_handler() { return(ring_handler); }
+
+void set_skb_ring_handler(handle_ring_skb the_handler) {
+ ring_handler = the_handler;
+}
+
+void do_skb_ring_handler(struct sk_buff *skb,
+ u_char recv_packet, u_char real_skb) {
+ if(ring_handler)
+ ring_handler(skb, recv_packet, real_skb);
+}
+
+/* ******************* */
+
+static handle_ring_buffer buffer_ring_handler = NULL;
+
+handle_ring_buffer get_buffer_ring_handler() { return(buffer_ring_handler); }
+
+void set_buffer_ring_handler(handle_ring_buffer the_handler) {
+ buffer_ring_handler = the_handler;
+}
+
+int do_buffer_ring_handler(struct net_device *dev, char *data, int len) {
+ if(buffer_ring_handler) {
+ buffer_ring_handler(dev, data, len);
+ return(1);
+ } else
+ return(0);
+}
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+EXPORT_SYMBOL(get_skb_ring_handler);
+EXPORT_SYMBOL(set_skb_ring_handler);
+EXPORT_SYMBOL(do_skb_ring_handler);
+
+EXPORT_SYMBOL(get_buffer_ring_handler);
+EXPORT_SYMBOL(set_buffer_ring_handler);
+EXPORT_SYMBOL(do_buffer_ring_handler);
+#endif
+
+#endif
/* 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
@@ -1293,6 +1343,10 @@
skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
#endif
if (q->enqueue) {
+#if defined (CONFIG_RING) || defined(CONFIG_RING_MODULE)
+ if(ring_handler) ring_handler(skb, 0, 1);
+#endif /* CONFIG_RING */
+
/* Grab device queue */
spin_lock(&dev->queue_lock);
@@ -1509,6 +1563,13 @@
preempt_disable();
err = netif_rx(skb);
+#if defined (CONFIG_RING) || defined(CONFIG_RING_MODULE)
+ if(ring_handler && ring_handler(skb, 1, 1)) {
+ /* The packet has been copied into a ring */
+ return(NET_RX_SUCCESS);
+ }
+#endif /* CONFIG_RING */
+
if (local_softirq_pending())
do_softirq();
preempt_enable();
@@ -1655,6 +1716,13 @@
int ret = NET_RX_DROP;
unsigned short type;
+#if defined (CONFIG_RING) || defined(CONFIG_RING_MODULE)
+ if(ring_handler && ring_handler(skb, 1, 1)) {
+ /* The packet has been copied into a ring */
+ return(NET_RX_SUCCESS);
+ }
+#endif /* CONFIG_RING */
+
/* if we've gotten here through NAPI, check netpoll */
if (skb->dev->poll && netpoll_rx(skb))
return NET_RX_DROP;
diff --unified --recursive --new-file linux-2.6.12.5/net/core/dev.c.ORG linux-2.6.12.5-1-686-smp-ring3/net/core/dev.c.ORG
--- linux-2.6.12.5/net/core/dev.c.ORG 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.12.5-1-686-smp-ring3/net/core/dev.c.ORG 2005-10-22 23:50:45.203461000 +0200
@@ -0,0 +1,3385 @@
+/*
+ * 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
+ * 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
+
+*******************************************************************************/
+
+/**
+ * __dev_get_by_name - find a device by its name
+ * @name: name to find
+ *
+ * Find an interface by name. Must be called under RTNL semaphore
+ * or @dev_base_lock. If the name is found a pointer to the device
+ * is returned. If the name is not found then %NULL is returned. The
+ * reference counters are not incremented so the caller must be
+ * careful with locks.
+ */
+
+struct net_device *__dev_get_by_name(const char *name)
+{
+ struct hlist_node *p;
+
+ hlist_for_each(p, dev_name_hash(name)) {
+ struct net_device *dev
+ = hlist_entry(p, struct net_device, name_hlist);
+ if (!strncmp(dev->name, name, IFNAMSIZ))
+ return dev;
+ }
+ return NULL;
+}
+
+/**
+ * dev_get_by_name - find a device by its name
+ * @name: name to find
+ *
+ * Find an interface by name. This can be called from any
+ * context and does its own locking. The returned handle has
+ * the usage count incremented and the caller must use dev_put() to
+ * release it when it is no longer needed. %NULL is returned if no
+ * matching device is found.
+ */
+
+struct net_device *dev_get_by_name(const char *name)
+{
+ struct net_device *dev;
+
+ read_lock(&dev_base_lock);
+ dev = __dev_get_by_name(name);
+ if (dev)
+ dev_hold(dev);
+ read_unlock(&dev_base_lock);
+ return dev;
+}
+
+/**
+ * __dev_get_by_index - find a device by its ifindex
+ * @ifindex: index of device
+ *
+ * Search for an interface by index. Returns %NULL if the device
+ * is not found or a pointer to the device. The device has not
+ * had its reference counter increased so the caller must be careful
+ * about locking. The caller must hold either the RTNL semaphore
+ * or @dev_base_lock.
+ */
+
+struct net_device *__dev_get_by_index(int ifindex)
+{
+ struct hlist_node *p;
+
+ hlist_for_each(p, dev_index_hash(ifindex)) {
+ struct net_device *dev
+ = hlist_entry(p, struct net_device, index_hlist);
+ if (dev->ifindex == ifindex)
+ return dev;
+ }
+ return NULL;
+}
+
+
+/**
+ * dev_get_by_index - find a device by its ifindex
+ * @ifindex: index of device
+ *
+ * Search for an interface by index. Returns NULL if the device
+ * is not found or a pointer to the device. The device returned has
+ * had a reference added and the pointer is safe until the user calls
+ * dev_put to indicate they have finished with it.
+ */
+
+struct net_device *dev_get_by_index(int ifindex)
+{
+ struct net_device *dev;
+
+ read_lock(&dev_base_lock);
+ dev = __dev_get_by_index(ifindex);
+ if (dev)
+ dev_hold(dev);
+ read_unlock(&dev_base_lock);
+ return dev;
+}
+
+/**
+ * dev_getbyhwaddr - find a device by its hardware address
+ * @type: media type of device
+ * @ha: hardware address
+ *
+ * Search for an interface by MAC address. Returns NULL if the device
+ * is not found or a pointer to the device. The caller must hold the
+ * rtnl semaphore. The returned device has not had its ref count increased
+ * and the caller must therefore be careful about locking
+ *
+ * BUGS:
+ * If the API was consistent this would be __dev_get_by_hwaddr
+ */
+
+struct net_device *dev_getbyhwaddr(unsigned short type, char *ha)
+{
+ struct net_device *dev;
+
+ ASSERT_RTNL();
+
+ for (dev = dev_base; dev; dev = dev->next)
+ if (dev->type == type &&
+ !memcmp(dev->dev_addr, ha, dev->addr_len))
+ break;
+ return dev;
+}
+
+struct net_device *dev_getfirstbyhwtype(unsigned short type)
+{
+ struct net_device *dev;
+
+ rtnl_lock();
+ for (dev = dev_base; dev; dev = dev->next) {
+ if (dev->type == type) {
+ dev_hold(dev);
+ break;
+ }
+ }
+ rtnl_unlock();
+ return dev;
+}
+
+EXPORT_SYMBOL(dev_getfirstbyhwtype);
+
+/**
+ * dev_get_by_flags - find any device with given flags
+ * @if_flags: IFF_* values
+ * @mask: bitmask of bits in if_flags to check
+ *
+ * Search for any interface with the given flags. Returns NULL if a device
+ * is not found or a pointer to the device. The device returned has
+ * had a reference added and the pointer is safe until the user calls
+ * dev_put to indicate they have finished with it.
+ */
+
+struct net_device * dev_get_by_flags(unsigned short if_flags, unsigned short mask)
+{
+ struct net_device *dev;
+
+ read_lock(&dev_base_lock);
+ for (dev = dev_base; dev != NULL; dev = dev->next) {
+ if (((dev->flags ^ if_flags) & mask) == 0) {
+ dev_hold(dev);
+ break;
+ }
+ }
+ read_unlock(&dev_base_lock);
+ return dev;
+}
+
+/**
+ * dev_valid_name - check if name is okay for network device
+ * @name: name string
+ *
+ * Network device names need to be valid file names to
+ * to allow sysfs to work
+ */
+static int dev_valid_name(const char *name)
+{
+ return !(*name == '\0'
+ || !strcmp(name, ".")
+ || !strcmp(name, "..")
+ || strchr(name, '/'));
+}
+
+/**
+ * dev_alloc_name - allocate a name for a device
+ * @dev: device
+ * @name: name format string
+ *
+ * Passed a format string - eg "lt%d" it will try and find a suitable
+ * id. Not efficient for many devices, not called a lot. The caller
+ * must hold the dev_base or rtnl lock while allocating the name and
+ * adding the device in order to avoid duplicates. Returns the number
+ * of the unit assigned or a negative errno code.
+ */
+
+int dev_alloc_name(struct net_device *dev, const char *name)
+{
+ int i = 0;
+ char buf[IFNAMSIZ];
+ const char *p;
+ const int max_netdevices = 8*PAGE_SIZE;
+ long *inuse;
+ struct net_device *d;
+
+ p = strnchr(name, IFNAMSIZ-1, '%');
+ if (p) {
+ /*
+ * Verify the string as this thing may have come from
+ * the user. There must be either one "%d" and no other "%"
+ * characters.
+ */
+ if (p[1] != 'd' || strchr(p + 2, '%'))
+ return -EINVAL;
+
+ /* Use one page as a bit array of possible slots */
+ inuse = (long *) get_zeroed_page(GFP_ATOMIC);
+ if (!inuse)
+ return -ENOMEM;
+
+ for (d = dev_base; d; d = d->next) {
+ if (!sscanf(d->name, name, &i))
+ continue;
+ if (i < 0 || i >= max_netdevices)
+ continue;
+
+ /* avoid cases where sscanf is not exact inverse of printf */
+ snprintf(buf, sizeof(buf), name, i);
+ if (!strncmp(buf, d->name, IFNAMSIZ))
+ set_bit(i, inuse);
+ }
+
+ i = find_first_zero_bit(inuse, max_netdevices);
+ free_page((unsigned long) inuse);
+ }
+
+ snprintf(buf, sizeof(buf), name, i);
+ if (!__dev_get_by_name(buf)) {
+ strlcpy(dev->name, buf, IFNAMSIZ);
+ return i;
+ }
+
+ /* It is possible to run out of possible slots
+ * when the name is long and there isn't enough space left
+ * for the digits, or if all bits are used.
+ */
+ return -ENFILE;
+}
+
+
+/**
+ * dev_change_name - change name of a device
+ * @dev: device
+ * @newname: name (or format string) must be at least IFNAMSIZ
+ *
+ * Change name of a device, can pass format strings "eth%d".
+ * for wildcarding.
+ */
+int dev_change_name(struct net_device *dev, char *newname)
+{
+ int err = 0;
+
+ ASSERT_RTNL();
+
+ if (dev->flags & IFF_UP)
+ return -EBUSY;
+
+ if (!dev_valid_name(newname))
+ return -EINVAL;
+
+ if (strchr(newname, '%')) {
+ err = dev_alloc_name(dev, newname);
+ if (err < 0)
+ return err;
+ strcpy(newname, dev->name);
+ }
+ else if (__dev_get_by_name(newname))
+ return -EEXIST;
+ else
+ strlcpy(dev->name, newname, IFNAMSIZ);
+
+ err = class_device_rename(&dev->class_dev, dev->name);
+ if (!err) {
+ hlist_del(&dev->name_hlist);
+ hlist_add_head(&dev->name_hlist, dev_name_hash(dev->name));
+ notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev);
+ }
+
+ return err;
+}
+
+/**
+ * netdev_features_change - device changes fatures
+ * @dev: device to cause notification
+ *
+ * Called to indicate a device has changed features.
+ */
+void netdev_features_change(struct net_device *dev)
+{
+ notifier_call_chain(&netdev_chain, NETDEV_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL(netdev_features_change);
+
+/**
+ * netdev_state_change - device changes state
+ * @dev: device to cause notification
+ *
+ * Called to indicate a device has changed state. This function calls
+ * the notifier chains for netdev_chain and sends a NEWLINK message
+ * to the routing socket.
+ */
+void netdev_state_change(struct net_device *dev)
+{
+ if (dev->flags & IFF_UP) {
+ notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev);
+ rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
+ }
+}
+
+/**
+ * dev_load - load a network module
+ * @name: name of interface
+ *
+ * If a network interface is not present and the process has suitable
+ * privileges this function loads the module. If module loading is not
+ * available in this kernel then it becomes a nop.
+ */
+
+void dev_load(const char *name)
+{
+ struct net_device *dev;
+
+ read_lock(&dev_base_lock);
+ dev = __dev_get_by_name(name);
+ read_unlock(&dev_base_lock);
+
+ if (!dev && capable(CAP_SYS_MODULE))
+ request_module("%s", name);
+}
+
+static int default_rebuild_header(struct sk_buff *skb)
+{
+ printk(KERN_DEBUG "%s: default_rebuild_header called -- BUG!\n",
+ skb->dev ? skb->dev->name : "NULL!!!");
+ kfree_skb(skb);
+ return 1;
+}
+
+
+/**
+ * dev_open - prepare an interface for use.
+ * @dev: device to open
+ *
+ * Takes a device from down to up state. The device's private open
+ * function is invoked and then the multicast lists are loaded. Finally
+ * the device is moved into the up state and a %NETDEV_UP message is
+ * sent to the netdev notifier chain.
+ *
+ * Calling this function on an active interface is a nop. On a failure
+ * a negative errno code is returned.
+ */
+int dev_open(struct net_device *dev)
+{
+ int ret = 0;
+
+ /*
+ * Is it already up?
+ */
+
+ if (dev->flags & IFF_UP)
+ return 0;
+
+ /*
+ * Is it even present?
+ */
+ if (!netif_device_present(dev))
+ return -ENODEV;
+
+ /*
+ * Call device private open method
+ */
+ set_bit(__LINK_STATE_START, &dev->state);
+ if (dev->open) {
+ ret = dev->open(dev);
+ if (ret)
+ clear_bit(__LINK_STATE_START, &dev->state);
+ }
+
+ /*
+ * If it went open OK then:
+ */
+
+ if (!ret) {
+ /*
+ * Set the flags.
+ */
+ dev->flags |= IFF_UP;
+
+ /*
+ * Initialize multicasting status
+ */
+ dev_mc_upload(dev);
+
+ /*
+ * Wakeup transmit queue engine
+ */
+ dev_activate(dev);
+
+ /*
+ * ... and announce new interface.
+ */
+ notifier_call_chain(&netdev_chain, NETDEV_UP, dev);
+ }
+ return ret;
+}
+
+/**
+ * dev_close - shutdown an interface.
+ * @dev: device to shutdown
+ *
+ * This function moves an active device into down state. A
+ * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
+ * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
+ * chain.
+ */
+int dev_close(struct net_device *dev)
+{
+ if (!(dev->flags & IFF_UP))
+ return 0;
+
+ /*
+ * Tell people we are going down, so that they can
+ * prepare to death, when device is still operating.
+ */
+ notifier_call_chain(&netdev_chain, NETDEV_GOING_DOWN, dev);
+
+ dev_deactivate(dev);
+
+ clear_bit(__LINK_STATE_START, &dev->state);
+
+ /* Synchronize to scheduled poll. We cannot touch poll list,
+ * it can be even on different cpu. So just clear netif_running(),
+ * and wait when poll really will happen. Actually, the best place
+ * for this is inside dev->stop() after device stopped its irq
+ * engine, but this requires more changes in devices. */
+
+ smp_mb__after_clear_bit(); /* Commit netif_running(). */
+ while (test_bit(__LINK_STATE_RX_SCHED, &dev->state)) {
+ /* No hurry. */
+ current->state = TASK_INTERRUPTIBLE;
+ schedule_timeout(1);
+ }
+
+ /*
+ * Call the device specific close. This cannot fail.
+ * Only if device is UP
+ *
+ * We allow it to be called even after a DETACH hot-plug
+ * event.
+ */
+ if (dev->stop)
+ dev->stop(dev);
+
+ /*
+ * Device is now down.
+ */
+
+ dev->flags &= ~IFF_UP;
+
+ /*
+ * Tell people we are down
+ */
+ notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev);
+
+ return 0;
+}
+
+
+/*
+ * Device change register/unregister. These are not inline or static
+ * as we export them to the world.
+ */
+
+/**
+ * register_netdevice_notifier - register a network notifier block
+ * @nb: notifier
+ *
+ * Register a notifier to be called when network device events occur.
+ * The notifier passed is linked into the kernel structures and must
+ * not be reused until it has been unregistered. A negative errno code
+ * is returned on a failure.
+ *
+ * When registered all registration and up events are replayed
+ * to the new notifier to allow device to have a race free
+ * view of the network device list.
