The virtio_net offload APIs are used on the NIC's peer (i.e. the tap
device). The API was defined to implicitly use nc->peer, saving the
caller the trouble.
This wasn't ideal because:
1. There are callers who have the peer but not the NIC. Currently they
are forced to bypass the API and access peer->info->... directly.
2. The rest of the net.h API uses nc, not nc->peer, so it is
inconsistent.
This patch pushes nc->peer back up to callers.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
This patch fixes configure so that the netmap backend is not compiled in if the
host doesn't support an API version >= 11. A version upper bound (15) has been
added so that the netmap API can be extended with some minor features without
requiring QEMU code modifications.
Moreover, some changes have been done to net/netmap.c in order to reflect the
current netmap API/ABI (11).
The NETMAP_WITH_LIBS macro makes possible to include some utilities (e.g.
netmap ring macros, D(), RD() and other high level functions) through the netmap
headers. In this way we get rid of the D and RD macro definitions in the QEMU
code, and we open the way for further code simplifications that will be
introduced by future patches.
Signed-off-by: Vincenzo Maffione <v.maffione@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Whit this patch, the netmap backend supports TSO/UFO/CSUM
offloadings, and accepts the virtio-net header, similarly to what
happens with TAP. The offloading callbacks in the NetClientInfo
interface have been implemented.
Signed-off-by: Vincenzo Maffione <v.maffione@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Since TAP offloadings are manipulated through a new API, it's
not necessary to export them in include/net/tap.h anymore.
Signed-off-by: Vincenzo Maffione <v.maffione@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The TAP NetClientInfo structure is inizialized with the TAP-specific
functions that manipulates offloading features.
Signed-off-by: Vincenzo Maffione <v.maffione@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Some new callbacks have been added to generalize the operations done
by virtio-net and vmxnet3 frontends to manipulate TAP offloadings.
Signed-off-by: Vincenzo Maffione <v.maffione@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The tap_has_vnet_hdr() and tap_has_vnet_hdr_len() functions used
to return int, even though they only return true/false values.
This patch changes the prototypes to return bool.
Signed-off-by: Vincenzo Maffione <v.maffione@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
error_is_set(&var) is the same as var != NULL, but it takes
whole-program analysis to figure that out. Unnecessarily hard for
optimizers, static checkers, and human readers. Dumb it down to
obvious.
Gets rid of several dozen Coverity false positives.
Note that the obvious form is already used in many places.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
assign_name() in net/net.c is using snprintf + g_strdup to get the same
result as g_strdup_printf.
Signed-off-by: Hani Benhabiles <kroosec@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
This improves readability and simplifies the code.
Cc: Anthony Liguori <aliguori@amazon.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Stefan Weil <sw@weilnetz.de>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
When a link change occurs on a backend (like tap), we currently do
not propage such change to the nic. As a result, when someone turns
off a link on a tap device, for instance, then a guest doesn't see
that change and continues to try to send traffic or run DHCP even
though the lower-layer is disconnected. This is OK when the network
is set up as a HUB since the the guest may be connected to other HUB
ports too, but when it's set up as a netdev, it makes thinkgs worse.
The patch addresses this by setting the peers link down only when the
peer is not a HUBPORT device. With this patch, in the following config
-netdev tap,id=net0 -device e1000,mac=XXXXX,netdev=net0
when net0 link is turned off, the guest e1000 shows lower-layer link
down. This allows guests to boot much faster in such configurations.
With windows guest, it also allows the network to recover properly
since windows will not configure the link-local IPv4 address, and
when the link is turned on, the proper address address is configured.
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
This patch adds support for a network backend based on netmap.
netmap is a framework for high speed packet I/O. You can use it
to build extremely fast traffic generators, monitors, software
switches or network middleboxes. Its companion software switch
VALE lets you interconnect virtual machines.
netmap and VALE are implemented as a non-intrusive kernel module,
support NICs from multiple vendors, are part of standard FreeBSD
distributions and available in source format for Linux too.
To compile QEMU with netmap support, use the following configure
options:
./configure [...] --enable-netmap --extra-cflags=-I/path/to/netmap/sys
where "/path/to/netmap" contains the netmap source code, available at
http://info.iet.unipi.it/~luigi/netmap/
The same webpage contains more information about the netmap project
(together with papers and presentations).
Signed-off-by: Vincenzo Maffione <v.maffione@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Do not return after net_hub_flush(). Always flush callee network client
incoming queue.
