*
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
* Ben Greear <greearb@candelatech.com>
- * Jens Låås <jens.laas@data.slu.se>
+ * 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
#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>
#endif
#include <asm/byteorder.h>
#include <linux/rcupdate.h>
-#include <asm/bitops.h>
-#include <asm/io.h>
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/timex.h>
+#include <linux/uaccess.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 VERSION "2.72"
#define IP_NAME_SZ 32
#define MAX_MPLS_LABELS 16 /* This is the max label stack depth */
#define MPLS_STACK_BOTTOM htonl(0x00000100)
#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() */
/* 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 */
+#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 */
/* If lock -- can be removed after some work */
#define if_lock(t) spin_lock(&(t->if_lock));
#define PKTGEN_MAGIC 0xbe9be955
#define PG_PROC_DIR "pktgen"
#define PGCTRL "pgctrl"
-static struct proc_dir_entry *pg_proc_dir = NULL;
+static struct proc_dir_entry *pg_proc_dir;
#define MAX_CFLOWS 65536
*/
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 */
+ struct list_head list; /* chaining in the thread's run-queue */
- int running; /* if this changes to false, the test will stop */
+ 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.
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 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, pkts will be re-sent */
+ __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.
+ * Or a failed transmit of some sort?
+ * This will keep sequence numbers in order
*/
- __u64 started_at; /* micro-seconds */
- __u64 stopped_at; /* micro-seconds */
- __u64 idle_acc; /* micro-seconds */
+ 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.
- * For instance, if you want to send 1024 identical packets
- * before creating a new packet, set clone_skb to 1024.
+ 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 */
__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) */
+ __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 nr_labels; /* Depth of stack, 0 = no MPLS */
__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;
*/
__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
+ 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. 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 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.)
+ */
struct flow_state *flows;
unsigned cflows; /* Concurrent flows (config) */
unsigned lflow; /* Flow length (config) */
};
struct pktgen_thread {
- spinlock_t if_lock;
+ 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. */
+ /* Field for thread to receive "posted" events terminate,
+ stop ifs etc. */
u32 control;
int cpu;
wait_queue_head_t queue;
+ struct completion start_done;
};
#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 <ccaputo@alt.net>
- * 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)
+static inline ktime_t ktime_now(void)
{
- 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);
+ struct timespec ts;
+ ktime_get_ts(&ts);
- if (PG_DIV == type) {
- return (((x ^ y) & (1ll << 63)) == 0) ? res : -(s64) res;
- } else {
- return ((x & (1ll << 63)) == 0) ? a : -(s64) a;
- }
+ return timespec_to_ktime(ts);
}
-/* End of hacks to deal with 64-bit math on x86 */
-
-/** Convert to milliseconds */
-static inline __u64 tv_to_ms(const struct timeval *tv)
+/* This works even if 32 bit because of careful byte order choice */
+static inline int ktime_lt(const ktime_t cmp1, const ktime_t cmp2)
{
- __u64 ms = tv->tv_usec / 1000;
- ms += (__u64) tv->tv_sec * (__u64) 1000;
- return ms;
+ return cmp1.tv64 < cmp2.tv64;
}
-/** 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 const char version[] =
+ "pktgen " VERSION ": Packet Generator for packet performance testing.\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);
const char *ifname);
static int pktgen_device_event(struct notifier_block *, unsigned long, void *);
static void pktgen_run_all_threads(void);
+static void pktgen_reset_all_threads(void);
static void pktgen_stop_all_threads_ifs(void);
-static int pktgen_stop_device(struct pktgen_dev *pkt_dev);
+
static void pktgen_stop(struct pktgen_thread *t);
static void pktgen_clear_counters(struct pktgen_dev *pkt_dev);
static unsigned int fmt_ip6(char *s, const char ip[16]);
/* Module parameters, defaults. */
-static int pg_count_d = 1000; /* 1000 pkts by default */
-static int pg_delay_d;
-static int pg_clone_skb_d;
-static int debug;
+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 LIST_HEAD(pktgen_threads);
static int pgctrl_show(struct seq_file *seq, void *v)
{
- seq_puts(seq, VERSION);
+ seq_puts(seq, version);
return 0;
}
-static ssize_t pgctrl_write(struct file *file, const char __user * buf,
- size_t count, loff_t * ppos)
+static ssize_t pgctrl_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
{
int err = 0;
char data[128];
else if (!strcmp(data, "start"))
pktgen_run_all_threads();
+ else if (!strcmp(data, "reset"))
+ pktgen_reset_all_threads();
+
else
printk(KERN_WARNING "pktgen: Unknown command: %s\n", data);
static int pktgen_if_show(struct seq_file *seq, void *v)
{
- int i;
- struct pktgen_dev *pkt_dev = seq->private;
- __u64 sa;
- __u64 stopped;
- __u64 now = getCurUs();
+ 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",
pkt_dev->max_pkt_size);
seq_printf(seq,
- " frags: %d delay: %u clone_skb: %d ifname: %s\n",
- pkt_dev->nfrags,
- 1000 * pkt_dev->delay_us + pkt_dev->delay_ns,
+ " 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->odev->name);
seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows,
" daddr: %s min_daddr: %s max_daddr: %s\n", b1,
b2, b3);
- } else
+ } else {
seq_printf(seq,
- " dst_min: %s dst_max: %s\n src_min: %s src_max: %s\n",
- pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min,
- pkt_dev->src_max);
+ " 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: ");
- if (is_zero_ether_addr(pkt_dev->src_mac))
- for (i = 0; i < 6; i++)
- seq_printf(seq, "%02X%s", pkt_dev->odev->dev_addr[i],
- i == 5 ? " " : ":");
- else
- for (i = 0; i < 6; i++)
- seq_printf(seq, "%02X%s", pkt_dev->src_mac[i],
- i == 5 ? " " : ":");
+ seq_printf(seq, "%pM ",
+ is_zero_ether_addr(pkt_dev->src_mac) ?
