Jason Wang
2012-Jul-06 09:31 UTC
[RFC V3 0/5] Multiqueue support for tap and virtio-net/vhost
Hello all:
This seires is an update of last version of multiqueue support to add multiqueue
capability to both tap and virtio-net.
Some kinds of tap backends has (macvatp in linux) or would (tap) support
multiqueue. In such kind of tap backend, each file descriptor of a tap is a
qeueu and ioctls were prodived to attach an exist tap file descriptor to the
tun/tap device. So the patch let qemu to use this kind of backend, and let it
can transmit and receving packets through multiple file descriptors.
Patch 1 introduce a new help to get all matched options, after this patch, we
could pass multiple file descriptors to a signle netdev by:
qemu -netdev tap,id=h0,queues=2,fd=10,fd=11 ...
Patch 2 introduce generic helpers in tap to attach or detach a file descriptor
from a tap device, emulated nics could use this helper to enable/disable queues.
Patch 3 modifies the NICState to allow multiple VLANClientState to be stored in
it, with this patch, qemu has basic support of multiple capable tap backend.
Patch 4 implement 1:1 mapping of tx/rx virtqueue pairs with vhost_net backend.
Patch 5 converts virtio-net to multiqueue device, after this patch, multiqueue
virtio-net device could be specified by:
qemu -netdev tap,id=h0,queues=2 -device virtio-net-pci,netdev=h0,queues=2
Performace numbers:
I post them in the threads of RFC of multiqueue virtio-net driver:
http://www.spinics.net/lists/kvm/msg75386.html
Multiqueue with vhost shows improvemnt in TCP_RR, and degradate for small packet
transmission.
Changes from V2:
- split vhost patch from virtio-net
- add the support of queue number negotiation through control virtqueue
- hotplug, set_link and migration support
- bug fixes
Changes from V1:
- rebase to the latest
- fix memory leak in parse_netdev
- fix guest notifiers assignment/de-assignment
- changes the command lines to:
qemu -netdev tap,queues=2 -device virtio-net-pci,queues=2
References:
- V2 http://www.spinics.net/lists/kvm/msg74588.html
- V1 http://comments.gmane.org/gmane.comp.emulators.qemu/100481
Jason Wang (5):
option: introduce qemu_get_opt_all()
tap: multiqueue support
net: multiqueue support
vhost: multiqueue support
virtio-net: add multiqueue support
hw/dp8393x.c | 2 +-
hw/mcf_fec.c | 2 +-
hw/qdev-properties.c | 34 +++-
hw/qdev.h | 3 +-
hw/vhost.c | 53 ++++--
hw/vhost.h | 2 +
hw/vhost_net.c | 7 +-
hw/vhost_net.h | 2 +-
hw/virtio-net.c | 505 ++++++++++++++++++++++++++++++++++----------------
hw/virtio-net.h | 12 ++
net.c | 83 +++++++--
net.h | 16 ++-
net/tap-aix.c | 13 ++-
net/tap-bsd.c | 13 ++-
net/tap-haiku.c | 13 ++-
net/tap-linux.c | 56 ++++++-
net/tap-linux.h | 4 +
net/tap-solaris.c | 13 ++-
net/tap-win32.c | 11 +
net/tap.c | 199 +++++++++++++-------
net/tap.h | 7 +-
qemu-option.c | 19 ++
qemu-option.h | 2 +
23 files changed, 787 insertions(+), 284 deletions(-)
Sometimes, we need to pass option like -netdev tap,fd=100,fd=101,fd=102 which
can not be properly parsed by qemu_find_opt() because it only returns the first
matched option. So qemu_get_opt_all() were introduced to return an array of
pointers which contains all matched option.
Signed-off-by: Jason Wang <jasowang at redhat.com>
---
qemu-option.c | 19 +++++++++++++++++++
qemu-option.h | 2 ++
2 files changed, 21 insertions(+), 0 deletions(-)
diff --git a/qemu-option.c b/qemu-option.c
index bb3886c..9263125 100644
--- a/qemu-option.c
+++ b/qemu-option.c
@@ -545,6 +545,25 @@ static QemuOpt *qemu_opt_find(QemuOpts *opts, const char
*name)
return NULL;
}
+int qemu_opt_get_all(QemuOpts *opts, const char *name, const char **optp,
+ int max)
+{
+ QemuOpt *opt;
+ int index = 0;
+
+ QTAILQ_FOREACH_REVERSE(opt, &opts->head, QemuOptHead, next) {
+ if (strcmp(opt->name, name) == 0) {
+ if (index < max) {
+ optp[index++] = opt->str;
+ }
+ if (index == max) {
+ break;
+ }
+ }
+ }
+ return index;
+}
+
const char *qemu_opt_get(QemuOpts *opts, const char *name)
{
QemuOpt *opt = qemu_opt_find(opts, name);
diff --git a/qemu-option.h b/qemu-option.h
index 951dec3..3c9a273 100644
--- a/qemu-option.h
+++ b/qemu-option.h
@@ -106,6 +106,8 @@ struct QemuOptsList {
QemuOptDesc desc[];
};
+int qemu_opt_get_all(QemuOpts *opts, const char *name, const char **optp,
+ int max);
const char *qemu_opt_get(QemuOpts *opts, const char *name);
bool qemu_opt_get_bool(QemuOpts *opts, const char *name, bool defval);
uint64_t qemu_opt_get_number(QemuOpts *opts, const char *name, uint64_t
defval);
--
1.7.1
Some operating system ( such as Linux ) supports multiqueue tap, this is done
through attaching multiple sockets to the net device and expose multiple file
descriptors.
This patch let qemu utilizes this kind of backend, and introduces helpter for:
- creating a multiple capable tap device
- increase and decrease the number of queues by introducing helpter to attach or
detach a file descriptor to the device
Then qemu can use this as the infrastructures of emulating a multiple queue
capable network cards.
Signed-off-by: Jason Wang <jasowang at redhat.com>
---
net.c | 4 +
net/tap-aix.c | 13 +++-
net/tap-bsd.c | 13 +++-
net/tap-haiku.c | 13 +++-
net/tap-linux.c | 56 +++++++++++++++-
net/tap-linux.h | 4 +
net/tap-solaris.c | 13 +++-
net/tap-win32.c | 11 +++
net/tap.c | 197 ++++++++++++++++++++++++++++++++++-------------------
net/tap.h | 7 ++-
10 files changed, 253 insertions(+), 78 deletions(-)
diff --git a/net.c b/net.c
index 4aa416c..eabe830 100644
--- a/net.c
+++ b/net.c
@@ -978,6 +978,10 @@ static const struct {
.name = "vhostforce",
.type = QEMU_OPT_BOOL,
.help = "force vhost on for non-MSIX virtio guests",
+ }, {
+ .name = "queues",
+ .type = QEMU_OPT_NUMBER,
+ .help = "number of queues the backend can provides",
},
#endif /* _WIN32 */
{ /* end of list */ }
diff --git a/net/tap-aix.c b/net/tap-aix.c
index e19aaba..f111e0f 100644
--- a/net/tap-aix.c
+++ b/net/tap-aix.c
@@ -25,7 +25,8 @@
#include "net/tap.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 attach)
{
fprintf(stderr, "no tap on AIX\n");
return -1;
@@ -59,3 +60,13 @@ void tap_fd_set_offload(int fd, int csum, int tso4,
int tso6, int ecn, int ufo)
{
}
+
+int tap_fd_attach(int fd, const char *ifname)
+{
+ return -1;
+}
+
+int tap_fd_detach(int fd, const char *ifname)
+{
+ return -1;
+}
diff --git a/net/tap-bsd.c b/net/tap-bsd.c
index 937a94b..44f3421 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 attach)
{
int fd;
#ifdef TAPGIFNAME
@@ -145,3 +146,13 @@ void tap_fd_set_offload(int fd, int csum, int tso4,
int tso6, int ecn, int ufo)
{
}
+
+int tap_fd_attach(int fd, const char *ifname)
+{
+ return -1;
+}
+
+int tap_fd_detach(int fd, const char *ifname)
+{
+ return -1;
+}
diff --git a/net/tap-haiku.c b/net/tap-haiku.c
index 91dda8e..6fb6719 100644
--- a/net/tap-haiku.c
+++ b/net/tap-haiku.c
@@ -25,7 +25,8 @@
#include "net/tap.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 attach)
{
fprintf(stderr, "no tap on Haiku\n");
return -1;
@@ -59,3 +60,13 @@ void tap_fd_set_offload(int fd, int csum, int tso4,
int tso6, int ecn, int ufo)
{
}
+
+int tap_fd_attach(int fd, const char *ifname)
+{
+ return -1;
+}
+
+int tap_fd_detach(int fd, const char *ifname)
+{
+ return -1;
+}
diff --git a/net/tap-linux.c b/net/tap-linux.c
index 41d581b..ed0afe9 100644
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -35,7 +35,8 @@
#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 attach)
{
struct ifreq ifr;
int fd, ret;
@@ -47,6 +48,8 @@ int tap_open(char *ifname, int ifname_size, int *vnet_hdr, int
vnet_hdr_required
}
memset(&ifr, 0, sizeof(ifr));
ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
+ if (!attach)
+ ifr.ifr_flags |= IFF_MULTI_QUEUE;
if (*vnet_hdr) {
unsigned int features;
@@ -71,7 +74,11 @@ int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
int vnet_hdr_required
pstrcpy(ifr.ifr_name, IFNAMSIZ, ifname);
else
pstrcpy(ifr.ifr_name, IFNAMSIZ, "tap%d");
- ret = ioctl(fd, TUNSETIFF, (void *) &ifr);
+ if (attach) {
+ ifr.ifr_flags |= IFF_ATTACH_QUEUE;
+ ret = ioctl(fd, TUNSETQUEUE, (void *) &ifr);
+ } else
+ ret = ioctl(fd, TUNSETIFF, (void *) &ifr);
if (ret != 0) {
if (ifname[0] != '\0') {
error_report("could not configure %s (%s): %m",
PATH_NET_TUN, ifr.ifr_name);
@@ -197,3 +204,48 @@ void tap_fd_set_offload(int fd, int csum, int tso4,
}
}
}
+
+/* Attach a file descriptor to a TUN/TAP device. This descriptor should be
+ * detached before.
+ */
+int tap_fd_attach(int fd, const char *ifname)
+{
+ struct ifreq ifr;
+ int ret;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR | IFF_ATTACH_QUEUE;
+ pstrcpy(ifr.ifr_name, IFNAMSIZ, ifname);
+
+ ret = ioctl(fd, TUNSETQUEUE, (void *) &ifr);
+
+ if (ret != 0) {
+ error_report("could not attach to %s", ifname);
+ }
+
+ return ret;
+}
+
+/* Detach a file descriptor to a TUN/TAP device. This file descriptor must have
+ * been attach to a device.