Signed-off-by: Sergey Fedorov <s.fedorov@samsung.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
[Assigning a multicast MAC address to a NIC leads to confusing behavior.
Reject multicast MAC addresses so users are alerted to their error
straight away.
The "net/eth.h" in6_addr rename prevents a name collision with
<netinet/in.h> on Linux.
-- Stefan]
Signed-off-by: Dmitry V. Krivenok <krivenok.dmitry@gmail.com>
Reviewed-by: Amos Kong <kongjianjun@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
SO_REUSEADDR should be avoided on Windows but is desired on other operating
systems. So instead of setting it we call socket_set_fast_reuse that will result
in the appropriate behaviour on all operating systems.
An exception to this rule are multicast sockets where it is sensible to have
multiple sockets listen on the same ip and port and we should set SO_REUSEADDR
on windows.
Signed-off-by: Sebastian Ottlik <ottlik@fzi.de>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Stefan Weil <sw@weilnetz.de>
Each networking client has a queue for packets that could not yet be
delivered to that client. Calling this queue "send_queue" is highly
confusing as it has nothing to to with packets send from this client but
to it. Avoid this confusing by renaming it to "incoming_queue".
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The following patch simplifies the *BSD tap/tun code and makes use of numbered
tap/tun interfaces on all *BSD OS's. NetBSD has a patch in their pkgsrc tree
to make use of this feature and DragonFly also supports this as well.
Signed-off-by: Brad Smith <brad@comstyle.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
This is an autogenerated patch using scripts/switch-timer-api.
Switch the entire code base to using the new timer API.
Note this patch may introduce some line length issues.
Signed-off-by: Alex Bligh <alex@alex.org.uk>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
include/qemu/timer.h has no need to include main-loop.h and
doing so causes an issue for the next patch. Unfortunately
various files assume including timers.h will pull in main-loop.h.
Untangle this mess.
Signed-off-by: Alex Bligh <alex@alex.org.uk>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The macro g_assert_not_reached is a better self documenting replacement
for assert(0) or assert(false).
Signed-off-by: Stefan Weil <sw@weilnetz.de>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Currently macvtap based macvlan device is working in promiscuous
mode, we want to implement mac-programming over macvtap through
Libvirt for better performance.
Design:
QEMU notifies Libvirt when rx-filter config is changed in guest,
then Libvirt query the rx-filter information by a monitor command,
and sync the change to macvtap device. Related rx-filter config
of the nic contains main mac, rx-mode items and vlan table.
This patch adds a QMP event to notify management of rx-filter change,
and adds a monitor command for management to query rx-filter
information.
Test:
If we repeatedly add/remove vlan, and change macaddr of vlan
interfaces in guest by a loop script.
Result:
The events will flood the QMP client(management), management takes
too much resource to process the events.
Event_throttle API (set rate to 1 ms) can avoid the events to flood
QMP client, but it could cause an unexpected delay (~1ms), guests
guests normally expect rx-filter updates immediately.
So we use a flag for each nic to avoid events flooding, the event
is emitted once until the query command is executed. The flag
implementation could not introduce unexpected delay.
There maybe exist an uncontrollable delay if we let Libvirt do the
real change, guests normally expect rx-filter updates immediately.
But it's another separate issue, we can investigate it when the
work in Libvirt side is done.
Michael S. Tsirkin: tweaked to enable events on start
Michael S. Tsirkin: fixed not to crash when no id
Michael S. Tsirkin: fold in patch:
"additional fixes for mac-programming feature"
Amos Kong: always notify QMP client if mactable is changed
Amos Kong: return NULL list if no net client supports rx-filter query
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Amos Kong <akong@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
reorder slirp config options. first check the dns-server-address,
then check the first-dhcp-address. the original code was comparing
the first-dhcp-address with the default dns-server-address, not
the configured dns-server-address.
Signed-off-by: Bas van Sisseren <bas@quarantainenet.nl>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
This patch forbid the following invalid parameters to tap:
1) fd and vhostfds were specified but vhostfd were not specified
2) vhostfds were specified but fds were not specified
3) fds and vhostfd were specified
For 1 and 2, net_init_tap_one() will still pass NULL as vhostfdname to
monitor_handle_fd_param(), which may crash the qemu.
Also remove the unnecessary has_fd check.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Stefan Hajnoczi <shajnocz@redhat.com>
Cc: Laszlo Ersek <lersek@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Only tap->vhostfd were checked net_init_tap_one(), but tap->vhostfds were
forgot, this will lead qemu to ignore all fds passed by management through
vhostfds, and tries to create vhost_net device itself. Fix by adding this check
also.
