commit 2e6d46d7 (vhost: add
vhost_get_features and vhost_ack_features) removes the step that
initializes the acked_features to backend_features.

As this field is now uninitialized, vhost initialization will sometimes
fail.

To fix, initialize acked_features on each ack.
Tested-by: NAndrey Korolyov <andrey@xdel.ru>
Cc: Nikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: NJason Wang <jasowang@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

commit a9f98bb5 "vhost: multiqueue
support" changed the order of stopping the device. Previously
vhost_dev_stop would disable backend and only afterwards, unset guest
notifiers. We now unset guest notifiers while vhost is still
active. This can lose interrupts causing guest networking to fail. In
particular, this has been observed during migration.

To fix this, several other changes are needed:
- remove the hdev->started assertion in vhost.c since we may want to
start the guest notifiers before vhost starts and stop the guest
notifiers after vhost is stopped.
- introduce the vhost_net_set_vq_index() and call it before setting
guest notifiers. This is to guarantee vhost_net has the correct
virtqueue index when setting guest notifiers.

MST: fix up error handling.

Cc: qemu-stable@nongnu.org
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Tested-by: NAndrey Korolyov <andrey@xdel.ru>
Reported-by: N"Zhangjie (HZ)" <zhangjie14@huawei.com>
Tested-by: NWilliam Dauchy <william@gandi.net>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

commit 783e7706
    virtio-net: stop/start bh when appropriate

is incomplete: BH might execute within the same main loop iteration but
after vmstop, so in theory, we might trigger an assertion.
I was unable to reproduce this in practice,
but it seems clear enough that the potential is there, so worth fixing.

Cc: qemu-stable@nongnu.org
Reported-by: NStefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Checking vhost device internal state in vhost_net looks like
a layering violation since vhost_net does not
set this flag: it is set and tested by vhost.c.
There seems to be no reason to check this:
caller in virtio net uses its own flag,
vhost_started, to ensure vhost is started/stopped
as appropriate.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NAmos Kong <akong@redhat.com>

The function is empty after the previous patch, so remove it.
Reviewed-by: NPeter Crosthwaite <peter.crosthwaite@xilinx.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The memory regions should be destroyed in the unrealize function;
since these NICs are not even qdev-ified, they cannot be unplugged
and they do not have to do anything to destroy their memory regions.
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NPeter Crosthwaite <peter.crosthwaite@xilinx.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

imitate nearby code about using '!value' or 'value == NULL'
Signed-off-by: NGonglei <arei.gonglei@huawei.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NEric Blake <eblake@redhat.com>
Signed-off-by: NMichael Tokarev <mjt@tls.msk.ru>

Signed-off-by: NGabriel Somlo <somlo@cmu.edu>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Make phyreg_writeops responsible for actually writing their
respective phy registers, rather than rely on set_mdic() to
do it on their behalf.

The only current instance of phyreg_writeops is set_phy_ctrl();
modify it to write the register on its own, while also correctly
handling reserved and self-clearing bits.

have_autoneg() does not need to check for MII_CR_RESTART_AUTO_NEG,
since the only time the flag comes into play is during set_phy_ctrl(),
and, following this patch, never actually gets written to the phy
control register.
Signed-off-by: NGabriel Somlo <somlo@cmu.edu>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

As of today, vhost assumes guest and host have the same endianness.
This is definitely not compatible with modern PPC64 and ARM that
can change endianness at runtime. Let's disable vhost-net and print
an error message when we detect such a case:

qemu-system-ppc64: vhost-net does not support cross-endian
qemu-system-ppc64: unable to start vhost net: 38: falling back on userspace virtio

This way users can continue to run VMs without changing their setup and
have a chance to know that performance will be impacted.
Suggested-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Reviewed-by: NAnthony Liguori <aliguori@us.ibm.com>
[ pass VirtIODevice * to memory accessors,
  converted new tswap locations to virtio_tswap,
  Greg Kurz <gkurz@linux.vnet.ibm.com> ]
Signed-off-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: NAlexander Graf <agraf@suse.de>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