+ pkt_dev->odev->dev_addr : pkt_dev->src_mac);
seq_printf(seq, "dst_mac: ");
- for (i = 0; i < 6; i++)
- seq_printf(seq, "%02X%s", pkt_dev->dst_mac[i],
- i == 5 ? "\n" : ":");
+ 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",
+ " 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);
i == pkt_dev->nr_labels-1 ? "\n" : ", ");
}
- if (pkt_dev->vlan_id != 0xffff) {
+ 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);
- }
+ pkt_dev->vlan_id, pkt_dev->vlan_p,
+ pkt_dev->vlan_cfi);
- if (pkt_dev->svlan_id != 0xffff) {
+ 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);
- }
+ pkt_dev->svlan_id, pkt_dev->svlan_p,
+ pkt_dev->svlan_cfi);
- if (pkt_dev->tos) {
+ if (pkt_dev->tos)
seq_printf(seq, " tos: 0x%02x\n", pkt_dev->tos);
- }
- if (pkt_dev->traffic_class) {
+ if (pkt_dev->traffic_class)
seq_printf(seq, " traffic_class: 0x%02x\n", pkt_dev->traffic_class);
- }
seq_printf(seq, " Flags: ");
if (pkt_dev->flags & F_QUEUE_MAP_RND)
seq_printf(seq, "QUEUE_MAP_RND ");
+ if (pkt_dev->flags & F_QUEUE_MAP_CPU)
+ seq_printf(seq, "QUEUE_MAP_CPU ");
+
if (pkt_dev->cflows) {
if (pkt_dev->flags & F_FLOW_SEQ)
seq_printf(seq, "FLOW_SEQ "); /*in sequence flows*/
seq_puts(seq, "\n");
- sa = pkt_dev->started_at;
- stopped = pkt_dev->stopped_at;
- if (pkt_dev->running)
- stopped = now; /* not really stopped, more like last-running-at */
+ /* not really stopped, more like last-running-at */
+ stopped = pkt_dev->running ? ktime_now() : 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 started: %lluus stopped: %lluus idle: %lluus\n",
+ "Current:\n pkts-sofar: %llu errors: %llu\n",
(unsigned long long)pkt_dev->sofar,
- (unsigned long long)pkt_dev->errors, (unsigned long long)sa,
- (unsigned long long)stopped,
- (unsigned long long)pkt_dev->idle_acc);
+ (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",
}
-static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, __u32 *num)
+static int hex32_arg(const char __user *user_buffer, unsigned long maxlen,
+ __u32 *num)
{
int i = 0;
*num = 0;
/* Read variable name */
len = strn_len(&user_buffer[i], sizeof(name) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
memset(name, 0, sizeof(name));
if (copy_from_user(name, &user_buffer[i], len))
return -EFAULT;
if (!strcmp(name, "min_pkt_size")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value < 14 + 20 + 8)
value = 14 + 20 + 8;
if (!strcmp(name, "max_pkt_size")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value < 14 + 20 + 8)
value = 14 + 20 + 8;
if (!strcmp(name, "pkt_size")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value < 14 + 20 + 8)
value = 14 + 20 + 8;
if (!strcmp(name, "debug")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
debug = value;
sprintf(pg_result, "OK: debug=%u", debug);
if (!strcmp(name, "frags")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->nfrags = value;
sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags);
}
if (!strcmp(name, "delay")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
- if (value == 0x7FFFFFFF) {
- pkt_dev->delay_us = 0x7FFFFFFF;
- pkt_dev->delay_ns = 0;
- } else {
- pkt_dev->delay_us = value / 1000;
- pkt_dev->delay_ns = value % 1000;
- }
- sprintf(pg_result, "OK: delay=%u",
- 1000 * pkt_dev->delay_us + pkt_dev->delay_ns);
+ if (value == 0x7FFFFFFF)
+ pkt_dev->delay = ULLONG_MAX;
+ else
+ pkt_dev->delay = (u64)value;
+
+ sprintf(pg_result, "OK: delay=%llu",
+ (unsigned long long) pkt_dev->delay);
return count;
}
if (!strcmp(name, "udp_src_min")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value != pkt_dev->udp_src_min) {
pkt_dev->udp_src_min = value;
}
if (!strcmp(name, "udp_dst_min")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value != pkt_dev->udp_dst_min) {
pkt_dev->udp_dst_min = value;
}
if (!strcmp(name, "udp_src_max")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value != pkt_dev->udp_src_max) {
pkt_dev->udp_src_max = value;
}
if (!strcmp(name, "udp_dst_max")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value != pkt_dev->udp_dst_max) {
pkt_dev->udp_dst_max = value;
}
if (!strcmp(name, "clone_skb")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->clone_skb = value;
}
if (!strcmp(name, "count")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->count = value;
sprintf(pg_result, "OK: count=%llu",
}
if (!strcmp(name, "src_mac_count")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (pkt_dev->src_mac_count != value) {
pkt_dev->src_mac_count = value;
}
if (!strcmp(name, "dst_mac_count")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (pkt_dev->dst_mac_count != value) {
pkt_dev->dst_mac_count = value;
char f[32];
memset(f, 0, 32);
len = strn_len(&user_buffer[i], sizeof(f) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
if (copy_from_user(f, &user_buffer[i], len))
return -EFAULT;
i += len;
else if (strcmp(f, "!QUEUE_MAP_RND") == 0)
pkt_dev->flags &= ~F_QUEUE_MAP_RND;
+
+ else if (strcmp(f, "QUEUE_MAP_CPU") == 0)
+ pkt_dev->flags |= F_QUEUE_MAP_CPU;
+
+ else if (strcmp(f, "!QUEUE_MAP_CPU") == 0)
+ pkt_dev->flags &= ~F_QUEUE_MAP_CPU;
#ifdef CONFIG_XFRM
else if (strcmp(f, "IPSEC") == 0)
pkt_dev->flags |= F_IPSEC_ON;
}
if (!strcmp(name, "dst_min") || !strcmp(name, "dst")) {
len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_min) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
if (copy_from_user(buf, &user_buffer[i], len))
return -EFAULT;
}
if (!strcmp(name, "dst_max")) {
len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_max) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
if (copy_from_user(buf, &user_buffer[i], len))
