pktgen.c

/*
 * Authors:
 * Copyright 2001, 2002 by Robert Olsson <robert.olsson@its.uu.se>
 *                             Uppsala University and
 *                             Swedish University of Agricultural Sciences
 *
 * Alexey Kuznetsov  <kuznet@ms2.inr.ac.ru>
 * Ben Greear <greearb@candelatech.com>
 * Jens Låås <jens.laas@data.slu.se>
 *
 * 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:
 *
 * Jens.Laas@data.slu.se
 * 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. 020417--sigurdur@linpro.no
 * 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 <greearb@candelatech.com>
 *
 * 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 <greearb@candelatech.com>
 *
 * Integrated to 2.5.x 021029 --Lucio Maciel (luciomaciel@zipmail.com.br)
 *
 *
 * 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_list is RCU protected, and the if_lock remains to protect updating
 * of if_list, from "add_device" as it invoked from userspace (via proc write).
 *
 * 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 <grundler@parisc-linux.org>
 *
 * Remove if fix from added Harald Welte <laforge@netfilter.org> 040419
 * ia64 compilation fix from  Aron Griffis <aron@hp.com> 040604
 *
 * New xmit() return, do_div and misc clean up by Stephen Hemminger
 * <shemminger@osdl.org> 040923
 *
 * Randy Dunlap fixed u64 printk compiler warning
 *
 * Remove FCS from BW calculation.  Lennert Buytenhek <buytenh@wantstofly.org>
 * New time handling. Lennert Buytenhek <buytenh@wantstofly.org> 041213
 *
 * Corrections from Nikolai Malykh (nmalykh@bilim.com)
 * Removed unused flags F_SET_SRCMAC & F_SET_SRCIP 041230
 *
 * interruptible_sleep_on_timeout() replaced Nishanth Aravamudan <nacc@us.ibm.com>
 * 050103
 *
 * MPLS support by Steven Whitehouse <steve@chygwyn.com>
 *
 * 802.1Q/Q-in-Q support by Francesco Fondelli (FF) <francesco.fondelli@gmail.com>
 *
 * Fixed src_mac command to set source mac of packet to value specified in
 * command by Adit Ranadive <adit.262@gmail.com>
 *
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#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/hrtimer.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 <linux/prefetch.h>
#include <net/net_namespace.h>
#include <net/checksum.h>
#include <net/ipv6.h>
#include <net/udp.h>
#include <net/ip6_checksum.h>
#include <net/addrconf.h>
#ifdef CONFIG_XFRM
#include <net/xfrm.h>
#endif
#include <net/netns/generic.h>
#include <asm/byteorder.h>
#include <linux/rcupdate.h>
#include <linux/bitops.h>
#include <linux/io.h>
#include <linux/timex.h>
#include <linux/uaccess.h>
#include <asm/dma.h>
#include <asm/div64.h>		/* do_div */

#define VERSION	"2.75"
#define IP_NAME_SZ 32
#define MAX_MPLS_LABELS 16 /* This is the max label stack depth */
#define MPLS_STACK_BOTTOM htonl(0x00000100)

#define func_enter() pr_debug("entering %s\n", __func__);

/* 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 */
#define F_QUEUE_MAP_CPU (1<<14)	/* queue map mirrors smp_processor_id() */
#define F_NODE          (1<<15)	/* Node memory alloc*/
#define F_UDPCSUM       (1<<16)	/* Include UDP checksum */
#define F_NO_TIMESTAMP  (1<<17)	/* Don't timestamp packets (default TS) */

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

/* Xmit modes */
#define M_START_XMIT		0	/* Default normal TX */
#define M_NETIF_RECEIVE 	1	/* Inject packets into stack */

/* If lock -- protects updating of if_list */
#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"

#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;		/* chaining in the thread's run-queue */
	struct rcu_head	 rcu;		/* freed by RCU */

	int running;		/* if 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 xmit_mode;
	int min_pkt_size;
	int max_pkt_size;
	int pkt_overhead;	/* overhead for MPLS, VLANs, IPSEC etc */
	int nfrags;
	int removal_mark;	/* non-zero => the device is marked for
				 * removal by worker thread */