+ */
+
+int register_netdevice_notifier(struct notifier_block *nb)
+{
+ struct net_device *dev;
+ int err;
+
+ rtnl_lock();
+ err = notifier_chain_register(&netdev_chain, nb);
+ if (!err) {
+ for (dev = dev_base; dev; dev = dev->next) {
+ nb->notifier_call(nb, NETDEV_REGISTER, dev);
+
+ if (dev->flags & IFF_UP)
+ nb->notifier_call(nb, NETDEV_UP, dev);
+ }
+ }
+ rtnl_unlock();
+ return err;
+}
+
+/**
+ * unregister_netdevice_notifier - unregister a network notifier block
+ * @nb: notifier
+ *
+ * Unregister a notifier previously registered by
+ * register_netdevice_notifier(). The notifier is unlinked into the
+ * kernel structures and may then be reused. A negative errno code
+ * is returned on a failure.
+ */
+
+int unregister_netdevice_notifier(struct notifier_block *nb)
+{
+ return notifier_chain_unregister(&netdev_chain, nb);
+}
+
+/**
+ * call_netdevice_notifiers - call all network notifier blocks
+ * @val: value passed unmodified to notifier function
+ * @v: pointer passed unmodified to notifier function
+ *
+ * Call all network notifier blocks. Parameters and return value
+ * are as for notifier_call_chain().
+ */
+
+int call_netdevice_notifiers(unsigned long val, void *v)
+{
+ return notifier_call_chain(&netdev_chain, val, v);
+}
+
+/* When > 0 there are consumers of rx skb time stamps */
+static atomic_t netstamp_needed = ATOMIC_INIT(0);
+
+void net_enable_timestamp(void)
+{
+ atomic_inc(&netstamp_needed);
+}
+
+void net_disable_timestamp(void)
+{
+ atomic_dec(&netstamp_needed);
+}
+
+static inline void net_timestamp(struct timeval *stamp)
+{
+ if (atomic_read(&netstamp_needed))
+ do_gettimeofday(stamp);
+ else {
+ stamp->tv_sec = 0;
+ stamp->tv_usec = 0;
+ }
+}
+
+/*
+ * Support routine. Sends outgoing frames to any network
+ * taps currently in use.
+ */
+
+void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct packet_type *ptype;
+ net_timestamp(&skb->stamp);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, &ptype_all, list) {
+ /* Never send packets back to the socket
+ * they originated from - MvS (miquels@drinkel.ow.org)
+ */
+ if ((ptype->dev == dev || !ptype->dev) &&
+ (ptype->af_packet_priv == NULL ||
+ (struct sock *)ptype->af_packet_priv != skb->sk)) {
+ struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC);
+ if (!skb2)
+ break;
+
+ /* skb->nh should be correctly
+ set by sender, so that the second statement is
+ just protection against buggy protocols.
+ */
+ skb2->mac.raw = skb2->data;
+
+ if (skb2->nh.raw < skb2->data ||
+ skb2->nh.raw > skb2->tail) {
+ if (net_ratelimit())
+ printk(KERN_CRIT "protocol %04x is "
+ "buggy, dev %s\n",
+ skb2->protocol, dev->name);
+ skb2->nh.raw = skb2->data;
+ }
+
+ skb2->h.raw = skb2->nh.raw;
+ skb2->pkt_type = PACKET_OUTGOING;
+ ptype->func(skb2, skb->dev, ptype);
+ }
+ }
+ rcu_read_unlock();
+}
+
+/*
+ * Invalidate hardware checksum when packet is to be mangled, and
+ * complete checksum manually on outgoing path.
+ */
+int skb_checksum_help(struct sk_buff *skb, int inward)
+{
+ unsigned int csum;
+ int ret = 0, offset = skb->h.raw - skb->data;
+
+ if (inward) {
+ skb->ip_summed = CHECKSUM_NONE;
+ goto out;
+ }
+
+ if (skb_cloned(skb)) {
+ ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+ if (ret)
+ goto out;
+ }
+
+ if (offset > (int)skb->len)
+ BUG();
+ csum = skb_checksum(skb, offset, skb->len-offset, 0);
+
+ offset = skb->tail - skb->h.raw;
+ if (offset <= 0)
+ BUG();
+ if (skb->csum + 2 > offset)
+ BUG();
+
+ *(u16*)(skb->h.raw + skb->csum) = csum_fold(csum);
+ skb->ip_summed = CHECKSUM_NONE;
+out:
+ return ret;
+}
+
+#ifdef CONFIG_HIGHMEM
+/* Actually, we should eliminate this check as soon as we know, that:
+ * 1. IOMMU is present and allows to map all the memory.
+ * 2. No high memory really exists on this machine.
+ */
+
+static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+{
+ int i;
+
+ if (dev->features & NETIF_F_HIGHDMA)
+ return 0;
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ if (PageHighMem(skb_shinfo(skb)->frags[i].page))
+ return 1;
+
+ return 0;
+}
+#else
+#define illegal_highdma(dev, skb) (0)
+#endif
+
+extern void skb_release_data(struct sk_buff *);
+
+/* Keep head the same: replace data */
+int __skb_linearize(struct sk_buff *skb, int gfp_mask)
+{
+ unsigned int size;
+ u8 *data;
+ long offset;
+ struct skb_shared_info *ninfo;
+ int headerlen = skb->data - skb->head;
+ int expand = (skb->tail + skb->data_len) - skb->end;
+
+ if (skb_shared(skb))
+ BUG();
+
+ if (expand <= 0)
+ expand = 0;
+
+ size = skb->end - skb->head + expand;
+ size = SKB_DATA_ALIGN(size);
+ data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+ if (!data)
+ return -ENOMEM;
+
+ /* Copy entire thing */
+ if (skb_copy_bits(skb, -headerlen, data, headerlen + skb->len))
+ BUG();
+
+ /* Set up shinfo */
+ ninfo = (struct skb_shared_info*)(data + size);
+ atomic_set(&ninfo->dataref, 1);
+ ninfo->tso_size = skb_shinfo(skb)->tso_size;
+ ninfo->tso_segs = skb_shinfo(skb)->tso_segs;
+ ninfo->nr_frags = 0;
+ ninfo->frag_list = NULL;
+
+ /* Offset between the two in bytes */
+ offset = data - skb->head;
+
+ /* Free old data. */
+ skb_release_data(skb);
+
+ skb->head = data;
+ skb->end = data + size;
+
+ /* Set up new pointers */
+ skb->h.raw += offset;
+ skb->nh.raw += offset;
+ skb->mac.raw += offset;
+ skb->tail += offset;
+ skb->data += offset;
+
+ /* We are no longer a clone, even if we were. */
+ skb->cloned = 0;
+
+ skb->tail += skb->data_len;
+ skb->data_len = 0;
+ return 0;
+}
+
+#define HARD_TX_LOCK(dev, cpu) { \
+ if ((dev->features & NETIF_F_LLTX) == 0) { \
+ spin_lock(&dev->xmit_lock); \
+ dev->xmit_lock_owner = cpu; \
+ } \
+}
+
+#define HARD_TX_UNLOCK(dev) { \
+ if ((dev->features & NETIF_F_LLTX) == 0) { \
+ dev->xmit_lock_owner = -1; \
+ spin_unlock(&dev->xmit_lock); \
+ } \
+}
+
+/**
+ * dev_queue_xmit - transmit a buffer
+ * @skb: buffer to transmit
+ *
+ * Queue a buffer for transmission to a network device. The caller must
+ * have set the device and priority and built the buffer before calling
+ * this function. The function can be called from an interrupt.
+ *
+ * A negative errno code is returned on a failure. A success does not
+ * guarantee the frame will be transmitted as it may be dropped due
+ * to congestion or traffic shaping.
+ *
+ * -----------------------------------------------------------------------------------
+ * I notice this method can also return errors from the queue disciplines,
+ * including NET_XMIT_DROP, which is a positive value. So, errors can also
+ * be positive.
+ *
+ * Regardless of the return value, the skb is consumed, so it is currently
+ * difficult to retry a send to this method. (You can bump the ref count
+ * before sending to hold a reference for retry if you are careful.)
+ *
+ * When calling this method, interrupts MUST be enabled. This is because
+ * the BH enable code must have IRQs enabled so that it will not deadlock.
+ * --BLG
+ */
+
+int dev_queue_xmit(struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+ struct Qdisc *q;
+ int rc = -ENOMEM;
+
+ if (skb_shinfo(skb)->frag_list &&
+ !(dev->features & NETIF_F_FRAGLIST) &&
+ __skb_linearize(skb, GFP_ATOMIC))
+ goto out_kfree_skb;
+
+ /* Fragmented skb is linearized if device does not support SG,
+ * or if at least one of fragments is in highmem and device
+ * does not support DMA from it.
+ */
+ if (skb_shinfo(skb)->nr_frags &&
+ (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
+ __skb_linearize(skb, GFP_ATOMIC))
+ goto out_kfree_skb;
+
+ /* If packet is not checksummed and device does not support
+ * checksumming for this protocol, complete checksumming here.
+ */
+ if (skb->ip_summed == CHECKSUM_HW &&
+ (!(dev->features & (NETIF_F_HW_CSUM | NETIF_F_NO_CSUM)) &&
+ (!(dev->features & NETIF_F_IP_CSUM) ||
+ skb->protocol != htons(ETH_P_IP))))
+ if (skb_checksum_help(skb, 0))
+ goto out_kfree_skb;
+
+ /* Disable soft irqs for various locks below. Also
+ * stops preemption for RCU.
+ */
+ local_bh_disable();
+
+ /* Updates of qdisc are serialized by queue_lock.
+ * The struct Qdisc which is pointed to by qdisc is now a
+ * rcu structure - it may be accessed without acquiring
+ * a lock (but the structure may be stale.) The freeing of the
+ * qdisc will be deferred until it's known that there are no
+ * more references to it.
+ *
+ * If the qdisc has an enqueue function, we still need to
+ * hold the queue_lock before calling it, since queue_lock
+ * also serializes access to the device queue.
+ */
+
+ q = rcu_dereference(dev->qdisc);
+#ifdef CONFIG_NET_CLS_ACT
+ skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
+#endif
+ if (q->enqueue) {
+ /* Grab device queue */
+ spin_lock(&dev->queue_lock);
+
+ rc = q->enqueue(skb, q);
+
+ qdisc_run(dev);
+
+ spin_unlock(&dev->queue_lock);
+ rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
+ goto out;
+ }
+
+ /* The device has no queue. Common case for software devices:
+ loopback, all the sorts of tunnels...
+
+ Really, it is unlikely that xmit_lock protection is necessary here.
+ (f.e. loopback and IP tunnels are clean ignoring statistics
+ counters.)
+ However, it is possible, that they rely on protection
+ made by us here.
+
+ Check this and shot the lock. It is not prone from deadlocks.
+ Either shot noqueue qdisc, it is even simpler 8)
+ */
+ if (dev->flags & IFF_UP) {
+ int cpu = smp_processor_id(); /* ok because BHs are off */
+
+ if (dev->xmit_lock_owner != cpu) {
+
+ HARD_TX_LOCK(dev, cpu);
+
+ if (!netif_queue_stopped(dev)) {
+ if (netdev_nit)
+ dev_queue_xmit_nit(skb, dev);
+
+ rc = 0;
+ if (!dev->hard_start_xmit(skb, dev)) {
+ HARD_TX_UNLOCK(dev);
+ goto out;
+ }
+ }
+ HARD_TX_UNLOCK(dev);
+ if (net_ratelimit())
+ printk(KERN_CRIT "Virtual device %s asks to "
+ "queue packet!\n", dev->name);
+ } else {
+ /* Recursion is detected! It is possible,
+ * unfortunately */
+ if (net_ratelimit())
+ printk(KERN_CRIT "Dead loop on virtual device "
+ "%s, fix it urgently!\n", dev->name);
+ }
+ }
+
+ rc = -ENETDOWN;
+ local_bh_enable();
+
+out_kfree_skb:
+ kfree_skb(skb);
+ return rc;
+out:
+ local_bh_enable();
+ return rc;
+}
+
+
+/*=======================================================================
+ Receiver routines
+ =======================================================================*/
+
+int netdev_max_backlog = 300;
+int weight_p = 64; /* old backlog weight */
+/* These numbers are selected based on intuition and some
+ * experimentatiom, if you have more scientific way of doing this
+ * please go ahead and fix things.
+ */
+int no_cong_thresh = 10;
+int no_cong = 20;
+int lo_cong = 100;
+int mod_cong = 290;
+
+DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
+
+
+static void get_sample_stats(int cpu)
+{
+#ifdef RAND_LIE
+ unsigned long rd;
+ int rq;
+#endif
+ struct softnet_data *sd = &per_cpu(softnet_data, cpu);
+ int blog = sd->input_pkt_queue.qlen;
+ int avg_blog = sd->avg_blog;
+
+ avg_blog = (avg_blog >> 1) + (blog >> 1);
+
+ if (avg_blog > mod_cong) {
+ /* Above moderate congestion levels. */
+ sd->cng_level = NET_RX_CN_HIGH;
+#ifdef RAND_LIE
+ rd = net_random();
+ rq = rd % netdev_max_backlog;
+ if (rq < avg_blog) /* unlucky bastard */
+ sd->cng_level = NET_RX_DROP;
+#endif
+ } else if (avg_blog > lo_cong) {
+ sd->cng_level = NET_RX_CN_MOD;
+#ifdef RAND_LIE
+ rd = net_random();
+ rq = rd % netdev_max_backlog;
+ if (rq < avg_blog) /* unlucky bastard */
+ sd->cng_level = NET_RX_CN_HIGH;
+#endif
+ } else if (avg_blog > no_cong)
+ sd->cng_level = NET_RX_CN_LOW;
+ else /* no congestion */
+ sd->cng_level = NET_RX_SUCCESS;
+
+ sd->avg_blog = avg_blog;
+}
+
+#ifdef OFFLINE_SAMPLE
+static void sample_queue(unsigned long dummy)
+{
+/* 10 ms 0r 1ms -- i don't care -- JHS */
+ int next_tick = 1;
+ int cpu = smp_processor_id();
+
+ get_sample_stats(cpu);
+ next_tick += jiffies;
+ mod_timer(&samp_timer, next_tick);
+}
+#endif
+
+
+/**
+ * netif_rx - post buffer to the network code
+ * @skb: buffer to post
+ *
+ * This function receives a packet from a device driver and queues it for
+ * the upper (protocol) levels to process. It always succeeds. The buffer
+ * may be dropped during processing for congestion control or by the
+ * protocol layers.
+ *
+ * return values:
+ * NET_RX_SUCCESS (no congestion)
+ * NET_RX_CN_LOW (low congestion)
+ * NET_RX_CN_MOD (moderate congestion)
+ * NET_RX_CN_HIGH (high congestion)
+ * NET_RX_DROP (packet was dropped)
+ *
+ */
+
+int netif_rx(struct sk_buff *skb)
+{
+ int this_cpu;
+ struct softnet_data *queue;
+ unsigned long flags;
+
+ /* if netpoll wants it, pretend we never saw it */
+ if (netpoll_rx(skb))
+ return NET_RX_DROP;
+
+ if (!skb->stamp.tv_sec)
+ net_timestamp(&skb->stamp);
+
+ /*
+ * The code is rearranged so that the path is the most
+ * short when CPU is congested, but is still operating.
+ */
+ local_irq_save(flags);
+ this_cpu = smp_processor_id();
+ queue = &__get_cpu_var(softnet_data);
+
+ __get_cpu_var(netdev_rx_stat).total++;
+ if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
+ if (queue->input_pkt_queue.qlen) {
+ if (queue->throttle)
+ goto drop;
+
+enqueue:
+ dev_hold(skb->dev);
+ __skb_queue_tail(&queue->input_pkt_queue, skb);
+#ifndef OFFLINE_SAMPLE
+ get_sample_stats(this_cpu);
+#endif
+ local_irq_restore(flags);
+ return queue->cng_level;
+ }
+
+ if (queue->throttle)
+ queue->throttle = 0;
+
+ netif_rx_schedule(&queue->backlog_dev);
+ goto enqueue;
+ }
+
+ if (!queue->throttle) {
+ queue->throttle = 1;
+ __get_cpu_var(netdev_rx_stat).throttled++;
+ }
+
+drop:
+ __get_cpu_var(netdev_rx_stat).dropped++;
+ local_irq_restore(flags);
+
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
+
+int netif_rx_ni(struct sk_buff *skb)
+{
+ int err;
+
+ preempt_disable();
+ err = netif_rx(skb);
+ if (local_softirq_pending())
+ do_softirq();
+ preempt_enable();
+
+ return err;
+}
+
+EXPORT_SYMBOL(netif_rx_ni);
+
+static __inline__ void skb_bond(struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+
+ if (dev->master) {
+ skb->real_dev = skb->dev;
+ skb->dev = dev->master;
+ }
+}
+
+static void net_tx_action(struct softirq_action *h)
+{
+ struct softnet_data *sd = &__get_cpu_var(softnet_data);
+
+ if (sd->completion_queue) {
+ struct sk_buff *clist;
+
+ local_irq_disable();
+ clist = sd->completion_queue;
+ sd->completion_queue = NULL;
+ local_irq_enable();
+
+ while (clist) {
+ struct sk_buff *skb = clist;
+ clist = clist->next;
+
+ BUG_TRAP(!atomic_read(&skb->users));
+ __kfree_skb(skb);
+ }
+ }
+
+ if (sd->output_queue) {
+ struct net_device *head;
+
+ local_irq_disable();
+ head = sd->output_queue;
+ sd->output_queue = NULL;
+ local_irq_enable();
+
+ while (head) {
+ struct net_device *dev = head;
+ head = head->next_sched;
+
+ smp_mb__before_clear_bit();
+ clear_bit(__LINK_STATE_SCHED, &dev->state);
+
+ if (spin_trylock(&dev->queue_lock)) {
+ qdisc_run(dev);
+ spin_unlock(&dev->queue_lock);
+ } else {
+ netif_schedule(dev);
+ }
+ }
+ }
+}
+
+static __inline__ int deliver_skb(struct sk_buff *skb,
+ struct packet_type *pt_prev)
+{
+ atomic_inc(&skb->users);
+ return pt_prev->func(skb, skb->dev, pt_prev);
+}
+
+#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE)
+int (*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff **pskb);
+struct net_bridge;
+struct net_bridge_fdb_entry *(*br_fdb_get_hook)(struct net_bridge *br,
+ unsigned char *addr);
+void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent);
+
+static __inline__ int handle_bridge(struct sk_buff **pskb,
+ struct packet_type **pt_prev, int *ret)
+{
+ struct net_bridge_port *port;
+
+ if ((*pskb)->pkt_type == PACKET_LOOPBACK ||
+ (port = rcu_dereference((*pskb)->dev->br_port)) == NULL)
+ return 0;
+
+ if (*pt_prev) {
+ *ret = deliver_skb(*pskb, *pt_prev);
+ *pt_prev = NULL;
+ }
+
+ return br_handle_frame_hook(port, pskb);
+}
+#else
+#define handle_bridge(skb, pt_prev, ret) (0)
+#endif
+
+#ifdef CONFIG_NET_CLS_ACT
+/* TODO: Maybe we should just force sch_ingress to be compiled in
+ * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
+ * a compare and 2 stores extra right now if we dont have it on
+ * but have CONFIG_NET_CLS_ACT
+ * NOTE: This doesnt stop any functionality; if you dont have
+ * the ingress scheduler, you just cant add policies on ingress.