return -EFAULT;
}
if (!strcmp(name, "src_min")) {
len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_min) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
if (copy_from_user(buf, &user_buffer[i], len))
return -EFAULT;
buf[len] = 0;
}
if (!strcmp(name, "src_max")) {
len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_max) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
if (copy_from_user(buf, &user_buffer[i], len))
return -EFAULT;
buf[len] = 0;
memcpy(old_dmac, pkt_dev->dst_mac, ETH_ALEN);
len = strn_len(&user_buffer[i], sizeof(valstr) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
memset(valstr, 0, sizeof(valstr));
if (copy_from_user(valstr, &user_buffer[i], len))
return -EFAULT;
memcpy(old_smac, pkt_dev->src_mac, ETH_ALEN);
len = strn_len(&user_buffer[i], sizeof(valstr) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
memset(valstr, 0, sizeof(valstr));
if (copy_from_user(valstr, &user_buffer[i], len))
return -EFAULT;
if (!strcmp(name, "flows")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value > MAX_CFLOWS)
value = MAX_CFLOWS;
if (!strcmp(name, "flowlen")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->lflow = value;
sprintf(pg_result, "OK: flowlen=%u", pkt_dev->lflow);
if (!strcmp(name, "queue_map_min")) {
len = num_arg(&user_buffer[i], 5, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->queue_map_min = value;
sprintf(pg_result, "OK: queue_map_min=%u", pkt_dev->queue_map_min);
if (!strcmp(name, "queue_map_max")) {
len = num_arg(&user_buffer[i], 5, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->queue_map_max = value;
sprintf(pg_result, "OK: queue_map_max=%u", pkt_dev->queue_map_max);
}
if (!strcmp(name, "mpls")) {
- unsigned n, offset;
+ unsigned n, cnt;
+
len = get_labels(&user_buffer[i], pkt_dev);
- if (len < 0) { return len; }
+ if (len < 0)
+ return len;
i += len;
- offset = sprintf(pg_result, "OK: mpls=");
+ cnt = sprintf(pg_result, "OK: mpls=");
for (n = 0; n < pkt_dev->nr_labels; n++)
- offset += sprintf(pg_result + offset,
- "%08x%s", ntohl(pkt_dev->labels[n]),
- n == pkt_dev->nr_labels-1 ? "" : ",");
+ cnt += sprintf(pg_result + cnt,
+ "%08x%s", ntohl(pkt_dev->labels[n]),
+ n == pkt_dev->nr_labels-1 ? "" : ",");
if (pkt_dev->nr_labels && pkt_dev->vlan_id != 0xffff) {
pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */
if (!strcmp(name, "vlan_id")) {
len = num_arg(&user_buffer[i], 4, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value <= 4095) {
pkt_dev->vlan_id = value; /* turn on VLAN */
if (!strcmp(name, "vlan_p")) {
len = num_arg(&user_buffer[i], 1, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 7) && (pkt_dev->vlan_id != 0xffff)) {
pkt_dev->vlan_p = value;
if (!strcmp(name, "vlan_cfi")) {
len = num_arg(&user_buffer[i], 1, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 1) && (pkt_dev->vlan_id != 0xffff)) {
pkt_dev->vlan_cfi = value;
if (!strcmp(name, "svlan_id")) {
len = num_arg(&user_buffer[i], 4, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 4095) && ((pkt_dev->vlan_id != 0xffff))) {
pkt_dev->svlan_id = value; /* turn on SVLAN */
if (!strcmp(name, "svlan_p")) {
len = num_arg(&user_buffer[i], 1, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 7) && (pkt_dev->svlan_id != 0xffff)) {
pkt_dev->svlan_p = value;
if (!strcmp(name, "svlan_cfi")) {
len = num_arg(&user_buffer[i], 1, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 1) && (pkt_dev->svlan_id != 0xffff)) {
pkt_dev->svlan_cfi = value;
if (!strcmp(name, "tos")) {
__u32 tmp_value = 0;
len = hex32_arg(&user_buffer[i], 2, &tmp_value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (len == 2) {
pkt_dev->tos = tmp_value;
if (!strcmp(name, "traffic_class")) {
__u32 tmp_value = 0;
len = hex32_arg(&user_buffer[i], 2, &tmp_value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (len == 2) {
pkt_dev->traffic_class = tmp_value;
static int pktgen_thread_show(struct seq_file *seq, void *v)
{
struct pktgen_thread *t = seq->private;
- struct pktgen_dev *pkt_dev;
+ const struct pktgen_dev *pkt_dev;
BUG_ON(!t);
remove_proc_entry(pkt_dev->entry->name, pg_proc_dir);
- pkt_dev->entry = create_proc_entry(dev->name, 0600,
- pg_proc_dir);
+ pkt_dev->entry = proc_create_data(dev->name, 0600,
+ pg_proc_dir,
+ &pktgen_if_fops,
+ pkt_dev);
if (!pkt_dev->entry)
printk(KERN_ERR "pktgen: can't move proc "
" entry for '%s'\n", dev->name);
{
struct net_device *dev = ptr;
+ if (!net_eq(dev_net(dev), &init_net))
+ return NOTIFY_DONE;
+
/* It is OK that we do not hold the group lock right now,
* as we run under the RTNL lock.
*/
return NOTIFY_DONE;
}
+static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev,
+ const char *ifname)
+{
+ char b[IFNAMSIZ+5];
+ int i = 0;
+
+ for (i = 0; ifname[i] != '@'; i++) {
+ if (i == IFNAMSIZ)
+ break;
+
+ b[i] = ifname[i];
+ }
+ b[i] = 0;
+
+ return dev_get_by_name(&init_net, b);
+}
+
+
/* Associate pktgen_dev with a device. */
static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname)
pkt_dev->odev = NULL;
}
- odev = dev_get_by_name(ifname);
+ odev = pktgen_dev_get_by_name(pkt_dev, ifname);
if (!odev) {
printk(KERN_ERR "pktgen: no such netdevice: \"%s\"\n", ifname);
return -ENODEV;
*/
static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
{
+ int ntxq;
+
if (!pkt_dev->odev) {
printk(KERN_ERR "pktgen: ERROR: pkt_dev->odev == NULL in "
"setup_inject.\n");
return;
}
+ /* make sure that we don't pick a non-existing transmit queue */
+ ntxq = pkt_dev->odev->real_num_tx_queues;
+
+ if (ntxq <= pkt_dev->queue_map_min) {
+ printk(KERN_WARNING "pktgen: WARNING: Requested "
