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@xxxxxxxxxx>
---
include/net/tap.h | 1 -
net/tap-aix.c | 3 +-
net/tap-bsd.c | 3 +-
net/tap-haiku.c | 3 +-
net/tap-linux.c | 4 +-
net/tap-solaris.c | 3 +-
net/tap.c | 158 +++++++++++++++++++++++++++++++++++++++++------------
net/tap_int.h | 3 +-
qapi-schema.json | 5 +-
9 files changed, 139 insertions(+), 44 deletions(-)
diff --git a/include/net/tap.h b/include/net/tap.h
index c523ff0..0caf8c4 100644
--- a/include/net/tap.h
+++ b/include/net/tap.h
@@ -37,7 +37,6 @@ void tap_set_offload(NetClientState *nc, int csum, int tso4, int tso6, int ecn,
void tap_set_vnet_hdr_len(NetClientState *nc, int len);
int tap_enable(NetClientState *nc);
int tap_disable(NetClientState *nc);
-int tap_get_ifname(NetClientState *nc, char *ifname);
int tap_get_fd(NetClientState *nc);
diff --git a/net/tap-aix.c b/net/tap-aix.c
index e760e9a..804d164 100644
--- a/net/tap-aix.c
+++ b/net/tap-aix.c
@@ -25,7 +25,8 @@
#include "tap_int.h"
#include <stdio.h>
-int tap_open(char *ifname, int ifname_size, int *vnet_hdr, int vnet_hdr_required)
+int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
+ int vnet_hdr_required, int mq_required)
{
fprintf(stderr, "no tap on AIX\n");
return -1;
diff --git a/net/tap-bsd.c b/net/tap-bsd.c
index 4f22109..bcdb268 100644
--- a/net/tap-bsd.c
+++ b/net/tap-bsd.c
@@ -33,7 +33,8 @@
#include <net/if_tap.h>
#endif
-int tap_open(char *ifname, int ifname_size, int *vnet_hdr, int vnet_hdr_required)
+int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
+ int vnet_hdr_required, int mq_required)
{
int fd;
#ifdef TAPGIFNAME
diff --git a/net/tap-haiku.c b/net/tap-haiku.c
index b3b5fbb..e5ce436 100644
--- a/net/tap-haiku.c
+++ b/net/tap-haiku.c
@@ -25,7 +25,8 @@
#include "tap_int.h"
#include <stdio.h>
-int tap_open(char *ifname, int ifname_size, int *vnet_hdr, int vnet_hdr_required)
+int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
+ int vnet_hdr_required, int mq_required)
{
fprintf(stderr, "no tap on Haiku\n");
return -1;
diff --git a/net/tap-linux.c b/net/tap-linux.c
index 6827c2a..a1a6128 100644
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -36,12 +36,12 @@
#define PATH_NET_TUN "/dev/net/tun"
-int tap_open(char *ifname, int ifname_size, int *vnet_hdr, int vnet_hdr_required)
+int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
+ int vnet_hdr_required, int mq_required)
{
struct ifreq ifr;
int fd, ret;
int len = sizeof(struct virtio_net_hdr);
- int mq_required = 0;
TFR(fd = open(PATH_NET_TUN, O_RDWR));
if (fd < 0) {
diff --git a/net/tap-solaris.c b/net/tap-solaris.c
index 214d95e..9c7278f 100644
--- a/net/tap-solaris.c
+++ b/net/tap-solaris.c
@@ -173,7 +173,8 @@ static int tap_alloc(char *dev, size_t dev_size)
return tap_fd;
}
-int tap_open(char *ifname, int ifname_size, int *vnet_hdr, int vnet_hdr_required)
+int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
+ int vnet_hdr_required, int mq_required)
{
char dev[10]="";
int fd;
diff --git a/net/tap.c b/net/tap.c
index 95e557b..072e166 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -560,17 +560,10 @@ int net_init_bridge(const NetClientOptions *opts, const char *name,
static int net_tap_init(const NetdevTapOptions *tap, int *vnet_hdr,
const char *setup_script, char *ifname,
- size_t ifname_sz)
+ size_t ifname_sz, int mq_required)
{
int fd, vnet_hdr_required;
- if (tap->has_ifname) {
- pstrcpy(ifname, ifname_sz, tap->ifname);
- } else {
- assert(ifname_sz > 0);
- ifname[0] = '\0';
- }
-
if (tap->has_vnet_hdr) {
*vnet_hdr = tap->vnet_hdr;
