pktgen.c

linux 内核源代码

/*
 * Authors:
 * Copyright 2001, 2002 by Robert Olsson <[e-mail]>
 *                             Uppsala University and
 *                             Swedish University of Agricultural Sciences
 *
 * Alexey Kuznetsov  <[e-mail]>
 * Ben Greear <[e-mail]>
 * Jens Låås <[e-mail]>
 *
 * 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.
 *
 *
 * A tool for loading the network with preconfigurated packets.
 * The tool is implemented as a linux module.  Parameters are output
 * device, delay (to hard_xmit), number of packets, and whether
 * to use multiple SKBs or just the same one.
 * pktgen uses the installed interface's output routine.
 *
 * Additional hacking by:
 *
 * [e-mail]
 * Improved by ANK. 010120.
 * Improved by ANK even more. 010212.
 * MAC address typo fixed. 010417 --ro
 * Integrated.  020301 --DaveM
 * Added multiskb option 020301 --DaveM
 * Scaling of results. [e-mail]
 * Significant re-work of the module:
 *   *  Convert to threaded model to more efficiently be able to transmit
 *       and receive on multiple interfaces at once.
 *   *  Converted many counters to __u64 to allow longer runs.
 *   *  Allow configuration of ranges, like min/max IP address, MACs,
 *       and UDP-ports, for both source and destination, and can
 *       set to use a random distribution or sequentially walk the range.
 *   *  Can now change most values after starting.
 *   *  Place 12-byte packet in UDP payload with magic number,
 *       sequence number, and timestamp.
 *   *  Add receiver code that detects dropped pkts, re-ordered pkts, and
 *       latencies (with micro-second) precision.
 *   *  Add IOCTL interface to easily get counters & configuration.
 *   --Ben Greear <[e-mail]>
 *
 * Renamed multiskb to clone_skb and cleaned up sending core for two distinct
 * skb modes. A clone_skb=0 mode for Ben "ranges" work and a clone_skb != 0
 * as a "fastpath" with a configurable number of clones after alloc's.
 * clone_skb=0 means all packets are allocated this also means ranges time
 * stamps etc can be used. clone_skb=100 means 1 malloc is followed by 100
 * clones.
 *
 * Also moved to /proc/net/pktgen/
 * --ro
 *
 * Sept 10:  Fixed threading/locking.  Lots of bone-headed and more clever
 *    mistakes.  Also merged in DaveM's patch in the -pre6 patch.
 * --Ben Greear <[e-mail]>
 *
 * Integrated to 2.5.x 021029 --Lucio Maciel ([e-mail])
 *
 *
 * 021124 Finished major redesign and rewrite for new functionality.
 * See Documentation/networking/pktgen.txt for how to use this.
 *
 * The new operation:
 * For each CPU one thread/process is created at start. This process checks
 * for running devices in the if_list and sends packets until count is 0 it
 * also the thread checks the thread->control which is used for inter-process
 * communication. controlling process "posts" operations to the threads this
 * way. The if_lock should be possible to remove when add/rem_device is merged
 * into this too.
 *
 * By design there should only be *one* "controlling" process. In practice
 * multiple write accesses gives unpredictable result. Understood by "write"
 * to /proc gives result code thats should be read be the "writer".
 * For practical use this should be no problem.
 *
 * Note when adding devices to a specific CPU there good idea to also assign
 * /proc/irq/XX/smp_affinity so TX-interrupts gets bound to the same CPU.
 * --ro
 *
 * Fix refcount off by one if first packet fails, potential null deref,
 * memleak 030710- KJP
 *
 * First "ranges" functionality for ipv6 030726 --ro
 *
 * Included flow support. 030802 ANK.
 *
 * Fixed unaligned access on IA-64 Grant Grundler <[e-mail]>
 *
 * Remove if fix from added Harald Welte <[e-mail]> 040419
 * ia64 compilation fix from  Aron Griffis <[e-mail]> 040604
 *
 * New xmit() return, do_div and misc clean up by Stephen Hemminger
 * <[e-mail]> 040923
 *
 * Randy Dunlap fixed u64 printk compiler waring
 *
 * Remove FCS from BW calculation.  Lennert Buytenhek <[e-mail]>
 * New time handling. Lennert Buytenhek <[e-mail]> 041213
 *
 * Corrections from Nikolai Malykh ([e-mail])
 * Removed unused flags F_SET_SRCMAC & F_SET_SRCIP 041230
 *
 * interruptible_sleep_on_timeout() replaced Nishanth Aravamudan <[e-mail]>
 * 050103
 *
 * MPLS support by Steven Whitehouse <[e-mail]>
 *
 * 802.1Q/Q-in-Q support by Francesco Fondelli (FF) <[e-mail]>
 *
 * Fixed src_mac command to set source mac of packet to value specified in
 * command by Adit Ranadive <[e-mail]>
 *
 */
#include <linux/sys.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/kernel.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/unistd.h>
#include <linux/string.h>
#include <linux/ptrace.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/freezer.h>
#include <linux/delay.h>
#include <linux/timer.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/rtnetlink.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/udp.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/wait.h>
#include <linux/etherdevice.h>
#include <linux/kthread.h>
#include <net/net_namespace.h>
#include <net/checksum.h>
#include <net/ipv6.h>
#include <net/addrconf.h>
#ifdef CONFIG_XFRM
#include <net/xfrm.h>
#endif
#include <asm/byteorder.h>
#include <linux/rcupdate.h>
#include <linux/bitops.h>
#include <asm/io.h>
#include <asm/dma.h>
#include <asm/uaccess.h>
#include <asm/div64.h>		/* do_div */
#include <asm/timex.h>