	struct page *page;
	u64 delay;		/* nano-seconds */

	__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, */

	/* runtime counters relating to clone_skb */

	__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
				 */
	ktime_t next_tx;
	ktime_t started_at;
	ktime_t stopped_at;
	u64	idle_acc;	/* nano-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.
				 * 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 MSB 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 int 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 ip_id;
	__u16 cur_udp_dst;
	__u16 cur_udp_src;
	__u16 cur_queue_map;
	__u32 cur_pkt_size;
	__u32 last_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, 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.
				  * Set when the user specifies the out-going
				  * device name (not when the inject is
				  * started as it used to do.)
				  */
	char odevname[32];
	struct flow_state *flows;
	unsigned int cflows;	/* Concurrent flows (config) */
	unsigned int lflow;		/* Flow length  (config) */
	unsigned int nflows;	/* accumulated flows (stats) */
	unsigned int curfl;		/* current sequenced flow (state)*/

	u16 queue_map_min;
	u16 queue_map_max;
	__u32 skb_priority;	/* skb priority field */
	unsigned int burst;	/* number of duplicated packets to burst */
	int node;               /* Memory node */

#ifdef CONFIG_XFRM
	__u8	ipsmode;		/* IPSEC mode (config) */
	__u8	ipsproto;		/* IPSEC type (config) */
	__u32	spi;
	struct dst_entry dst;
	struct dst_ops dstops;
#endif
	char result[512];
};

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


static int pg_net_id __read_mostly;

struct pktgen_net {
	struct net		*net;
	struct proc_dir_entry	*proc_dir;
	struct list_head	pktgen_threads;
	bool			pktgen_exiting;
};

struct pktgen_thread {
	spinlock_t if_lock;		/* for list of devices */
	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;
	struct completion start_done;
	struct pktgen_net *net;
};

#define REMOVE 1
#define FIND   0

static const char version[] =
	"Packet Generator for packet performance testing. "
	"Version: " VERSION "\n";

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, bool exact);
static int pktgen_device_event(struct notifier_block *, unsigned long, void *);
static void pktgen_run_all_threads(struct pktgen_net *pn);
static void pktgen_reset_all_threads(struct pktgen_net *pn);
static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn);

static void pktgen_stop(struct pktgen_thread *t);
static void pktgen_clear_counters(struct pktgen_dev *pkt_dev);

/* Module parameters, defaults. */
static int pg_count_d __read_mostly = 1000;
static int pg_delay_d __read_mostly;
static int pg_clone_skb_d  __read_mostly;
static int debug  __read_mostly;

static DEFINE_MUTEX(pktgen_thread_lock);

static struct notifier_block pktgen_notifier_block = {
	.notifier_call = pktgen_device_event,
};

/*
 * /proc handling functions
 *
 */

static int pgctrl_show(struct seq_file *seq, void *v)
{
	seq_puts(seq, version);
	return 0;
}

static ssize_t pgctrl_write(struct file *file, const char __user *buf,
			    size_t count, loff_t *ppos)
{
	char data[128];
	struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id);

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	if (count == 0)
		return -EINVAL;

	if (count > sizeof(data))
		count = sizeof(data);

	if (copy_from_user(data, buf, count))
		return -EFAULT;

	data[count - 1] = 0;	/* Strip trailing '\n' and terminate string */

	if (!strcmp(data, "stop"))
		pktgen_stop_all_threads_ifs(pn);

	else if (!strcmp(data, "start"))
		pktgen_run_all_threads(pn);

	else if (!strcmp(data, "reset"))
		pktgen_reset_all_threads(pn);

	else
		return -EINVAL;

	return count;
}

static int pgctrl_open(struct inode *inode, struct file *file)
{
	return single_open(file, pgctrl_show, PDE_DATA(inode));
}

static const struct file_operations pktgen_fops = {
	.owner   = THIS_MODULE,
	.open    = pgctrl_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.write   = pgctrl_write,
	.release = single_release,
};

static int pktgen_if_show(struct seq_file *seq, void *v)
{
	const struct pktgen_dev *pkt_dev = seq->private;
	ktime_t stopped;
	u64 idle;

	seq_printf(seq,
		   "Params: count %llu  min_pkt_size: %u  max_pkt_size: %u\n",
		   (unsigned long long)pkt_dev->count, pkt_dev->min_pkt_size,
		   pkt_dev->max_pkt_size);

	seq_printf(seq,
		   "     frags: %d  delay: %llu  clone_skb: %d  ifname: %s\n",
		   pkt_dev->nfrags, (unsigned long long) pkt_dev->delay,
		   pkt_dev->clone_skb, pkt_dev->odevname);

	seq_printf(seq, "     flows: %u flowlen: %u\n", pkt_dev->cflows,
		   pkt_dev->lflow);

	seq_printf(seq,
		   "     queue_map_min: %u  queue_map_max: %u\n",
		   pkt_dev->queue_map_min,
		   pkt_dev->queue_map_max);