Reportyed-by: Michal Privoznik <mprivozn@redhat.com>
Cc: Michal Privoznik <mprivozn@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
assign_name() creates a name MODEL.NUM, where MODEL is the client's model,
and NUM is the number of MODELs that already exist.
Markus added NIC naming for non-VLAN clients in commit 53e51d85.
commit d33d93b2 incorrectly added a judgement of net-hub. It caused
net clients created with -netdev get same names.
eg:
# qemu-upstream -device virtio-net-pci,netdev=h1 -netdev tap,id=h1 \
-device virtio-net-pci,netdev=h2 -netdev tap,id=h2 ..
(qemu) info network
virtio-net-pci.0: index=0,type=nic,model=virtio-net-pci,macaddr=52:54:00:12:34:56
\ h1: index=0,type=tap,ifname=tap0,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown
virtio-net-pci.0: index=0,type=nic,model=virtio-net-pci,macaddr=52:54:00:12:34:57
\ h2: index=0,type=tap,ifname=tap1,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown
This patch removed the check of nic-hub, and created unique names for
all net clients that have same model.
v2: update commitlog & comments
Signed-off-by: Amos Kong <akong@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Many of these should be cleaned up with proper qdev-/QOM-ification.
Right now there are many catch-all headers in include/hw/ARCH depending
on cpu.h, and this makes it necessary to compile these files per-target.
However, fixing this does not belong in these patches.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
chardev-frontends need to explictly check, increase and decrement the
avail_connections "property" of the chardev when they are not using a
qdev-chardev-property for the chardev.
This fixes things like:
qemu-kvm -chardev stdio,id=foo -device isa-serial,chardev=foo \
-mon chardev=foo
Working, where they should fail. Most of the changes here are due to
old hardware emulation code which is using serial_hds directly rather then
a qdev-chardev-property.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Message-id: 1364412581-3672-3-git-send-email-hdegoede@redhat.com
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
There are several code paths in net_init_socket() depending on how the
socket is created: file descriptor passing, UDP multicast, TCP, or UDP.
Some of these support both listen and connect.
Not all code paths set the socket to non-blocking. This patch addresses
the file descriptor passing and UDP cases which were missing
socket_set_nonblock(fd) calls.
I considered moving socket_set_nonblock(fd) to a central location but it
turns out the code paths are different enough to require non-blocking at
different places.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
The fcntl(fd, F_SETFL, O_NONBLOCK) flag is not specific to sockets.
Rename to qemu_set_nonblock() just like qemu_set_cloexec().
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
Socket buffer sizes were hard-coded to 4K for VDE and socket netdevs. Bump this
up to 68K (ala tap netdev) to handle maximum GSO packet size (64k) plus plenty
of room for the ethernet and virtio_net headers.
Originally, ran into this limitation when using -netdev UDP sockets to connect
VM-to-VM, where VM interface is configure with MTU=9000. (Using virtio_net
NIC model). Test is simple: ping -M do -s 8500 <target>. This test will
attempt to ping with unfragmented packet of given size. Without patch, size
is limited to < 4K (minus protocol hdrs). With patch, ping test works with pkt
size up to 9000 (again, minus protocol hdrs).
v2: per Stefan, increase buf size to (4096+65536) as done in tap and apply
to vde and socket netdevs.
v1: increase buf size to 12K just for -netdev UDP sockets
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
net_checksum_add_cont()
checksum calculation for scattered data with odd chunk sizes
net_raw_checksum()
checksum calculation for a buffer
Signed-off-by: Dmitry Fleytman <dmitry@daynix.com>
Signed-off-by: Yan Vugenfirer <yan@daynix.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reduce -netdev socket latency by disabling the Nagle algorithm on
SOCK_STREAM sockets in net/socket.c. Since we are tunelling Ethernet
over TCP we shouldn't artificially delay outgoing packets, let the guest
decide packet scheduling.
I already get sub-millisecond -netdev socket ping times on localhost, so
there was no measurable difference in my testing. This won't hurt
though and may improve remote socket performance.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
Fix various typos and misspellings. The bulk of these were found with
codespell.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Stefan Weil <sw@weilnetz.de>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Instead of adding missing type casts which are needed by MinGW for the
4th argument, the patch uses qemu_setsockopt which was invented for this
purpose.