+ */
+int tap_fd_detach(int fd, const char *ifname)
+{
+ struct ifreq ifr;
+ int ret;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR | IFF_DETACH_QUEUE;
+ pstrcpy(ifr.ifr_name, IFNAMSIZ, ifname);
+
+ ret = ioctl(fd, TUNSETQUEUE, (void *) &ifr);
+
+ if (ret != 0) {
+ error_report("could not detach to %s", ifname);
+ }
+
+ return ret;
+}
+
diff --git a/net/tap-linux.h b/net/tap-linux.h
index 659e981..648d29f 100644
--- a/net/tap-linux.h
+++ b/net/tap-linux.h
@@ -29,6 +29,7 @@
#define TUNSETSNDBUF _IOW('T', 212, int)
#define TUNGETVNETHDRSZ _IOR('T', 215, int)
#define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNSETQUEUE _IOW('T', 217, int)
#endif
@@ -36,6 +37,9 @@
#define IFF_TAP 0x0002
#define IFF_NO_PI 0x1000
#define IFF_VNET_HDR 0x4000
+#define IFF_MULTI_QUEUE 0x0100
+#define IFF_ATTACH_QUEUE 0x0200
+#define IFF_DETACH_QUEUE 0x0400
/* Features for GSO (TUNSETOFFLOAD). */
#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */
diff --git a/net/tap-solaris.c b/net/tap-solaris.c
index cf76463..f7c8e8d 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 attach)
{
char dev[10]="";
int fd;
@@ -225,3 +226,13 @@ void tap_fd_set_offload(int fd, int csum, int tso4,
int tso6, int ecn, int ufo)
{
}
+
+int tap_fd_attach(int fd, const char *ifname)
+{
+ return -1;
+}
+
+int tap_fd_detach(int fd, const char *ifname)
+{
+ return -1;
+}
diff --git a/net/tap-win32.c b/net/tap-win32.c
index a801a55..dae1c00 100644
--- a/net/tap-win32.c
+++ b/net/tap-win32.c
@@ -749,3 +749,14 @@ struct vhost_net *tap_get_vhost_net(VLANClientState *nc)
{
return NULL;
}
+
+int tap_attach(VLANClientState *nc)
+{
+ return -1;
+}
+
+int tap_detach(VLANClientState *nc)
+{
+ return -1;
+}
+
diff --git a/net/tap.c b/net/tap.c
index 5ac4ba3..65457e5 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -53,11 +53,13 @@ typedef struct TAPState {
int fd;
char down_script[1024];
char down_script_arg[128];
+ char ifname[128];
uint8_t buf[TAP_BUFSIZE];
unsigned int read_poll : 1;
unsigned int write_poll : 1;
unsigned int using_vnet_hdr : 1;
unsigned int has_ufo: 1;
+ unsigned int enabled:1;
VHostNetState *vhost_net;
unsigned host_vnet_hdr_len;
} TAPState;
@@ -248,8 +250,10 @@ void tap_set_vnet_hdr_len(VLANClientState *nc, int len)
assert(len == sizeof(struct virtio_net_hdr_mrg_rxbuf) ||
len == sizeof(struct virtio_net_hdr));
- tap_fd_set_vnet_hdr_len(s->fd, len);
- s->host_vnet_hdr_len = len;
+ if (s->enabled) {
+ tap_fd_set_vnet_hdr_len(s->fd, len);
+ s->host_vnet_hdr_len = len;
+ }
}
void tap_using_vnet_hdr(VLANClientState *nc, int using_vnet_hdr)
@@ -546,7 +550,7 @@ int net_init_bridge(QemuOpts *opts, const char *name,
VLANState *vlan)
return 0;
}
-static int net_tap_init(QemuOpts *opts, int *vnet_hdr)
+static int net_tap_init(QemuOpts *opts, int *vnet_hdr, int attach)
{
int fd, vnet_hdr_required;
char ifname[128] = {0,};
@@ -563,7 +567,9 @@ static int net_tap_init(QemuOpts *opts, int *vnet_hdr)
vnet_hdr_required = 0;
}
- TFR(fd = tap_open(ifname, sizeof(ifname), vnet_hdr, vnet_hdr_required));
+ TFR(fd = tap_open(ifname, sizeof(ifname), vnet_hdr, vnet_hdr_required,
+ attach));
+
if (fd < 0) {
return -1;
}
@@ -572,7 +578,7 @@ static int net_tap_init(QemuOpts *opts, int *vnet_hdr)
if (setup_script &&
setup_script[0] != '\0' &&
strcmp(setup_script, "no") != 0 &&
- launch_script(setup_script, ifname, fd)) {
+ (!attach && launch_script(setup_script, ifname, fd))) {
close(fd);
return -1;
}
@@ -582,74 +588,11 @@ static int net_tap_init(QemuOpts *opts, int *vnet_hdr)
return fd;
}
-int net_init_tap(QemuOpts *opts, const char *name, VLANState *vlan)
+static int __net_init_tap(QemuOpts *opts, Monitor *mon, const char *name,
+ VLANState *vlan, int fd, int vnet_hdr)
{
- TAPState *s;
- int fd, vnet_hdr = 0;
- const char *model;
-
- if (qemu_opt_get(opts, "fd")) {
- if (qemu_opt_get(opts, "ifname") ||
- qemu_opt_get(opts, "script") ||
- qemu_opt_get(opts, "downscript") ||
- qemu_opt_get(opts, "vnet_hdr") ||
- qemu_opt_get(opts, "helper")) {
- error_report("ifname=, script=, downscript=, vnet_hdr=, "
- "and helper= are invalid with fd=");
- return -1;
- }
-
- fd = net_handle_fd_param(cur_mon, qemu_opt_get(opts, "fd"));
- if (fd == -1) {
- return -1;
- }
+ TAPState *s = net_tap_fd_init(vlan, "tap", name, fd, vnet_hdr);
- fcntl(fd, F_SETFL, O_NONBLOCK);
-
- vnet_hdr = tap_probe_vnet_hdr(fd);
-
- model = "tap";
-
- } else if (qemu_opt_get(opts, "helper")) {
- if (qemu_opt_get(opts, "ifname") ||
- qemu_opt_get(opts, "script") ||
- qemu_opt_get(opts, "downscript") ||
- qemu_opt_get(opts, "vnet_hdr")) {
- error_report("ifname=, script=, downscript=, and vnet_hdr=
"
- "are invalid with helper=");
- return -1;
- }
-
- fd = net_bridge_run_helper(qemu_opt_get(opts, "helper"),
- DEFAULT_BRIDGE_INTERFACE);
- if (fd == -1) {
- return -1;
- }
-
- fcntl(fd, F_SETFL, O_NONBLOCK);
-
- vnet_hdr = tap_probe_vnet_hdr(fd);
-
- model = "bridge";
-
- } else {
- if (!qemu_opt_get(opts, "script")) {
- qemu_opt_set(opts, "script", DEFAULT_NETWORK_SCRIPT);
- }
-
- if (!qemu_opt_get(opts, "downscript")) {
- qemu_opt_set(opts, "downscript",
DEFAULT_NETWORK_DOWN_SCRIPT);
- }
-
- fd = net_tap_init(opts, &vnet_hdr);
- if (fd == -1) {
- return -1;
- }
-
- model = "tap";
- }
-
- s = net_tap_fd_init(vlan, model, name, fd, vnet_hdr);
if (!s) {
close(fd);
return -1;
@@ -671,6 +614,7 @@ int net_init_tap(QemuOpts *opts, const char *name, VLANState
*vlan)
script = qemu_opt_get(opts, "script");
downscript = qemu_opt_get(opts, "downscript");
+ pstrcpy(s->ifname, sizeof(s->ifname), ifname);
snprintf(s->nc.info_str, sizeof(s->nc.info_str),
"ifname=%s,script=%s,downscript=%s",
ifname, script, downscript);
@@ -704,6 +648,84 @@ int net_init_tap(QemuOpts *opts, const char *name,
VLANState *vlan)
return -1;
}
+ s->enabled = 1;
+ return 0;
+}
+
+int net_init_tap(QemuOpts *opts, const char *name, VLANState *vlan)
+{
+ int i, fd, vnet_hdr = 0;
+ int numqueues = qemu_opt_get_number(opts, "queues", 1);
+
+ if (qemu_opt_get(opts, "fd")) {
+ const char *fdp[16];
+ if (qemu_opt_get(opts, "ifname") ||
+ qemu_opt_get(opts, "script") ||
+ qemu_opt_get(opts, "downscript") ||
+ qemu_opt_get(opts, "vnet_hdr") ||
+ qemu_opt_get(opts, "helper")) {
+ error_report("ifname=, script=, downscript=, vnet_hdr=, "
+ "and helper= are invalid with fd=");
+ return -1;
+ }
+
+ if (numqueues != qemu_opt_get_all(opts, "fd", fdp, 16)) {
+ error_report("the number of queue does not match the"
+ "number of fd passed");
+ return -1;
+ }
+
+ for (i = 0; i < numqueues; i++) {
+ fd = net_handle_fd_param(cur_mon, fdp[i]);
+ if (fd == -1) {
+ return -1;
+ }
+
+ fcntl(fd, F_SETFL, O_NONBLOCK);
+
+ vnet_hdr = tap_probe_vnet_hdr(fd);
+
+ if (__net_init_tap(opts, cur_mon, name, vlan, fd, vnet_hdr))
+ return -1;
+ }
+ } else if (qemu_opt_get(opts, "helper")) {
+ if (qemu_opt_get(opts, "ifname") ||
+ qemu_opt_get(opts, "script") ||
+ qemu_opt_get(opts, "downscript") ||
+ qemu_opt_get(opts, "vnet_hdr") ||
+ numqueues > 1) {
+ error_report("ifname=, script=, downscript=, and vnet_hdr=,
"
+ "and queues > 1 are invalid with
helper=");
+ return -1;
+ }
+
+ fd = net_bridge_run_helper(qemu_opt_get(opts, "helper"),
+ DEFAULT_BRIDGE_INTERFACE);
+ if (fd == -1) {
+ return -1;
+ }
+
+ fcntl(fd, F_SETFL, O_NONBLOCK);
+
+ vnet_hdr = tap_probe_vnet_hdr(fd);
+ } else {
+ if (!qemu_opt_get(opts, "script")) {
+ qemu_opt_set(opts, "script", DEFAULT_NETWORK_SCRIPT);
+ }
+
+ if (!qemu_opt_get(opts, "downscript")) {
+ qemu_opt_set(opts, "downscript",
DEFAULT_NETWORK_DOWN_SCRIPT);
+ }
+
+ for (i = 0; i < numqueues; i++) {
+ fd = net_tap_init(opts, &vnet_hdr, i != 0);
+ if (fd == -1) {
+ return -1;
+ }
+ if(__net_init_tap(opts, cur_mon, name, vlan, fd, vnet_hdr))
+ return -1;
+ }
+ }
return 0;
}
@@ -713,3 +735,36 @@ VHostNetState *tap_get_vhost_net(VLANClientState *nc)
assert(nc->info->type == NET_CLIENT_TYPE_TAP);
return s->vhost_net;
}
+
+int tap_attach(VLANClientState *nc)
+{
+ TAPState *s = DO_UPCAST(TAPState, nc, nc);
+ int ret;
+
+ if (s->enabled) {
+ return 0;
+ } else {
+ ret = tap_fd_attach(s->fd, s->ifname);
+ if (ret == 0) {
+ s->enabled = 1;
+ }
+ return ret;
+ }
+}
+
+int tap_detach(VLANClientState *nc)
+{
+ TAPState *s = DO_UPCAST(TAPState, nc, nc);
+ int ret;
+
+ if (s->enabled == 0) {
+ return 0;
+ } else {
+ ret = tap_fd_detach(s->fd, s->ifname);
+ if (ret == 0) {
+ s->enabled = 0;
+ }
+ return ret;
+ }
+}
+
diff --git a/net/tap.h b/net/tap.h
index b2a9450..cead7ca 100644
--- a/net/tap.h
+++ b/net/tap.h
@@ -34,7 +34,8 @@
int net_init_tap(QemuOpts *opts, const char *name, VLANState *vlan);
-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 attach);
ssize_t tap_read_packet(int tapfd, uint8_t *buf, int maxlen);
@@ -51,6 +52,10 @@ int tap_probe_vnet_hdr_len(int fd, int len);
int tap_probe_has_ufo(int fd);
void tap_fd_set_offload(int fd, int csum, int tso4, int tso6, int ecn, int
ufo);
void tap_fd_set_vnet_hdr_len(int fd, int len);
+int tap_attach(VLANClientState *vc);
+int tap_detach(VLANClientState *vc);
+int tap_fd_attach(int fd, const char *ifname);
+int tap_fd_detach(int fd, const char *ifname);
int tap_get_fd(VLANClientState *vc);
--
1.7.1
This patch adds the multiqueues support for emulated nics. Each VLANClientState
pairs are now abstract as a queue instead of a nic, and multiple VLANClientState
pointers were stored in the NICState. A queue_index were also introduced to let
the emulated nics know which queue the packet were came from or sent
out. Virtio-net would be the first user.