+ *
+ */
+static int ing_filter(struct sk_buff *skb)
+{
+ struct Qdisc *q;
+ struct net_device *dev = skb->dev;
+ int result = TC_ACT_OK;
+
+ if (dev->qdisc_ingress) {
+ __u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd);
+ if (MAX_RED_LOOP < ttl++) {
+ printk("Redir loop detected Dropping packet (%s->%s)\n",
+ skb->input_dev?skb->input_dev->name:"??",skb->dev->name);
+ return TC_ACT_SHOT;
+ }
+
+ skb->tc_verd = SET_TC_RTTL(skb->tc_verd,ttl);
+
+ skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_INGRESS);
+ if (NULL == skb->input_dev) {
+ skb->input_dev = skb->dev;
+ printk("ing_filter: fixed %s out %s\n",skb->input_dev->name,skb->dev->name);
+ }
+ spin_lock(&dev->ingress_lock);
+ if ((q = dev->qdisc_ingress) != NULL)
+ result = q->enqueue(skb, q);
+ spin_unlock(&dev->ingress_lock);
+
+ }
+
+ return result;
+}
+#endif
+
+int netif_receive_skb(struct sk_buff *skb)
+{
+ struct packet_type *ptype, *pt_prev;
+ int ret = NET_RX_DROP;
+ unsigned short type;
+
+ /* if we've gotten here through NAPI, check netpoll */
+ if (skb->dev->poll && netpoll_rx(skb))
+ return NET_RX_DROP;
+
+ if (!skb->stamp.tv_sec)
+ net_timestamp(&skb->stamp);
+
+ skb_bond(skb);
+
+ __get_cpu_var(netdev_rx_stat).total++;
+
+ skb->h.raw = skb->nh.raw = skb->data;
+ skb->mac_len = skb->nh.raw - skb->mac.raw;
+
+ pt_prev = NULL;
+
+ rcu_read_lock();
+
+#ifdef CONFIG_NET_CLS_ACT
+ if (skb->tc_verd & TC_NCLS) {
+ skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
+ goto ncls;
+ }
+#endif
+
+ list_for_each_entry_rcu(ptype, &ptype_all, list) {
+ if (!ptype->dev || ptype->dev == skb->dev) {
+ if (pt_prev)
+ ret = deliver_skb(skb, pt_prev);
+ pt_prev = ptype;
+ }
+ }
+
+#ifdef CONFIG_NET_CLS_ACT
+ if (pt_prev) {
+ ret = deliver_skb(skb, pt_prev);
+ pt_prev = NULL; /* noone else should process this after*/
+ } else {
+ skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
+ }
+
+ ret = ing_filter(skb);
+
+ if (ret == TC_ACT_SHOT || (ret == TC_ACT_STOLEN)) {
+ kfree_skb(skb);
+ goto out;
+ }
+
+ skb->tc_verd = 0;
+ncls:
+#endif
+
+ handle_diverter(skb);
+
+ if (handle_bridge(&skb, &pt_prev, &ret))
+ goto out;
+
+ type = skb->protocol;
+ list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type)&15], list) {
+ if (ptype->type == type &&
+ (!ptype->dev || ptype->dev == skb->dev)) {
+ if (pt_prev)
+ ret = deliver_skb(skb, pt_prev);
+ pt_prev = ptype;
+ }
+ }
+
+ if (pt_prev) {
+ ret = pt_prev->func(skb, skb->dev, pt_prev);
+ } else {
+ kfree_skb(skb);
+ /* Jamal, now you will not able to escape explaining
+ * me how you were going to use this. :-)
+ */
+ ret = NET_RX_DROP;
+ }
+
+out:
+ rcu_read_unlock();
+ return ret;
+}
+
+static int process_backlog(struct net_device *backlog_dev, int *budget)
+{
+ int work = 0;
+ int quota = min(backlog_dev->quota, *budget);
+ struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ unsigned long start_time = jiffies;
+
+ backlog_dev->weight = weight_p;
+ for (;;) {
+ struct sk_buff *skb;
+ struct net_device *dev;
+
+ local_irq_disable();
+ skb = __skb_dequeue(&queue->input_pkt_queue);
+ if (!skb)
+ goto job_done;
+ local_irq_enable();
+
+ dev = skb->dev;
+
+ netif_receive_skb(skb);
+
+ dev_put(dev);
+
+ work++;
+
+ if (work >= quota || jiffies - start_time > 1)
+ break;
+
+ }
+
+ backlog_dev->quota -= work;
+ *budget -= work;
+ return -1;
+
+job_done:
+ backlog_dev->quota -= work;
+ *budget -= work;
+
+ list_del(&backlog_dev->poll_list);
+ smp_mb__before_clear_bit();
+ netif_poll_enable(backlog_dev);
+
+ if (queue->throttle)
+ queue->throttle = 0;
+ local_irq_enable();
+ return 0;
+}
+
+static void net_rx_action(struct softirq_action *h)
+{
+ struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ unsigned long start_time = jiffies;
+ int budget = netdev_max_backlog;
+
+
+ local_irq_disable();
+
+ while (!list_empty(&queue->poll_list)) {
+ struct net_device *dev;
+
+ if (budget <= 0 || jiffies - start_time > 1)
+ goto softnet_break;
+
+ local_irq_enable();
+
+ dev = list_entry(queue->poll_list.next,
+ struct net_device, poll_list);
+ netpoll_poll_lock(dev);
+
+ if (dev->quota <= 0 || dev->poll(dev, &budget)) {
+ netpoll_poll_unlock(dev);
+ local_irq_disable();
+ list_del(&dev->poll_list);
+ list_add_tail(&dev->poll_list, &queue->poll_list);
+ if (dev->quota < 0)
+ dev->quota += dev->weight;
+ else
+ dev->quota = dev->weight;
+ } else {
+ netpoll_poll_unlock(dev);
+ dev_put(dev);
+ local_irq_disable();
+ }
+ }
+out:
+ local_irq_enable();
+ return;
+
+softnet_break:
+ __get_cpu_var(netdev_rx_stat).time_squeeze++;
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ goto out;
+}
+
+static gifconf_func_t * gifconf_list [NPROTO];
+
+/**
+ * register_gifconf - register a SIOCGIF handler
+ * @family: Address family
+ * @gifconf: Function handler
+ *
+ * Register protocol dependent address dumping routines. The handler
+ * that is passed must not be freed or reused until it has been replaced
+ * by another handler.
+ */
+int register_gifconf(unsigned int family, gifconf_func_t * gifconf)
+{
+ if (family >= NPROTO)
+ return -EINVAL;
+ gifconf_list[family] = gifconf;
+ return 0;
+}
+
+
+/*
+ * Map an interface index to its name (SIOCGIFNAME)
+ */
+
+/*
+ * We need this ioctl for efficient implementation of the
+ * if_indextoname() function required by the IPv6 API. Without
+ * it, we would have to search all the interfaces to find a
+ * match. --pb
+ */
+
+static int dev_ifname(struct ifreq __user *arg)
+{
+ struct net_device *dev;
+ struct ifreq ifr;
+
+ /*
+ * Fetch the caller's info block.
+ */
+
+ if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+ return -EFAULT;
+
+ read_lock(&dev_base_lock);
+ dev = __dev_get_by_index(ifr.ifr_ifindex);
+ if (!dev) {
+ read_unlock(&dev_base_lock);
+ return -ENODEV;
+ }
+
+ strcpy(ifr.ifr_name, dev->name);
+ read_unlock(&dev_base_lock);
+
+ if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
+ return -EFAULT;
+ return 0;
+}
+
+/*
+ * Perform a SIOCGIFCONF call. This structure will change
+ * size eventually, and there is nothing I can do about it.
+ * Thus we will need a 'compatibility mode'.
+ */
+
+static int dev_ifconf(char __user *arg)
+{
+ struct ifconf ifc;
+ struct net_device *dev;
+ char __user *pos;
+ int len;
+ int total;
+ int i;
+
+ /*
+ * Fetch the caller's info block.
+ */
+
+ if (copy_from_user(&ifc, arg, sizeof(struct ifconf)))
+ return -EFAULT;
+
+ pos = ifc.ifc_buf;
+ len = ifc.ifc_len;
+
+ /*
+ * Loop over the interfaces, and write an info block for each.
+ */
+
+ total = 0;
+ for (dev = dev_base; dev; dev = dev->next) {
+ for (i = 0; i < NPROTO; i++) {
+ if (gifconf_list[i]) {
+ int done;
+ if (!pos)
+ done = gifconf_list[i](dev, NULL, 0);
+ else
+ done = gifconf_list[i](dev, pos + total,
+ len - total);
+ if (done < 0)
+ return -EFAULT;
+ total += done;
+ }
+ }
+ }
+
+ /*
+ * All done. Write the updated control block back to the caller.
+ */
+ ifc.ifc_len = total;
+
+ /*
+ * Both BSD and Solaris return 0 here, so we do too.
+ */
+ return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
+}
+
+#ifdef CONFIG_PROC_FS
+/*
+ * This is invoked by the /proc filesystem handler to display a device
+ * in detail.
+ */
+static __inline__ struct net_device *dev_get_idx(loff_t pos)
+{
+ struct net_device *dev;
+ loff_t i;
+
+ for (i = 0, dev = dev_base; dev && i < pos; ++i, dev = dev->next);
+
+ return i == pos ? dev : NULL;
+}
+
+void *dev_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ read_lock(&dev_base_lock);
+ return *pos ? dev_get_idx(*pos - 1) : SEQ_START_TOKEN;
+}
+
+void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ ++*pos;
+ return v == SEQ_START_TOKEN ? dev_base : ((struct net_device *)v)->next;
+}
+
+void dev_seq_stop(struct seq_file *seq, void *v)
+{
+ read_unlock(&dev_base_lock);
+}
+
+static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
+{
+ if (dev->get_stats) {
+ struct net_device_stats *stats = dev->get_stats(dev);
+
+ seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
+ "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
+ dev->name, stats->rx_bytes, stats->rx_packets,
+ stats->rx_errors,
+ stats->rx_dropped + stats->rx_missed_errors,
+ stats->rx_fifo_errors,
+ stats->rx_length_errors + stats->rx_over_errors +
+ stats->rx_crc_errors + stats->rx_frame_errors,
+ stats->rx_compressed, stats->multicast,
+ stats->tx_bytes, stats->tx_packets,
+ stats->tx_errors, stats->tx_dropped,
+ stats->tx_fifo_errors, stats->collisions,
+ stats->tx_carrier_errors +
+ stats->tx_aborted_errors +
+ stats->tx_window_errors +
+ stats->tx_heartbeat_errors,
+ stats->tx_compressed);
+ } else
+ seq_printf(seq, "%6s: No statistics available.\n", dev->name);
+}
+
+/*
+ * Called from the PROCfs module. This now uses the new arbitrary sized
+ * /proc/net interface to create /proc/net/dev
+ */
+static int dev_seq_show(struct seq_file *seq, void *v)
+{
+ if (v == SEQ_START_TOKEN)
+ seq_puts(seq, "Inter-| Receive "
+ " | Transmit\n"
+ " face |bytes packets errs drop fifo frame "
+ "compressed multicast|bytes packets errs "
+ "drop fifo colls carrier compressed\n");
+ else
+ dev_seq_printf_stats(seq, v);
+ return 0;
+}
+
+static struct netif_rx_stats *softnet_get_online(loff_t *pos)
+{
+ struct netif_rx_stats *rc = NULL;
+
+ while (*pos < NR_CPUS)
+ if (cpu_online(*pos)) {
+ rc = &per_cpu(netdev_rx_stat, *pos);
+ break;
+ } else
+ ++*pos;
+ return rc;
+}
+
+static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ return softnet_get_online(pos);
+}
+
+static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ ++*pos;
+ return softnet_get_online(pos);
+}
+
+static void softnet_seq_stop(struct seq_file *seq, void *v)
+{
+}
+
+static int softnet_seq_show(struct seq_file *seq, void *v)
+{
+ struct netif_rx_stats *s = v;
+
+ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+ s->total, s->dropped, s->time_squeeze, s->throttled,
+ s->fastroute_hit, s->fastroute_success, s->fastroute_defer,
+ s->fastroute_deferred_out,
+#if 0
+ s->fastroute_latency_reduction
+#else
+ s->cpu_collision
+#endif
+ );
+ return 0;
+}
+
+static struct seq_operations dev_seq_ops = {
+ .start = dev_seq_start,
+ .next = dev_seq_next,
+ .stop = dev_seq_stop,
+ .show = dev_seq_show,
+};
+
+static int dev_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &dev_seq_ops);
+}
+
+static struct file_operations dev_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = dev_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static struct seq_operations softnet_seq_ops = {
+ .start = softnet_seq_start,
+ .next = softnet_seq_next,
+ .stop = softnet_seq_stop,
+ .show = softnet_seq_show,
+};
+
+static int softnet_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &softnet_seq_ops);
+}
+
+static struct file_operations softnet_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = softnet_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+#ifdef WIRELESS_EXT
+extern int wireless_proc_init(void);
+#else
+#define wireless_proc_init() 0
+#endif
+
+static int __init dev_proc_init(void)
+{
+ int rc = -ENOMEM;
+
+ if (!proc_net_fops_create("dev", S_IRUGO, &dev_seq_fops))
+ goto out;
+ if (!proc_net_fops_create("softnet_stat", S_IRUGO, &softnet_seq_fops))
+ goto out_dev;
+ if (wireless_proc_init())
+ goto out_softnet;
+ rc = 0;
+out:
+ return rc;
+out_softnet:
+ proc_net_remove("softnet_stat");
+out_dev:
+ proc_net_remove("dev");
+ goto out;
+}
+#else
+#define dev_proc_init() 0
+#endif /* CONFIG_PROC_FS */
+
+
+/**
+ * netdev_set_master - set up master/slave pair
+ * @slave: slave device
+ * @master: new master device
+ *
+ * Changes the master device of the slave. Pass %NULL to break the
+ * bonding. The caller must hold the RTNL semaphore. On a failure
+ * a negative errno code is returned. On success the reference counts
+ * are adjusted, %RTM_NEWLINK is sent to the routing socket and the
+ * function returns zero.
+ */
+int netdev_set_master(struct net_device *slave, struct net_device *master)
+{
+ struct net_device *old = slave->master;
+
+ ASSERT_RTNL();
+
+ if (master) {
+ if (old)
+ return -EBUSY;
+ dev_hold(master);
+ }
+
+ slave->master = master;
+
+ synchronize_net();
+
+ if (old)
+ dev_put(old);
+
+ if (master)
+ slave->flags |= IFF_SLAVE;
+ else
+ slave->flags &= ~IFF_SLAVE;
+
+ rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
+ return 0;
+}
+
+/**
+ * dev_set_promiscuity - update promiscuity count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove promsicuity from a device. While the count in the device
+ * remains above zero the interface remains promiscuous. Once it hits zero
+ * the device reverts back to normal filtering operation. A negative inc
+ * value is used to drop promiscuity on the device.