vnet_hdr_required = *vnet_hdr;
@@ -579,7 +572,8 @@ static int net_tap_init(const NetdevTapOptions *tap, int *vnet_hdr,
vnet_hdr_required = 0;
}
- TFR(fd = tap_open(ifname, ifname_sz, vnet_hdr, vnet_hdr_required));
+ TFR(fd = tap_open(ifname, ifname_sz, vnet_hdr, vnet_hdr_required,
+ mq_required));
if (fd < 0) {
return -1;
}
@@ -595,6 +589,8 @@ static int net_tap_init(const NetdevTapOptions *tap, int *vnet_hdr,
return fd;
}
+#define MAX_TAP_QUEUES 1024
+
static int net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
const char *model, const char *name,
const char *ifname, const char *script,
@@ -613,17 +609,12 @@ static int net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
return -1;
}
- if (tap->has_fd) {
+ if (tap->has_fd || tap->has_fds) {
snprintf(s->nc.info_str, sizeof(s->nc.info_str), "fd=%d", fd);
} else if (tap->has_helper) {
snprintf(s->nc.info_str, sizeof(s->nc.info_str), "helper=%s",
tap->helper);
} else {
- const char *downscript;
-
- downscript = tap->has_downscript ? tap->downscript :
- DEFAULT_NETWORK_DOWN_SCRIPT;
-
snprintf(s->nc.info_str, sizeof(s->nc.info_str),
"ifname=%s,script=%s,downscript=%s", ifname, script,
downscript);
@@ -654,7 +645,7 @@ static int net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
error_report("vhost-net requested but could not be initialized");
return -1;
}
- } else if (tap->has_vhostfd) {
+ } else if (tap->has_vhostfd || tap->has_vhostfds) {
error_report("vhostfd= is not valid without vhost");
return -1;
}
@@ -662,27 +653,54 @@ static int net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
return 0;
}
+static int get_fds(char *str, char *fds[], int max)
+{
+ char *ptr = str, *this;
+ size_t len = strlen(str);
+ int i = 0;
+
+ while (i < max && ptr < str + len) {
+ this = strchr(ptr, ':');
+
+ if (this == NULL) {
+ fds[i] = g_strdup(ptr);
+ } else {
+ fds[i] = g_strndup(ptr, this - ptr);
+ }
+
+ i++;
+ if (this == NULL) {
+ break;
+ } else {
+ ptr = this + 1;
+ }
+ }
+
+ return i;
+}
+
int net_init_tap(const NetClientOptions *opts, const char *name,
NetClientState *peer)
{
const NetdevTapOptions *tap;
-
- int fd, vnet_hdr = 0;
- const char *model;
-
+ int fd, vnet_hdr = 0, i = 0, queues;
/* for the no-fd, no-helper case */
const char *script = NULL; /* suppress wrong "uninit'd use" gcc warning */
const char *downscript = NULL;
+ const char *vhostfdname;
char ifname[128];
assert(opts->kind == NET_CLIENT_OPTIONS_KIND_TAP);
tap = opts->tap;
+ queues = tap->has_queues ? tap->queues : 1;
+ vhostfdname = tap->has_vhostfd ? tap->vhostfd : NULL;
if (tap->has_fd) {
if (tap->has_ifname || tap->has_script || tap->has_downscript ||
- tap->has_vnet_hdr || tap->has_helper) {
+ tap->has_vnet_hdr || tap->has_helper || tap->has_queues ||
+ tap->has_fds) {
error_report("ifname=, script=, downscript=, vnet_hdr=, "
- "and helper= are invalid with fd=");
+ "helper=, queues=, and fds= are invalid with fd=");
return -1;
}
@@ -695,13 +713,61 @@ int net_init_tap(const NetClientOptions *opts, const char *name,
vnet_hdr = tap_probe_vnet_hdr(fd);
- model = "tap";
+ if (net_init_tap_one(tap, peer, "tap", NULL, NULL,
+ script, downscript,
+ vhostfdname, vnet_hdr, fd)) {
+ return -1;
+ }
+ } else if (tap->has_fds) {
+ char *fds[MAX_TAP_QUEUES];
+ char *vhost_fds[MAX_TAP_QUEUES];
+ int nfds, nvhosts;
+
+ if (tap->has_ifname || tap->has_script || tap->has_downscript ||
+ tap->has_vnet_hdr || tap->has_helper || tap->has_queues ||
+ tap->has_fd) {
+ error_report("ifname=, script=, downscript=, vnet_hdr=, "
+ "helper=, queues=, and fd= are invalid with fds=");