Signed-off-by: Jason Wang <jasowang at redhat.com>
---
hw/dp8393x.c | 2 +-
hw/mcf_fec.c | 2 +-
hw/qdev-properties.c | 34 +++++++++++++++++----
hw/qdev.h | 3 +-
net.c | 79 +++++++++++++++++++++++++++++++++++++++++---------
net.h | 16 +++++++--
net/tap.c | 2 +-
7 files changed, 110 insertions(+), 28 deletions(-)
diff --git a/hw/dp8393x.c b/hw/dp8393x.c
index 017d074..483a868 100644
--- a/hw/dp8393x.c
+++ b/hw/dp8393x.c
@@ -900,7 +900,7 @@ void dp83932_init(NICInfo *nd, target_phys_addr_t base, int
it_shift,
s->conf.macaddr = nd->macaddr;
s->conf.vlan = nd->vlan;
- s->conf.peer = nd->netdev;
+ s->conf.peers[0] = nd->netdev;
s->nic = qemu_new_nic(&net_dp83932_info, &s->conf,
nd->model, nd->name, s);
diff --git a/hw/mcf_fec.c b/hw/mcf_fec.c
index ae37bef..69f508d 100644
--- a/hw/mcf_fec.c
+++ b/hw/mcf_fec.c
@@ -473,7 +473,7 @@ void mcf_fec_init(MemoryRegion *sysmem, NICInfo *nd,
s->conf.macaddr = nd->macaddr;
s->conf.vlan = nd->vlan;
- s->conf.peer = nd->netdev;
+ s->conf.peers[0] = nd->netdev;
s->nic = qemu_new_nic(&net_mcf_fec_info, &s->conf,
nd->model, nd->name, s);
diff --git a/hw/qdev-properties.c b/hw/qdev-properties.c
index 9ae3187..88e97e9 100644
--- a/hw/qdev-properties.c
+++ b/hw/qdev-properties.c
@@ -554,16 +554,38 @@ PropertyInfo qdev_prop_chr = {
static int parse_netdev(DeviceState *dev, const char *str, void **ptr)
{
- VLANClientState *netdev = qemu_find_netdev(str);
+ VLANClientState ***nc = (VLANClientState ***)ptr;
+ VLANClientState *vcs[MAX_QUEUE_NUM];
+ int queues, i = 0;
+ int ret;
- if (netdev == NULL) {
- return -ENOENT;
+ *nc = g_malloc(MAX_QUEUE_NUM * sizeof(VLANClientState *));
+ queues = qemu_find_netdev_all(str, vcs, MAX_QUEUE_NUM);
+ if (queues == 0) {
+ ret = -ENOENT;
+ goto err;
}
- if (netdev->peer) {
- return -EEXIST;
+
+ for (i = 0; i < queues; i++) {
+ if (vcs[i] == NULL) {
+ ret = -ENOENT;
+ goto err;
+ }
+
+ if (vcs[i]->peer) {
+ ret = -EEXIST;
+ goto err;
+ }
+
+ (*nc)[i] = vcs[i];
+ vcs[i]->queue_index = i;
}
- *ptr = netdev;
+
return 0;
+
+err:
+ g_free(*nc);
+ return ret;
}
static const char *print_netdev(void *ptr)
diff --git a/hw/qdev.h b/hw/qdev.h
index 5386b16..1c023b4 100644
--- a/hw/qdev.h
+++ b/hw/qdev.h
@@ -248,6 +248,7 @@ extern PropertyInfo qdev_prop_blocksize;
.defval = (bool)_defval, \
}
+
#define DEFINE_PROP_UINT8(_n, _s, _f, _d) \
DEFINE_PROP_DEFAULT(_n, _s, _f, _d, qdev_prop_uint8, uint8_t)
#define DEFINE_PROP_UINT16(_n, _s, _f, _d) \
@@ -274,7 +275,7 @@ extern PropertyInfo qdev_prop_blocksize;
#define DEFINE_PROP_STRING(_n, _s, _f) \
DEFINE_PROP(_n, _s, _f, qdev_prop_string, char*)
#define DEFINE_PROP_NETDEV(_n, _s, _f) \
- DEFINE_PROP(_n, _s, _f, qdev_prop_netdev, VLANClientState*)
+ DEFINE_PROP(_n, _s, _f, qdev_prop_netdev, VLANClientState**)
#define DEFINE_PROP_VLAN(_n, _s, _f) \
DEFINE_PROP(_n, _s, _f, qdev_prop_vlan, VLANState*)
#define DEFINE_PROP_DRIVE(_n, _s, _f) \
diff --git a/net.c b/net.c
index eabe830..f5db537 100644
--- a/net.c
+++ b/net.c
@@ -238,16 +238,33 @@ NICState *qemu_new_nic(NetClientInfo *info,
{
VLANClientState *nc;
NICState *nic;
+ int i;
assert(info->type == NET_CLIENT_TYPE_NIC);
assert(info->size >= sizeof(NICState));
- nc = qemu_new_net_client(info, conf->vlan, conf->peer, model, name);
+ if (conf->peers) {
+ nc = qemu_new_net_client(info, NULL, conf->peers[0], model, name);
+ } else {
+ nc = qemu_new_net_client(info, conf->vlan, NULL, model, name);
+ }
nic = DO_UPCAST(NICState, nc, nc);
nic->conf = conf;
nic->opaque = opaque;
+ /* For compatiablity with single queue nic */
+ nic->ncs[0] = nc;
+ nc->opaque = nic;
+
+ for (i = 1 ; i < conf->queues; i++) {
+ VLANClientState *vc = qemu_new_net_client(info, NULL,
conf->peers[i],
+ model, name);
+ vc->opaque = nic;
+ nic->ncs[i] = vc;
+ vc->queue_index = i;
+ }
+
return nic;
}
@@ -283,11 +300,10 @@ void qemu_del_vlan_client(VLANClientState *vc)
{
/* If there is a peer NIC, delete and cleanup client, but do not free. */
if (!vc->vlan && vc->peer &&
vc->peer->info->type == NET_CLIENT_TYPE_NIC) {
- NICState *nic = DO_UPCAST(NICState, nc, vc->peer);
- if (nic->peer_deleted) {
+ if (vc->peer_deleted) {
return;
}
- nic->peer_deleted = true;
+ vc->peer_deleted = true;
/* Let NIC know peer is gone. */
vc->peer->link_down = true;
if (vc->peer->info->link_status_changed) {
@@ -299,8 +315,7 @@ void qemu_del_vlan_client(VLANClientState *vc)
/* If this is a peer NIC and peer has already been deleted, free it now. */
if (!vc->vlan && vc->peer && vc->info->type ==
NET_CLIENT_TYPE_NIC) {
- NICState *nic = DO_UPCAST(NICState, nc, vc);
- if (nic->peer_deleted) {
+ if (vc->peer_deleted) {
qemu_free_vlan_client(vc->peer);
}
}
@@ -342,14 +357,14 @@ void qemu_foreach_nic(qemu_nic_foreach func, void *opaque)
QTAILQ_FOREACH(nc, &non_vlan_clients, next) {
if (nc->info->type == NET_CLIENT_TYPE_NIC) {
- func(DO_UPCAST(NICState, nc, nc), opaque);
+ func((NICState *)nc->opaque, opaque);
}
}
QTAILQ_FOREACH(vlan, &vlans, next) {
QTAILQ_FOREACH(nc, &vlan->clients, next) {
if (nc->info->type == NET_CLIENT_TYPE_NIC) {
- func(DO_UPCAST(NICState, nc, nc), opaque);
+ func((NICState *)nc->opaque, opaque);
}
}
}
@@ -674,6 +689,26 @@ VLANClientState *qemu_find_netdev(const char *id)
return NULL;
}
+int qemu_find_netdev_all(const char *id, VLANClientState **vcs, int max)
+{
+ VLANClientState *vc;
+ int ret = 0;
+
+ QTAILQ_FOREACH(vc, &non_vlan_clients, next) {
+ if (vc->info->type == NET_CLIENT_TYPE_NIC) {
+ continue;
+ }
+ if (!strcmp(vc->name, id) && ret < max) {
+ vcs[ret++] = vc;
+ }
+ if (ret >= max) {
+ break;
+ }
+ }
+
+ return ret;
+}
+
static int nic_get_free_idx(void)
{
int index;
@@ -1275,22 +1310,27 @@ exit_err:
void qmp_netdev_del(const char *id, Error **errp)
{
- VLANClientState *vc;
+ VLANClientState *vcs[MAX_QUEUE_NUM];
+ int queues, i;
- vc = qemu_find_netdev(id);
- if (!vc) {
+ queues = qemu_find_netdev_all(id, vcs, MAX_QUEUE_NUM);
+ if (queues == 0) {
error_set(errp, QERR_DEVICE_NOT_FOUND, id);
return;
}
- qemu_del_vlan_client(vc);
+ for (i = 0; i < queues; i++) {
+ /* FIXME: pointer check? */
+ qemu_del_vlan_client(vcs[i]);
+ }
qemu_opts_del(qemu_opts_find(qemu_find_opts_err("netdev", errp),
id));
}
static void print_net_client(Monitor *mon, VLANClientState *vc)
{
- monitor_printf(mon, "%s: type=%s,%s\n", vc->name,
- net_client_types[vc->info->type].type,
vc->info_str);
+ monitor_printf(mon, "%s: type=%s,%s, queue=%d\n", vc->name,
+ net_client_types[vc->info->type].type,
vc->info_str,
+ vc->queue_index);
}
void do_info_network(Monitor *mon)
@@ -1326,6 +1366,17 @@ void qmp_set_link(const char *name, bool up, Error
**errp)
{
VLANState *vlan;
VLANClientState *vc = NULL;
+ VLANClientState *vcs[MAX_QUEUE_NUM];
+ int queues, i;
+
+ queues = qemu_find_netdev_all(name, vcs, MAX_QUEUE_NUM);
+ if (queues) {
+ for (i = 1; i < queues; i++) {
+ vcs[i]->link_down = !up;
+ }
+ vc = vcs[0];
+ goto done;
+ }
QTAILQ_FOREACH(vlan, &vlans, next) {
QTAILQ_FOREACH(vc, &vlan->clients, next) {
diff --git a/net.h b/net.h
index bdc2a06..40378ce 100644
--- a/net.h
+++ b/net.h
@@ -12,20 +12,24 @@ struct MACAddr {
uint8_t a[6];
};
+#define MAX_QUEUE_NUM 32
+
/* qdev nic properties */
typedef struct NICConf {
MACAddr macaddr;
VLANState *vlan;
- VLANClientState *peer;
+ VLANClientState **peers;
int32_t bootindex;
+ int32_t queues;
} NICConf;
#define DEFINE_NIC_PROPERTIES(_state, _conf) \
DEFINE_PROP_MACADDR("mac", _state, _conf.macaddr),
\