Signed-off-by: Stefan Weil <sw@weilnetz.de>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Edivaldo reports a problem that the array of NetClientState in NICState is too
large - MAX_QUEUE_NUM(1024) which will wastes memory even if multiqueue is not
used.
Instead of static arrays, solving this issue by allocating the queues on demand
for both the NetClientState array in NICState and VirtIONetQueue array in
VirtIONet.
Tested by myself, with single virtio-net-pci device. The memory allocation is
almost the same as when multiqueue is not merged.
Cc: Edivaldo de Araujo Pereira <edivaldoapereira@yahoo.com.br>
Cc: qemu-stable@nongnu.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
historically the kernel queues packets two times. once
at the device and second in qdisc. this is believed to cause
interface stalls if one of these queues overruns.
setting IFF_ONE_QUEUE is the default in kernels >= 3.8. the
flag is ignored since then. see kernel commit
5d097109257c03a71845729f8db6b5770c4bbedc
Signed-off-by: Peter Lieven <pl@kamp.de>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Obviously, hub does not support multiqueue tap. So this patch forbids creating
multiple queue tap when hub is used to prevent the crash when command line such
as "-net tap,queues=2" is used.
Cc: qemu-stable@nongnu.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
In the current implementation of qemu, running without a network
backend will cause the queue to grow unbounded when the guest is
transmitting traffic.
This patch fixes the problem by implementing bounded size NetQueue,
used with an arbitrary limit of 10000 packets, and dropping packets
when the queue is full _and_ the sender does not pass a callback.
The second condition makes sure that we never drop packets that
contains a callback (which would be tricky, because the producer
expects the callback to be run when all previous packets have been
consumed; so we cannot run it when the packet is dropped).
If documentation is correct, producers that submit a callback should
stop sending when their packet is queued, so there is no real risk
that the queue exceeds the max size by large values.
Signed-off-by: Luigi Rizzo <rizzo@iet.unipi.it>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
When frontend and backend are connected through a hub as below
(showing only one direction), and the frontend (or in general, all
output ports of the hub) cannot accept more traffic, the backend
queues packets in queue-A.
When the frontend (or in general, one output port) becomes ready again,
quemu tries to flush packets from queue-B, which is unfortunately empty.
e1000.0 <--[queue B]-- hub0port0(hub)hub0port1 <--[queue A]-- tap.0
To fix this i propose to introduce a new function net_hub_flush()
which is called when trying to flush a queue connected to a hub.
Signed-off-by: Luigi Rizzo <rizzo@iet.unipi.it>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The pSeries machine and some other devices don't supply a cleanup
callback. Revert part of 1ceef9f273 that
started calling it unconditionally.
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Andreas Färber <afaerber@suse.de>
Message-id: 1360707366-9271-1-git-send-email-afaerber@suse.de
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
1ceef9f273 added handling for cleaning
up multiple queues in qemu_del_nic() for cases where multiqueue is in
use. To determine the number of queues it looks at nic->conf->queues,
then iterates through all the queues to cleanup the associated
NetClientStates. If no queues are found, no NetClientStates are deleted.
However, nic->conf->queues is only set when a peer is created via
-netdev or netdev_add, and is otherwise 0. This causes us to spin in
net_cleanup() if we attempt to shut down qemu before adding a host
device.
Since qemu_new_nic() unconditionally creates at least 1
queue/NetClientState at queue idx 0, make qemu_del_nic() always attempt
to clean it up.
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
The multiqueue patch series broke -netdev tap,fd=X which manifests
as libvirt not being able to start a guest. This was because it
passed NULL for the netdev name which results in an anonymous netdev
device regardless of what the user specified.
Cc: Jason Wang <jasowang@redhat.com>
Cc: Bruce Rogers <brogers@suse.com>
Reported-by: Bruce Rogers <brogers@suse.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
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>
This patch introduces a helper tap_get_ifname() to get the device name of tap
device. This is needed when ifname is unspecified in the command line and qemu
were asked to create tap device by itself. In this situation, the name were
allocated by kernel, so if multiqueue is asked, we need to fetch its name after
creating the first queue.
Only linux has this support since it's the only platform that supports
multiqueue tap.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
This patch introduce a new bit - enabled in TAPState which tracks whether a
specific queue/fd is enabled. The tap/fd is enabled during initialization and
could be enabled/disabled by tap_enalbe() and tap_disable() which calls platform
specific helpers to do the real work. Polling of a tap fd can only done when
the tap was enabled.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Stefan Hajnoczi