#define VERSION  "pktgen v2.69: Packet Generator for packet performance testing.\n"

/* The buckets are exponential in 'width' */
#define LAT_BUCKETS_MAX 32
#define IP_NAME_SZ 32
#define MAX_MPLS_LABELS 16 /* This is the max label stack depth */
#define MPLS_STACK_BOTTOM htonl(0x00000100)

/* Device flag bits */
#define F_IPSRC_RND   (1<<0)	/* IP-Src Random  */
#define F_IPDST_RND   (1<<1)	/* IP-Dst Random  */
#define F_UDPSRC_RND  (1<<2)	/* UDP-Src Random */
#define F_UDPDST_RND  (1<<3)	/* UDP-Dst Random */
#define F_MACSRC_RND  (1<<4)	/* MAC-Src Random */
#define F_MACDST_RND  (1<<5)	/* MAC-Dst Random */
#define F_TXSIZE_RND  (1<<6)	/* Transmit size is random */
#define F_IPV6        (1<<7)	/* Interface in IPV6 Mode */
#define F_MPLS_RND    (1<<8)	/* Random MPLS labels */
#define F_VID_RND     (1<<9)	/* Random VLAN ID */
#define F_SVID_RND    (1<<10)	/* Random SVLAN ID */
#define F_FLOW_SEQ    (1<<11)	/* Sequential flows */
#define F_IPSEC_ON    (1<<12)	/* ipsec on for flows */
#define F_QUEUE_MAP_RND (1<<13)	/* queue map Random */

/* Thread control flag bits */
#define T_TERMINATE   (1<<0)
#define T_STOP        (1<<1)	/* Stop run */
#define T_RUN         (1<<2)	/* Start run */
#define T_REMDEVALL   (1<<3)	/* Remove all devs */
#define T_REMDEV      (1<<4)	/* Remove one dev */

/* If lock -- can be removed after some work */
#define   if_lock(t)           spin_lock(&(t->if_lock));
#define   if_unlock(t)           spin_unlock(&(t->if_lock));

/* Used to help with determining the pkts on receive */
#define PKTGEN_MAGIC 0xbe9be955
#define PG_PROC_DIR "pktgen"
#define PGCTRL	    "pgctrl"
static struct proc_dir_entry *pg_proc_dir = NULL;

#define MAX_CFLOWS  65536

#define VLAN_TAG_SIZE(x) ((x)->vlan_id == 0xffff ? 0 : 4)
#define SVLAN_TAG_SIZE(x) ((x)->svlan_id == 0xffff ? 0 : 4)

struct flow_state {
	__be32 cur_daddr;
	int count;
#ifdef CONFIG_XFRM
	struct xfrm_state *x;
#endif
	__u32 flags;
};

/* flow flag bits */
#define F_INIT   (1<<0)		/* flow has been initialized */

struct pktgen_dev {
	/*
	 * Try to keep frequent/infrequent used vars. separated.
	 */
	struct proc_dir_entry *entry;	/* proc file */
	struct pktgen_thread *pg_thread;/* the owner */
	struct list_head list;		/* Used for chaining in the thread's run-queue */

	int running;		/* if this changes to false, the test will stop */

	/* If min != max, then we will either do a linear iteration, or
	 * we will do a random selection from within the range.
	 */
	__u32 flags;
	int removal_mark;	/* non-zero => the device is marked for
				 * removal by worker thread */

	int min_pkt_size;	/* = ETH_ZLEN; */
	int max_pkt_size;	/* = ETH_ZLEN; */
	int pkt_overhead;	/* overhead for MPLS, VLANs, IPSEC etc */
	int nfrags;
	__u32 delay_us;		/* Default delay */
	__u32 delay_ns;
	__u64 count;		/* Default No packets to send */
	__u64 sofar;		/* How many pkts we've sent so far */
	__u64 tx_bytes;		/* How many bytes we've transmitted */
	__u64 errors;		/* Errors when trying to transmit, pkts will be re-sent */

