xemu/net/tap-solaris.c
Jason Wang 264986e2c8 tap: multiqueue support
Recently, linux support multiqueue tap which could let userspace call TUNSETIFF
for a signle device many times to create multiple file descriptors as
independent queues. User could also enable/disabe a specific queue through
TUNSETQUEUE.

The patch adds the generic infrastructure to create multiqueue taps. To achieve
this a new parameter "queues" were introduced to specify how many queues were
expected to be created for tap by qemu itself. Alternatively, management could
also pass multiple pre-created tap file descriptors separated with ':' through a
new parameter fds like -netdev tap,id=hn0,fds="X:Y:..:Z". Multiple vhost file
descriptors could also be passed in this way.

Each TAPState were still associated to a tap fd, which mean multiple TAPStates
were created when user needs multiqueue taps. Since each TAPState contains one
NetClientState, with the multiqueue nic support, an N peers of NetClientState
were built up.

A new parameter, mq_required were introduce in tap_open() to create multiqueue
tap fds.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2013-02-01 11:03:02 -06:00

244 lines
6.4 KiB
C

/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "tap_int.h"
#include "sysemu/sysemu.h"
#include <sys/stat.h>
#include <sys/ethernet.h>
#include <sys/sockio.h>
#include <netinet/arp.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h> // must come after ip.h
#include <netinet/udp.h>
#include <netinet/tcp.h>
#include <net/if.h>
#include <syslog.h>
#include <stropts.h>
#include "qemu/error-report.h"
ssize_t tap_read_packet(int tapfd, uint8_t *buf, int maxlen)
{
struct strbuf sbuf;
int f = 0;
sbuf.maxlen = maxlen;
sbuf.buf = (char *)buf;
return getmsg(tapfd, NULL, &sbuf, &f) >= 0 ? sbuf.len : -1;
}
#define TUNNEWPPA (('T'<<16) | 0x0001)
/*
* Allocate TAP device, returns opened fd.
* Stores dev name in the first arg(must be large enough).
*/
static int tap_alloc(char *dev, size_t dev_size)
{
int tap_fd, if_fd, ppa = -1;
static int ip_fd = 0;
char *ptr;
static int arp_fd = 0;
int ip_muxid, arp_muxid;
struct strioctl strioc_if, strioc_ppa;
int link_type = I_PLINK;
struct lifreq ifr;
char actual_name[32] = "";
memset(&ifr, 0x0, sizeof(ifr));
if( *dev ){
ptr = dev;
while( *ptr && !qemu_isdigit((int)*ptr) ) ptr++;
ppa = atoi(ptr);
}
/* Check if IP device was opened */
if( ip_fd )
close(ip_fd);
TFR(ip_fd = open("/dev/udp", O_RDWR, 0));
if (ip_fd < 0) {
syslog(LOG_ERR, "Can't open /dev/ip (actually /dev/udp)");
return -1;
}
TFR(tap_fd = open("/dev/tap", O_RDWR, 0));
if (tap_fd < 0) {
syslog(LOG_ERR, "Can't open /dev/tap");
return -1;
}
/* Assign a new PPA and get its unit number. */
strioc_ppa.ic_cmd = TUNNEWPPA;
strioc_ppa.ic_timout = 0;
strioc_ppa.ic_len = sizeof(ppa);
strioc_ppa.ic_dp = (char *)&ppa;
if ((ppa = ioctl (tap_fd, I_STR, &strioc_ppa)) < 0)
syslog (LOG_ERR, "Can't assign new interface");