DEFINE_PROP_VLAN("vlan", _state, _conf.vlan),
\
- DEFINE_PROP_NETDEV("netdev", _state, _conf.peer),
\
- DEFINE_PROP_INT32("bootindex", _state, _conf.bootindex, -1)
+ DEFINE_PROP_NETDEV("netdev", _state, _conf.peers),
\
+ DEFINE_PROP_INT32("bootindex", _state, _conf.bootindex, -1),
\
+ DEFINE_PROP_INT32("queues", _state, _conf.queues, 1)
/* VLANs support */
@@ -72,13 +76,16 @@ struct VLANClientState {
char *name;
char info_str[256];
unsigned receive_disabled : 1;
+ unsigned int queue_index;
+ bool peer_deleted;
+ void *opaque;
};
typedef struct NICState {
VLANClientState nc;
+ VLANClientState *ncs[MAX_QUEUE_NUM];
NICConf *conf;
void *opaque;
- bool peer_deleted;
} NICState;
struct VLANState {
@@ -90,6 +97,7 @@ struct VLANState {
VLANState *qemu_find_vlan(int id, int allocate);
VLANClientState *qemu_find_netdev(const char *id);
+int qemu_find_netdev_all(const char *id, VLANClientState **vcs, int max);
VLANClientState *qemu_new_net_client(NetClientInfo *info,
VLANState *vlan,
VLANClientState *peer,
diff --git a/net/tap.c b/net/tap.c
index 65457e5..4ce83b8 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -290,7 +290,7 @@ static void tap_cleanup(VLANClientState *nc)
qemu_purge_queued_packets(nc);
- if (s->down_script[0])
+ if (s->down_script[0] && nc->queue_index == 0)
launch_script(s->down_script, s->down_script_arg, s->fd);
tap_read_poll(s, 0);
--
1.7.1
This patch converts the vhost to support multiqueue queues. It implement a 1:1
mapping of vhost devs and tap fds. That it to say, the patch creates and uses
N vhost devs as the backend of the N queues virtio-net deivce.
The main work is to convert the virtqueue index into vhost queue index, this is
done by introducing an vq_index filed in vhost_dev struct to record the index of
first virtuque that is used by the vhost devs. Then vhost could simply convert
it to the local vhost queue index and issue ioctls.
Signed-off-by: Jason Wang <jasowang at redhat.com>
---
hw/vhost.c | 53 ++++++++++++++++++++++++++++++++++-------------------
hw/vhost.h | 2 ++
hw/vhost_net.c | 7 +++++--
hw/vhost_net.h | 2 +-
hw/virtio-net.c | 2 +-
5 files changed, 43 insertions(+), 23 deletions(-)
diff --git a/hw/vhost.c b/hw/vhost.c
index 43664e7..3eb6037 100644
--- a/hw/vhost.c
+++ b/hw/vhost.c
@@ -620,11 +620,12 @@ static int vhost_virtqueue_init(struct vhost_dev *dev,
{
target_phys_addr_t s, l, a;
int r;
+ int vhost_vq_index = (idx > 2 ? idx - 1 : idx) % dev->nvqs;
struct vhost_vring_file file = {
- .index = idx,
+ .index = vhost_vq_index
};
struct vhost_vring_state state = {
- .index = idx,
+ .index = vhost_vq_index
};
struct VirtQueue *vvq = virtio_get_queue(vdev, idx);
@@ -670,11 +671,12 @@ static int vhost_virtqueue_init(struct vhost_dev *dev,
goto fail_alloc_ring;
}
- r = vhost_virtqueue_set_addr(dev, vq, idx, dev->log_enabled);
+ r = vhost_virtqueue_set_addr(dev, vq, vhost_vq_index, dev->log_enabled);
if (r < 0) {
r = -errno;
goto fail_alloc;
}
+
file.fd = event_notifier_get_fd(virtio_queue_get_host_notifier(vvq));
r = ioctl(dev->control, VHOST_SET_VRING_KICK, &file);
if (r) {
@@ -715,7 +717,7 @@ static void vhost_virtqueue_cleanup(struct vhost_dev *dev,
unsigned idx)
{
struct vhost_vring_state state = {
- .index = idx,
+ .index = (idx > 2 ? idx - 1 : idx) % dev->nvqs,
};
int r;
r = ioctl(dev->control, VHOST_GET_VRING_BASE, &state);
@@ -829,7 +831,9 @@ int vhost_dev_enable_notifiers(struct vhost_dev *hdev,
VirtIODevice *vdev)
}
for (i = 0; i < hdev->nvqs; ++i) {
- r = vdev->binding->set_host_notifier(vdev->binding_opaque, i,
true);
+ r = vdev->binding->set_host_notifier(vdev->binding_opaque,
+ hdev->vq_index + i,
+ true);
if (r < 0) {
fprintf(stderr, "vhost VQ %d notifier binding failed:
%d\n", i, -r);
goto fail_vq;
@@ -839,7 +843,9 @@ int vhost_dev_enable_notifiers(struct vhost_dev *hdev,
VirtIODevice *vdev)
return 0;
fail_vq:
while (--i >= 0) {
- r = vdev->binding->set_host_notifier(vdev->binding_opaque, i,
false);
+ r = vdev->binding->set_host_notifier(vdev->binding_opaque,
+ hdev->vq_index + i,
+ false);
if (r < 0) {
fprintf(stderr, "vhost VQ %d notifier cleanup error:
%d\n", i, -r);
fflush(stderr);
@@ -860,7 +866,9 @@ void vhost_dev_disable_notifiers(struct vhost_dev *hdev,
VirtIODevice *vdev)
int i, r;
for (i = 0; i < hdev->nvqs; ++i) {
- r = vdev->binding->set_host_notifier(vdev->binding_opaque, i,
false);
+ r = vdev->binding->set_host_notifier(vdev->binding_opaque,
+ hdev->vq_index + i,
+ false);
if (r < 0) {
fprintf(stderr, "vhost VQ %d notifier cleanup failed:
%d\n", i, -r);
fflush(stderr);
@@ -879,10 +887,12 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice
*vdev)
goto fail;
}
- r = vdev->binding->set_guest_notifiers(vdev->binding_opaque,
true);
- if (r < 0) {
- fprintf(stderr, "Error binding guest notifier: %d\n", -r);
- goto fail_notifiers;
+ if (hdev->vq_index == 0) {
+ r = vdev->binding->set_guest_notifiers(vdev->binding_opaque,
true);
+ if (r < 0) {
+ fprintf(stderr, "Error binding guest notifier: %d\n",
-r);
+ goto fail_notifiers;
+ }
}
r = vhost_dev_set_features(hdev, hdev->log_enabled);
@@ -898,7 +908,7 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice
*vdev)
r = vhost_virtqueue_init(hdev,
vdev,
hdev->vqs + i,
- i);
+ hdev->vq_index + i);
if (r < 0) {
goto fail_vq;
}
@@ -925,8 +935,9 @@ fail_vq:
vhost_virtqueue_cleanup(hdev,
vdev,
hdev->vqs + i,
- i);
+ hdev->vq_index + i);
}
+ i = hdev->nvqs;
fail_mem:
fail_features:
vdev->binding->set_guest_notifiers(vdev->binding_opaque, false);
@@ -944,18 +955,22 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice
*vdev)
vhost_virtqueue_cleanup(hdev,
vdev,
hdev->vqs + i,
- i);
+ hdev->vq_index + i);
}
+
for (i = 0; i < hdev->n_mem_sections; ++i) {
vhost_sync_dirty_bitmap(hdev, &hdev->mem_sections[i],
0, (target_phys_addr_t)~0x0ull);
}
- r = vdev->binding->set_guest_notifiers(vdev->binding_opaque,
false);
- if (r < 0) {
- fprintf(stderr, "vhost guest notifier cleanup failed: %d\n",
r);
- fflush(stderr);
+
+ if (hdev->vq_index == 0) {
+ r = vdev->binding->set_guest_notifiers(vdev->binding_opaque, false);
+ if (r < 0) {
+ fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", r);
+ fflush(stderr);
+ }
+ assert (r >= 0);
}
- assert (r >= 0);
hdev->started = false;
g_free(hdev->log);
diff --git a/hw/vhost.h b/hw/vhost.h
index 80e64df..edfe9d2 100644
--- a/hw/vhost.h
+++ b/hw/vhost.h
@@ -34,6 +34,8 @@ struct vhost_dev {
MemoryRegionSection *mem_sections;
struct vhost_virtqueue *vqs;
int nvqs;
+ /* the first virtuque which would be used by this vhost dev */
+ int vq_index;
unsigned long long features;
unsigned long long acked_features;
unsigned long long backend_features;
diff --git a/hw/vhost_net.c b/hw/vhost_net.c
index f672e9d..7cc3339 100644
--- a/hw/vhost_net.c
+++ b/hw/vhost_net.c
@@ -138,13 +138,15 @@ bool vhost_net_query(VHostNetState *net, VirtIODevice
*dev)
}
int vhost_net_start(struct vhost_net *net,
- VirtIODevice *dev)
+ VirtIODevice *dev,
+ int vq_index)
{
struct vhost_vring_file file = { };
int r;
net->dev.nvqs = 2;
net->dev.vqs = net->vqs;
+ net->dev.vq_index = vq_index;
r = vhost_dev_enable_notifiers(&net->dev, dev);
if (r < 0) {
@@ -227,7 +229,8 @@ bool vhost_net_query(VHostNetState *net, VirtIODevice *dev)
}
int vhost_net_start(struct vhost_net *net,
- VirtIODevice *dev)
+ VirtIODevice *dev,
+ int vq_index)
{
return -ENOSYS;
}
diff --git a/hw/vhost_net.h b/hw/vhost_net.h
index 91e40b1..6282b2c 100644
--- a/hw/vhost_net.h