	if (pkt_dev->skb_priority)
		seq_printf(seq, "     skb_priority: %u\n",
			   pkt_dev->skb_priority);

	if (pkt_dev->flags & F_IPV6) {
		seq_printf(seq,
			   "     saddr: %pI6c  min_saddr: %pI6c  max_saddr: %pI6c\n"
			   "     daddr: %pI6c  min_daddr: %pI6c  max_daddr: %pI6c\n",
			   &pkt_dev->in6_saddr,
			   &pkt_dev->min_in6_saddr, &pkt_dev->max_in6_saddr,
			   &pkt_dev->in6_daddr,
			   &pkt_dev->min_in6_daddr, &pkt_dev->max_in6_daddr);
	} else {
		seq_printf(seq,
			   "     dst_min: %s  dst_max: %s\n",
			   pkt_dev->dst_min, pkt_dev->dst_max);
		seq_printf(seq,
			   "     src_min: %s  src_max: %s\n",
			   pkt_dev->src_min, pkt_dev->src_max);
	}

	seq_puts(seq, "     src_mac: ");

	seq_printf(seq, "%pM ",
		   is_zero_ether_addr(pkt_dev->src_mac) ?
			     pkt_dev->odev->dev_addr : pkt_dev->src_mac);

	seq_puts(seq, "dst_mac: ");
	seq_printf(seq, "%pM\n", pkt_dev->dst_mac);

	seq_printf(seq,
		   "     udp_src_min: %d  udp_src_max: %d"
		   "  udp_dst_min: %d  udp_dst_max: %d\n",
		   pkt_dev->udp_src_min, pkt_dev->udp_src_max,
		   pkt_dev->udp_dst_min, pkt_dev->udp_dst_max);

	seq_printf(seq,
		   "     src_mac_count: %d  dst_mac_count: %d\n",
		   pkt_dev->src_mac_count, pkt_dev->dst_mac_count);

	if (pkt_dev->nr_labels) {
		unsigned int i;
		seq_puts(seq, "     mpls: ");
		for (i = 0; i < pkt_dev->nr_labels; i++)
			seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]),
				   i == pkt_dev->nr_labels-1 ? "\n" : ", ");
	}

	if (pkt_dev->vlan_id != 0xffff)
		seq_printf(seq, "     vlan_id: %u  vlan_p: %u  vlan_cfi: %u\n",
			   pkt_dev->vlan_id, pkt_dev->vlan_p,
			   pkt_dev->vlan_cfi);

	if (pkt_dev->svlan_id != 0xffff)
		seq_printf(seq, "     svlan_id: %u  vlan_p: %u  vlan_cfi: %u\n",
			   pkt_dev->svlan_id, pkt_dev->svlan_p,
			   pkt_dev->svlan_cfi);

	if (pkt_dev->tos)
		seq_printf(seq, "     tos: 0x%02x\n", pkt_dev->tos);

	if (pkt_dev->traffic_class)
		seq_printf(seq, "     traffic_class: 0x%02x\n", pkt_dev->traffic_class);

	if (pkt_dev->burst > 1)
		seq_printf(seq, "     burst: %d\n", pkt_dev->burst);

	if (pkt_dev->node >= 0)
		seq_printf(seq, "     node: %d\n", pkt_dev->node);

	if (pkt_dev->xmit_mode == M_NETIF_RECEIVE)
		seq_puts(seq, "     xmit_mode: netif_receive\n");

	seq_puts(seq, "     Flags: ");

	if (pkt_dev->flags & F_IPV6)
		seq_puts(seq, "IPV6  ");

	if (pkt_dev->flags & F_IPSRC_RND)
		seq_puts(seq, "IPSRC_RND  ");

	if (pkt_dev->flags & F_IPDST_RND)
		seq_puts(seq, "IPDST_RND  ");

	if (pkt_dev->flags & F_TXSIZE_RND)
		seq_puts(seq, "TXSIZE_RND  ");

	if (pkt_dev->flags & F_UDPSRC_RND)
		seq_puts(seq, "UDPSRC_RND  ");

	if (pkt_dev->flags & F_UDPDST_RND)
		seq_puts(seq, "UDPDST_RND  ");

	if (pkt_dev->flags & F_UDPCSUM)
		seq_puts(seq, "UDPCSUM  ");

	if (pkt_dev->flags & F_NO_TIMESTAMP)
		seq_puts(seq, "NO_TIMESTAMP  ");

	if (pkt_dev->flags & F_MPLS_RND)
		seq_puts(seq,  "MPLS_RND  ");

	if (pkt_dev->flags & F_QUEUE_MAP_RND)
		seq_puts(seq,  "QUEUE_MAP_RND  ");

	if (pkt_dev->flags & F_QUEUE_MAP_CPU)
		seq_puts(seq,  "QUEUE_MAP_CPU  ");

	if (pkt_dev->cflows) {
		if (pkt_dev->flags & F_FLOW_SEQ)
			seq_puts(seq,  "FLOW_SEQ  "); /*in sequence flows*/
		else
			seq_puts(seq,  "FLOW_RND  ");
	}