+ "queue_map_min (zero-based) (%d) exceeds valid range "
+ "[0 - %d] for (%d) queues on %s, resetting\n",
+ pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq,
+ pkt_dev->odev->name);
+ pkt_dev->queue_map_min = ntxq - 1;
+ }
+ if (pkt_dev->queue_map_max >= ntxq) {
+ printk(KERN_WARNING "pktgen: WARNING: Requested "
+ "queue_map_max (zero-based) (%d) exceeds valid range "
+ "[0 - %d] for (%d) queues on %s, resetting\n",
+ pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq,
+ pkt_dev->odev->name);
+ pkt_dev->queue_map_max = ntxq - 1;
+ }
+
/* Default to the interface's mac if not explicitly set. */
if (is_zero_ether_addr(pkt_dev->src_mac))
*/
rcu_read_lock();
- if ((idev = __in6_dev_get(pkt_dev->odev)) != NULL) {
+ idev = __in6_dev_get(pkt_dev->odev);
+ if (idev) {
struct inet6_ifaddr *ifp;
read_lock_bh(&idev->lock);
pkt_dev->nflows = 0;
}
-static void spin(struct pktgen_dev *pkt_dev, __u64 spin_until_us)
+
+static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
{
- __u64 start;
- __u64 now;
+ ktime_t start_time, end_time;
+ s64 remaining;
+ struct hrtimer_sleeper t;
- start = now = getCurUs();
- printk(KERN_INFO "sleeping for %d\n", (int)(spin_until_us - now));
- while (now < spin_until_us) {
- /* TODO: optimize sleeping behavior */
- if (spin_until_us - now > jiffies_to_usecs(1) + 1)
- schedule_timeout_interruptible(1);
- else if (spin_until_us - now > 100) {
- if (!pkt_dev->running)
- return;
- if (need_resched())
+ hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_set_expires(&t.timer, spin_until);
+
+ remaining = ktime_to_us(hrtimer_expires_remaining(&t.timer));
+ if (remaining <= 0) {
+ pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay);
+ return;
+ }
+
+ start_time = ktime_now();
+ if (remaining < 100)
+ udelay(remaining); /* really small just spin */
+ else {
+ /* see do_nanosleep */
+ hrtimer_init_sleeper(&t, current);
+ do {
+ set_current_state(TASK_INTERRUPTIBLE);
+ hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
+ if (!hrtimer_active(&t.timer))
+ t.task = NULL;
+
+ if (likely(t.task))
schedule();
- }
- now = getCurUs();
+ hrtimer_cancel(&t.timer);
+ } while (t.task && pkt_dev->running && !signal_pending(current));
+ __set_current_state(TASK_RUNNING);
}
+ end_time = ktime_now();
- pkt_dev->idle_acc += now - start;
+ pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time));
+ pkt_dev->next_tx = ktime_add_ns(end_time, pkt_dev->delay);
}
static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev)
pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev);
}
-static inline int f_seen(struct pktgen_dev *pkt_dev, int flow)
+static inline int f_seen(const struct pktgen_dev *pkt_dev, int flow)
{
-
- if (pkt_dev->flows[flow].flags & F_INIT)
- return 1;
- else
- return 0;
+ return !!(pkt_dev->flows[flow].flags & F_INIT);
}
static inline int f_pick(struct pktgen_dev *pkt_dev)
if (pkt_dev->flows[flow].count >= pkt_dev->lflow) {
/* reset time */
pkt_dev->flows[flow].count = 0;
+ pkt_dev->flows[flow].flags = 0;
pkt_dev->curfl += 1;
if (pkt_dev->curfl >= pkt_dev->cflows)
pkt_dev->curfl = 0; /*reset */
}
} else {
flow = random32() % pkt_dev->cflows;
+ pkt_dev->curfl = flow;
- if (pkt_dev->flows[flow].count > pkt_dev->lflow)
+ if (pkt_dev->flows[flow].count > pkt_dev->lflow) {
pkt_dev->flows[flow].count = 0;
+ pkt_dev->flows[flow].flags = 0;
+ }
}
return pkt_dev->curfl;
struct xfrm_state *x = pkt_dev->flows[flow].x;
if (!x) {
/*slow path: we dont already have xfrm_state*/
- x = xfrm_stateonly_find((xfrm_address_t *)&pkt_dev->cur_daddr,
+ x = xfrm_stateonly_find(&init_net,
+ (xfrm_address_t *)&pkt_dev->cur_daddr,
(xfrm_address_t *)&pkt_dev->cur_saddr,
AF_INET,
pkt_dev->ipsmode,
if (x) {
pkt_dev->flows[flow].x = x;
set_pkt_overhead(pkt_dev);
- pkt_dev->pkt_overhead+=x->props.header_len;
+ pkt_dev->pkt_overhead += x->props.header_len;
}
}
}
#endif
+static void set_cur_queue_map(struct pktgen_dev *pkt_dev)
+{
+
+ if (pkt_dev->flags & F_QUEUE_MAP_CPU)
+ pkt_dev->cur_queue_map = smp_processor_id();
+
+ else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) {
+ __u16 t;
+ if (pkt_dev->flags & F_QUEUE_MAP_RND) {
+ t = random32() %
+ (pkt_dev->queue_map_max -
+ pkt_dev->queue_map_min + 1)
+ + pkt_dev->queue_map_min;
+ } else {
+ t = pkt_dev->cur_queue_map + 1;
+ if (t > pkt_dev->queue_map_max)
+ t = pkt_dev->queue_map_min;
+ }
+ pkt_dev->cur_queue_map = t;
+ }
+ pkt_dev->cur_queue_map = pkt_dev->cur_queue_map % pkt_dev->odev->real_num_tx_queues;
+}
+
/* Increment/randomize headers according to flags and current values
* for IP src/dest, UDP src/dst port, MAC-Addr src/dst
*/
mc = random32() % pkt_dev->src_mac_count;
else {
mc = pkt_dev->cur_src_mac_offset++;
- if (pkt_dev->cur_src_mac_offset >
+ if (pkt_dev->cur_src_mac_offset >=
pkt_dev->src_mac_count)
pkt_dev->cur_src_mac_offset = 0;
}
else {
mc = pkt_dev->cur_dst_mac_offset++;
- if (pkt_dev->cur_dst_mac_offset >
+ if (pkt_dev->cur_dst_mac_offset >=
pkt_dev->dst_mac_count) {
pkt_dev->cur_dst_mac_offset = 0;
}
if (!(pkt_dev->flags & F_IPV6)) {
- if ((imn = ntohl(pkt_dev->saddr_min)) < (imx =
- ntohl(pkt_dev->
- saddr_max))) {
+ imn = ntohl(pkt_dev->saddr_min);
+ imx = ntohl(pkt_dev->saddr_max);
+ if (imn < imx) {
__u32 t;
if (pkt_dev->flags & F_IPSRC_RND)
t = random32() % (imx - imn) + imn;
else {
t = ntohl(pkt_dev->cur_saddr);
t++;
- if (t > imx) {
+ if (t > imx)
t = imn;
- }
+
}
pkt_dev->cur_saddr = htonl(t);
}
t = random32() % (imx - imn) + imn;
s = htonl(t);
- while (LOOPBACK(s) || MULTICAST(s)
- || BADCLASS(s) || ZERONET(s)
- || LOCAL_MCAST(s)) {