	/* runtime counters relating to clone_skb */
	__u64 next_tx_us;	/* timestamp of when to tx next */
	__u32 next_tx_ns;

	__u64 allocated_skbs;
	__u32 clone_count;
	int last_ok;		/* Was last skb sent?
				 * Or a failed transmit of some sort?  This will keep
				 * sequence numbers in order, for example.
				 */
	__u64 started_at;	/* micro-seconds */
	__u64 stopped_at;	/* micro-seconds */
	__u64 idle_acc;		/* micro-seconds */
	__u32 seq_num;

	int clone_skb;		/* Use multiple SKBs during packet gen.  If this number
				 * is greater than 1, then that many copies of the same
				 * packet will be sent before a new packet is allocated.
				 * For instance, if you want to send 1024 identical packets
				 * before creating a new packet, set clone_skb to 1024.
				 */

	char dst_min[IP_NAME_SZ];	/* IP, ie 1.2.3.4 */
	char dst_max[IP_NAME_SZ];	/* IP, ie 1.2.3.4 */
	char src_min[IP_NAME_SZ];	/* IP, ie 1.2.3.4 */
	char src_max[IP_NAME_SZ];	/* IP, ie 1.2.3.4 */

	struct in6_addr in6_saddr;
	struct in6_addr in6_daddr;
	struct in6_addr cur_in6_daddr;
	struct in6_addr cur_in6_saddr;
	/* For ranges */
	struct in6_addr min_in6_daddr;
	struct in6_addr max_in6_daddr;
	struct in6_addr min_in6_saddr;
	struct in6_addr max_in6_saddr;

	/* If we're doing ranges, random or incremental, then this
	 * defines the min/max for those ranges.
	 */
	__be32 saddr_min;	/* inclusive, source IP address */
	__be32 saddr_max;	/* exclusive, source IP address */
	__be32 daddr_min;	/* inclusive, dest IP address */
	__be32 daddr_max;	/* exclusive, dest IP address */

	__u16 udp_src_min;	/* inclusive, source UDP port */
	__u16 udp_src_max;	/* exclusive, source UDP port */
	__u16 udp_dst_min;	/* inclusive, dest UDP port */
	__u16 udp_dst_max;	/* exclusive, dest UDP port */

	/* DSCP + ECN */
	__u8 tos;            /* six most significant bits of (former) IPv4 TOS are for dscp codepoint */
	__u8 traffic_class;  /* ditto for the (former) Traffic Class in IPv6 (see RFC 3260, sec. 4) */

	/* MPLS */
	unsigned nr_labels;	/* Depth of stack, 0 = no MPLS */
	__be32 labels[MAX_MPLS_LABELS];

	/* VLAN/SVLAN (802.1Q/Q-in-Q) */
	__u8  vlan_p;
	__u8  vlan_cfi;
	__u16 vlan_id;  /* 0xffff means no vlan tag */

	__u8  svlan_p;
	__u8  svlan_cfi;
	__u16 svlan_id; /* 0xffff means no svlan tag */

	__u32 src_mac_count;	/* How many MACs to iterate through */
	__u32 dst_mac_count;	/* How many MACs to iterate through */

	unsigned char dst_mac[ETH_ALEN];
	unsigned char src_mac[ETH_ALEN];

	__u32 cur_dst_mac_offset;
	__u32 cur_src_mac_offset;
	__be32 cur_saddr;
	__be32 cur_daddr;
	__u16 cur_udp_dst;
	__u16 cur_udp_src;
	__u16 cur_queue_map;
	__u32 cur_pkt_size;