#ifdef CONFIG_XFRM
	if (pkt_dev->flags & F_IPSEC_ON) {
		seq_puts(seq,  "IPSEC  ");
		if (pkt_dev->spi)
			seq_printf(seq, "spi:%u", pkt_dev->spi);
	}
#endif

	if (pkt_dev->flags & F_MACSRC_RND)
		seq_puts(seq, "MACSRC_RND  ");

	if (pkt_dev->flags & F_MACDST_RND)
		seq_puts(seq, "MACDST_RND  ");

	if (pkt_dev->flags & F_VID_RND)
		seq_puts(seq, "VID_RND  ");

	if (pkt_dev->flags & F_SVID_RND)
		seq_puts(seq, "SVID_RND  ");

	if (pkt_dev->flags & F_NODE)
		seq_puts(seq, "NODE_ALLOC  ");

	seq_puts(seq, "\n");

	/* not really stopped, more like last-running-at */
	stopped = pkt_dev->running ? ktime_get() : pkt_dev->stopped_at;
	idle = pkt_dev->idle_acc;
	do_div(idle, NSEC_PER_USEC);

	seq_printf(seq,
		   "Current:\n     pkts-sofar: %llu  errors: %llu\n",
		   (unsigned long long)pkt_dev->sofar,
		   (unsigned long long)pkt_dev->errors);

	seq_printf(seq,
		   "     started: %lluus  stopped: %lluus idle: %lluus\n",
		   (unsigned long long) ktime_to_us(pkt_dev->started_at),
		   (unsigned long long) ktime_to_us(stopped),
		   (unsigned long long) idle);

	seq_printf(seq,
		   "     seq_num: %d  cur_dst_mac_offset: %d  cur_src_mac_offset: %d\n",
		   pkt_dev->seq_num, pkt_dev->cur_dst_mac_offset,
		   pkt_dev->cur_src_mac_offset);

	if (pkt_dev->flags & F_IPV6) {
		seq_printf(seq, "     cur_saddr: %pI6c  cur_daddr: %pI6c\n",
				&pkt_dev->cur_in6_saddr,
				&pkt_dev->cur_in6_daddr);
	} else
		seq_printf(seq, "     cur_saddr: %pI4  cur_daddr: %pI4\n",
			   &pkt_dev->cur_saddr, &pkt_dev->cur_daddr);

	seq_printf(seq, "     cur_udp_dst: %d  cur_udp_src: %d\n",
		   pkt_dev->cur_udp_dst, pkt_dev->cur_udp_src);

	seq_printf(seq, "     cur_queue_map: %u\n", pkt_dev->cur_queue_map);

	seq_printf(seq, "     flows: %u\n", pkt_dev->nflows);

	if (pkt_dev->result[0])
		seq_printf(seq, "Result: %s\n", pkt_dev->result);
	else
		seq_puts(seq, "Result: Idle\n");

	return 0;
}


static int hex32_arg(const char __user *user_buffer, unsigned long maxlen,
		     __u32 *num)
{
	int i = 0;
	*num = 0;

	for (; i < maxlen; i++) {
		int value;
		char c;
		*num <<= 4;
		if (get_user(c, &user_buffer[i]))
			return -EFAULT;
		value = hex_to_bin(c);
		if (value >= 0)
			*num |= value;
		else
			break;
	}
	return i;
}

static int count_trail_chars(const char __user * user_buffer,
			     unsigned int maxlen)
{
	int i;

	for (i = 0; i < maxlen; i++) {
		char c;
		if (get_user(c, &user_buffer[i]))
			return -EFAULT;
		switch (c) {
		case '\"':
		case '\n':
		case '\r':
		case '\t':
		case ' ':
		case '=':
			break;
		default:
			goto done;
		}
	}
done:
	return i;
}

static long num_arg(const char __user *user_buffer, unsigned long maxlen,
				unsigned long *num)
{
	int i;
	*num = 0;

	for (i = 0; i < maxlen; i++) {
		char c;
		if (get_user(c, &user_buffer[i]))
			return -EFAULT;
		if ((c >= '0') && (c <= '9')) {
			*num *= 10;
			*num += c - '0';
		} else
			break;
	}
	return i;
}