+ while (ipv4_is_loopback(s) ||
+ ipv4_is_multicast(s) ||
+ ipv4_is_lbcast(s) ||
+ ipv4_is_zeronet(s) ||
+ ipv4_is_local_multicast(s)) {
t = random32() % (imx - imn) + imn;
s = htonl(t);
}
pkt_dev->cur_pkt_size = t;
}
- if (pkt_dev->queue_map_min < pkt_dev->queue_map_max) {
- __u16 t;
- if (pkt_dev->flags & F_QUEUE_MAP_RND) {
- t = random32() %
- (pkt_dev->queue_map_max - pkt_dev->queue_map_min + 1)
- + pkt_dev->queue_map_min;
- } else {
- t = pkt_dev->cur_queue_map + 1;
- if (t > pkt_dev->queue_map_max)
- t = pkt_dev->queue_map_min;
- }
- pkt_dev->cur_queue_map = t;
- }
+ set_cur_queue_map(pkt_dev);
pkt_dev->flows[flow].count++;
}
spin_lock(&x->lock);
iph = ip_hdr(skb);
- err = x->mode->output(x, skb);
+ err = x->outer_mode->output(x, skb);
if (err)
goto error;
err = x->type->output(x, skb);
if (err)
goto error;
- x->curlft.bytes +=skb->len;
+ x->curlft.bytes += skb->len;
x->curlft.packets++;
- spin_unlock(&x->lock);
-
error:
spin_unlock(&x->lock);
return err;
}
-static inline void free_SAs(struct pktgen_dev *pkt_dev)
+static void free_SAs(struct pktgen_dev *pkt_dev)
{
if (pkt_dev->cflows) {
/* let go of the SAs if we have them */
int i = 0;
- for (; i < pkt_dev->nflows; i++){
+ for (; i < pkt_dev->cflows; i++) {
struct xfrm_state *x = pkt_dev->flows[i].x;
if (x) {
xfrm_state_put(x);
}
}
-static inline int process_ipsec(struct pktgen_dev *pkt_dev,
+static int process_ipsec(struct pktgen_dev *pkt_dev,
struct sk_buff *skb, __be16 protocol)
{
if (pkt_dev->flags & F_IPSEC_ON) {
int ret;
__u8 *eth;
nhead = x->props.header_len - skb_headroom(skb);
- if (nhead >0) {
+ if (nhead > 0) {
ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC);
if (ret < 0) {
printk(KERN_ERR "Error expanding "
- "ipsec packet %d\n",ret);
- return 0;
+ "ipsec packet %d\n", ret);
+ goto err;
}
}
ret = pktgen_output_ipsec(skb, pkt_dev);
if (ret) {
printk(KERN_ERR "Error creating ipsec "
- "packet %d\n",ret);
- kfree_skb(skb);
- return 0;
+ "packet %d\n", ret);
+ goto err;
}
/* restore ll */
eth = (__u8 *) skb_push(skb, ETH_HLEN);
memcpy(eth, pkt_dev->hh, 12);
- *(u16 *) & eth[12] = protocol;
+ *(u16 *) ð[12] = protocol;
}
}
return 1;
+err:
+ kfree_skb(skb);
+ return 0;
}
#endif
static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev)
{
unsigned i;
- for (i = 0; i < pkt_dev->nr_labels; i++) {
+ for (i = 0; i < pkt_dev->nr_labels; i++)
*mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM;
- }
+
mpls--;
*mpls |= MPLS_STACK_BOTTOM;
}
__be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */
__be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */
__be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */
-
+ u16 queue_map;
if (pkt_dev->nr_labels)
protocol = htons(ETH_P_MPLS_UC);
/* Update any of the values, used when we're incrementing various
* fields.
*/
+ queue_map = pkt_dev->cur_queue_map;
mod_cur_headers(pkt_dev);
datalen = (odev->hard_header_len + 16) & ~0xf;
- skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + datalen +
- pkt_dev->pkt_overhead, GFP_ATOMIC);
+ skb = __netdev_alloc_skb(odev,
+ pkt_dev->cur_pkt_size + 64
+ + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
return NULL;
skb->network_header = skb->tail;
skb->transport_header = skb->network_header + sizeof(struct iphdr);
skb_put(skb, sizeof(struct iphdr) + sizeof(struct udphdr));
- skb->queue_mapping = pkt_dev->cur_queue_map;
-
+ skb_set_queue_mapping(skb, queue_map);
iph = ip_hdr(skb);
udph = udp_hdr(skb);
iph->protocol = IPPROTO_UDP; /* UDP */
iph->saddr = pkt_dev->cur_saddr;
iph->daddr = pkt_dev->cur_daddr;
+ iph->id = htons(pkt_dev->ip_id);
+ pkt_dev->ip_id++;
iph->frag_off = 0;
iplen = 20 + 8 + datalen;
iph->tot_len = htons(iplen);
skb->dev = odev;
skb->pkt_type = PACKET_HOST;
- if (pkt_dev->nfrags <= 0)
+ if (pkt_dev->nfrags <= 0) {
pgh = (struct pktgen_hdr *)skb_put(skb, datalen);
- else {
+ memset(pgh + 1, 0, datalen - sizeof(struct pktgen_hdr));
+ } else {
int frags = pkt_dev->nfrags;
- int i;
+ int i, len;
pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8);
if (frags > MAX_SKB_FRAGS)
frags = MAX_SKB_FRAGS;
if (datalen > frags * PAGE_SIZE) {
- skb_put(skb, datalen - frags * PAGE_SIZE);
+ len = datalen - frags * PAGE_SIZE;
+ memset(skb_put(skb, len), 0, len);
datalen = frags * PAGE_SIZE;
}
i = 0;
while (datalen > 0) {
- struct page *page = alloc_pages(GFP_KERNEL, 0);
+ struct page *page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
skb_shinfo(skb)->frags[i].page = page;
skb_shinfo(skb)->frags[i].page_offset = 0;
skb_shinfo(skb)->frags[i].size =
}
}
- /* Stamp the time, and sequence number, convert them to network byte order */
-
+ /* Stamp the time, and sequence number,
+ * convert them to network byte order
+ */
if (pgh) {
struct timeval timestamp;
unsigned int prefixlen = 0;
unsigned int suffixlen = 0;
__be32 tmp;
+ char *pos;
for (i = 0; i < 16; i++)
ip[i] = 0;
}
s++;
}
- {
- char *tmp;
- u = simple_strtoul(s, &tmp, 16);
- i = tmp - s;
- }
+ u = simple_strtoul(s, &pos, 16);
+ i = pos - s;
if (!i)
return 0;
if (prefixlen == 12 && s[i] == '.') {
len++;
} else if (suffixlen != 0)
break;
- {
- char *tmp;
- u = simple_strtol(s, &tmp, 16);
- i = tmp - s;
- }
+
+ u = simple_strtol(s, &pos, 16);
+ i = pos - s;
if (!i) {
if (*s)
len--;
__be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */
__be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */
__be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */
+ u16 queue_map;
if (pkt_dev->nr_labels)
protocol = htons(ETH_P_MPLS_UC);
/* Update any of the values, used when we're incrementing various
* fields.