+ return -1;
+ }
+
+ nfds = get_fds(tap->fds, fds, MAX_TAP_QUEUES);
+ if (tap->has_vhostfds) {
+ nvhosts = get_fds(tap->vhostfds, vhost_fds, MAX_TAP_QUEUES);
+ if (nfds != nvhosts) {
+ error_report("The number of fds passed does not match the "
+ "number of vhostfds passed");
+ return -1;
+ }
+ }
+
+ for (i = 0; i < nfds; i++) {
+ fd = monitor_handle_fd_param(cur_mon, fds[i]);
+ if (fd == -1) {
+ return -1;
+ }
+
+ fcntl(fd, F_SETFL, O_NONBLOCK);
+ if (i == 0) {
+ vnet_hdr = tap_probe_vnet_hdr(fd);
+ } else if (vnet_hdr != tap_probe_vnet_hdr(fd)) {
+ error_report("vnet_hdr not consistent across given tap fds");
+ return -1;
+ }
+
+ if (net_init_tap_one(tap, peer, "tap", name, ifname,
+ script, downscript,
+ tap->has_vhostfds ? vhost_fds[i] : NULL,
+ vnet_hdr, fd)) {
+ return -1;
+ }
+ }
} else if (tap->has_helper) {
if (tap->has_ifname || tap->has_script || tap->has_downscript ||
- tap->has_vnet_hdr) {
+ tap->has_vnet_hdr || tap->has_queues || tap->has_fds) {
error_report("ifname=, script=, downscript=, and vnet_hdr= "
- "are invalid with helper=");
+ "queues=, and fds= are invalid with helper=");
return -1;
}
@@ -711,26 +777,48 @@ int net_init_tap(const NetClientOptions *opts, const char *name,
}
fcntl(fd, F_SETFL, O_NONBLOCK);
-
vnet_hdr = tap_probe_vnet_hdr(fd);
- model = "bridge";
-
+ if (net_init_tap_one(tap, peer, "bridge", name, ifname,
+ script, downscript, vhostfdname,
+ vnet_hdr, fd)) {
+ return -1;
+ }
} else {
script = tap->has_script ? tap->script : DEFAULT_NETWORK_SCRIPT;
downscript = tap->has_downscript ? tap->downscript :
DEFAULT_NETWORK_DOWN_SCRIPT;
- fd = net_tap_init(tap, &vnet_hdr, script, ifname, sizeof ifname);
- if (fd == -1) {
- return -1;
+
+ if (tap->has_ifname) {
+ pstrcpy(ifname, sizeof ifname, tap->ifname);
+ } else {
+ ifname[0] = '\0';
}
- model = "tap";
+ for (i = 0; i < queues; i++) {
+ fd = net_tap_init(tap, &vnet_hdr, i >= 1 ? "no" : script,
+ ifname, sizeof ifname, queues > 1);
+ if (fd == -1) {
+ return -1;
+ }
+
+ if (queues > 1 && i == 0 && !tap->has_ifname) {
+ if (tap_fd_get_ifname(fd, ifname)) {
+ error_report("Fail to get ifname");
+ return -1;
+ }
+ }
+
+ if (net_init_tap_one(tap, peer, "tap", name, ifname,
+ i >= 1 ? "no" : script,
+ i >= 1 ? "no" : downscript,
+ vhostfdname, vnet_hdr, fd)) {
+ return -1;
+ }
+ }
}
- return net_init_tap_one(tap, peer, model, name, ifname, script,
- downscript, tap->has_vhostfd ? tap->vhostfd : NULL,
- vnet_hdr, fd);
+ return 0;
}
VHostNetState *tap_get_vhost_net(NetClientState *nc)
diff --git a/net/tap_int.h b/net/tap_int.h
index 125f83d..86bb224 100644
--- a/net/tap_int.h
+++ b/net/tap_int.h
@@ -32,7 +32,8 @@
#define DEFAULT_NETWORK_SCRIPT "/etc/qemu-ifup"
#define DEFAULT_NETWORK_DOWN_SCRIPT "/etc/qemu-ifdown"
-int tap_open(char *ifname, int ifname_size, int *vnet_hdr, int vnet_hdr_required);
+int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
+ int vnet_hdr_required, int mq_required);
ssize_t tap_read_packet(int tapfd, uint8_t *buf, int maxlen);
diff --git a/qapi-schema.json b/qapi-schema.json
index 6d7252b..4737800 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -2466,6 +2466,7 @@
'data': {
'*ifname': 'str',
'*fd': 'str',
+ '*fds': 'str',
'*script': 'str',
'*downscript': 'str',
'*helper': 'str',
@@ -2473,7 +2474,9 @@
'*vnet_hdr': 'bool',
'*vhost': 'bool',
'*vhostfd': 'str',
- '*vhostforce': 'bool' } }
+ '*vhostfds': 'str',
+ '*vhostforce': 'bool',
+ '*queues': 'uint32'} }
##
# @NetdevSocketOptions
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