+++ b/hw/vhost_net.h
@@ -9,7 +9,7 @@ typedef struct vhost_net VHostNetState;
VHostNetState *vhost_net_init(VLANClientState *backend, int devfd, bool force);
bool vhost_net_query(VHostNetState *net, VirtIODevice *dev);
-int vhost_net_start(VHostNetState *net, VirtIODevice *dev);
+int vhost_net_start(VHostNetState *net, VirtIODevice *dev, int vq_index);
void vhost_net_stop(VHostNetState *net, VirtIODevice *dev);
void vhost_net_cleanup(VHostNetState *net);
diff --git a/hw/virtio-net.c b/hw/virtio-net.c
index 3f190d4..30eb4f4 100644
--- a/hw/virtio-net.c
+++ b/hw/virtio-net.c
@@ -124,7 +124,7 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t
status)
if (!vhost_net_query(tap_get_vhost_net(n->nic->nc.peer),
&n->vdev)) {
return;
}
- r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer),
&n->vdev);
+ r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer),
&n->vdev, 0);
if (r < 0) {
error_report("unable to start vhost net: %d: "
"falling back on userspace virtio", -r);
--
1.7.1
Based on the multiqueue support for taps and NICState, this patch add the
capability of multiqueue for virtio-net. For userspace virtio-net emulation,
each pair of VLANClientState peers were abstracted as a tx/rx queue. For vhost,
the vhost net devices were created per virtio-net tx/rx queue pairs, so when
multiqueue is enabled, N vhost devices/threads were created for a N queues
virtio-net devices.
Since guest may not want to use all queues that qemu provided ( one example is
the old guest w/o multiqueue support). The files were attached/detached on
demand when guest set status for virtio_net.
This feature was negotiated through VIRTIO_NET_F_MULTIQUEUE. A new property
"queues" were added to virtio-net device to specify the number of
queues it
supported. With this patch a virtio-net backend with N queues could be created
by:
qemu -netdev tap,id=hn0,queues=2 -device virtio-net-pci,netdev=hn0,queues=2
To let user tweak the performance, guest could negotiate the num of queues it
wishes to use through control virtqueue.
Signed-off-by: Jason Wang <jasowang at redhat.com>
---
hw/virtio-net.c | 505 ++++++++++++++++++++++++++++++++++++++-----------------
hw/virtio-net.h | 12 ++
2 files changed, 361 insertions(+), 156 deletions(-)
diff --git a/hw/virtio-net.c b/hw/virtio-net.c
index 30eb4f4..afe69e8 100644
--- a/hw/virtio-net.c
+++ b/hw/virtio-net.c
@@ -21,39 +21,48 @@
#include "virtio-net.h"
#include "vhost_net.h"
-#define VIRTIO_NET_VM_VERSION 11
+#define VIRTIO_NET_VM_VERSION 12
#define MAC_TABLE_ENTRIES 64
#define MAX_VLAN (1 << 12) /* Per 802.1Q definition */
-typedef struct VirtIONet
+struct VirtIONet;
+
+typedef struct VirtIONetQueue
{
- VirtIODevice vdev;
- uint8_t mac[ETH_ALEN];
- uint16_t status;
VirtQueue *rx_vq;
VirtQueue *tx_vq;
- VirtQueue *ctrl_vq;
- NICState *nic;
QEMUTimer *tx_timer;
QEMUBH *tx_bh;
uint32_t tx_timeout;
- int32_t tx_burst;
int tx_waiting;
- uint32_t has_vnet_hdr;
- uint8_t has_ufo;
struct {
VirtQueueElement elem;
ssize_t len;
} async_tx;
+ struct VirtIONet *n;
+ uint8_t vhost_started;
+} VirtIONetQueue;
+
+typedef struct VirtIONet
+{
+ VirtIODevice vdev;
+ uint8_t mac[ETH_ALEN];
+ uint16_t status;
+ VirtIONetQueue vqs[MAX_QUEUE_NUM];
+ VirtQueue *ctrl_vq;
+ NICState *nic;
+ int32_t tx_burst;
+ uint32_t has_vnet_hdr;
+ uint8_t has_ufo;
int mergeable_rx_bufs;
+ int multiqueue;
uint8_t promisc;
uint8_t allmulti;
uint8_t alluni;
uint8_t nomulti;
uint8_t nouni;
uint8_t nobcast;
- uint8_t vhost_started;
struct {
int in_use;
int first_multi;
@@ -63,6 +72,8 @@ typedef struct VirtIONet
} mac_table;
uint32_t *vlans;
DeviceState *qdev;
+ uint16_t queues;
+ uint16_t real_queues;
} VirtIONet;
/* TODO
@@ -74,12 +85,25 @@ static VirtIONet *to_virtio_net(VirtIODevice *vdev)
return (VirtIONet *)vdev;
}
+static int vq_get_pair_index(VirtIONet *n, VirtQueue *vq)
+{
+ int i;
+ for (i = 0; i < n->queues; i++) {
+ if (n->vqs[i].tx_vq == vq || n->vqs[i].rx_vq == vq) {
+ return i;
+ }
+ }
+ assert(1);
+ return -1;
+}
+
static void virtio_net_get_config(VirtIODevice *vdev, uint8_t *config)
{
VirtIONet *n = to_virtio_net(vdev);
struct virtio_net_config netcfg;
stw_p(&netcfg.status, n->status);
+ netcfg.queues = n->queues * 2;
memcpy(netcfg.mac, n->mac, ETH_ALEN);
memcpy(config, &netcfg, sizeof(netcfg));
}
@@ -103,78 +127,146 @@ static bool virtio_net_started(VirtIONet *n, uint8_t
status)
(n->status & VIRTIO_NET_S_LINK_UP) &&
n->vdev.vm_running;
}
-static void virtio_net_vhost_status(VirtIONet *n, uint8_t status)
+static void virtio_net_vhost_status(VLANClientState *nc, VirtIONet *n,
+ uint8_t status)
{
- if (!n->nic->nc.peer) {
+ int queue_index = nc->queue_index;
+ VLANClientState *peer = nc->peer;
+ VirtIONetQueue *netq = &n->vqs[nc->queue_index];
+
+ if (!peer) {
return;
}
- if (n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) {
+ if (peer->info->type != NET_CLIENT_TYPE_TAP) {
return;
}
- if (!tap_get_vhost_net(n->nic->nc.peer)) {
+ if (!tap_get_vhost_net(peer)) {
return;
}
- if (!!n->vhost_started == virtio_net_started(n, status) &&
- !n->nic->nc.peer->link_down) {
+ if (!!netq->vhost_started == virtio_net_started(n, status) &&
+ !peer->link_down) {
return;
}
- if (!n->vhost_started) {
- int r;
- if (!vhost_net_query(tap_get_vhost_net(n->nic->nc.peer),
&n->vdev)) {
+ if (!netq->vhost_started) {
+ int r;
+ if (!vhost_net_query(tap_get_vhost_net(peer), &n->vdev)) {
return;
}
- r = vhost_net_start(tap_get_vhost_net(n->nic->nc.peer),
&n->vdev, 0);
+
+ r = vhost_net_start(tap_get_vhost_net(peer), &n->vdev,
+ queue_index == 0 ? 0 : queue_index * 2 + 1);
if (r < 0) {
error_report("unable to start vhost net: %d: "
"falling back on userspace virtio", -r);
} else {
- n->vhost_started = 1;
+ netq->vhost_started = 1;
}
} else {
- vhost_net_stop(tap_get_vhost_net(n->nic->nc.peer),
&n->vdev);
- n->vhost_started = 0;
+ vhost_net_stop(tap_get_vhost_net(peer), &n->vdev);
+ netq->vhost_started = 0;
}
}
-static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
+static int peer_attach(VirtIONet *n, int index)
{
- VirtIONet *n = to_virtio_net(vdev);
+ if (!n->nic->ncs[index]->peer) {
+ return -1;
+ }
- virtio_net_vhost_status(n, status);
+ if (n->nic->ncs[index]->peer->info->type !=
NET_CLIENT_TYPE_TAP) {
+ return -1;
+ }
- if (!n->tx_waiting) {
- return;
+ return tap_attach(n->nic->ncs[index]->peer);
+}
+
+static int peer_detach(VirtIONet *n, int index)
+{
+ if (!n->nic->ncs[index]->peer) {
+ return -1;
}
- if (virtio_net_started(n, status) && !n->vhost_started) {
- if (n->tx_timer) {
- qemu_mod_timer(n->tx_timer,
- qemu_get_clock_ns(vm_clock) + n->tx_timeout);
+ if (n->nic->ncs[index]->peer->info->type !=
NET_CLIENT_TYPE_TAP) {
+ return -1;
+ }
+
+ return tap_detach(n->nic->ncs[index]->peer);
+}
+
+static void virtio_net_set_queues(VirtIONet *n)
+{
+ int i;
+ for (i = 0; i < n->queues; i++) {
+ if ((!n->multiqueue && i != 0) || i >= n->real_queues)
{
+ assert(peer_detach(n, i) == 0);
} else {
- qemu_bh_schedule(n->tx_bh);
+ assert(peer_attach(n, i) == 0);
}
- } else {
- if (n->tx_timer) {
- qemu_del_timer(n->tx_timer);
+ }
+}
+
+static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
+{
+ VirtIONet *n = to_virtio_net(vdev);
+ int i;
+
+ virtio_net_set_queues(n);
+
+ for (i = 0; i < n->queues; i++) {
+ VirtIONetQueue *netq = &n->vqs[i];
+
+ if ((!n->multiqueue && i != 0) || i >= n->real_queues)
+ status = 0;
+
+ virtio_net_vhost_status(n->nic->ncs[i], n, status);
+