*/
+ queue_map = pkt_dev->cur_queue_map;
mod_cur_headers(pkt_dev);
- skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16 +
- pkt_dev->pkt_overhead, GFP_ATOMIC);
+ skb = __netdev_alloc_skb(odev,
+ pkt_dev->cur_pkt_size + 64
+ + 16 + pkt_dev->pkt_overhead, GFP_NOWAIT);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
return NULL;
skb->network_header = skb->tail;
skb->transport_header = skb->network_header + sizeof(struct ipv6hdr);
skb_put(skb, sizeof(struct ipv6hdr) + sizeof(struct udphdr));
- skb->queue_mapping = pkt_dev->cur_queue_map;
-
+ skb_set_queue_mapping(skb, queue_map);
iph = ipv6_hdr(skb);
udph = udp_hdr(skb);
memcpy(eth, pkt_dev->hh, 12);
- *(__be16 *) & eth[12] = protocol;
+ *(__be16 *) ð[12] = protocol;
/* Eth + IPh + UDPh + mpls */
datalen = pkt_dev->cur_pkt_size - 14 -
}
}
- /* Stamp the time, and sequence number, convert them to network byte order */
- /* should we update cloned packets too ? */
+ /* Stamp the time, and sequence number,
+ * convert them to network byte order
+ * should we update cloned packets too ?
+ */
if (pgh) {
struct timeval timestamp;
return skb;
}
-static inline struct sk_buff *fill_packet(struct net_device *odev,
- struct pktgen_dev *pkt_dev)
+static struct sk_buff *fill_packet(struct net_device *odev,
+ struct pktgen_dev *pkt_dev)
{
if (pkt_dev->flags & F_IPV6)
return fill_packet_ipv6(odev, pkt_dev);
pktgen_clear_counters(pkt_dev);
pkt_dev->running = 1; /* Cranke yeself! */
pkt_dev->skb = NULL;
- pkt_dev->started_at = getCurUs();
- pkt_dev->next_tx_us = getCurUs(); /* Transmit immediately */
- pkt_dev->next_tx_ns = 0;
+ pkt_dev->started_at =
+ pkt_dev->next_tx = ktime_now();
+
set_pkt_overhead(pkt_dev);
strcpy(pkt_dev->result, "Starting");
mutex_unlock(&pktgen_thread_lock);
}
-static int thread_is_running(struct pktgen_thread *t)
+static int thread_is_running(const struct pktgen_thread *t)
{
- struct pktgen_dev *pkt_dev;
- int res = 0;
+ const struct pktgen_dev *pkt_dev;
list_for_each_entry(pkt_dev, &t->if_list, list)
- if (pkt_dev->running) {
- res = 1;
- break;
- }
- return res;
+ if (pkt_dev->running)
+ return 1;
+ return 0;
}
static int pktgen_wait_thread_run(struct pktgen_thread *t)
mutex_unlock(&pktgen_thread_lock);
- schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */
+ /* Propagate thread->control */
+ schedule_timeout_interruptible(msecs_to_jiffies(125));
pktgen_wait_all_threads_run();
}
-static void show_results(struct pktgen_dev *pkt_dev, int nr_frags)
+static void pktgen_reset_all_threads(void)
{
- __u64 total_us, bps, mbps, pps, idle;
- char *p = pkt_dev->result;
+ struct pktgen_thread *t;
- total_us = pkt_dev->stopped_at - pkt_dev->started_at;
+ pr_debug("pktgen: entering pktgen_reset_all_threads.\n");
- idle = pkt_dev->idle_acc;
+ mutex_lock(&pktgen_thread_lock);
- p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n",
- (unsigned long long)total_us,
- (unsigned long long)(total_us - idle),
- (unsigned long long)idle,
- (unsigned long long)pkt_dev->sofar,
- pkt_dev->cur_pkt_size, nr_frags);
+ list_for_each_entry(t, &pktgen_threads, th_list)
+ t->control |= (T_REMDEVALL);
- pps = pkt_dev->sofar * USEC_PER_SEC;
+ mutex_unlock(&pktgen_thread_lock);
- while ((total_us >> 32) != 0) {
- pps >>= 1;
- total_us >>= 1;
- }
+ /* Propagate thread->control */
+ schedule_timeout_interruptible(msecs_to_jiffies(125));
+
+ pktgen_wait_all_threads_run();
+}
+
+static void show_results(struct pktgen_dev *pkt_dev, int nr_frags)
+{
+ __u64 bps, mbps, pps;
+ char *p = pkt_dev->result;
+ ktime_t elapsed = ktime_sub(pkt_dev->stopped_at,
+ pkt_dev->started_at);
+ ktime_t idle = ns_to_ktime(pkt_dev->idle_acc);
+
+ p += sprintf(p, "OK: %llu(c%llu+d%llu) nsec, %llu (%dbyte,%dfrags)\n",
+ (unsigned long long)ktime_to_us(elapsed),
+ (unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)),
+ (unsigned long long)ktime_to_us(idle),
+ (unsigned long long)pkt_dev->sofar,
+ pkt_dev->cur_pkt_size, nr_frags);
- do_div(pps, total_us);
+ pps = div64_u64(pkt_dev->sofar * NSEC_PER_SEC,
+ ktime_to_ns(elapsed));
bps = pps * 8 * pkt_dev->cur_pkt_size;
}
/* Set stopped-at timer, remove from running list, do counters & statistics */
-
static int pktgen_stop_device(struct pktgen_dev *pkt_dev)
{
int nr_frags = pkt_dev->skb ? skb_shinfo(pkt_dev->skb)->nr_frags : -1;
return -EINVAL;
}
- pkt_dev->stopped_at = getCurUs();
+ kfree_skb(pkt_dev->skb);
+ pkt_dev->skb = NULL;
+ pkt_dev->stopped_at = ktime_now();
pkt_dev->running = 0;
show_results(pkt_dev, nr_frags);
continue;
if (best == NULL)
best = pkt_dev;
- else if (pkt_dev->next_tx_us < best->next_tx_us)
+ else if (ktime_lt(pkt_dev->next_tx, best->next_tx))
best = pkt_dev;
}
if_unlock(t);
list_for_each_entry(pkt_dev, &t->if_list, list) {
pktgen_stop_device(pkt_dev);
- if (pkt_dev->skb)
- kfree_skb(pkt_dev->skb);
-
- pkt_dev->skb = NULL;
}
if_unlock(t);
if (!cur->removal_mark)
continue;
- if (cur->skb)
- kfree_skb(cur->skb);
+ kfree_skb(cur->skb);
cur->skb = NULL;
pktgen_remove_device(t, cur);