+ */
+void dev_set_promiscuity(struct net_device *dev, int inc)
+{
+ unsigned short old_flags = dev->flags;
+
+ dev->flags |= IFF_PROMISC;
+ if ((dev->promiscuity += inc) == 0)
+ dev->flags &= ~IFF_PROMISC;
+ if (dev->flags ^ old_flags) {
+ dev_mc_upload(dev);
+ printk(KERN_INFO "device %s %s promiscuous mode\n",
+ dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
+ "left");
+ }
+}
+
+/**
+ * dev_set_allmulti - update allmulti count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove reception of all multicast frames to a device. While the
+ * count in the device remains above zero the interface remains listening
+ * to all interfaces. Once it hits zero the device reverts back to normal
+ * filtering operation. A negative @inc value is used to drop the counter
+ * when releasing a resource needing all multicasts.
+ */
+
+void dev_set_allmulti(struct net_device *dev, int inc)
+{
+ unsigned short old_flags = dev->flags;
+
+ dev->flags |= IFF_ALLMULTI;
+ if ((dev->allmulti += inc) == 0)
+ dev->flags &= ~IFF_ALLMULTI;
+ if (dev->flags ^ old_flags)
+ dev_mc_upload(dev);
+}
+
+unsigned dev_get_flags(const struct net_device *dev)
+{
+ unsigned flags;
+
+ flags = (dev->flags & ~(IFF_PROMISC |
+ IFF_ALLMULTI |
+ IFF_RUNNING)) |
+ (dev->gflags & (IFF_PROMISC |
+ IFF_ALLMULTI));
+
+ if (netif_running(dev) && netif_carrier_ok(dev))
+ flags |= IFF_RUNNING;
+
+ return flags;
+}
+
+int dev_change_flags(struct net_device *dev, unsigned flags)
+{
+ int ret;
+ int old_flags = dev->flags;
+
+ /*
+ * Set the flags on our device.
+ */
+
+ dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP |
+ IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL |
+ IFF_AUTOMEDIA)) |
+ (dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC |
+ IFF_ALLMULTI));
+
+ /*
+ * Load in the correct multicast list now the flags have changed.
+ */
+
+ dev_mc_upload(dev);
+
+ /*
+ * Have we downed the interface. We handle IFF_UP ourselves
+ * according to user attempts to set it, rather than blindly
+ * setting it.
+ */
+
+ ret = 0;
+ if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */
+ ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev);
+
+ if (!ret)
+ dev_mc_upload(dev);
+ }
+
+ if (dev->flags & IFF_UP &&
+ ((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
+ IFF_VOLATILE)))
+ notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev);
+
+ if ((flags ^ dev->gflags) & IFF_PROMISC) {
+ int inc = (flags & IFF_PROMISC) ? +1 : -1;
+ dev->gflags ^= IFF_PROMISC;
+ dev_set_promiscuity(dev, inc);
+ }
+
+ /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI
+ is important. Some (broken) drivers set IFF_PROMISC, when
+ IFF_ALLMULTI is requested not asking us and not reporting.
+ */
+ if ((flags ^ dev->gflags) & IFF_ALLMULTI) {
+ int inc = (flags & IFF_ALLMULTI) ? +1 : -1;
+ dev->gflags ^= IFF_ALLMULTI;
+ dev_set_allmulti(dev, inc);
+ }
+
+ if (old_flags ^ dev->flags)
+ rtmsg_ifinfo(RTM_NEWLINK, dev, old_flags ^ dev->flags);
+
+ return ret;
+}
+
+int dev_set_mtu(struct net_device *dev, int new_mtu)
+{
+ int err;
+
+ if (new_mtu == dev->mtu)
+ return 0;
+
+ /* MTU must be positive. */
+ if (new_mtu < 0)
+ return -EINVAL;
+
+ if (!netif_device_present(dev))
+ return -ENODEV;
+
+ err = 0;
+ if (dev->change_mtu)
+ err = dev->change_mtu(dev, new_mtu);
+ else
+ dev->mtu = new_mtu;
+ if (!err && dev->flags & IFF_UP)
+ notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGEMTU, dev);
+ return err;
+}
+
+int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
+{
+ int err;
+
+ if (!dev->set_mac_address)
+ return -EOPNOTSUPP;
+ if (sa->sa_family != dev->type)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ err = dev->set_mac_address(dev, sa);
+ if (!err)
+ notifier_call_chain(&netdev_chain, NETDEV_CHANGEADDR, dev);
+ return err;
+}
+
+/*
+ * Perform the SIOCxIFxxx calls.
+ */
+static int dev_ifsioc(struct ifreq *ifr, unsigned int cmd)
+{
+ int err;
+ struct net_device *dev = __dev_get_by_name(ifr->ifr_name);
+
+ if (!dev)
+ return -ENODEV;
+
+ switch (cmd) {
+ case SIOCGIFFLAGS: /* Get interface flags */
+ ifr->ifr_flags = dev_get_flags(dev);
+ return 0;
+
+ case SIOCSIFFLAGS: /* Set interface flags */
+ return dev_change_flags(dev, ifr->ifr_flags);
+
+ case SIOCGIFMETRIC: /* Get the metric on the interface
+ (currently unused) */
+ ifr->ifr_metric = 0;
+ return 0;
+
+ case SIOCSIFMETRIC: /* Set the metric on the interface
+ (currently unused) */
+ return -EOPNOTSUPP;
+
+ case SIOCGIFMTU: /* Get the MTU of a device */
+ ifr->ifr_mtu = dev->mtu;
+ return 0;
+
+ case SIOCSIFMTU: /* Set the MTU of a device */
+ return dev_set_mtu(dev, ifr->ifr_mtu);
+
+ case SIOCGIFHWADDR:
+ if (!dev->addr_len)
+ memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
+ else
+ memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ ifr->ifr_hwaddr.sa_family = dev->type;
+ return 0;
+
+ case SIOCSIFHWADDR:
+ return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+
+ case SIOCSIFHWBROADCAST:
+ if (ifr->ifr_hwaddr.sa_family != dev->type)
+ return -EINVAL;
+ memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGEADDR, dev);
+ return 0;
+
+ case SIOCGIFMAP:
+ ifr->ifr_map.mem_start = dev->mem_start;
+ ifr->ifr_map.mem_end = dev->mem_end;
+ ifr->ifr_map.base_addr = dev->base_addr;
+ ifr->ifr_map.irq = dev->irq;
+ ifr->ifr_map.dma = dev->dma;
+ ifr->ifr_map.port = dev->if_port;
+ return 0;
+
+ case SIOCSIFMAP:
+ if (dev->set_config) {
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev->set_config(dev, &ifr->ifr_map);
+ }
+ return -EOPNOTSUPP;
+
+ case SIOCADDMULTI:
+ if (!dev->set_multicast_list ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
+
+ case SIOCDELMULTI:
+ if (!dev->set_multicast_list ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
+
+ case SIOCGIFINDEX:
+ ifr->ifr_ifindex = dev->ifindex;
+ return 0;
+
+ case SIOCGIFTXQLEN:
+ ifr->ifr_qlen = dev->tx_queue_len;
+ return 0;
+
+ case SIOCSIFTXQLEN:
+ if (ifr->ifr_qlen < 0)
+ return -EINVAL;
+ dev->tx_queue_len = ifr->ifr_qlen;
+ return 0;
+
+ case SIOCSIFNAME:
+ ifr->ifr_newname[IFNAMSIZ-1] = '\0';
+ return dev_change_name(dev, ifr->ifr_newname);
+
+ /*
+ * Unknown or private ioctl
+ */
+
+ default:
+ if ((cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15) ||
+ cmd == SIOCBONDENSLAVE ||
+ cmd == SIOCBONDRELEASE ||
+ cmd == SIOCBONDSETHWADDR ||
+ cmd == SIOCBONDSLAVEINFOQUERY ||
+ cmd == SIOCBONDINFOQUERY ||
+ cmd == SIOCBONDCHANGEACTIVE ||
+ cmd == SIOCGMIIPHY ||
+ cmd == SIOCGMIIREG ||
+ cmd == SIOCSMIIREG ||
+ cmd == SIOCBRADDIF ||
+ cmd == SIOCBRDELIF ||
+ cmd == SIOCWANDEV) {
+ err = -EOPNOTSUPP;
+ if (dev->do_ioctl) {
+ if (netif_device_present(dev))
+ err = dev->do_ioctl(dev, ifr,
+ cmd);
+ else
+ err = -ENODEV;
+ }
+ } else
+ err = -EINVAL;
+
+ }
+ return err;
+}
+
+/*
+ * This function handles all "interface"-type I/O control requests. The actual
+ * 'doing' part of this is dev_ifsioc above.
+ */
+
+/**
+ * dev_ioctl - network device ioctl
+ * @cmd: command to issue
+ * @arg: pointer to a struct ifreq in user space
+ *
+ * Issue ioctl functions to devices. This is normally called by the
+ * user space syscall interfaces but can sometimes be useful for
+ * other purposes. The return value is the return from the syscall if
+ * positive or a negative errno code on error.
+ */
+
+int dev_ioctl(unsigned int cmd, void __user *arg)
+{
+ struct ifreq ifr;
+ int ret;
+ char *colon;
+
+ /* One special case: SIOCGIFCONF takes ifconf argument
+ and requires shared lock, because it sleeps writing
+ to user space.
+ */
+
+ if (cmd == SIOCGIFCONF) {
+ rtnl_shlock();
+ ret = dev_ifconf((char __user *) arg);
+ rtnl_shunlock();
+ return ret;
+ }
+ if (cmd == SIOCGIFNAME)
+ return dev_ifname((struct ifreq __user *)arg);
+
+ if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+ return -EFAULT;
+
+ ifr.ifr_name[IFNAMSIZ-1] = 0;
+
+ colon = strchr(ifr.ifr_name, ':');
+ if (colon)
+ *colon = 0;
+
+ /*
+ * See which interface the caller is talking about.
+ */
+
+ switch (cmd) {
+ /*
+ * These ioctl calls:
+ * - can be done by all.
+ * - atomic and do not require locking.
+ * - return a value
+ */
+ case SIOCGIFFLAGS:
+ case SIOCGIFMETRIC:
+ case SIOCGIFMTU:
+ case SIOCGIFHWADDR:
+ case SIOCGIFSLAVE:
+ case SIOCGIFMAP:
+ case SIOCGIFINDEX:
+ case SIOCGIFTXQLEN:
+ dev_load(ifr.ifr_name);
+ read_lock(&dev_base_lock);
+ ret = dev_ifsioc(&ifr, cmd);
+ read_unlock(&dev_base_lock);
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
+
+ case SIOCETHTOOL:
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ethtool(&ifr);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
+
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - return a value
+ */
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCSIFNAME:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(&ifr, cmd);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
+
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - do not return a value
+ */
+ case SIOCSIFFLAGS:
+ case SIOCSIFMETRIC:
+ case SIOCSIFMTU:
+ case SIOCSIFMAP:
+ case SIOCSIFHWADDR:
+ case SIOCSIFSLAVE:
+ case SIOCADDMULTI:
+ case SIOCDELMULTI:
+ case SIOCSIFHWBROADCAST:
+ case SIOCSIFTXQLEN:
+ case SIOCSMIIREG:
+ case SIOCBONDENSLAVE:
+ case SIOCBONDRELEASE:
+ case SIOCBONDSETHWADDR:
+ case SIOCBONDSLAVEINFOQUERY:
+ case SIOCBONDINFOQUERY:
+ case SIOCBONDCHANGEACTIVE:
+ case SIOCBRADDIF:
+ case SIOCBRDELIF:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(&ifr, cmd);
+ rtnl_unlock();
+ return ret;
+
+ case SIOCGIFMEM:
+ /* Get the per device memory space. We can add this but
+ * currently do not support it */
+ case SIOCSIFMEM:
+ /* Set the per device memory buffer space.
+ * Not applicable in our case */
+ case SIOCSIFLINK:
+ return -EINVAL;
+
+ /*
+ * Unknown or private ioctl.
+ */
+ default:
+ if (cmd == SIOCWANDEV ||
+ (cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15)) {
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(&ifr, cmd);
+ rtnl_unlock();
+ if (!ret && copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ return ret;
+ }
+#ifdef WIRELESS_EXT
+ /* Take care of Wireless Extensions */
+ if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
+ /* If command is `set a parameter', or
+ * `get the encoding parameters', check if
+ * the user has the right to do it */
+ if (IW_IS_SET(cmd) || cmd == SIOCGIWENCODE) {
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ }
+ dev_load(ifr.ifr_name);
+ rtnl_lock();
+ /* Follow me in net/core/wireless.c */
+ ret = wireless_process_ioctl(&ifr, cmd);
+ rtnl_unlock();
+ if (IW_IS_GET(cmd) &&
+ copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ return ret;
+ }
+#endif /* WIRELESS_EXT */
+ return -EINVAL;
+ }
+}
+
+
+/**
+ * dev_new_index - allocate an ifindex
+ *
+ * Returns a suitable unique value for a new device interface
+ * number. The caller must hold the rtnl semaphore or the
+ * dev_base_lock to be sure it remains unique.
+ */
+static int dev_new_index(void)
+{
+ static int ifindex;
+ for (;;) {
+ if (++ifindex <= 0)
+ ifindex = 1;
+ if (!__dev_get_by_index(ifindex))
+ return ifindex;
+ }
+}
+
+static int dev_boot_phase = 1;
+
+/* Delayed registration/unregisteration */
+static DEFINE_SPINLOCK(net_todo_list_lock);
+static struct list_head net_todo_list = LIST_HEAD_INIT(net_todo_list);
+
+static inline void net_set_todo(struct net_device *dev)
+{
+ spin_lock(&net_todo_list_lock);
+ list_add_tail(&dev->todo_list, &net_todo_list);
+ spin_unlock(&net_todo_list_lock);
+}
+
+/**
+ * register_netdevice - register a network device
+ * @dev: device to register
+ *
+ * Take a completed network device structure and add it to the kernel
+ * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
+ * chain. 0 is returned on success. A negative errno code is returned
+ * on a failure to set up the device, or if the name is a duplicate.
+ *
+ * Callers must hold the rtnl semaphore. You may want
+ * register_netdev() instead of this.
+ *
+ * BUGS:
+ * The locking appears insufficient to guarantee two parallel registers
+ * will not get the same name.
+ */
+
+int register_netdevice(struct net_device *dev)
+{
+ struct hlist_head *head;
+ struct hlist_node *p;
+ int ret;
+
+ BUG_ON(dev_boot_phase);
+ ASSERT_RTNL();
+
+ /* When net_device's are persistent, this will be fatal. */
+ BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
+
+ spin_lock_init(&dev->queue_lock);
+ spin_lock_init(&dev->xmit_lock);
+ dev->xmit_lock_owner = -1;
+#ifdef CONFIG_NET_CLS_ACT
+ spin_lock_init(&dev->ingress_lock);
+#endif
+
+ ret = alloc_divert_blk(dev);
+ if (ret)
+ goto out;
+
+ dev->iflink = -1;
+
+ /* Init, if this function is available */
+ if (dev->init) {
+ ret = dev->init(dev);
+ if (ret) {
+ if (ret > 0)
+ ret = -EIO;
+ goto out_err;
+ }
+ }
+
+ if (!dev_valid_name(dev->name)) {
+ ret = -EINVAL;
+ goto out_err;
+ }
+
+ dev->ifindex = dev_new_index();
+ if (dev->iflink == -1)
+ dev->iflink = dev->ifindex;
+
+ /* Check for existence of name */
+ head = dev_name_hash(dev->name);
+ hlist_for_each(p, head) {
+ struct net_device *d
+ = hlist_entry(p, struct net_device, name_hlist);
+ if (!strncmp(d->name, dev->name, IFNAMSIZ)) {
+ ret = -EEXIST;
+ goto out_err;
+ }
+ }
+
+ /* Fix illegal SG+CSUM combinations. */
+ if ((dev->features & NETIF_F_SG) &&
+ !(dev->features & (NETIF_F_IP_CSUM |
+ NETIF_F_NO_CSUM |
+ NETIF_F_HW_CSUM))) {
+ printk("%s: Dropping NETIF_F_SG since no checksum feature.\n",
+ dev->name);
+ dev->features &= ~NETIF_F_SG;
+ }
+
+ /* TSO requires that SG is present as well. */
+ if ((dev->features & NETIF_F_TSO) &&
+ !(dev->features & NETIF_F_SG)) {
+ printk("%s: Dropping NETIF_F_TSO since no SG feature.\n",
+ dev->name);
+ dev->features &= ~NETIF_F_TSO;
+ }
+
+ /*
+ * nil rebuild_header routine,
+ * that should be never called and used as just bug trap.
+ */
+
+ if (!dev->rebuild_header)
+ dev->rebuild_header = default_rebuild_header;
+
+ /*
+ * Default initial state at registry is that the
+ * device is present.