+ if (!netq->tx_waiting) {
+ continue;
+ }
+
+ if (virtio_net_started(n, status) && !netq->vhost_started) {
+ if (netq->tx_timer) {
+ qemu_mod_timer(netq->tx_timer,
+ qemu_get_clock_ns(vm_clock) +
netq->tx_timeout);
+ } else {
+ qemu_bh_schedule(netq->tx_bh);
+ }
} else {
- qemu_bh_cancel(n->tx_bh);
+ if (netq->tx_timer) {
+ qemu_del_timer(netq->tx_timer);
+ } else {
+ qemu_bh_cancel(netq->tx_bh);
+ }
+ }
+ }
+}
+
+static bool virtio_net_is_link_up(VirtIONet *n)
+{
+ int i;
+ for (i = 0; i < n->queues; i++) {
+ if (n->nic->ncs[i]->link_down) {
+ return false;
}
}
+ return true;
}
static void virtio_net_set_link_status(VLANClientState *nc)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ VirtIONet *n = ((NICState *)(nc->opaque))->opaque;
uint16_t old_status = n->status;
- if (nc->link_down)
- n->status &= ~VIRTIO_NET_S_LINK_UP;
- else
+ if (virtio_net_is_link_up(n)) {
n->status |= VIRTIO_NET_S_LINK_UP;
+ } else {
+ n->status &= ~VIRTIO_NET_S_LINK_UP;
+ }
- if (n->status != old_status)
+ if (n->status != old_status) {
virtio_notify_config(&n->vdev);
+ }
virtio_net_set_status(&n->vdev, n->vdev.status);
}
@@ -190,6 +282,7 @@ static void virtio_net_reset(VirtIODevice *vdev)
n->nomulti = 0;
n->nouni = 0;
n->nobcast = 0;
+ n->real_queues = n->queues;
/* Flush any MAC and VLAN filter table state */
n->mac_table.in_use = 0;
@@ -202,13 +295,15 @@ static void virtio_net_reset(VirtIODevice *vdev)
static int peer_has_vnet_hdr(VirtIONet *n)
{
- if (!n->nic->nc.peer)
+ if (!n->nic->ncs[0]->peer) {
return 0;
+ }
- if (n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP)
+ if (n->nic->ncs[0]->peer->info->type != NET_CLIENT_TYPE_TAP)
{
return 0;
+ }
- n->has_vnet_hdr = tap_has_vnet_hdr(n->nic->nc.peer);
+ n->has_vnet_hdr = tap_has_vnet_hdr(n->nic->ncs[0]->peer);
return n->has_vnet_hdr;
}
@@ -218,7 +313,7 @@ static int peer_has_ufo(VirtIONet *n)
if (!peer_has_vnet_hdr(n))
return 0;
- n->has_ufo = tap_has_ufo(n->nic->nc.peer);
+ n->has_ufo = tap_has_ufo(n->nic->ncs[0]->peer);
return n->has_ufo;
}
@@ -228,9 +323,13 @@ static uint32_t virtio_net_get_features(VirtIODevice *vdev,
uint32_t features)
VirtIONet *n = to_virtio_net(vdev);
features |= (1 << VIRTIO_NET_F_MAC);
+ features |= (1 << VIRTIO_NET_F_MULTIQUEUE);
if (peer_has_vnet_hdr(n)) {
- tap_using_vnet_hdr(n->nic->nc.peer, 1);
+ int i;
+ for (i = 0; i < n->queues; i++) {
+ tap_using_vnet_hdr(n->nic->ncs[i]->peer, 1);
+ }
} else {
features &= ~(0x1 << VIRTIO_NET_F_CSUM);
features &= ~(0x1 << VIRTIO_NET_F_HOST_TSO4);
@@ -248,14 +347,15 @@ static uint32_t virtio_net_get_features(VirtIODevice
*vdev, uint32_t features)
features &= ~(0x1 << VIRTIO_NET_F_HOST_UFO);
}
- if (!n->nic->nc.peer ||
- n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) {
+ if (!n->nic->ncs[0]->peer ||
+ n->nic->ncs[0]->peer->info->type != NET_CLIENT_TYPE_TAP)
{
return features;
}
- if (!tap_get_vhost_net(n->nic->nc.peer)) {
+ if (!tap_get_vhost_net(n->nic->ncs[0]->peer)) {
return features;
}
- return vhost_net_get_features(tap_get_vhost_net(n->nic->nc.peer),
features);
+ return
vhost_net_get_features(tap_get_vhost_net(n->nic->ncs[0]->peer),
+ features);
}
static uint32_t virtio_net_bad_features(VirtIODevice *vdev)
@@ -276,25 +376,36 @@ static uint32_t virtio_net_bad_features(VirtIODevice
*vdev)
static void virtio_net_set_features(VirtIODevice *vdev, uint32_t features)
{
VirtIONet *n = to_virtio_net(vdev);
+ int i;
n->mergeable_rx_bufs = !!(features & (1 <<
VIRTIO_NET_F_MRG_RXBUF));
+ n->multiqueue = !!(features & (1 << VIRTIO_NET_F_MULTIQUEUE));
- if (n->has_vnet_hdr) {
- tap_set_offload(n->nic->nc.peer,
- (features >> VIRTIO_NET_F_GUEST_CSUM) & 1,
- (features >> VIRTIO_NET_F_GUEST_TSO4) & 1,
- (features >> VIRTIO_NET_F_GUEST_TSO6) & 1,
- (features >> VIRTIO_NET_F_GUEST_ECN) & 1,
- (features >> VIRTIO_NET_F_GUEST_UFO) & 1);
- }
- if (!n->nic->nc.peer ||
- n->nic->nc.peer->info->type != NET_CLIENT_TYPE_TAP) {
- return;
- }
- if (!tap_get_vhost_net(n->nic->nc.peer)) {
- return;
+ if (!n->multiqueue)
+ n->real_queues = 1;
+
+ /* attach the files for tap_set_offload */
+ virtio_net_set_queues(n);
+
+ for (i = 0; i < n->real_queues; i++) {
+ if (n->has_vnet_hdr) {
+ tap_set_offload(n->nic->ncs[i]->peer,
+ (features >> VIRTIO_NET_F_GUEST_CSUM) &
1,
+ (features >> VIRTIO_NET_F_GUEST_TSO4) &
1,
+ (features >> VIRTIO_NET_F_GUEST_TSO6) &
1,
+ (features >> VIRTIO_NET_F_GUEST_ECN) &
1,
+ (features >> VIRTIO_NET_F_GUEST_UFO) &
1);
+ }
+ if (!n->nic->ncs[i]->peer ||
+ n->nic->ncs[i]->peer->info->type !=
NET_CLIENT_TYPE_TAP) {
+ continue;
+ }
+ if (!tap_get_vhost_net(n->nic->ncs[i]->peer)) {
+ continue;
+ }
+
vhost_net_ack_features(tap_get_vhost_net(n->nic->ncs[i]->peer),
+ features);
}
- vhost_net_ack_features(tap_get_vhost_net(n->nic->nc.peer), features);
}
static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
@@ -404,6 +515,26 @@ static int virtio_net_handle_vlan_table(VirtIONet *n,
uint8_t cmd,
return VIRTIO_NET_OK;
}
+static int virtio_net_handle_multiqueue(VirtIONet *n, uint8_t cmd,
+ VirtQueueElement *elem)
+{
+ if (elem->out_num != 2 ||
+ elem->out_sg[1].iov_len != sizeof(n->real_queues)) {
+ error_report("virtio-net ctrl invalid multiqueue command");
+ return VIRTIO_NET_ERR;
+ }
+
+ n->real_queues = lduw_p(elem->out_sg[1].iov_base);
+ if (n->real_queues > n->queues) {
+ return VIRTIO_NET_ERR;
+ }
+
+ virtio_net_set_status(&n->vdev, n->vdev.status);
+
+ return VIRTIO_NET_OK;
+}
+
+
static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIONet *n = to_virtio_net(vdev);
@@ -432,6 +563,8 @@ static void virtio_net_handle_ctrl(VirtIODevice *vdev,
VirtQueue *vq)
status = virtio_net_handle_mac(n, ctrl.cmd, &elem);
else if (ctrl.class == VIRTIO_NET_CTRL_VLAN)
status = virtio_net_handle_vlan_table(n, ctrl.cmd, &elem);
+ else if (ctrl.class == VIRTIO_NET_CTRL_MULTIQUEUE)
+ status = virtio_net_handle_multiqueue(n, ctrl.cmd, &elem);
stb_p(elem.in_sg[elem.in_num - 1].iov_base, status);
@@ -446,7 +579,7 @@ static void virtio_net_handle_rx(VirtIODevice *vdev,
VirtQueue *vq)
{
VirtIONet *n = to_virtio_net(vdev);
- qemu_flush_queued_packets(&n->nic->nc);
+ qemu_flush_queued_packets(n->nic->ncs[vq_get_pair_index(n, vq)]);
/* We now have RX buffers, signal to the IO thread to break out of the
* select to re-poll the tap file descriptor */
@@ -455,36 +588,37 @@ static void virtio_net_handle_rx(VirtIODevice *vdev,
VirtQueue *vq)
static int virtio_net_can_receive(VLANClientState *nc)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ int queue_index = nc->queue_index;
+ VirtIONet *n = ((NICState *)nc->opaque)->opaque;
+
if (!n->vdev.vm_running) {
return 0;
}
- if (!virtio_queue_ready(n->rx_vq) ||
+ if (!virtio_queue_ready(n->vqs[queue_index].rx_vq) ||
!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
return 0;
return 1;
}
-static int virtio_net_has_buffers(VirtIONet *n, int bufsize)
+static int virtio_net_has_buffers(VirtIONet *n, int bufsize, VirtQueue *vq)
{
- if (virtio_queue_empty(n->rx_vq) ||
- (n->mergeable_rx_bufs &&
- !virtqueue_avail_bytes(n->rx_vq, bufsize, 0))) {
- virtio_queue_set_notification(n->rx_vq, 1);
+ if (virtio_queue_empty(vq) || (n->mergeable_rx_bufs &&
+ !virtqueue_avail_bytes(vq, bufsize, 0))) {
+ virtio_queue_set_notification(vq, 1);
/* To avoid a race condition where the guest has made some buffers
* available after the above check but before notification was
* enabled, check for available buffers again.