static int strn_len(const char __user * user_buffer, unsigned int maxlen)
{
	int i;

	for (i = 0; i < maxlen; i++) {
		char c;
		if (get_user(c, &user_buffer[i]))
			return -EFAULT;
		switch (c) {
		case '\"':
		case '\n':
		case '\r':
		case '\t':
		case ' ':
			goto done_str;
		default:
			break;
		}
	}
done_str:
	return i;
}

static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
{
	unsigned int n = 0;
	char c;
	ssize_t i = 0;
	int len;

	pkt_dev->nr_labels = 0;
	do {
		__u32 tmp;
		len = hex32_arg(&buffer[i], 8, &tmp);
		if (len <= 0)
			return len;
		pkt_dev->labels[n] = htonl(tmp);
		if (pkt_dev->labels[n] & MPLS_STACK_BOTTOM)
			pkt_dev->flags |= F_MPLS_RND;
		i += len;
		if (get_user(c, &buffer[i]))
			return -EFAULT;
		i++;
		n++;
		if (n >= MAX_MPLS_LABELS)
			return -E2BIG;
	} while (c == ',');

	pkt_dev->nr_labels = n;
	return i;
}

static ssize_t pktgen_if_write(struct file *file,
			       const char __user * user_buffer, size_t count,
			       loff_t * offset)
{
	struct seq_file *seq = file->private_data;
	struct pktgen_dev *pkt_dev = seq->private;
	int i, max, len;
	char name[16], valstr[32];
	unsigned long value = 0;
	char *pg_result = NULL;
	int tmp = 0;
	char buf[128];

	pg_result = &(pkt_dev->result[0]);

	if (count < 1) {
		pr_warn("wrong command format\n");
		return -EINVAL;
	}

	max = count;
	tmp = count_trail_chars(user_buffer, max);
	if (tmp < 0) {
		pr_warn("illegal format\n");
		return tmp;
	}
	i = tmp;

	/* Read variable name */

	len = strn_len(&user_buffer[i], sizeof(name) - 1);
	if (len < 0)
		return len;

	memset(name, 0, sizeof(name));
	if (copy_from_user(name, &user_buffer[i], len))
		return -EFAULT;
	i += len;

	max = count - i;
	len = count_trail_chars(&user_buffer[i], max);
	if (len < 0)
		return len;

	i += len;

	if (debug) {
		size_t copy = min_t(size_t, count, 1023);
		char tb[copy + 1];
		if (copy_from_user(tb, user_buffer, copy))
			return -EFAULT;
		tb[copy] = 0;
		pr_debug("%s,%lu  buffer -:%s:-\n",
			 name, (unsigned long)count, tb);
	}

	if (!strcmp(name, "min_pkt_size")) {
		len = num_arg(&user_buffer[i], 10, &value);
		if (len < 0)
			return len;

		i += len;
		if (value < 14 + 20 + 8)
			value = 14 + 20 + 8;
		if (value != pkt_dev->min_pkt_size) {
			pkt_dev->min_pkt_size = value;
			pkt_dev->cur_pkt_size = value;
		}
		sprintf(pg_result, "OK: min_pkt_size=%u",
			pkt_dev->min_pkt_size);
		return count;
	}

	if (!strcmp(name, "max_pkt_size")) {
		len = num_arg(&user_buffer[i], 10, &value);
		if (len < 0)
			return len;

		i += len;
		if (value < 14 + 20 + 8)
			value = 14 + 20 + 8;
		if (value != pkt_dev->max_pkt_size) {
			pkt_dev->max_pkt_size = value;
			pkt_dev->cur_pkt_size = value;
		}
		sprintf(pg_result, "OK: max_pkt_size=%u",
			pkt_dev->max_pkt_size);
		return count;
	}

	/* Shortcut for min = max */

	if (!strcmp(name, "pkt_size")) {
		len = num_arg(&user_buffer[i], 10, &value);
		if (len < 0)
			return len;

		i += len;
		if (value < 14 + 20 + 8)
			value = 14 + 20 + 8;
		if (value != pkt_dev->min_pkt_size) {
			pkt_dev->min_pkt_size = value;
			pkt_dev->max_pkt_size = value;
			pkt_dev->cur_pkt_size = value;
		}
		sprintf(pg_result, "OK: pkt_size=%u", pkt_dev->min_pkt_size);
		return count;
	}

	if (!strcmp(name, "debug")) {
		len = num_arg(&user_buffer[i], 10, &value);
		if (len < 0)
			return len;