+ */
+
+ set_bit(__LINK_STATE_PRESENT, &dev->state);
+
+ dev->next = NULL;
+ dev_init_scheduler(dev);
+ write_lock_bh(&dev_base_lock);
+ *dev_tail = dev;
+ dev_tail = &dev->next;
+ hlist_add_head(&dev->name_hlist, head);
+ hlist_add_head(&dev->index_hlist, dev_index_hash(dev->ifindex));
+ dev_hold(dev);
+ dev->reg_state = NETREG_REGISTERING;
+ write_unlock_bh(&dev_base_lock);
+
+ /* Notify protocols, that a new device appeared. */
+ notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev);
+
+ /* Finish registration after unlock */
+ net_set_todo(dev);
+ ret = 0;
+
+out:
+ return ret;
+out_err:
+ free_divert_blk(dev);
+ goto out;
+}
+
+/**
+ * register_netdev - register a network device
+ * @dev: device to register
+ *
+ * Take a completed network device structure and add it to the kernel
+ * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
+ * chain. 0 is returned on success. A negative errno code is returned
+ * on a failure to set up the device, or if the name is a duplicate.
+ *
+ * This is a wrapper around register_netdev that takes the rtnl semaphore
+ * and expands the device name if you passed a format string to
+ * alloc_netdev.
+ */
+int register_netdev(struct net_device *dev)
+{
+ int err;
+
+ rtnl_lock();
+
+ /*
+ * If the name is a format string the caller wants us to do a
+ * name allocation.
+ */
+ if (strchr(dev->name, '%')) {
+ err = dev_alloc_name(dev, dev->name);
+ if (err < 0)
+ goto out;
+ }
+
+ /*
+ * Back compatibility hook. Kill this one in 2.5
+ */
+ if (dev->name[0] == 0 || dev->name[0] == ' ') {
+ err = dev_alloc_name(dev, "eth%d");
+ if (err < 0)
+ goto out;
+ }
+
+ err = register_netdevice(dev);
+out:
+ rtnl_unlock();
+ return err;
+}
+EXPORT_SYMBOL(register_netdev);
+
+/*
+ * netdev_wait_allrefs - wait until all references are gone.
+ *
+ * This is called when unregistering network devices.
+ *
+ * Any protocol or device that holds a reference should register
+ * for netdevice notification, and cleanup and put back the
+ * reference if they receive an UNREGISTER event.
+ * We can get stuck here if buggy protocols don't correctly
+ * call dev_put.
+ */
+static void netdev_wait_allrefs(struct net_device *dev)
+{
+ unsigned long rebroadcast_time, warning_time;
+
+ rebroadcast_time = warning_time = jiffies;
+ while (atomic_read(&dev->refcnt) != 0) {
+ if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
+ rtnl_shlock();
+
+ /* Rebroadcast unregister notification */
+ notifier_call_chain(&netdev_chain,
+ NETDEV_UNREGISTER, dev);
+
+ if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
+ &dev->state)) {
+ /* We must not have linkwatch events
+ * pending on unregister. If this
+ * happens, we simply run the queue
+ * unscheduled, resulting in a noop
+ * for this device.
+ */
+ linkwatch_run_queue();
+ }
+
+ rtnl_shunlock();
+
+ rebroadcast_time = jiffies;
+ }
+
+ msleep(250);
+
+ if (time_after(jiffies, warning_time + 10 * HZ)) {
+ printk(KERN_EMERG "unregister_netdevice: "
+ "waiting for %s to become free. Usage "
+ "count = %d\n",
+ dev->name, atomic_read(&dev->refcnt));
+ warning_time = jiffies;
+ }
+ }
+}
+
+/* The sequence is:
+ *
+ * rtnl_lock();
+ * ...
+ * register_netdevice(x1);
+ * register_netdevice(x2);
+ * ...
+ * unregister_netdevice(y1);
+ * unregister_netdevice(y2);
+ * ...
+ * rtnl_unlock();
+ * free_netdev(y1);
+ * free_netdev(y2);
+ *
+ * We are invoked by rtnl_unlock() after it drops the semaphore.
+ * This allows us to deal with problems:
+ * 1) We can create/delete sysfs objects which invoke hotplug
+ * without deadlocking with linkwatch via keventd.
+ * 2) Since we run with the RTNL semaphore not held, we can sleep
+ * safely in order to wait for the netdev refcnt to drop to zero.
+ */
+static DECLARE_MUTEX(net_todo_run_mutex);
+void netdev_run_todo(void)
+{
+ struct list_head list = LIST_HEAD_INIT(list);
+ int err;
+
+
+ /* Need to guard against multiple cpu's getting out of order. */
+ down(&net_todo_run_mutex);
+
+ /* Not safe to do outside the semaphore. We must not return
+ * until all unregister events invoked by the local processor
+ * have been completed (either by this todo run, or one on
+ * another cpu).
+ */
+ if (list_empty(&net_todo_list))
+ goto out;
+
+ /* Snapshot list, allow later requests */
+ spin_lock(&net_todo_list_lock);
+ list_splice_init(&net_todo_list, &list);
+ spin_unlock(&net_todo_list_lock);
+
+ while (!list_empty(&list)) {
+ struct net_device *dev
+ = list_entry(list.next, struct net_device, todo_list);
+ list_del(&dev->todo_list);
+
+ switch(dev->reg_state) {
+ case NETREG_REGISTERING:
+ err = netdev_register_sysfs(dev);
+ if (err)
+ printk(KERN_ERR "%s: failed sysfs registration (%d)\n",
+ dev->name, err);
+ dev->reg_state = NETREG_REGISTERED;
+ break;
+
+ case NETREG_UNREGISTERING:
+ netdev_unregister_sysfs(dev);
+ dev->reg_state = NETREG_UNREGISTERED;
+
+ netdev_wait_allrefs(dev);
+
+ /* paranoia */
+ BUG_ON(atomic_read(&dev->refcnt));
+ BUG_TRAP(!dev->ip_ptr);
+ BUG_TRAP(!dev->ip6_ptr);
+ BUG_TRAP(!dev->dn_ptr);
+
+
+ /* It must be the very last action,
+ * after this 'dev' may point to freed up memory.
+ */
+ if (dev->destructor)
+ dev->destructor(dev);
+ break;
+
+ default:
+ printk(KERN_ERR "network todo '%s' but state %d\n",
+ dev->name, dev->reg_state);
+ break;
+ }
+ }
+
+out:
+ up(&net_todo_run_mutex);
+}
+
+/**
+ * alloc_netdev - allocate network device
+ * @sizeof_priv: size of private data to allocate space for
+ * @name: device name format string
+ * @setup: callback to initialize device
+ *
+ * Allocates a struct net_device with private data area for driver use
+ * and performs basic initialization.
+ */
+struct net_device *alloc_netdev(int sizeof_priv, const char *name,
+ void (*setup)(struct net_device *))
+{
+ void *p;
+ struct net_device *dev;
+ int alloc_size;
+
+ /* ensure 32-byte alignment of both the device and private area */
+ alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST;
+ alloc_size += sizeof_priv + NETDEV_ALIGN_CONST;
+
+ p = kmalloc(alloc_size, GFP_KERNEL);
+ if (!p) {
+ printk(KERN_ERR "alloc_dev: Unable to allocate device.\n");
+ return NULL;
+ }
+ memset(p, 0, alloc_size);
+
+ dev = (struct net_device *)
+ (((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST);
+ dev->padded = (char *)dev - (char *)p;
+
+ if (sizeof_priv)
+ dev->priv = netdev_priv(dev);
+
+ setup(dev);
+ strcpy(dev->name, name);
+ return dev;
+}
+EXPORT_SYMBOL(alloc_netdev);
+
+/**
+ * free_netdev - free network device
+ * @dev: device
+ *
+ * This function does the last stage of destroying an allocated device
+ * interface. The reference to the device object is released.
+ * If this is the last reference then it will be freed.
+ */
+void free_netdev(struct net_device *dev)
+{
+#ifdef CONFIG_SYSFS
+ /* Compatiablity with error handling in drivers */
+ if (dev->reg_state == NETREG_UNINITIALIZED) {
+ kfree((char *)dev - dev->padded);
+ return;
+ }
+
+ BUG_ON(dev->reg_state != NETREG_UNREGISTERED);
+ dev->reg_state = NETREG_RELEASED;
+
+ /* will free via class release */
+ class_device_put(&dev->class_dev);
+#else
+ kfree((char *)dev - dev->padded);
+#endif
+}
+
+/* Synchronize with packet receive processing. */
+void synchronize_net(void)
+{
+ might_sleep();
+ synchronize_rcu();
+}
+
+/**
+ * unregister_netdevice - remove device from the kernel
+ * @dev: device
+ *
+ * This function shuts down a device interface and removes it
+ * from the kernel tables. On success 0 is returned, on a failure
+ * a negative errno code is returned.
+ *
+ * Callers must hold the rtnl semaphore. You may want
+ * unregister_netdev() instead of this.
+ */
+
+int unregister_netdevice(struct net_device *dev)
+{
+ struct net_device *d, **dp;
+
+ BUG_ON(dev_boot_phase);
+ ASSERT_RTNL();
+
+ /* Some devices call without registering for initialization unwind. */
+ if (dev->reg_state == NETREG_UNINITIALIZED) {
+ printk(KERN_DEBUG "unregister_netdevice: device %s/%p never "
+ "was registered\n", dev->name, dev);
+ return -ENODEV;
+ }
+
+ BUG_ON(dev->reg_state != NETREG_REGISTERED);
+
+ /* If device is running, close it first. */
+ if (dev->flags & IFF_UP)
+ dev_close(dev);
+
+ /* And unlink it from device chain. */
+ for (dp = &dev_base; (d = *dp) != NULL; dp = &d->next) {
+ if (d == dev) {
+ write_lock_bh(&dev_base_lock);
+ hlist_del(&dev->name_hlist);
+ hlist_del(&dev->index_hlist);
+ if (dev_tail == &dev->next)
+ dev_tail = dp;
+ *dp = d->next;
+ write_unlock_bh(&dev_base_lock);
+ break;
+ }
+ }
+ if (!d) {
+ printk(KERN_ERR "unregister net_device: '%s' not found\n",
+ dev->name);
+ return -ENODEV;
+ }
+
+ dev->reg_state = NETREG_UNREGISTERING;
+
+ synchronize_net();
+
+ /* Shutdown queueing discipline. */
+ dev_shutdown(dev);
+
+
+ /* Notify protocols, that we are about to destroy
+ this device. They should clean all the things.
+ */
+ notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev);
+
+ /*
+ * Flush the multicast chain
+ */
+ dev_mc_discard(dev);
+
+ if (dev->uninit)
+ dev->uninit(dev);
+
+ /* Notifier chain MUST detach us from master device. */
+ BUG_TRAP(!dev->master);
+
+ free_divert_blk(dev);
+
+ /* Finish processing unregister after unlock */
+ net_set_todo(dev);
+
+ synchronize_net();
+
+ dev_put(dev);
+ return 0;
+}
+
+/**
+ * unregister_netdev - remove device from the kernel
+ * @dev: device
+ *
+ * This function shuts down a device interface and removes it
+ * from the kernel tables. On success 0 is returned, on a failure
+ * a negative errno code is returned.
+ *
+ * This is just a wrapper for unregister_netdevice that takes
+ * the rtnl semaphore. In general you want to use this and not
+ * unregister_netdevice.
+ */
+void unregister_netdev(struct net_device *dev)
+{
+ rtnl_lock();
+ unregister_netdevice(dev);
+ rtnl_unlock();
+}
+
+EXPORT_SYMBOL(unregister_netdev);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int dev_cpu_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *ocpu)
+{
+ struct sk_buff **list_skb;
+ struct net_device **list_net;
+ struct sk_buff *skb;
+ unsigned int cpu, oldcpu = (unsigned long)ocpu;
+ struct softnet_data *sd, *oldsd;
+
+ if (action != CPU_DEAD)
+ return NOTIFY_OK;
+
+ local_irq_disable();
+ cpu = smp_processor_id();
+ sd = &per_cpu(softnet_data, cpu);
+ oldsd = &per_cpu(softnet_data, oldcpu);
+
+ /* Find end of our completion_queue. */
+ list_skb = &sd->completion_queue;
+ while (*list_skb)
+ list_skb = &(*list_skb)->next;
+ /* Append completion queue from offline CPU. */
+ *list_skb = oldsd->completion_queue;
+ oldsd->completion_queue = NULL;
+
+ /* Find end of our output_queue. */
+ list_net = &sd->output_queue;
+ while (*list_net)
+ list_net = &(*list_net)->next_sched;
+ /* Append output queue from offline CPU. */
+ *list_net = oldsd->output_queue;
+ oldsd->output_queue = NULL;
+
+ raise_softirq_irqoff(NET_TX_SOFTIRQ);
+ local_irq_enable();
+
+ /* Process offline CPU's input_pkt_queue */
+ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue)))
+ netif_rx(skb);
+
+ return NOTIFY_OK;
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+
+/*
+ * Initialize the DEV module. At boot time this walks the device list and
+ * unhooks any devices that fail to initialise (normally hardware not
+ * present) and leaves us with a valid list of present and active devices.
+ *
+ */
+
+/*
+ * This is called single threaded during boot, so no need
+ * to take the rtnl semaphore.
+ */
+static int __init net_dev_init(void)
+{
+ int i, rc = -ENOMEM;
+
+ BUG_ON(!dev_boot_phase);
+
+ net_random_init();
+
+ if (dev_proc_init())
+ goto out;
+
+ if (netdev_sysfs_init())
+ goto out;
+
+ INIT_LIST_HEAD(&ptype_all);
+ for (i = 0; i < 16; i++)
+ INIT_LIST_HEAD(&ptype_base[i]);
+
+ for (i = 0; i < ARRAY_SIZE(dev_name_head); i++)
+ INIT_HLIST_HEAD(&dev_name_head[i]);
+
+ for (i = 0; i < ARRAY_SIZE(dev_index_head); i++)
+ INIT_HLIST_HEAD(&dev_index_head[i]);
+
+ /*
+ * Initialise the packet receive queues.
+ */
+
+ for (i = 0; i < NR_CPUS; i++) {
+ struct softnet_data *queue;
+
+ queue = &per_cpu(softnet_data, i);
+ skb_queue_head_init(&queue->input_pkt_queue);
+ queue->throttle = 0;
+ queue->cng_level = 0;
+ queue->avg_blog = 10; /* arbitrary non-zero */
+ queue->completion_queue = NULL;
+ INIT_LIST_HEAD(&queue->poll_list);
+ set_bit(__LINK_STATE_START, &queue->backlog_dev.state);
+ queue->backlog_dev.weight = weight_p;
+ queue->backlog_dev.poll = process_backlog;
+ atomic_set(&queue->backlog_dev.refcnt, 1);
+ }
+
+#ifdef OFFLINE_SAMPLE
+ samp_timer.expires = jiffies + (10 * HZ);
+ add_timer(&samp_timer);
+#endif
+
+ dev_boot_phase = 0;
+
+ open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
+ open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL);
+
+ hotcpu_notifier(dev_cpu_callback, 0);
+ dst_init();
+ dev_mcast_init();
+ rc = 0;
+out:
+ return rc;
+}
+
+subsys_initcall(net_dev_init);
+
+EXPORT_SYMBOL(__dev_get_by_index);
+EXPORT_SYMBOL(__dev_get_by_name);
+EXPORT_SYMBOL(__dev_remove_pack);
+EXPORT_SYMBOL(__skb_linearize);
+EXPORT_SYMBOL(dev_add_pack);
+EXPORT_SYMBOL(dev_alloc_name);
+EXPORT_SYMBOL(dev_close);
+EXPORT_SYMBOL(dev_get_by_flags);
+EXPORT_SYMBOL(dev_get_by_index);
+EXPORT_SYMBOL(dev_get_by_name);
+EXPORT_SYMBOL(dev_ioctl);
+EXPORT_SYMBOL(dev_open);
+EXPORT_SYMBOL(dev_queue_xmit);
+EXPORT_SYMBOL(dev_remove_pack);
+EXPORT_SYMBOL(dev_set_allmulti);
+EXPORT_SYMBOL(dev_set_promiscuity);
+EXPORT_SYMBOL(dev_change_flags);
+EXPORT_SYMBOL(dev_set_mtu);
+EXPORT_SYMBOL(dev_set_mac_address);
+EXPORT_SYMBOL(free_netdev);
+EXPORT_SYMBOL(netdev_boot_setup_check);
+EXPORT_SYMBOL(netdev_set_master);
+EXPORT_SYMBOL(netdev_state_change);
+EXPORT_SYMBOL(netif_receive_skb);
+EXPORT_SYMBOL(netif_rx);
+EXPORT_SYMBOL(register_gifconf);
+EXPORT_SYMBOL(register_netdevice);
+EXPORT_SYMBOL(register_netdevice_notifier);
+EXPORT_SYMBOL(skb_checksum_help);
+EXPORT_SYMBOL(synchronize_net);
+EXPORT_SYMBOL(unregister_netdevice);
+EXPORT_SYMBOL(unregister_netdevice_notifier);
+EXPORT_SYMBOL(net_enable_timestamp);
+EXPORT_SYMBOL(net_disable_timestamp);
+EXPORT_SYMBOL(dev_get_flags);
+
+#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)
+EXPORT_SYMBOL(br_handle_frame_hook);
+EXPORT_SYMBOL(br_fdb_get_hook);
+EXPORT_SYMBOL(br_fdb_put_hook);
+#endif
+
+#ifdef CONFIG_KMOD
+EXPORT_SYMBOL(dev_load);
+#endif
+
+EXPORT_PER_CPU_SYMBOL(softnet_data);
diff --unified --recursive --new-file linux-2.6.12.5/net/ring/Kconfig linux-2.6.12.5-1-686-smp-ring3/net/ring/Kconfig
--- linux-2.6.12.5/net/ring/Kconfig 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.12.5-1-686-smp-ring3/net/ring/Kconfig 2005-10-22 23:50:45.539482000 +0200
@@ -0,0 +1,14 @@
+config RING
+ tristate "PF_RING sockets (EXPERIMENTAL)"
+ depends on EXPERIMENTAL
+ ---help---
+ PF_RING socket family, optimized for packet capture.