*/
- if (virtio_queue_empty(n->rx_vq) ||
- (n->mergeable_rx_bufs &&
- !virtqueue_avail_bytes(n->rx_vq, bufsize, 0)))
+ if (virtio_queue_empty(vq) || (n->mergeable_rx_bufs &&
+ !virtqueue_avail_bytes(vq, bufsize, 0))) {
return 0;
+ }
}
- virtio_queue_set_notification(n->rx_vq, 0);
+ virtio_queue_set_notification(vq, 0);
return 1;
}
@@ -595,12 +729,15 @@ static int receive_filter(VirtIONet *n, const uint8_t
*buf, int size)
static ssize_t virtio_net_receive(VLANClientState *nc, const uint8_t *buf,
size_t size)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ int queue_index = nc->queue_index;
+ VirtIONet *n = ((NICState *)(nc->opaque))->opaque;
+ VirtQueue *vq = n->vqs[queue_index].rx_vq;
struct virtio_net_hdr_mrg_rxbuf *mhdr = NULL;
size_t guest_hdr_len, offset, i, host_hdr_len;
- if (!virtio_net_can_receive(&n->nic->nc))
+ if (!virtio_net_can_receive(n->nic->ncs[queue_index])) {
return -1;
+ }
/* hdr_len refers to the header we supply to the guest */
guest_hdr_len = n->mergeable_rx_bufs ?
@@ -608,7 +745,7 @@ static ssize_t virtio_net_receive(VLANClientState *nc, const
uint8_t *buf, size_
host_hdr_len = n->has_vnet_hdr ? sizeof(struct virtio_net_hdr) : 0;
- if (!virtio_net_has_buffers(n, size + guest_hdr_len - host_hdr_len))
+ if (!virtio_net_has_buffers(n, size + guest_hdr_len - host_hdr_len, vq))
return 0;
if (!receive_filter(n, buf, size))
@@ -623,7 +760,7 @@ static ssize_t virtio_net_receive(VLANClientState *nc, const
uint8_t *buf, size_
total = 0;
- if (virtqueue_pop(n->rx_vq, &elem) == 0) {
+ if (virtqueue_pop(vq, &elem) == 0) {
if (i == 0)
return -1;
error_report("virtio-net unexpected empty queue: "
@@ -675,47 +812,50 @@ static ssize_t virtio_net_receive(VLANClientState *nc,
const uint8_t *buf, size_
}
/* signal other side */
- virtqueue_fill(n->rx_vq, &elem, total, i++);
+ virtqueue_fill(vq, &elem, total, i++);
}
if (mhdr) {
stw_p(&mhdr->num_buffers, i);
}
- virtqueue_flush(n->rx_vq, i);
- virtio_notify(&n->vdev, n->rx_vq);
+ virtqueue_flush(vq, i);
+ virtio_notify(&n->vdev, vq);
return size;
}
-static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq);
+static int32_t virtio_net_flush_tx(VirtIONet *n, VirtIONetQueue *tvq);
static void virtio_net_tx_complete(VLANClientState *nc, ssize_t len)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ VirtIONet *n = ((NICState *)nc->opaque)->opaque;
+ VirtIONetQueue *netq = &n->vqs[nc->queue_index];
- virtqueue_push(n->tx_vq, &n->async_tx.elem, n->async_tx.len);
- virtio_notify(&n->vdev, n->tx_vq);
+ virtqueue_push(netq->tx_vq, &netq->async_tx.elem,
netq->async_tx.len);
+ virtio_notify(&n->vdev, netq->tx_vq);
- n->async_tx.elem.out_num = n->async_tx.len = 0;
+ netq->async_tx.elem.out_num = netq->async_tx.len;
- virtio_queue_set_notification(n->tx_vq, 1);
- virtio_net_flush_tx(n, n->tx_vq);
+ virtio_queue_set_notification(netq->tx_vq, 1);
+ virtio_net_flush_tx(n, netq);
}
/* TX */
-static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue *vq)
+static int32_t virtio_net_flush_tx(VirtIONet *n, VirtIONetQueue *netq)
{
VirtQueueElement elem;
int32_t num_packets = 0;
+ VirtQueue *vq = netq->tx_vq;
+
if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)) {
return num_packets;
}
assert(n->vdev.vm_running);
- if (n->async_tx.elem.out_num) {
- virtio_queue_set_notification(n->tx_vq, 0);
+ if (netq->async_tx.elem.out_num) {
+ virtio_queue_set_notification(vq, 0);
return num_packets;
}
@@ -747,12 +887,12 @@ static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue
*vq)
len += hdr_len;
}
- ret = qemu_sendv_packet_async(&n->nic->nc, out_sg, out_num,
- virtio_net_tx_complete);
+ ret = qemu_sendv_packet_async(n->nic->ncs[vq_get_pair_index(n,
vq)],
+ out_sg, out_num, virtio_net_tx_complete);
if (ret == 0) {
- virtio_queue_set_notification(n->tx_vq, 0);
- n->async_tx.elem = elem;
- n->async_tx.len = len;
+ virtio_queue_set_notification(vq, 0);
+ netq->async_tx.elem = elem;
+ netq->async_tx.len = len;
return -EBUSY;
}
@@ -771,22 +911,23 @@ static int32_t virtio_net_flush_tx(VirtIONet *n, VirtQueue
*vq)
static void virtio_net_handle_tx_timer(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIONet *n = to_virtio_net(vdev);
+ VirtIONetQueue *netq = &n->vqs[vq_get_pair_index(n, vq)];
/* This happens when device was stopped but VCPU wasn't. */
if (!n->vdev.vm_running) {
- n->tx_waiting = 1;
+ netq->tx_waiting = 1;
return;
}
- if (n->tx_waiting) {
+ if (netq->tx_waiting) {
virtio_queue_set_notification(vq, 1);
- qemu_del_timer(n->tx_timer);
- n->tx_waiting = 0;
- virtio_net_flush_tx(n, vq);
+ qemu_del_timer(netq->tx_timer);
+ netq->tx_waiting = 0;
+ virtio_net_flush_tx(n, netq);
} else {
- qemu_mod_timer(n->tx_timer,
- qemu_get_clock_ns(vm_clock) + n->tx_timeout);
- n->tx_waiting = 1;
+ qemu_mod_timer(netq->tx_timer,
+ qemu_get_clock_ns(vm_clock) + netq->tx_timeout);
+ netq->tx_waiting = 1;
virtio_queue_set_notification(vq, 0);
}
}
@@ -794,48 +935,53 @@ static void virtio_net_handle_tx_timer(VirtIODevice *vdev,
VirtQueue *vq)
static void virtio_net_handle_tx_bh(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIONet *n = to_virtio_net(vdev);
+ VirtIONetQueue *netq = &n->vqs[vq_get_pair_index(n, vq)];
- if (unlikely(n->tx_waiting)) {
+ if (unlikely(netq->tx_waiting)) {
return;
}
- n->tx_waiting = 1;
+ netq->tx_waiting = 1;
/* This happens when device was stopped but VCPU wasn't. */
if (!n->vdev.vm_running) {
return;
}
virtio_queue_set_notification(vq, 0);
- qemu_bh_schedule(n->tx_bh);
+ qemu_bh_schedule(netq->tx_bh);
}
static void virtio_net_tx_timer(void *opaque)
{
- VirtIONet *n = opaque;
+ VirtIONetQueue *netq = opaque;
+ VirtIONet *n = netq->n;
+
assert(n->vdev.vm_running);
- n->tx_waiting = 0;
+ netq->tx_waiting = 0;
/* Just in case the driver is not ready on more */
if (!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
return;
- virtio_queue_set_notification(n->tx_vq, 1);
- virtio_net_flush_tx(n, n->tx_vq);
+ virtio_queue_set_notification(netq->tx_vq, 1);
+ virtio_net_flush_tx(n, netq);
}
static void virtio_net_tx_bh(void *opaque)
{
- VirtIONet *n = opaque;
+ VirtIONetQueue *netq = opaque;
+ VirtQueue *vq = netq->tx_vq;
+ VirtIONet *n = netq->n;
int32_t ret;
assert(n->vdev.vm_running);
- n->tx_waiting = 0;
+ netq->tx_waiting = 0;
/* Just in case the driver is not ready on more */
if (unlikely(!(n->vdev.status & VIRTIO_CONFIG_S_DRIVER_OK)))
return;
- ret = virtio_net_flush_tx(n, n->tx_vq);
+ ret = virtio_net_flush_tx(n, netq);
if (ret == -EBUSY) {
return; /* Notification re-enable handled by tx_complete */
}
@@ -843,33 +989,39 @@ static void virtio_net_tx_bh(void *opaque)
/* If we flush a full burst of packets, assume there are
* more coming and immediately reschedule */
if (ret >= n->tx_burst) {
- qemu_bh_schedule(n->tx_bh);
- n->tx_waiting = 1;
+ qemu_bh_schedule(netq->tx_bh);
+ netq->tx_waiting = 1;
return;
}
/* If less than a full burst, re-enable notification and flush
* anything that may have come in while we weren't looking. If
* we find something, assume the guest is still active and reschedule */
- virtio_queue_set_notification(n->tx_vq, 1);
- if (virtio_net_flush_tx(n, n->tx_vq) > 0) {
- virtio_queue_set_notification(n->tx_vq, 0);
- qemu_bh_schedule(n->tx_bh);
- n->tx_waiting = 1;
+ virtio_queue_set_notification(vq, 1);
+ if (virtio_net_flush_tx(n, netq) > 0) {
+ virtio_queue_set_notification(vq, 0);
+ qemu_bh_schedule(netq->tx_bh);
+ netq->tx_waiting = 1;
}
}
static void virtio_net_save(QEMUFile *f, void *opaque)
{
VirtIONet *n = opaque;
+ int i;
/* At this point, backend must be stopped, otherwise
* it might keep writing to memory. */
- assert(!n->vhost_started);
+ for (i = 0; i < n->queues; i++) {
+ assert(!n->vqs[i].vhost_started);
+ }
virtio_save(&n->vdev, f);
qemu_put_buffer(f, n->mac, ETH_ALEN);