	__u8 hh[14];
	/* = {
	   0x00, 0x80, 0xC8, 0x79, 0xB3, 0xCB,

	   We fill in SRC address later
	   0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	   0x08, 0x00
	   };
	 */
	__u16 pad;		/* pad out the hh struct to an even 16 bytes */

	struct sk_buff *skb;	/* skb we are to transmit next, mainly used for when we
				 * are transmitting the same one multiple times
				 */
	struct net_device *odev;	/* The out-going device.  Note that the device should
					 * have it's pg_info pointer pointing back to this
					 * device.  This will be set when the user specifies
					 * the out-going device name (not when the inject is
					 * started as it used to do.)
					 */
	struct flow_state *flows;
	unsigned cflows;	/* Concurrent flows (config) */
	unsigned lflow;		/* Flow length  (config) */
	unsigned nflows;	/* accumulated flows (stats) */
	unsigned curfl;		/* current sequenced flow (state)*/

	u16 queue_map_min;
	u16 queue_map_max;

#ifdef CONFIG_XFRM
	__u8	ipsmode;		/* IPSEC mode (config) */
	__u8	ipsproto;		/* IPSEC type (config) */
#endif
	char result[512];
};

struct pktgen_hdr {
	__be32 pgh_magic;
	__be32 seq_num;
	__be32 tv_sec;
	__be32 tv_usec;
};

struct pktgen_thread {
	spinlock_t if_lock;
	struct list_head if_list;	/* All device here */
	struct list_head th_list;
	struct task_struct *tsk;
	char result[512];

	/* Field for thread to receive "posted" events terminate, stop ifs etc. */

	u32 control;
	int cpu;

	wait_queue_head_t queue;
};

#define REMOVE 1
#define FIND   0

/*  This code works around the fact that do_div cannot handle two 64-bit
    numbers, and regular 64-bit division doesn't work on x86 kernels.
    --Ben
*/

#define PG_DIV 0

/* This was emailed to LMKL by: Chris Caputo <[e-mail]>
 * Function copied/adapted/optimized from:
 *
 *  nemesis.sourceforge.net/browse/lib/static/intmath/ix86/intmath.c.html
 *
 * Copyright 1994, University of Cambridge Computer Laboratory
 * All Rights Reserved.
 *
 */
static inline s64 divremdi3(s64 x, s64 y, int type)
{
	u64 a = (x < 0) ? -x : x;
	u64 b = (y < 0) ? -y : y;
	u64 res = 0, d = 1;

	if (b > 0) {
		while (b < a) {
			b <<= 1;
			d <<= 1;
		}
	}

	do {
		if (a >= b) {
			a -= b;
			res += d;
		}
		b >>= 1;
		d >>= 1;
	}
	while (d);

	if (PG_DIV == type) {
		return (((x ^ y) & (1ll << 63)) == 0) ? res : -(s64) res;
	} else {
		return ((x & (1ll << 63)) == 0) ? a : -(s64) a;
	}
}

/* End of hacks to deal with 64-bit math on x86 */

/** Convert to milliseconds */
static inline __u64 tv_to_ms(const struct timeval *tv)
{
	__u64 ms = tv->tv_usec / 1000;
	ms += (__u64) tv->tv_sec * (__u64) 1000;
	return ms;
}

/** Convert to micro-seconds */
static inline __u64 tv_to_us(const struct timeval *tv)
{
	__u64 us = tv->tv_usec;
	us += (__u64) tv->tv_sec * (__u64) 1000000;
	return us;
}

static inline __u64 pg_div(__u64 n, __u32 base)
{
	__u64 tmp = n;
	do_div(tmp, base);
	/* printk("pktgen: pg_div, n: %llu  base: %d  rv: %llu\n",
	   n, base, tmp); */
	return tmp;
}

static inline __u64 pg_div64(__u64 n, __u64 base)
{
	__u64 tmp = n;
/*
 * How do we know if the architecture we are running on
 * supports division with 64 bit base?
 *
 */
#if defined(__sparc_v9__) || defined(__powerpc64__) || defined(__alpha__) || defined(__x86_64__) || defined(__ia64__)

	do_div(tmp, base);
#else
	tmp = divremdi3(n, base, PG_DIV);
#endif
	return tmp;
}

static inline __u64 getCurMs(void)
{
	struct timeval tv;
	do_gettimeofday(&tv);
	return tv_to_ms(&tv);
}

static inline __u64 getCurUs(void)
{
	struct timeval tv;
	do_gettimeofday(&tv);
	return tv_to_us(&tv);
}

static inline __u64 tv_diff(const struct timeval *a, const struct timeval *b)
{
	return tv_to_us(a) - tv_to_us(b);
}

/* old include end */

static char version[] __initdata = VERSION;

static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i);
static int pktgen_add_device(struct pktgen_thread *t, const char *ifname);
static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t,
					  const char *ifname);
static int pktgen_device_event(struct notifier_block *, unsigned long, void *);
static void pktgen_run_all_threads(void);