list_for_each_safe(q, n, &t->if_list) {
cur = list_entry(q, struct pktgen_dev, list);
- if (cur->skb)
- kfree_skb(cur->skb);
+ kfree_skb(cur->skb);
cur->skb = NULL;
pktgen_remove_device(t, cur);
mutex_unlock(&pktgen_thread_lock);
}
-static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
+static void pktgen_resched(struct pktgen_dev *pkt_dev)
{
- struct net_device *odev = NULL;
- __u64 idle_start = 0;
- int ret;
-
- odev = pkt_dev->odev;
-
- if (pkt_dev->delay_us || pkt_dev->delay_ns) {
- u64 now;
-
- now = getCurUs();
- if (now < pkt_dev->next_tx_us)
- spin(pkt_dev, pkt_dev->next_tx_us);
+ ktime_t idle_start = ktime_now();
+ schedule();
+ pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start));
+}
- /* This is max DELAY, this has special meaning of
- * "never transmit"
- */
- if (pkt_dev->delay_us == 0x7FFFFFFF) {
- pkt_dev->next_tx_us = getCurUs() + pkt_dev->delay_us;
- pkt_dev->next_tx_ns = pkt_dev->delay_ns;
- goto out;
- }
- }
+static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev)
+{
+ ktime_t idle_start = ktime_now();
- if ((netif_queue_stopped(odev) ||
- (pkt_dev->skb &&
- netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping))) ||
- need_resched()) {
- idle_start = getCurUs();
+ while (atomic_read(&(pkt_dev->skb->users)) != 1) {
+ if (signal_pending(current))
+ break;
- if (!netif_running(odev)) {
- pktgen_stop_device(pkt_dev);
- if (pkt_dev->skb)
- kfree_skb(pkt_dev->skb);
- pkt_dev->skb = NULL;
- goto out;
- }
if (need_resched())
- schedule();
-
- pkt_dev->idle_acc += getCurUs() - idle_start;
-
- if (netif_queue_stopped(odev) ||
- netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping)) {
- pkt_dev->next_tx_us = getCurUs(); /* TODO */
- pkt_dev->next_tx_ns = 0;
- goto out; /* Try the next interface */
- }
+ pktgen_resched(pkt_dev);
+ else
+ cpu_relax();
}
+ pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start));
+}
- if (pkt_dev->last_ok || !pkt_dev->skb) {
- if ((++pkt_dev->clone_count >= pkt_dev->clone_skb)
- || (!pkt_dev->skb)) {
- /* build a new pkt */
- if (pkt_dev->skb)
- kfree_skb(pkt_dev->skb);
+static void pktgen_xmit(struct pktgen_dev *pkt_dev)
+{
+ struct net_device *odev = pkt_dev->odev;
+ netdev_tx_t (*xmit)(struct sk_buff *, struct net_device *)
+ = odev->netdev_ops->ndo_start_xmit;
+ struct netdev_queue *txq;
+ u16 queue_map;
+ int ret;
- pkt_dev->skb = fill_packet(odev, pkt_dev);
- if (pkt_dev->skb == NULL) {
- printk(KERN_ERR "pktgen: ERROR: couldn't "
- "allocate skb in fill_packet.\n");
- schedule();
- pkt_dev->clone_count--; /* back out increment, OOM */
- goto out;
- }
- pkt_dev->allocated_skbs++;
- pkt_dev->clone_count = 0; /* reset counter */
- }
+ /* If device is offline, then don't send */
+ if (unlikely(!netif_running(odev) || !netif_carrier_ok(odev))) {
+ pktgen_stop_device(pkt_dev);
+ return;
}
- netif_tx_lock_bh(odev);
- if (!netif_queue_stopped(odev) &&
- !netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping)) {
-
- atomic_inc(&(pkt_dev->skb->users));
- retry_now:
- ret = odev->hard_start_xmit(pkt_dev->skb, odev);
- if (likely(ret == NETDEV_TX_OK)) {
- pkt_dev->last_ok = 1;
- pkt_dev->sofar++;
- pkt_dev->seq_num++;
- pkt_dev->tx_bytes += pkt_dev->cur_pkt_size;
-
- } else if (ret == NETDEV_TX_LOCKED
- && (odev->features & NETIF_F_LLTX)) {
- cpu_relax();
- goto retry_now;
- } else { /* Retry it next time */
-
- atomic_dec(&(pkt_dev->skb->users));
+ /* This is max DELAY, this has special meaning of
+ * "never transmit"
+ */
+ if (unlikely(pkt_dev->delay == ULLONG_MAX)) {
+ pkt_dev->next_tx = ktime_add_ns(ktime_now(), ULONG_MAX);
+ return;
+ }
- if (debug && net_ratelimit())
- printk(KERN_INFO "pktgen: Hard xmit error\n");
+ /* If no skb or clone count exhausted then get new one */
+ if (!pkt_dev->skb || (pkt_dev->last_ok &&
+ ++pkt_dev->clone_count >= pkt_dev->clone_skb)) {
+ /* build a new pkt */
+ kfree_skb(pkt_dev->skb);
- pkt_dev->errors++;
- pkt_dev->last_ok = 0;
+ pkt_dev->skb = fill_packet(odev, pkt_dev);
+ if (pkt_dev->skb == NULL) {
+ printk(KERN_ERR "pktgen: ERROR: couldn't "
+ "allocate skb in fill_packet.\n");
+ schedule();
+ pkt_dev->clone_count--; /* back out increment, OOM */
+ return;
}
- pkt_dev->next_tx_us = getCurUs();
- pkt_dev->next_tx_ns = 0;
+ pkt_dev->allocated_skbs++;
+ pkt_dev->clone_count = 0; /* reset counter */
+ }
+
+ if (pkt_dev->delay && pkt_dev->last_ok)
+ spin(pkt_dev, pkt_dev->next_tx);
- pkt_dev->next_tx_us += pkt_dev->delay_us;
- pkt_dev->next_tx_ns += pkt_dev->delay_ns;
+ queue_map = skb_get_queue_mapping(pkt_dev->skb);
+ txq = netdev_get_tx_queue(odev, queue_map);
- if (pkt_dev->next_tx_ns > 1000) {
- pkt_dev->next_tx_us++;
- pkt_dev->next_tx_ns -= 1000;
- }
- }
+ __netif_tx_lock_bh(txq);
+ atomic_inc(&(pkt_dev->skb->users));
- else { /* Retry it next time */
+ if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq)))
+ ret = NETDEV_TX_BUSY;
+ else
+ ret = (*xmit)(pkt_dev->skb, odev);
+
+ switch (ret) {
+ case NETDEV_TX_OK:
+ txq_trans_update(txq);