+ If a PF_RING socket is bound to an adapter (via the bind() system
+ call), such adapter will be used in read-only mode until the socket
+ is destroyed. Whenever an incoming packet is received from the adapter
+ it will not passed to upper layers, but instead it is copied to a ring
+ buffer, which in turn is exported to user space applications via mmap.
+ Please refer to http://luca.ntop.org/Ring.pdf for more.
+
+ Say N unless you know what you are doing.
+
diff --unified --recursive --new-file linux-2.6.12.5/net/ring/Makefile linux-2.6.12.5-1-686-smp-ring3/net/ring/Makefile
--- linux-2.6.12.5/net/ring/Makefile 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.12.5-1-686-smp-ring3/net/ring/Makefile 2005-10-22 23:50:45.051451500 +0200
@@ -0,0 +1,7 @@
+#
+# Makefile for the ring driver.
+#
+
+obj-m += ring.o
+
+ring-objs := ring_packet.o
diff --unified --recursive --new-file linux-2.6.12.5/net/ring/ring_packet.c linux-2.6.12.5-1-686-smp-ring3/net/ring/ring_packet.c
--- linux-2.6.12.5/net/ring/ring_packet.c 1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.12.5-1-686-smp-ring3/net/ring/ring_packet.c 2005-10-22 23:50:45.159458250 +0200
@@ -0,0 +1,1592 @@
+/*
+ *
+ * (C) 2004-05 - Luca Deri <deri@ntop.org>
+ *
+ * This code includes patches courtesy of
+ * - Jeff Randall <jrandall@nexvu.com>
+ * - Helmut Manck <helmut.manck@secunet.com>
+ * - Brad Doctor <bdoctor@ps-ax.com>
+ *
+ */
+
+/* FIX: add an entry inside the /proc filesystem */
+
+#include <linux/version.h>
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/socket.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/init.h>
+#include <linux/filter.h>
+#include <linux/ring.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/list.h>
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+#include <net/xfrm.h>
+#else
+#include <linux/poll.h>
+#endif
+#include <net/sock.h>
+#include <asm/io.h> /* needed for virt_to_phys() */
+
+/* #define RING_DEBUG */
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,11))
+static inline int remap_page_range(struct vm_area_struct *vma,
+ unsigned long uvaddr,
+ unsigned long paddr,
+ unsigned long size,
+ pgprot_t prot) {
+ return(remap_pfn_range(vma, uvaddr, paddr >> PAGE_SHIFT,
+ size, prot));
+}
+#endif
+
+/* ************************************************* */
+
+#define CLUSTER_LEN 8
+
+struct ring_cluster {
+ u_short cluster_id; /* 0 = no cluster */
+ u_short num_cluster_elements;
+ enum cluster_type hashing_mode;
+ u_short hashing_id;
+ struct sock *sk[CLUSTER_LEN];
+ struct ring_cluster *next; /* NULL = last element of the cluster */
+};
+
+/* ************************************************* */
+
+struct ring_element {
+ struct list_head list;
+ struct sock *sk;
+};
+
+/* ************************************************* */
+
+struct ring_opt {
+ struct net_device *ring_netdev;
+
+ /* Cluster */
+ u_short cluster_id; /* 0 = no cluster */
+
+ /* Reflector */
+ struct net_device *reflector_dev;
+
+ /* Packet buffers */
+ unsigned long order;
+
+ /* Ring Slots */
+ unsigned long ring_memory;
+ FlowSlotInfo *slots_info; /* Basically it points to ring_memory */
+ char *ring_slots; /* Basically it points to ring_memory
+ +sizeof(FlowSlotInfo) */
+
+ /* Packet Sampling */
+ u_int pktToSample, sample_rate;
+
+ /* BPF Filter */
+ struct sk_filter *bpfFilter;
+
+ /* Locks */
+ atomic_t num_ring_slots_waiters;
+ wait_queue_head_t ring_slots_waitqueue;
+ rwlock_t ring_index_lock;
+
+ /* Indexes (Internal) */
+ u_int insert_page_id, insert_slot_id;
+};
+
+/* ************************************************* */
+
+/* List of all ring sockets. */
+static struct list_head ring_table;
+
+/* List of all clusters */
+static struct ring_cluster *ring_cluster_list;
+
+static rwlock_t ring_mgmt_lock = RW_LOCK_UNLOCKED;
+
+/* ********************************** */
+
+/* Forward */
+static struct proto_ops ring_ops;
+
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,11))
+static struct proto ring_proto;
+#endif
+
+static int skb_ring_handler(struct sk_buff *skb, u_char recv_packet,
+ u_char real_skb);
+static int buffer_ring_handler(struct net_device *dev, char *data, int len);
+static int remove_from_cluster(struct sock *sock, struct ring_opt *pfr);
+
+/* Extern */
+
+/* ********************************** */
+
+/* Defaults */
+static u_int bucket_len = 128, num_slots = 4096, sample_rate = 1,
+ transparent_mode = 0, enable_tx_capture = 0;
+
+MODULE_PARM(bucket_len, "i");
+MODULE_PARM_DESC(bucket_len, "Number of ring buckets");
+MODULE_PARM(num_slots, "i");
+MODULE_PARM_DESC(num_slots, "Number of ring slots");
+MODULE_PARM(sample_rate, "i");
+MODULE_PARM_DESC(sample_rate, "Ring packet sample rate");
+MODULE_PARM(transparent_mode, "i");
+MODULE_PARM_DESC(transparent_mode,
+ "Set to 1 to set transparent mode "
+ "(slower but backwards compatible)");
+MODULE_PARM(enable_tx_capture, "i");
+MODULE_PARM_DESC(enable_tx_capture, "Set to 1 to capture outgoing packets");
+
+/* ********************************** */
+
+#define MIN_QUEUED_PKTS 64
+#define MAX_QUEUE_LOOPS 64
+
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+#define ring_sk_datatype(__sk) ((struct ring_opt *)__sk)
+#define ring_sk(__sk) ((__sk)->sk_protinfo)
+#else
+#define ring_sk_datatype(a) (a)
+#define ring_sk(__sk) ((__sk)->protinfo.pf_ring)
+#endif
+
+/*
+ int dev_queue_xmit(struct sk_buff *skb)
+ skb->dev;
+ struct net_device *dev_get_by_name(const char *name)
+*/
+
+/* ********************************** */
+
+static void ring_sock_destruct(struct sock *sk) {
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+ skb_queue_purge(&sk->sk_receive_queue);
+
+ if (!sock_flag(sk, SOCK_DEAD)) {
+#if defined(RING_DEBUG)
+ printk("Attempt to release alive ring socket: %p\n", sk);
+#endif
+ return;
+ }
+
+ BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
+ BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
+#else
+
+ BUG_TRAP(atomic_read(&sk->rmem_alloc)==0);
+ BUG_TRAP(atomic_read(&sk->wmem_alloc)==0);
+
+ if (!sk->dead) {
+#if defined(RING_DEBUG)
+ printk("Attempt to release alive ring socket: %p\n", sk);
+#endif
+ return;
+ }
+#endif
+
+ kfree(ring_sk(sk));
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0))
+ MOD_DEC_USE_COUNT;
+#endif
+}
+
+/* ********************************** */
+/*
+ * ring_insert()
+ *
+ * store the sk in a new element and add it
+ * to the head of the list.
+ */
+static inline void ring_insert(struct sock *sk) {
+ struct ring_element *next;
+
+#if defined(RING_DEBUG)
+ printk("RING: ring_insert()\n");
+#endif
+
+ next = kmalloc(sizeof(struct ring_element), GFP_ATOMIC);
+ if(next != NULL) {
+ next->sk = sk;
+ write_lock_irq(&ring_mgmt_lock);
+ list_add(&next->list, &ring_table);
+ write_unlock_irq(&ring_mgmt_lock);
+ } else {
+ if (net_ratelimit())
+ printk("RING: could not kmalloc slot!!\n");
+ }
+}
+
+/* ********************************** */
+/*
+ * ring_remove()
+ *
+ * For each of the elements in the list:
+ * - check if this is the element we want to delete
+ * - if it is, remove it from the list, and free it.
+ *
+ * stop when we find the one we're looking for (break),
+ * or when we reach the end of the list.
+ */
+static inline void ring_remove(struct sock *sk) {
+ struct list_head *ptr;
+ struct ring_element *entry;
+
+
+ for(ptr = ring_table.next; ptr != &ring_table; ptr = ptr->next) {
+ entry = list_entry(ptr, struct ring_element, list);
+
+ if(entry->sk == sk) {
+ write_lock_irq(&ring_mgmt_lock);
+ list_del(ptr);
+ kfree(ptr);
+ write_unlock_irq(&ring_mgmt_lock);
+ break;
+ }
+ }
+
+}
+
+/* ********************************** */
+
+static u_int32_t num_queued_pkts(struct ring_opt *pfr) {
+
+ if(pfr->ring_slots != NULL) {
+
+ u_int32_t tot_insert = pfr->slots_info->insert_idx,
+#if defined(RING_DEBUG)
+ tot_read = pfr->slots_info->tot_read, tot_pkts;
+#else
+ tot_read = pfr->slots_info->tot_read;
+#endif
+
+ if(tot_insert >= tot_read) {
+#if defined(RING_DEBUG)
+ tot_pkts = tot_insert-tot_read;
+#endif
+ return(tot_insert-tot_read);
+ } else {
+#if defined(RING_DEBUG)
+ tot_pkts = ((u_int32_t)-1)+tot_insert-tot_read;
+#endif
+ return(((u_int32_t)-1)+tot_insert-tot_read);
+ }
+
+#if defined(RING_DEBUG)
+ printk("-> num_queued_pkts=%d [tot_insert=%d][tot_read=%d]\n",
+ tot_pkts, tot_insert, tot_read);
+#endif
+
+ } else
+ return(0);
+}
+
+/* ********************************** */
+
+static inline FlowSlot* get_insert_slot(struct ring_opt *pfr) {
+#if defined(RING_DEBUG)
+ printk("get_insert_slot(%d)\n", pfr->slots_info->insert_idx);
+#endif
+
+ if(pfr->ring_slots != NULL) {
+ FlowSlot *slot = (FlowSlot*)&(pfr->ring_slots[pfr->slots_info->insert_idx
+ *pfr->slots_info->slot_len]);
+ return(slot);
+ } else
+ return(NULL);
+}
+
+/* ********************************** */
+
+static inline FlowSlot* get_remove_slot(struct ring_opt *pfr) {
+#if defined(RING_DEBUG)
+ printk("get_remove_slot(%d)\n", pfr->slots_info->remove_idx);
+#endif
+
+ if(pfr->ring_slots != NULL)
+ return((FlowSlot*)&(pfr->ring_slots[pfr->slots_info->remove_idx*
+ pfr->slots_info->slot_len]));
+ else
+ return(NULL);
+}
+
+/* ********************************** */
+
+static void add_skb_to_ring(struct sk_buff *skb,
+ struct ring_opt *pfr,
+ u_char recv_packet,
+ u_char real_skb /* 1=skb 0=faked skb */) {
+ FlowSlot *theSlot;
+ int idx, displ;
+
+ if(recv_packet) {
+ /* Hack for identifying a packet received by the e1000 */
+ if(real_skb) {
+ displ = SKB_DISPLACEMENT;
+ } else
+ displ = 0; /* Received by the e1000 wrapper */
+ } else
+ displ = 0;
+
+ write_lock(&pfr->ring_index_lock);
+ pfr->slots_info->tot_pkts++;
+ write_unlock(&pfr->ring_index_lock);
+
+ /* BPF Filtering (from af_packet.c) */
+ if(pfr->bpfFilter != NULL) {
+ unsigned res = 1, len;
+
+ len = skb->len-skb->data_len;
+
+ write_lock(&pfr->ring_index_lock);
+ skb->data -= displ;
+ res = sk_run_filter(skb, pfr->bpfFilter->insns, pfr->bpfFilter->len);
+ skb->data += displ;
+ write_unlock(&pfr->ring_index_lock);
+
+ if(res == 0) {
+ /* Filter failed */
+
+#if defined(RING_DEBUG)
+ printk("add_skb_to_ring(skb): Filter failed [len=%d][tot=%llu]"
+ "[insertIdx=%d][pkt_type=%d][cloned=%d]\n",
+ (int)skb->len, pfr->slots_info->tot_pkts,
+ pfr->slots_info->insert_idx,
+ skb->pkt_type, skb->cloned);
+#endif
+
+ return;
+ }
+ }
+
+ /* ************************** */
+
+ if(pfr->sample_rate > 1) {
+ if(pfr->pktToSample == 0) {
+ write_lock(&pfr->ring_index_lock);
+ pfr->pktToSample = pfr->sample_rate;
+ write_unlock(&pfr->ring_index_lock);
+ } else {
+ write_lock(&pfr->ring_index_lock);
+ pfr->pktToSample--;
+ write_unlock(&pfr->ring_index_lock);
+
+#if defined(RING_DEBUG)
+ printk("add_skb_to_ring(skb): sampled packet [len=%d]"
+ "[tot=%llu][insertIdx=%d][pkt_type=%d][cloned=%d]\n",
+ (int)skb->len, pfr->slots_info->tot_pkts,
+ pfr->slots_info->insert_idx,
+ skb->pkt_type, skb->cloned);
+#endif
+ return;
+ }
+ }
+
+ /* ************************************* */
+
+ if((pfr->reflector_dev != NULL)
+ && (!netif_queue_stopped(pfr->reflector_dev))) {
+ int cpu = smp_processor_id();
+
+ /* increase reference counter so that this skb is not freed */
+ atomic_inc(&skb->users);
+
+ skb->data -= displ;
+
+ /* send it */
+ if (pfr->reflector_dev->xmit_lock_owner != cpu) {
+ spin_lock_bh(&pfr->reflector_dev->xmit_lock);
+ pfr->reflector_dev->xmit_lock_owner = cpu;
+ spin_unlock_bh(&pfr->reflector_dev->xmit_lock);
+
+ if (pfr->reflector_dev->hard_start_xmit(skb,
+ pfr->reflector_dev) == 0) {
+ spin_lock_bh(&pfr->reflector_dev->xmit_lock);
+ pfr->reflector_dev->xmit_lock_owner = -1;
+ skb->data += displ;
+ spin_unlock_bh(&pfr->reflector_dev->xmit_lock);
+#if defined(RING_DEBUG)
+ printk("++ hard_start_xmit succeeded\n");
+#endif
+ return; /* OK */
+ }
+
+ spin_lock_bh(&pfr->reflector_dev->xmit_lock);
+ pfr->reflector_dev->xmit_lock_owner = -1;
+ spin_unlock_bh(&pfr->reflector_dev->xmit_lock);
+ }
+
+#if defined(RING_DEBUG)
+ printk("++ hard_start_xmit failed\n");
+#endif
+ skb->data += displ;
+ return; /* -ENETDOWN */
+ }
+
+ /* ************************************* */
+
+#if defined(RING_DEBUG)
+ printk("add_skb_to_ring(skb) [len=%d][tot=%llu][insertIdx=%d]"
+ "[pkt_type=%d][cloned=%d]\n",
+ (int)skb->len, pfr->slots_info->tot_pkts,
+ pfr->slots_info->insert_idx,
+ skb->pkt_type, skb->cloned);
+#endif
+
+ idx = pfr->slots_info->insert_idx;
+ theSlot = get_insert_slot(pfr);
+
+ if((theSlot != NULL) && (theSlot->slot_state == 0)) {
+ struct pcap_pkthdr *hdr;
+ unsigned int bucketSpace;
+ char *bucket;
+
+ /* Update Index */
+ idx++;
+
+ if(idx == pfr->slots_info->tot_slots) {
+ write_lock(&pfr->ring_index_lock);
+ pfr->slots_info->insert_idx = 0;
+ write_unlock(&pfr->ring_index_lock);
+ } else {
+ write_lock(&pfr->ring_index_lock);
+ pfr->slots_info->insert_idx = idx;
+ write_unlock(&pfr->ring_index_lock);
+ }
+
+ bucketSpace = pfr->slots_info->slot_len
+#ifdef RING_MAGIC
+ - sizeof(u_char)
+#endif
+ - sizeof(u_char) /* flowSlot.slot_state */
+ - sizeof(struct pcap_pkthdr)
+ - 1 /* 10 */ /* safe boundary */;
+
+ bucket = &theSlot->bucket;
+ hdr = (struct pcap_pkthdr*)bucket;
+
+ if(skb->stamp.tv_sec == 0) do_gettimeofday(&skb->stamp);
+
+ hdr->ts.tv_sec = skb->stamp.tv_sec, hdr->ts.tv_usec = skb->stamp.tv_usec;
+ hdr->caplen = skb->len+displ;
+
+ if(hdr->caplen > bucketSpace)
+ hdr->caplen = bucketSpace;
+
+ hdr->len = skb->len+displ;
+ memcpy(&bucket[sizeof(struct pcap_pkthdr)],
+ skb->data-displ, hdr->caplen);
+
+#if defined(RING_DEBUG)
+ {
+ static unsigned int lastLoss = 0;
+
+ if(pfr->slots_info->tot_lost
+ && (lastLoss != pfr->slots_info->tot_lost)) {
+ printk("add_skb_to_ring(%d): [bucketSpace=%d]"
+ "[hdr.caplen=%d][skb->len=%d]"
+ "[pcap_pkthdr=%d][removeIdx=%d]"
+ "[loss=%lu][page=%u][slot=%u]\n",
+ idx-1, bucketSpace, hdr->caplen, skb->len,
+ sizeof(struct pcap_pkthdr),
+ pfr->slots_info->remove_idx,
+ (long unsigned int)pfr->slots_info->tot_lost,
+ pfr->insert_page_id, pfr->insert_slot_id);
+
+ lastLoss = pfr->slots_info->tot_lost;
+ }
+ }
+#endif
+
+ write_lock(&pfr->ring_index_lock);
+ pfr->slots_info->tot_insert++;
+ theSlot->slot_state = 1;
+ write_unlock(&pfr->ring_index_lock);
+ } else {
+ write_lock(&pfr->ring_index_lock);
+ pfr->slots_info->tot_lost++;
+ write_unlock(&pfr->ring_index_lock);
+
+#if defined(RING_DEBUG)
+ printk("add_skb_to_ring(skb): packet lost [loss=%lu]"
+ "[removeIdx=%u][insertIdx=%u]\n",
+ (long unsigned int)pfr->slots_info->tot_lost,
+ pfr->slots_info->remove_idx, pfr->slots_info->insert_idx);
+#endif
+ }
+
+ /* wakeup in case of poll() */
+ if(waitqueue_active(&pfr->ring_slots_waitqueue))
+ wake_up_interruptible(&pfr->ring_slots_waitqueue);
+}
+
+/* ********************************** */
+
+static u_int hash_skb(struct ring_cluster *cluster_ptr,
+ struct sk_buff *skb, u_char recv_packet) {
+ u_int idx;
+ int displ;
+ struct iphdr *ip;
+
+ if(cluster_ptr->hashing_mode == cluster_round_robin) {
+ idx = cluster_ptr->hashing_id++;
+ } else {
+ /* Per-flow clustering */
+ if(skb->len > sizeof(struct iphdr)+sizeof(struct tcphdr)) {
+ if(recv_packet)
+ displ = 0;
+ else
+ displ = SKB_DISPLACEMENT;
+
+ /*
+ skb->data+displ
+
+ Always points to to the IP part of the packet
+ */
+
+ ip = (struct iphdr*)(skb->data+displ);
+
+ idx = ip->saddr+ip->daddr+ip->protocol;
+
+ if(ip->protocol == IPPROTO_TCP) {
+ struct tcphdr *tcp = (struct tcphdr*)(skb->data+displ
+ +sizeof(struct iphdr));
+ idx += tcp->source+tcp->dest;
+ } else if(ip->protocol == IPPROTO_UDP) {
+ struct udphdr *udp = (struct udphdr*)(skb->data+displ
+ +sizeof(struct iphdr));
+ idx += udp->source+udp->dest;
+ }
+ } else
+ idx = skb->len;
+ }
+
+ return(idx % cluster_ptr->num_cluster_elements);
+}
+
+/* ********************************** */
+
+static int skb_ring_handler(struct sk_buff *skb,
+ u_char recv_packet,
+ u_char real_skb /* 1=skb 0=faked skb */) {
+ struct sock *skElement;
+ int rc = 0;
+ struct list_head *ptr;
+ struct ring_cluster *cluster_ptr;
+
+ if((!skb) /* Invalid skb */
+ || ((!enable_tx_capture) && (!recv_packet))) {
+ /*
+ An outgoing packet is about to be sent out
+ but we decided not to handle transmitted
+ packets.