- qemu_put_be32(f, n->tx_waiting);
+ qemu_put_be32(f, n->queues);
+ for (i = 0; i < n->queues; i++) {
+ qemu_put_be32(f, n->vqs[i].tx_waiting);
+ }
qemu_put_be32(f, n->mergeable_rx_bufs);
qemu_put_be16(f, n->status);
qemu_put_byte(f, n->promisc);
@@ -885,6 +1037,8 @@ static void virtio_net_save(QEMUFile *f, void *opaque)
qemu_put_byte(f, n->nouni);
qemu_put_byte(f, n->nobcast);
qemu_put_byte(f, n->has_ufo);
+ qemu_put_be16(f, n->queues);
+ qemu_put_be16(f, n->real_queues);
}
static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
@@ -902,7 +1056,10 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int
version_id)
}
qemu_get_buffer(f, n->mac, ETH_ALEN);
- n->tx_waiting = qemu_get_be32(f);
+ n->queues = qemu_get_be32(f);
+ for (i = 0; i < n->queues; i++) {
+ n->vqs[i].tx_waiting = qemu_get_be32(f);
+ }
n->mergeable_rx_bufs = qemu_get_be32(f);
if (version_id >= 3)
@@ -930,7 +1087,7 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int
version_id)
n->mac_table.in_use = 0;
}
}
-
+
if (version_id >= 6)
qemu_get_buffer(f, (uint8_t *)n->vlans, MAX_VLAN >> 3);
@@ -941,13 +1098,16 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int
version_id)
}
if (n->has_vnet_hdr) {
- tap_using_vnet_hdr(n->nic->nc.peer, 1);
- tap_set_offload(n->nic->nc.peer,
- (n->vdev.guest_features >>
VIRTIO_NET_F_GUEST_CSUM) & 1,
- (n->vdev.guest_features >>
VIRTIO_NET_F_GUEST_TSO4) & 1,
- (n->vdev.guest_features >>
VIRTIO_NET_F_GUEST_TSO6) & 1,
- (n->vdev.guest_features >> VIRTIO_NET_F_GUEST_ECN)
& 1,
- (n->vdev.guest_features >> VIRTIO_NET_F_GUEST_UFO)
& 1);
+ for(i = 0; i < n->queues; i++) {
+ tap_using_vnet_hdr(n->nic->ncs[i]->peer, 1);
+ tap_set_offload(n->nic->ncs[i]->peer,
+ (n->vdev.guest_features >>
VIRTIO_NET_F_GUEST_CSUM) & 1,
+ (n->vdev.guest_features >>
VIRTIO_NET_F_GUEST_TSO4) & 1,
+ (n->vdev.guest_features >>
VIRTIO_NET_F_GUEST_TSO6) & 1,
+ (n->vdev.guest_features >>
VIRTIO_NET_F_GUEST_ECN) & 1,
+ (n->vdev.guest_features >>
VIRTIO_NET_F_GUEST_UFO) &
+ 1);
+ }
}
}
@@ -970,6 +1130,13 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int
version_id)
}
}
+ if (version_id >= 12) {
+ if (n->queues != qemu_get_be16(f)) {
+ error_report("virtio-net: the number of queues does not
match");
+ }
+ n->real_queues = qemu_get_be16(f);
+ }
+
/* Find the first multicast entry in the saved MAC filter */
for (i = 0; i < n->mac_table.in_use; i++) {
if (n->mac_table.macs[i * ETH_ALEN] & 1) {
@@ -982,7 +1149,7 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int
version_id)
static void virtio_net_cleanup(VLANClientState *nc)
{
- VirtIONet *n = DO_UPCAST(NICState, nc, nc)->opaque;
+ VirtIONet *n = ((NICState *)nc->opaque)->opaque;
n->nic = NULL;
}
@@ -1000,6 +1167,7 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf
*conf,
virtio_net_conf *net)
{
VirtIONet *n;
+ int i;
n = (VirtIONet *)virtio_common_init("virtio-net", VIRTIO_ID_NET,
sizeof(struct virtio_net_config),
@@ -1012,7 +1180,6 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf
*conf,
n->vdev.bad_features = virtio_net_bad_features;
n->vdev.reset = virtio_net_reset;
n->vdev.set_status = virtio_net_set_status;
- n->rx_vq = virtio_add_queue(&n->vdev, 256, virtio_net_handle_rx);
if (net->tx && strcmp(net->tx, "timer") &&
strcmp(net->tx, "bh")) {
error_report("virtio-net: "
@@ -1021,15 +1188,6 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf
*conf,
error_report("Defaulting to \"bh\"");
}
- if (net->tx && !strcmp(net->tx, "timer")) {
- n->tx_vq = virtio_add_queue(&n->vdev, 256,
virtio_net_handle_tx_timer);
- n->tx_timer = qemu_new_timer_ns(vm_clock, virtio_net_tx_timer, n);
- n->tx_timeout = net->txtimer;
- } else {
- n->tx_vq = virtio_add_queue(&n->vdev, 256,
virtio_net_handle_tx_bh);
- n->tx_bh = qemu_bh_new(virtio_net_tx_bh, n);
- }
- n->ctrl_vq = virtio_add_queue(&n->vdev, 64,
virtio_net_handle_ctrl);
qemu_macaddr_default_if_unset(&conf->macaddr);
memcpy(&n->mac[0], &conf->macaddr, sizeof(n->mac));
n->status = VIRTIO_NET_S_LINK_UP;
@@ -1038,7 +1196,6 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf
*conf,
qemu_format_nic_info_str(&n->nic->nc, conf->macaddr.a);
- n->tx_waiting = 0;
n->tx_burst = net->txburst;
n->mergeable_rx_bufs = 0;
n->promisc = 1; /* for compatibility */
@@ -1046,6 +1203,33 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf
*conf,
n->mac_table.macs = g_malloc0(MAC_TABLE_ENTRIES * ETH_ALEN);
n->vlans = g_malloc0(MAX_VLAN >> 3);
+ n->queues = conf->queues;
+ n->real_queues = n->queues;
+
+ /* Allocate per rx/tx vq's */
+ for (i = 0; i < n->queues; i++) {
+ n->vqs[i].rx_vq = virtio_add_queue(&n->vdev, 256,
virtio_net_handle_rx);
+ if (net->tx && !strcmp(net->tx, "timer")) {
+ n->vqs[i].tx_vq = virtio_add_queue(&n->vdev, 256,
+ virtio_net_handle_tx_timer);
+ n->vqs[i].tx_timer = qemu_new_timer_ns(vm_clock,
+ virtio_net_tx_timer,
+ &n->vqs[i]);
+ n->vqs[i].tx_timeout = net->txtimer;
+ } else {
+ n->vqs[i].tx_vq = virtio_add_queue(&n->vdev, 256,
+ virtio_net_handle_tx_bh);
+ n->vqs[i].tx_bh = qemu_bh_new(virtio_net_tx_bh,
&n->vqs[i]);
+ }
+
+ n->vqs[i].tx_waiting = 0;
+ n->vqs[i].n = n;
+
+ if (i == 0) {
+ /* keep compatiable with spec and old guest */
+ n->ctrl_vq = virtio_add_queue(&n->vdev, 64,
virtio_net_handle_ctrl);
+ }
+ }
n->qdev = dev;
register_savevm(dev, "virtio-net", -1, VIRTIO_NET_VM_VERSION,
@@ -1059,24 +1243,33 @@ VirtIODevice *virtio_net_init(DeviceState *dev, NICConf
*conf,
void virtio_net_exit(VirtIODevice *vdev)
{
VirtIONet *n = DO_UPCAST(VirtIONet, vdev, vdev);
+ int i;
/* This will stop vhost backend if appropriate. */
virtio_net_set_status(vdev, 0);
- qemu_purge_queued_packets(&n->nic->nc);
+ for (i = 0; i < n->queues; i++) {
+ qemu_purge_queued_packets(n->nic->ncs[i]);
+ }
unregister_savevm(n->qdev, "virtio-net", n);
g_free(n->mac_table.macs);
g_free(n->vlans);
- if (n->tx_timer) {
- qemu_del_timer(n->tx_timer);
- qemu_free_timer(n->tx_timer);
- } else {
- qemu_bh_delete(n->tx_bh);
+ for (i = 0; i < n->queues; i++) {
+ VirtIONetQueue *netq = &n->vqs[i];
+ if (netq->tx_timer) {
+ qemu_del_timer(netq->tx_timer);
+ qemu_free_timer(netq->tx_timer);
+ } else {
+ qemu_bh_delete(netq->tx_bh);
+ }
}
- qemu_del_vlan_client(&n->nic->nc);
virtio_cleanup(&n->vdev);
+
+ for (i = 0; i < n->queues; i++) {
+ qemu_del_vlan_client(n->nic->ncs[i]);
+ }
}
diff --git a/hw/virtio-net.h b/hw/virtio-net.h
index 36aa463..987b5dd 100644
--- a/hw/virtio-net.h
+++ b/hw/virtio-net.h
@@ -44,6 +44,7 @@
#define VIRTIO_NET_F_CTRL_RX 18 /* Control channel RX mode support */
#define VIRTIO_NET_F_CTRL_VLAN 19 /* Control channel VLAN filtering */
#define VIRTIO_NET_F_CTRL_RX_EXTRA 20 /* Extra RX mode control support */
+#define VIRTIO_NET_F_MULTIQUEUE 22
#define VIRTIO_NET_S_LINK_UP 1 /* Link is up */
@@ -72,6 +73,8 @@ struct virtio_net_config
uint8_t mac[ETH_ALEN];
/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
uint16_t status;
+
+ uint16_t queues;
} QEMU_PACKED;
/* This is the first element of the scatter-gather list. If you don't
@@ -168,6 +171,15 @@ struct virtio_net_ctrl_mac {
#define VIRTIO_NET_CTRL_VLAN_ADD 0
#define VIRTIO_NET_CTRL_VLAN_DEL 1
+/* Control Multiqueue
+ *
+ */
+struct virtio_net_ctrl_multiqueue {
+ uint16_t num_queue_pairs;
+};
+#define VIRTIO_NET_CTRL_MULTIQUEUE 4
+ #define VIRTIO_NET_CTRL_MULTIQUEUE_QNUM 0
+
#define DEFINE_VIRTIO_NET_FEATURES(_state, _field) \
DEFINE_VIRTIO_COMMON_FEATURES(_state, _field), \
DEFINE_PROP_BIT("csum", _state, _field, VIRTIO_NET_F_CSUM,
true), \
--
1.7.1
Possibly Parallel Threads
- [RFC V2 PATCH 0/4] Multiqueue support for tap and virtio-net/vhost
- [RFC V2 PATCH 0/4] Multiqueue support for tap and virtio-net/vhost
- [RFC V3 0/5] Multiqueue support for tap and virtio-net/vhost
- [PATCHv3 3/4] qemu-kvm: vhost-net implementation
- [PATCHv3 3/4] qemu-kvm: vhost-net implementation