TFR(if_fd = open("/dev/tap", O_RDWR, 0));
if (if_fd < 0) {
syslog(LOG_ERR, "Can't open /dev/tap (2)");
return -1;
}
if(ioctl(if_fd, I_PUSH, "ip") < 0){
syslog(LOG_ERR, "Can't push IP module");
return -1;
}
if (ioctl(if_fd, SIOCGLIFFLAGS, &ifr) < 0)
syslog(LOG_ERR, "Can't get flags\n");
snprintf (actual_name, 32, "tap%d", ppa);
pstrcpy(ifr.lifr_name, sizeof(ifr.lifr_name), actual_name);
ifr.lifr_ppa = ppa;
/* Assign ppa according to the unit number returned by tun device */
if (ioctl (if_fd, SIOCSLIFNAME, &ifr) < 0)
syslog (LOG_ERR, "Can't set PPA %d", ppa);
if (ioctl(if_fd, SIOCGLIFFLAGS, &ifr) <0)
syslog (LOG_ERR, "Can't get flags\n");
/* Push arp module to if_fd */
if (ioctl (if_fd, I_PUSH, "arp") < 0)
syslog (LOG_ERR, "Can't push ARP module (2)");
/* Push arp module to ip_fd */
if (ioctl (ip_fd, I_POP, NULL) < 0)
syslog (LOG_ERR, "I_POP failed\n");
if (ioctl (ip_fd, I_PUSH, "arp") < 0)
syslog (LOG_ERR, "Can't push ARP module (3)\n");
/* Open arp_fd */
TFR(arp_fd = open ("/dev/tap", O_RDWR, 0));
if (arp_fd < 0)
syslog (LOG_ERR, "Can't open %s\n", "/dev/tap");
/* Set ifname to arp */
strioc_if.ic_cmd = SIOCSLIFNAME;
strioc_if.ic_timout = 0;
strioc_if.ic_len = sizeof(ifr);
strioc_if.ic_dp = (char *)&ifr;
if (ioctl(arp_fd, I_STR, &strioc_if) < 0){
syslog (LOG_ERR, "Can't set ifname to arp\n");
}
if((ip_muxid = ioctl(ip_fd, I_LINK, if_fd)) < 0){
syslog(LOG_ERR, "Can't link TAP device to IP");
return -1;
}
if ((arp_muxid = ioctl (ip_fd, link_type, arp_fd)) < 0)
syslog (LOG_ERR, "Can't link TAP device to ARP");
close (if_fd);
memset(&ifr, 0x0, sizeof(ifr));
pstrcpy(ifr.lifr_name, sizeof(ifr.lifr_name), actual_name);
ifr.lifr_ip_muxid = ip_muxid;
ifr.lifr_arp_muxid = arp_muxid;
if (ioctl (ip_fd, SIOCSLIFMUXID, &ifr) < 0)
{
ioctl (ip_fd, I_PUNLINK , arp_muxid);
ioctl (ip_fd, I_PUNLINK, ip_muxid);
syslog (LOG_ERR, "Can't set multiplexor id");
}
snprintf(dev, dev_size, "tap%d", ppa);
return tap_fd;
}
int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
int vnet_hdr_required, int mq_required)
{
char dev[10]="";
int fd;
if( (fd = tap_alloc(dev, sizeof(dev))) < 0 ){
fprintf(stderr, "Cannot allocate TAP device\n");
return -1;
}
pstrcpy(ifname, ifname_size, dev);
if (*vnet_hdr) {
/* Solaris doesn't have IFF_VNET_HDR */
*vnet_hdr = 0;
if (vnet_hdr_required && !*vnet_hdr) {
error_report("vnet_hdr=1 requested, but no kernel "
"support for IFF_VNET_HDR available");
close(fd);
return -1;
}
}
fcntl(fd, F_SETFL, O_NONBLOCK);
return fd;
}
int tap_set_sndbuf(int fd, const NetdevTapOptions *tap)
{
return 0;
}
int tap_probe_vnet_hdr(int fd)
{
return 0;
}
int tap_probe_has_ufo(int fd)
{
return 0;
}
int tap_probe_vnet_hdr_len(int fd, int len)
{
return 0;
}
void tap_fd_set_vnet_hdr_len(int fd, int len)
{
}
void tap_fd_set_offload(int fd, int csum, int tso4,
int tso6, int ecn, int ufo)
{
}
int tap_fd_enable(int fd)
{
return -1;
}
int tap_fd_disable(int fd)
{
return -1;
}
int tap_fd_get_ifname(int fd, char *ifname)
{
return -1;
}