+ */
+ return(0);
+ }
+
+#if defined(RING_DEBUG)
+ if(0) {
+ printk("skb_ring_handler() [len=%d][dev=%s]\n", skb->len,
+ skb->dev->name == NULL ? "<NULL>" : skb->dev->name);
+ }
+#endif
+
+ /* [1] Check unclustered sockets */
+ for (ptr = ring_table.next; ptr != &ring_table; ptr = ptr->next) {
+ struct ring_opt *pfr;
+ struct ring_element *entry;
+
+ entry = list_entry(ptr, struct ring_element, list);
+
+ read_lock(&ring_mgmt_lock);
+ skElement = entry->sk;
+ pfr = ring_sk(skElement);
+ read_unlock(&ring_mgmt_lock);
+
+ if((pfr != NULL)
+ && (pfr->cluster_id == 0 /* No cluster */)
+ && (pfr->ring_slots != NULL)
+ && (pfr->ring_netdev == skb->dev)) {
+ /* We've found the ring where the packet can be stored */
+ read_lock(&ring_mgmt_lock);
+ add_skb_to_ring(skb, pfr, recv_packet, real_skb);
+ read_unlock(&ring_mgmt_lock);
+
+ rc = 1; /* Ring found: we've done our job */
+ }
+ }
+
+ /* [2] Check socket clusters */
+ cluster_ptr = ring_cluster_list;
+
+ while(cluster_ptr != NULL) {
+ struct ring_opt *pfr;
+
+ if(cluster_ptr->num_cluster_elements > 0) {
+ u_int skb_hash = hash_skb(cluster_ptr, skb, recv_packet);
+
+ read_lock(&ring_mgmt_lock);
+ skElement = cluster_ptr->sk[skb_hash];
+ read_unlock(&ring_mgmt_lock);
+
+ if(skElement != NULL) {
+ pfr = ring_sk(skElement);
+
+ if((pfr != NULL)
+ && (pfr->ring_slots != NULL)
+ && (pfr->ring_netdev == skb->dev)) {
+ /* We've found the ring where the packet can be stored */
+ read_lock(&ring_mgmt_lock);
+ add_skb_to_ring(skb, pfr, recv_packet, real_skb);
+ read_unlock(&ring_mgmt_lock);
+
+ rc = 1; /* Ring found: we've done our job */
+ }
+ }
+ }
+
+ cluster_ptr = cluster_ptr->next;
+ }
+
+ if(transparent_mode) rc = 0;
+
+ if((rc != 0) && real_skb)
+ dev_kfree_skb(skb); /* Free the skb */
+
+ return(rc); /* 0 = packet not handled */
+}
+
+/* ********************************** */
+
+struct sk_buff skb;
+
+static int buffer_ring_handler(struct net_device *dev,
+ char *data, int len) {
+
+#if defined(RING_DEBUG)
+ printk("buffer_ring_handler: [dev=%s][len=%d]\n",
+ dev->name == NULL ? "<NULL>" : dev->name, len);
+#endif
+
+ skb.dev = dev, skb.len = len, skb.data = data,
+ skb.data_len = len, skb.stamp.tv_sec = 0; /* Calculate the time */
+
+ skb_ring_handler(&skb, 1, 0 /* fake skb */);
+
+ return(0);
+}
+
+/* ********************************** */
+
+static int ring_create(struct socket *sock, int protocol) {
+ struct sock *sk;
+ struct ring_opt *pfr;
+ int err;
+
+#if defined(RING_DEBUG)
+ printk("RING: ring_create()\n");
+#endif
+
+ /* Are you root, superuser or so ? */
+ if(!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if(sock->type != SOCK_RAW)
+ return -ESOCKTNOSUPPORT;
+
+ if(protocol != htons(ETH_P_ALL))
+ return -EPROTONOSUPPORT;
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0))
+ MOD_INC_USE_COUNT;
+#endif
+
+ err = -ENOMEM;
+
+ // BD: -- broke this out to keep it more simple and clear as to what the
+ // options are.
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,11))
+ sk = sk_alloc(PF_RING, GFP_KERNEL, 1, NULL);
+#endif
+#endif
+
+ // BD: API changed in 2.6.12, ref:
+ // http://svn.clkao.org/svnweb/linux/revision/?rev=28201
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,11))
+ sk = sk_alloc(PF_RING, GFP_ATOMIC, &ring_proto, 1);
+#endif
+
+ if (sk == NULL)
+ goto out;
+
+ sock->ops = &ring_ops;
+ sock_init_data(sock, sk);
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,11))
+ sk_set_owner(sk, THIS_MODULE);
+#endif
+#endif
+
+ err = -ENOMEM;
+ ring_sk(sk) = ring_sk_datatype(kmalloc(sizeof(*pfr), GFP_KERNEL));
+
+ if (!(pfr = ring_sk(sk))) {
+ sk_free(sk);
+ goto out;
+ }
+ memset(pfr, 0, sizeof(*pfr));
+ init_waitqueue_head(&pfr->ring_slots_waitqueue);
+ pfr->ring_index_lock = RW_LOCK_UNLOCKED;
+ atomic_set(&pfr->num_ring_slots_waiters, 0);
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+ sk->sk_family = PF_RING;
+ sk->sk_destruct = ring_sock_destruct;
+#else
+ sk->family = PF_RING;
+ sk->destruct = ring_sock_destruct;
+ sk->num = protocol;
+#endif
+
+ ring_insert(sk);
+
+#if defined(RING_DEBUG)
+ printk("RING: ring_create() - created\n");
+#endif
+
+ return(0);
+ out:
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0))
+ MOD_DEC_USE_COUNT;
+#endif
+ return err;
+}
+
+/* *********************************************** */
+
+static int ring_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct ring_opt *pfr = ring_sk(sk);
+
+ if(!sk)
+ return 0;
+
+#if defined(RING_DEBUG)
+ printk("RING: called ring_release\n");
+#endif
+
+#if defined(RING_DEBUG)
+ printk("RING: ring_release entered\n");
+#endif
+
+ ring_remove(sk);
+
+ sock_orphan(sk);
+ sock->sk = NULL;
+
+ /* Free the ring buffer */
+ if(pfr->ring_memory) {
+ struct page *page, *page_end;
+
+ page_end = virt_to_page(pfr->ring_memory + (PAGE_SIZE << pfr->order) - 1);
+ for(page = virt_to_page(pfr->ring_memory); page <= page_end; page++)
+ ClearPageReserved(page);
+
+ free_pages(pfr->ring_memory, pfr->order);
+ }
+
+ kfree(pfr);
+ ring_sk(sk) = NULL;
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+ skb_queue_purge(&sk->sk_write_queue);
+#endif
+ sock_put(sk);
+
+#if defined(RING_DEBUG)
+ printk("RING: ring_release leaving\n");
+#endif
+
+ return 0;
+}
+
+/* ********************************** */
+/*
+ * We create a ring for this socket and bind it to the specified device
+ */
+static int packet_ring_bind(struct sock *sk, struct net_device *dev)
+{
+ u_int the_slot_len;
+ u_int32_t tot_mem;
+ struct ring_opt *pfr = ring_sk(sk);
+ struct page *page, *page_end;
+
+ if(!dev) return(-1);
+
+#if defined(RING_DEBUG)
+ printk("RING: packet_ring_bind(%s) called\n", dev->name);
+#endif
+
+ /* **********************************************
+
+ *************************************
+ * *
+ * FlowSlotInfo *
+ * *
+ ************************************* <-+
+ * FlowSlot * |
+ ************************************* |
+ * FlowSlot * |
+ ************************************* +- num_slots
+ * FlowSlot * |
+ ************************************* |
+ * FlowSlot * |
+ ************************************* <-+
+
+ ********************************************** */
+
+ the_slot_len = sizeof(u_char) /* flowSlot.slot_state */
+ + sizeof(u_short) /* flowSlot.slot_len */
+ + bucket_len /* flowSlot.bucket */;
+
+ tot_mem = sizeof(FlowSlotInfo) + num_slots*the_slot_len;
+
+ /*
+ Calculate the value of the order parameter used later.
+ See http://www.linuxjournal.com/article.php?sid=1133
+ */
+ for(pfr->order = 0;(PAGE_SIZE << pfr->order) < tot_mem; pfr->order++) ;
+
+ /*
+ We now try to allocate the memory as required. If we fail
+ we try to allocate a smaller amount or memory (hence a
+ smaller ring).
+ */
+ while((pfr->ring_memory = __get_free_pages(GFP_ATOMIC, pfr->order)) == 0)
+ if(pfr->order-- == 0)
+ break;
+
+ if(pfr->order == 0) {
+#if defined(RING_DEBUG)
+ printk("ERROR: not enough memory\n");
+#endif
+ return(-1);
+ } else {
+#if defined(RING_DEBUG)
+ printk("RING: succesfully allocated %lu KB [tot_mem=%d][order=%ld]\n",
+ PAGE_SIZE >> (10 - pfr->order), tot_mem, pfr->order);
+#endif
+ }
+
+ tot_mem = PAGE_SIZE << pfr->order;
+ memset((char*)pfr->ring_memory, 0, tot_mem);
+
+ /* Now we need to reserve the pages */
+ page_end = virt_to_page(pfr->ring_memory + (PAGE_SIZE << pfr->order) - 1);
+ for(page = virt_to_page(pfr->ring_memory); page <= page_end; page++)
+ SetPageReserved(page);
+
+ pfr->slots_info = (FlowSlotInfo*)pfr->ring_memory;
+ pfr->ring_slots = (char*)(pfr->ring_memory+sizeof(FlowSlotInfo));
+
+ pfr->slots_info->version = RING_FLOWSLOT_VERSION;
+ pfr->slots_info->slot_len = the_slot_len;
+ pfr->slots_info->tot_slots = (tot_mem-sizeof(FlowSlotInfo))/the_slot_len;
+ pfr->slots_info->tot_mem = tot_mem;
+ pfr->slots_info->sample_rate = sample_rate;
+
+#if defined(RING_DEBUG)
+ printk("RING: allocated %d slots [slot_len=%d][tot_mem=%u]\n",
+ pfr->slots_info->tot_slots, pfr->slots_info->slot_len,
+ pfr->slots_info->tot_mem);
+#endif
+
+#ifdef RING_MAGIC
+ {
+ int i;
+
+ for(i=0; i<pfr->slots_info->tot_slots; i++) {
+ unsigned long idx = i*pfr->slots_info->slot_len;
+ FlowSlot *slot = (FlowSlot*)&pfr->ring_slots[idx];
+ slot->magic = RING_MAGIC_VALUE; slot->slot_state = 0;
+ }
+ }
+#endif
+
+ pfr->insert_page_id = 1, pfr->insert_slot_id = 0;
+
+ /*
+ IMPORTANT
+ Leave this statement here as last one. In fact when
+ the ring_netdev != NULL the socket is ready to be used.