+ pkt_dev->last_ok = 1;
+ pkt_dev->sofar++;
+ pkt_dev->seq_num++;
+ pkt_dev->tx_bytes += pkt_dev->cur_pkt_size;
+ break;
+ default: /* Drivers are not supposed to return other values! */
+ if (net_ratelimit())
+ pr_info("pktgen: %s xmit error: %d\n",
+ odev->name, ret);
+ pkt_dev->errors++;
+ /* fallthru */
+ case NETDEV_TX_LOCKED:
+ case NETDEV_TX_BUSY:
+ /* Retry it next time */
+ atomic_dec(&(pkt_dev->skb->users));
pkt_dev->last_ok = 0;
- pkt_dev->next_tx_us = getCurUs(); /* TODO */
- pkt_dev->next_tx_ns = 0;
}
-
- netif_tx_unlock_bh(odev);
+ __netif_tx_unlock_bh(txq);
/* If pkt_dev->count is zero, then run forever */
if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) {
- if (atomic_read(&(pkt_dev->skb->users)) != 1) {
- idle_start = getCurUs();
- while (atomic_read(&(pkt_dev->skb->users)) != 1) {
- if (signal_pending(current)) {
- break;
- }
- schedule();
- }
- pkt_dev->idle_acc += getCurUs() - idle_start;
- }
+ pktgen_wait_for_skb(pkt_dev);
/* Done with this */
pktgen_stop_device(pkt_dev);
- if (pkt_dev->skb)
- kfree_skb(pkt_dev->skb);
- pkt_dev->skb = NULL;
}
-out:;
}
/*
BUG_ON(smp_processor_id() != cpu);
init_waitqueue_head(&t->queue);
+ complete(&t->start_done);
- pr_debug("pktgen: starting pktgen/%d: pid=%d\n", cpu, current->pid);
+ pr_debug("pktgen: starting pktgen/%d: pid=%d\n",
+ cpu, task_pid_nr(current));
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
pkt_dev = next_to_run(t);
- if (!pkt_dev &&
- (t->control & (T_STOP | T_RUN | T_REMDEVALL | T_REMDEV))
- == 0) {
- prepare_to_wait(&(t->queue), &wait,
- TASK_INTERRUPTIBLE);
- schedule_timeout(HZ / 10);
- finish_wait(&(t->queue), &wait);
+ if (unlikely(!pkt_dev && t->control == 0)) {
+ wait_event_interruptible_timeout(t->queue,
+ t->control != 0,
+ HZ/10);
+ continue;
}
__set_current_state(TASK_RUNNING);
- if (pkt_dev)
+ if (likely(pkt_dev)) {
pktgen_xmit(pkt_dev);
+ if (need_resched())
+ pktgen_resched(pkt_dev);
+ else
+ cpu_relax();
+ }
+
if (t->control & T_STOP) {
pktgen_stop(t);
t->control &= ~(T_STOP);
pkt_dev->max_pkt_size = ETH_ZLEN;
pkt_dev->nfrags = 0;
pkt_dev->clone_skb = pg_clone_skb_d;
- pkt_dev->delay_us = pg_delay_d / 1000;
- pkt_dev->delay_ns = pg_delay_d % 1000;
+ pkt_dev->delay = pg_delay_d;
pkt_dev->count = pg_count_d;
pkt_dev->sofar = 0;
pkt_dev->udp_src_min = 9; /* sink port */
if (err)
goto out1;
- pkt_dev->entry = create_proc_entry(ifname, 0600, pg_proc_dir);
+ pkt_dev->entry = proc_create_data(ifname, 0600, pg_proc_dir,
+ &pktgen_if_fops, pkt_dev);
if (!pkt_dev->entry) {
printk(KERN_ERR "pktgen: cannot create %s/%s procfs entry.\n",
PG_PROC_DIR, ifname);
err = -EINVAL;
goto out2;
}
- pkt_dev->entry->proc_fops = &pktgen_if_fops;
- pkt_dev->entry->data = pkt_dev;
#ifdef CONFIG_XFRM
pkt_dev->ipsmode = XFRM_MODE_TRANSPORT;
pkt_dev->ipsproto = IPPROTO_ESP;
#ifdef CONFIG_XFRM
free_SAs(pkt_dev);
#endif
- if (pkt_dev->flows)
- vfree(pkt_dev->flows);
+ vfree(pkt_dev->flows);
kfree(pkt_dev);
return err;
}
INIT_LIST_HEAD(&t->if_list);
list_add_tail(&t->th_list, &pktgen_threads);
+ init_completion(&t->start_done);
p = kthread_create(pktgen_thread_worker, t, "kpktgend_%d", cpu);
if (IS_ERR(p)) {
kthread_bind(p, cpu);
t->tsk = p;
- pe = create_proc_entry(t->tsk->comm, 0600, pg_proc_dir);
+ pe = proc_create_data(t->tsk->comm, 0600, pg_proc_dir,
+ &pktgen_thread_fops, t);
if (!pe) {
printk(KERN_ERR "pktgen: cannot create %s/%s procfs entry.\n",
PG_PROC_DIR, t->tsk->comm);
return -EINVAL;
}
- pe->proc_fops = &pktgen_thread_fops;
- pe->data = t;
-
wake_up_process(p);
+ wait_for_completion(&t->start_done);
return 0;
}
#ifdef CONFIG_XFRM
free_SAs(pkt_dev);
#endif
- if (pkt_dev->flows)
- vfree(pkt_dev->flows);
+ vfree(pkt_dev->flows);
kfree(pkt_dev);
return 0;
}
pg_proc_dir = proc_mkdir(PG_PROC_DIR, init_net.proc_net);
if (!pg_proc_dir)
return -ENODEV;
- pg_proc_dir->owner = THIS_MODULE;
- pe = create_proc_entry(PGCTRL, 0600, pg_proc_dir);
+ pe = proc_create(PGCTRL, 0600, pg_proc_dir, &pktgen_fops);
if (pe == NULL) {
printk(KERN_ERR "pktgen: ERROR: cannot create %s "
"procfs entry.\n", PGCTRL);
return -EINVAL;
}
- pe->proc_fops = &pktgen_fops;
- pe->data = NULL;
-
/* Register us to receive netdevice events */
register_netdevice_notifier(&pktgen_notifier_block);
module_init(pg_init);
module_exit(pg_cleanup);
-MODULE_AUTHOR("Robert Olsson <robert.olsson@its.uu.se");
+MODULE_AUTHOR("Robert Olsson <robert.olsson@its.uu.se>");
MODULE_DESCRIPTION("Packet Generator tool");
MODULE_LICENSE("GPL");
+MODULE_VERSION(VERSION);
module_param(pg_count_d, int, 0);
+MODULE_PARM_DESC(pg_count_d, "Default number of packets to inject");
module_param(pg_delay_d, int, 0);
+MODULE_PARM_DESC(pg_delay_d, "Default delay between packets (nanoseconds)");
module_param(pg_clone_skb_d, int, 0);
+MODULE_PARM_DESC(pg_clone_skb_d, "Default number of copies of the same packet");
module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "Enable debugging of pktgen module");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff