*
* 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/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>
#endif
#include <asm/byteorder.h>
#include <linux/rcupdate.h>
-#include <asm/bitops.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"
+#define VERSION "pktgen v2.70: 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)
#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)
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)
-{
- 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)
{
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)
+static __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_if_show(struct seq_file *seq, void *v)
{
- int i;
struct pktgen_dev *pkt_dev = seq->private;
__u64 sa;
__u64 stopped;
__u64 now = getCurUs();
+ DECLARE_MAC_BUF(mac);
seq_printf(seq,
"Params: count %llu min_pkt_size: %u max_pkt_size: %u\n",
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, "%s ",
+ print_mac(mac, 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, "%s\n", print_mac(mac, pkt_dev->dst_mac));
seq_printf(seq,
" udp_src_min: %d udp_src_max: %d udp_dst_min: %d udp_dst_max: %d\n",
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*/
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, "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 */
{
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 <= num_online_cpus() && (pkt_dev->flags & F_QUEUE_MAP_CPU)) {
+ printk(KERN_WARNING "pktgen: WARNING: QUEUE_MAP_CPU "
+ "disabled because CPU count (%d) exceeds number ",
+ num_online_cpus());
+ printk(KERN_WARNING "pktgen: WARNING: of tx queues "
+ "(%d) on %s \n", ntxq, pkt_dev->odev->name);
+ pkt_dev->flags &= ~F_QUEUE_MAP_CPU;
+ }
+ if (ntxq <= pkt_dev->queue_map_min) {
+ printk(KERN_WARNING "pktgen: WARNING: Requested "
+ "queue_map_min (%d) exceeds number of tx\n",
+ pkt_dev->queue_map_min);
+ printk(KERN_WARNING "pktgen: WARNING: queues (%d) on "
+ "%s, resetting\n", ntxq, pkt_dev->odev->name);
+ pkt_dev->queue_map_min = ntxq - 1;
+ }
+ if (ntxq <= pkt_dev->queue_map_max) {
+ printk(KERN_WARNING "pktgen: WARNING: Requested "
+ "queue_map_max (%d) exceeds number of tx\n",
+ pkt_dev->queue_map_max);
+ printk(KERN_WARNING "pktgen: WARNING: queues (%d) on "
+ "%s, resetting\n", 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))
__u64 now;
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)
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;
}
}
#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;
+ }
+}
+
/* 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;
}
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);
x->curlft.bytes +=skb->len;
x->curlft.packets++;
- spin_unlock(&x->lock);
-
error:
spin_unlock(&x->lock);
return err;
if (ret < 0) {
printk(KERN_ERR "Error expanding "
"ipsec packet %d\n",ret);
- return 0;
+ goto err;
}
}
if (ret) {
printk(KERN_ERR "Error creating ipsec "
"packet %d\n",ret);
- kfree_skb(skb);
- return 0;
+ goto err;
}
/* restore ll */
eth = (__u8 *) skb_push(skb, ETH_HLEN);
}
}
return 1;
+err:
+ kfree_skb(skb);
+ return 0;
}
#endif
__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->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);
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 +
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);
static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
{
struct net_device *odev = NULL;
+ struct netdev_queue *txq;
__u64 idle_start = 0;
+ u16 queue_map;
int ret;
odev = pkt_dev->odev;
}
}
- if ((netif_queue_stopped(odev) ||
- (pkt_dev->skb &&
- netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping))) ||
+ if (!pkt_dev->skb) {
+ set_cur_queue_map(pkt_dev);
+ queue_map = pkt_dev->cur_queue_map;
+ } else {
+ queue_map = skb_get_queue_mapping(pkt_dev->skb);
+ }
+
+ txq = netdev_get_tx_queue(odev, queue_map);
+ if (netif_tx_queue_stopped(txq) ||
+ netif_tx_queue_frozen(txq) ||
need_resched()) {
idle_start = getCurUs();
pkt_dev->idle_acc += getCurUs() - idle_start;
- if (netif_queue_stopped(odev) ||
- netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping)) {
+ if (netif_tx_queue_stopped(txq) ||
+ netif_tx_queue_frozen(txq)) {
pkt_dev->next_tx_us = getCurUs(); /* TODO */
pkt_dev->next_tx_ns = 0;
goto out; /* Try the next interface */
}
}
- netif_tx_lock_bh(odev);
- if (!netif_queue_stopped(odev) &&
- !netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping)) {
+ /* fill_packet() might have changed the queue */
+ queue_map = skb_get_queue_mapping(pkt_dev->skb);
+ txq = netdev_get_tx_queue(odev, queue_map);
+
+ __netif_tx_lock_bh(txq);
+ if (!netif_tx_queue_stopped(txq) &&
+ !netif_tx_queue_frozen(txq)) {
atomic_inc(&(pkt_dev->skb->users));
retry_now:
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)) {
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);
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;
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;
}
printk(KERN_INFO "%s", version);
- pg_proc_dir = proc_mkdir(PG_PROC_DIR, proc_net);
+ 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);
- proc_net_remove(PG_PROC_DIR);
+ proc_net_remove(&init_net, PG_PROC_DIR);
return -EINVAL;
}
- pe->proc_fops = &pktgen_fops;
- pe->data = NULL;
-
/* Register us to receive netdevice events */
register_netdevice_notifier(&pktgen_notifier_block);
"all threads\n");
unregister_netdevice_notifier(&pktgen_notifier_block);
remove_proc_entry(PGCTRL, pg_proc_dir);
- proc_net_remove(PG_PROC_DIR);
+ proc_net_remove(&init_net, PG_PROC_DIR);
return -ENODEV;
}
/* Clean up proc file system */
remove_proc_entry(PGCTRL, pg_proc_dir);
- proc_net_remove(PG_PROC_DIR);
+ proc_net_remove(&init_net, PG_PROC_DIR);
}
module_init(pg_init);