+ */
+ pfr->ring_netdev = dev;
+
+ return(0);
+}
+
+/* ************************************* */
+
+/* Bind to a device */
+static int ring_bind(struct socket *sock,
+ struct sockaddr *sa, int addr_len)
+{
+ struct sock *sk=sock->sk;
+ struct net_device *dev = NULL;
+
+#if defined(RING_DEBUG)
+ printk("RING: ring_bind() called\n");
+#endif
+
+ /*
+ * Check legality
+ */
+ if (addr_len != sizeof(struct sockaddr))
+ return -EINVAL;
+ if (sa->sa_family != PF_RING)
+ return -EINVAL;
+
+ /* Safety check: add trailing zero if missing */
+ sa->sa_data[sizeof(sa->sa_data)-1] = '\0';
+
+#if defined(RING_DEBUG)
+ printk("RING: searching device %s\n", sa->sa_data);
+#endif
+
+ if((dev = __dev_get_by_name(sa->sa_data)) == NULL) {
+#if defined(RING_DEBUG)
+ printk("RING: search failed\n");
+#endif
+ return(-EINVAL);
+ } else
+ return(packet_ring_bind(sk, dev));
+}
+
+/* ************************************* */
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+
+volatile void* virt_to_kseg(volatile void* address) {
+ pte_t *pte;
+ pud_t *pud;
+ unsigned long addr = (unsigned long)address;
+
+ pud = pud_offset(pgd_offset_k((unsigned long) address),
+ (unsigned long) address);
+
+ /*
+ High-memory support courtesy of
+ Brad Doctor <bdoctor@ps-ax.com>
+ */
+#if defined(CONFIG_X86_PAE) && (!defined(CONFIG_NOHIGHMEM))
+ pte = pte_offset_map(pmd_offset(pud, addr), addr);
+#else
+ pte = pmd_offset_map(pud, addr);
+#endif
+
+ return((volatile void*)pte_page(*pte));
+}
+
+#else /* 2.4 */
+
+/* http://www.scs.ch/~frey/linux/memorymap.html */
+volatile void *virt_to_kseg(volatile void *address)
+{
+ pgd_t *pgd; pmd_t *pmd; pte_t *ptep, pte;
+ unsigned long va, ret = 0UL;
+
+ va=VMALLOC_VMADDR((unsigned long)address);
+
+ /* get the page directory. Use the kernel memory map. */
+ pgd = pgd_offset_k(va);
+
+ /* check whether we found an entry */
+ if (!pgd_none(*pgd))
+ {
+ /* get the page middle directory */
+ pmd = pmd_offset(pgd, va);
+ /* check whether we found an entry */
+ if (!pmd_none(*pmd))
+ {
+ /* get a pointer to the page table entry */
+ ptep = pte_offset(pmd, va);
+ pte = *ptep;
+ /* check for a valid page */
+ if (pte_present(pte))
+ {
+ /* get the address the page is refering to */
+ ret = (unsigned long)page_address(pte_page(pte));
+ /* add the offset within the page to the page address */
+ ret |= (va & (PAGE_SIZE -1));
+ }
+ }
+ }
+ return((volatile void *)ret);
+}
+#endif
+
+/* ************************************* */
+
+static int ring_mmap(struct file *file,
+ struct socket *sock,
+ struct vm_area_struct *vma)
+{
+ struct sock *sk = sock->sk;
+ struct ring_opt *pfr = ring_sk(sk);
+ unsigned long size, start;
+ u_int pagesToMap;
+ char *ptr;
+
+#if defined(RING_DEBUG)
+ printk("RING: ring_mmap() called\n");
+#endif
+
+ if(pfr->ring_memory == 0) {
+#if defined(RING_DEBUG)
+ printk("RING: ring_mmap() failed: mapping area to an unbound socket\n");
+#endif
+ return -EINVAL;
+ }
+
+ size = (unsigned long)(vma->vm_end-vma->vm_start);
+
+ if(size % PAGE_SIZE) {
+#if defined(RING_DEBUG)
+ printk("RING: ring_mmap() failed: len is not multiple of PAGE_SIZE\n");
+#endif
+ return(-EINVAL);
+ }
+
+ /* if userspace tries to mmap beyond end of our buffer, fail */
+ if(size > pfr->slots_info->tot_mem) {
+#if defined(RING_DEBUG)
+ printk("proc_mmap() failed: area too large [%ld > %d]\n", size, pfr->slots_info->tot_mem);
+#endif
+ return(-EINVAL);
+ }
+
+ pagesToMap = size/PAGE_SIZE;
+
+#if defined(RING_DEBUG)
+ printk("RING: ring_mmap() called. %d pages to map\n", pagesToMap);
+#endif
+
+#if defined(RING_DEBUG)
+ printk("RING: mmap [slot_len=%d][tot_slots=%d] for ring on device %s\n",
+ pfr->slots_info->slot_len, pfr->slots_info->tot_slots,
+ pfr->ring_netdev->name);
+#endif
+
+ /* we do not want to have this area swapped out, lock it */
+ vma->vm_flags |= VM_LOCKED;
+ start = vma->vm_start;
+
+ /* Ring slots start from page 1 (page 0 is reserved for FlowSlotInfo) */
+ ptr = (char*)(start+PAGE_SIZE);
+
+ if(remap_page_range(
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+ vma,
+#endif
+ start,
+ __pa(pfr->ring_memory),
+ PAGE_SIZE*pagesToMap, vma->vm_page_prot)) {
+#if defined(RING_DEBUG)
+ printk("remap_page_range() failed\n");
+#endif
+ return(-EAGAIN);
+ }
+
+#if defined(RING_DEBUG)
+ printk("proc_mmap(pagesToMap=%d): success.\n", pagesToMap);
+#endif
+
+ return 0;
+}
+
+/* ************************************* */
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+static int ring_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *msg, size_t len, int flags)
+#else
+ static int ring_recvmsg(struct socket *sock, struct msghdr *msg, int len,
+ int flags, struct scm_cookie *scm)
+#endif
+{
+ FlowSlot* slot;
+ struct ring_opt *pfr = ring_sk(sock->sk);
+ u_int32_t queued_pkts, num_loops = 0;
+
+#if defined(RING_DEBUG)
+ printk("ring_recvmsg called\n");
+#endif
+
+ slot = get_remove_slot(pfr);
+
+ while((queued_pkts = num_queued_pkts(pfr)) < MIN_QUEUED_PKTS) {
+ wait_event_interruptible(pfr->ring_slots_waitqueue, 1);
+
+#if defined(RING_DEBUG)
+ printk("-> ring_recvmsg returning %d [queued_pkts=%d][num_loops=%d]\n",
+ slot->slot_state, queued_pkts, num_loops);
+#endif
+
+ if(queued_pkts > 0) {
+ if(num_loops++ > MAX_QUEUE_LOOPS)
+ break;
+ }
+ }
+
+#if defined(RING_DEBUG)
+ if(slot != NULL)
+ printk("ring_recvmsg is returning [queued_pkts=%d][num_loops=%d]\n",
+ queued_pkts, num_loops);
+#endif
+
+ return(queued_pkts);
+}
+
+/* ************************************* */
+
+unsigned int ring_poll(struct file * file,
+ struct socket *sock, poll_table *wait)
+{
+ FlowSlot* slot;
+ struct ring_opt *pfr = ring_sk(sock->sk);
+
+#if defined(RING_DEBUG)
+ printk("poll called\n");
+#endif
+
+ slot = get_remove_slot(pfr);
+
+ if((slot != NULL) && (slot->slot_state == 0))
+ poll_wait(file, &pfr->ring_slots_waitqueue, wait);
+
+#if defined(RING_DEBUG)
+ printk("poll returning %d\n", slot->slot_state);
+#endif
+
+ if((slot != NULL) && (slot->slot_state == 1))
+ return(POLLIN | POLLRDNORM);
+ else
+ return(0);
+}
+
+/* ************************************* */
+
+int add_to_cluster_list(struct ring_cluster *el,
+ struct sock *sock) {
+
+ if(el->num_cluster_elements == CLUSTER_LEN)
+ return(-1); /* Cluster full */
+
+ ring_sk_datatype(ring_sk(sock))->cluster_id = el->cluster_id;
+ el->sk[el->num_cluster_elements] = sock;
+ el->num_cluster_elements++;
+ return(0);
+}
+
+/* ************************************* */
+
+int remove_from_cluster_list(struct ring_cluster *el,
+ struct sock *sock) {
+ int i, j;
+
+ for(i=0; i<CLUSTER_LEN; i++)
+ if(el->sk[i] == sock) {
+ el->num_cluster_elements--;
+
+ if(el->num_cluster_elements > 0) {
+ /* The cluster contains other elements */
+ for(j=i; j<CLUSTER_LEN-1; j++)
+ el->sk[j] = el->sk[j+1];
+
+ el->sk[CLUSTER_LEN-1] = NULL;
+ } else {
+ /* Empty cluster */
+ memset(el->sk, 0, sizeof(el->sk));
+ }
+
+ return(0);
+ }
+
+ return(-1); /* Not found */
+}
+
+/* ************************************* */
+
+static int remove_from_cluster(struct sock *sock,
+ struct ring_opt *pfr)
+{
+ struct ring_cluster *el;
+
+#if defined(RING_DEBUG)
+ printk("--> remove_from_cluster(%d)\n", pfr->cluster_id);
+#endif
+
+ if(pfr->cluster_id == 0 /* 0 = No Cluster */)
+ return(0); /* Noting to do */
+
+ el = ring_cluster_list;
+
+ while(el != NULL) {
+ if(el->cluster_id == pfr->cluster_id) {
+ return(remove_from_cluster_list(el, sock));
+ } else
+ el = el->next;
+ }
+
+ return(-EINVAL); /* Not found */
+}
+
+/* ************************************* */
+
+static int add_to_cluster(struct sock *sock,
+ struct ring_opt *pfr,
+ u_short cluster_id)
+{
+ struct ring_cluster *el;
+
+#ifndef RING_DEBUG
+ printk("--> add_to_cluster(%d)\n", cluster_id);
+#endif
+
+ if(cluster_id == 0 /* 0 = No Cluster */) return(-EINVAL);
+
+ if(pfr->cluster_id != 0)
+ remove_from_cluster(sock, pfr);
+
+ el = ring_cluster_list;
+
+ while(el != NULL) {
+ if(el->cluster_id == cluster_id) {
+ return(add_to_cluster_list(el, sock));
+ } else
+ el = el->next;
+ }
+
+ /* There's no existing cluster. We need to create one */
+ if((el = kmalloc(sizeof(struct ring_cluster), GFP_KERNEL)) == NULL)
+ return(-ENOMEM);
+
+ el->cluster_id = cluster_id;
+ el->num_cluster_elements = 1;
+ el->hashing_mode = cluster_per_flow; /* Default */
+ el->hashing_id = 0;
+
+ memset(el->sk, 0, sizeof(el->sk));
+ el->sk[0] = sock;
+ el->next = ring_cluster_list;
+ ring_cluster_list = el;
+ pfr->cluster_id = cluster_id;
+
+ return(0); /* 0 = OK */
+}
+
+/* ************************************* */
+
+/* Code taken/inspired from core/sock.c */
+static int ring_setsockopt(struct socket *sock,
+ int level, int optname,
+ char *optval, int optlen)
+{
+ struct ring_opt *pfr = ring_sk(sock->sk);
+ int val, found, ret = 0;
+ u_int cluster_id;
+ char devName[8];
+
+ if((optlen<sizeof(int)) || (pfr == NULL))
+ return(-EINVAL);
+
+ if (get_user(val, (int *)optval))
+ return -EFAULT;
+
+ found = 1;
+
+ switch(optname)
+ {
+ case SO_ATTACH_FILTER:
+ ret = -EINVAL;
+ if (optlen == sizeof(struct sock_fprog)) {
+ unsigned int fsize;
+ struct sock_fprog fprog;
+ struct sk_filter *filter;
+
+ ret = -EFAULT;
+
+ /*
+ NOTE
+
+ Do not call copy_from_user within a held
+ splinlock (e.g. ring_mgmt_lock) as this caused
+ problems when certain debugging was enabled under
+ 2.6.5 -- including hard lockups of the machine.
+ */
+ if(copy_from_user(&fprog, optval, sizeof(fprog)))
+ break;
+
+ fsize = sizeof(struct sock_filter) * fprog.len;
+ filter = kmalloc(fsize, GFP_KERNEL);
+
+ if(filter == NULL) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ if(copy_from_user(filter->insns, fprog.filter, fsize))
+ break;
+
+ filter->len = fprog.len;
+
+ if(sk_chk_filter(filter->insns, filter->len) != 0) {
+ /* Bad filter specified */
+ kfree(filter);
+ pfr->bpfFilter = NULL;
+ break;
+ }
+
+ /* get the lock, set the filter, release the lock */
+ write_lock(&ring_mgmt_lock);
+ pfr->bpfFilter = filter;
+ write_unlock(&ring_mgmt_lock);
+ }
+ ret = 0;
+ break;
+
+ case SO_DETACH_FILTER:
+ write_lock(&ring_mgmt_lock);
+ found = 1;
+ if(pfr->bpfFilter != NULL) {
+ kfree(pfr->bpfFilter);
+ pfr->bpfFilter = NULL;
+ write_unlock(&ring_mgmt_lock);
+ break;
+ }
+ ret = -ENONET;
+ break;
+
+ case SO_ADD_TO_CLUSTER:
+ if (optlen!=sizeof(val))
+ return -EINVAL;
+
+ if (copy_from_user(&cluster_id, optval, sizeof(cluster_id)))
+ return -EFAULT;
+
+ write_lock(&ring_mgmt_lock);
+ ret = add_to_cluster(sock->sk, pfr, cluster_id);
+ write_unlock(&ring_mgmt_lock);
+ break;
+
+ case SO_REMOVE_FROM_CLUSTER:
+ write_lock(&ring_mgmt_lock);
+ ret = remove_from_cluster(sock->sk, pfr);
+ write_unlock(&ring_mgmt_lock);
+ break;
+
+ case SO_SET_REFLECTOR:
+ if(optlen >= (sizeof(devName)-1))
+ return -EINVAL;
+
+ if(optlen > 0) {
+ if(copy_from_user(devName, optval, optlen))
+ return -EFAULT;
+ }
+
+ devName[optlen] = '\0';
+
+#if defined(RING_DEBUG)
+ printk("+++ SO_SET_REFLECTOR(%s)\n", devName);
+#endif
+
+ write_lock(&ring_mgmt_lock);
+ pfr->reflector_dev = dev_get_by_name(devName);
+ write_unlock(&ring_mgmt_lock);
+
+#if defined(RING_DEBUG)
+ if(pfr->reflector_dev != NULL)
+ printk("SO_SET_REFLECTOR(%s): succeded\n", devName);
+ else
+ printk("SO_SET_REFLECTOR(%s): device unknown\n", devName);
+#endif
+ break;
+
+ default:
+ found = 0;
+ break;
+ }
+
+ if(found)
+ return(ret);
+ else
+ return(sock_setsockopt(sock, level, optname, optval, optlen));
+}
+
+/* ************************************* */
+
+static int ring_ioctl(struct socket *sock,
+ unsigned int cmd, unsigned long arg)
+{
+ switch(cmd)
+ {
+ case SIOCGIFFLAGS:
+ case SIOCSIFFLAGS:
+ case SIOCGIFCONF:
+ case SIOCGIFMETRIC:
+ case SIOCSIFMETRIC:
+ case SIOCGIFMEM:
+ case SIOCSIFMEM:
+ case SIOCGIFMTU:
+ case SIOCSIFMTU:
+ case SIOCSIFLINK:
+ case SIOCGIFHWADDR:
+ case SIOCSIFHWADDR:
+ case SIOCSIFMAP:
+ case SIOCGIFMAP:
+ case SIOCSIFSLAVE:
+ case SIOCGIFSLAVE:
+ case SIOCGIFINDEX:
+ case SIOCGIFNAME:
+ case SIOCGIFCOUNT:
+ case SIOCSIFHWBROADCAST:
+ return(dev_ioctl(cmd,(void *) arg));
+
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+/* ************************************* */
+
+static struct proto_ops ring_ops = {
+ .family = PF_RING,
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+ .owner = THIS_MODULE,
+#endif
+
+ /* Operations that make no sense on ring sockets. */
+ .connect = sock_no_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .sendpage = sock_no_sendpage,
+ .sendmsg = sock_no_sendmsg,
+ .getsockopt = sock_no_getsockopt,
+
+ /* Now the operations that really occur. */
+ .release = ring_release,
+ .bind = ring_bind,
+ .mmap = ring_mmap,
+ .poll = ring_poll,
+ .setsockopt = ring_setsockopt,
+ .ioctl = ring_ioctl,
+ .recvmsg = ring_recvmsg,
+};
+
+/* ************************************ */
+
+static struct net_proto_family ring_family_ops = {
+ .family = PF_RING,
+ .create = ring_create,
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+ .owner = THIS_MODULE,
+#endif
+};
+
+// BD: API changed in 2.6.12, ref:
+// http://svn.clkao.org/svnweb/linux/revision/?rev=28201
+#if (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,11))
+static struct proto ring_proto = {
+ .name = "PF_RING",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct sock),
+};
+#endif
+
+/* ************************************ */
+
+static void __exit ring_exit(void)
+{
+ struct list_head *ptr;
+ struct ring_element *entry;
+
+ for(ptr = ring_table.next; ptr != &ring_table; ptr = ptr->next) {
+ entry = list_entry(ptr, struct ring_element, list);
+ kfree(entry);
+ }
+
+ while(ring_cluster_list != NULL) {
+ struct ring_cluster *next = ring_cluster_list->next;
+ kfree(ring_cluster_list);
+ ring_cluster_list = next;
+ }
+
+ set_skb_ring_handler(NULL);
+ set_buffer_ring_handler(NULL);
+ sock_unregister(PF_RING);
+
+ printk("PF_RING shut down.\n");
+}
+
+/* ************************************ */
+
+static int __init ring_init(void)
+{
+ printk("Welcome to PF_RING %s\n(C) 2004 L.Deri <deri@ntop.org>\n",
+ RING_VERSION);
+
+ INIT_LIST_HEAD(&ring_table);
+ ring_cluster_list = NULL;
+
+ sock_register(&ring_family_ops);
+
+ set_skb_ring_handler(skb_ring_handler);
+ set_buffer_ring_handler(buffer_ring_handler);
+
+ if(get_buffer_ring_handler() != buffer_ring_handler) {
+ printk("PF_RING: set_buffer_ring_handler FAILED\n");
+
+ set_skb_ring_handler(NULL);
+ set_buffer_ring_handler(NULL);
+ sock_unregister(PF_RING);
+ return -1;
+ } else {
+ printk("PF_RING: bucket length %d bytes\n", bucket_len);
+ printk("PF_RING: ring slots %d\n", num_slots);
+ printk("PF_RING: sample rate %d [1=no sampling]\n", sample_rate);
+ printk("PF_RING: capture TX %s\n",
+ enable_tx_capture ? "Yes [RX+TX]" : "No [RX only]");
+ printk("PF_RING: transparent mode %s\n",
+ transparent_mode ? "Yes" : "No");
+
+ printk("PF_RING initialized correctly.\n");
+ return 0;
+ }
+}
+
+module_init(ring_init);
+module_exit(ring_exit);
+MODULE_LICENSE("GPL");
+
+#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,0))
+MODULE_ALIAS_NETPROTO(PF_RING);
+#endif
Copy Permalink