In order to migrate virtio subsections, they should be streamed after
the device itself. We need the device specific code to be called from
the common migration code to achieve this. This patch introduces load
and save methods for this purpose.
Suggested-by: NAndreas Färber <afaerber@suse.de>
Signed-off-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: NAlexander Graf <agraf@suse.de>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

TCP connectivity fails when the guest has a different endianness.
The packets are silently dropped on the host by the tap backend
when they are read from user space because the endianness of the
virtio-net header is in the wrong order. These lines may appear
in the guest console:

[  454.709327] skbuff: bad partial csum: csum=8704/4096 len=74
[  455.702554] skbuff: bad partial csum: csum=8704/4096 len=74

The issue that got first spotted with a ppc64le PowerKVM guest,
but it also exists for the less common case of a x86_64 guest run
by a big-endian ppc64 TCG hypervisor.
Signed-off-by: NCédric Le Goater <clg@fr.ibm.com>
[ Ported from PowerKVM,
  Greg Kurz <gkurz@linux.vnet.ibm.com> ]
Signed-off-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Although we defined an eepro100_mdi_mask[] array indicating which bits
in the registers are read-only, we weren't actually doing anything with
it. Make the MDI register-write code use it rather than manually making
register 1 read-only and leaving the rest as reads-as-written. (The
special-case handling of register 0 remains as before since its mask is
all-zeros and the special casing happens before we apply the masking.)
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>
Message-id: 1402159924-13853-1-git-send-email-peter.maydell@linaro.org
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

It indicates the number of elements in ncs field and makes sense to have
int inside NICPeers. Also in parse_netdev we do not need to access
container and work with NICPeers only.
Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

Param name is declared as optional, since in code it is an optional
one.
Signed-off-by: NWenchao Xia <wenchaoqemu@gmail.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NEric Blake <eblake@redhat.com>
Signed-off-by: NLuiz Capitulino <lcapitulino@redhat.com>

Also fix minor indentation issues in the surrounding code.
Suggested-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NGabriel Somlo <somlo@cmu.edu>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Enable calling set_ics() from within e1000_autoneg_timer() without
the need for a forward declaration.

This patch contains no functional changes.
Signed-off-by: NGabriel Somlo <somlo@cmu.edu>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Generate a link status change interrupt once link auto-netotiation
is successfully completed. This does not affect Linux and Windows
(XP and 7 tested) in any way, but is needed by the stock OS X driver
(AppleIntel8254XEthernet.kext), which would otherwise fail to notice
the link status change event.
Signed-off-by: NGabriel Somlo <somlo@cmu.edu>
Reviewed-by: NAlexander Graf <agraf@suse.de>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Using mii-tool (on F20-live), the following output is produced:

  SIOCGMIIREG on ens3 failed: Input/output error
  ens3: no autonegotiation, 1000baseT-FD flow-control, link ok

The first line (SIOCGMIIREG error) is due to mii-tool's inability
to read the PHY auto-negotiation expansion register.
On the second line, "no autonegotiation" is wrong, and caused by
the absence of a flag in the link partner ability register which
would indicate that our link partner has acked us. This flag is
listed as "reserved" in the Intel e1000 manual, but mii-tool uses
it as LPA_LPACK from /usr/include/linux/mii.h.

This patch adds read access to PHY_AUTONEG_EXP and defines the
link partner ack flag, allowing mii-tool to generate output as
normally expected:

  ens3: negotiated 1000baseT-FD flow-control, link ok
Signed-off-by: NGabriel Somlo <somlo@cmu.edu>
Reviewed-by: NAlexander Graf <agraf@suse.de>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

This patch emulates auto-negotiation when the network link status
is modified externally (i.e. via "set_link <id> off/on").

Also, a couple of cleanup items:
  - unset PHY status reg. AUTONEG_COMPLETE during link_down()
  - set PHY status reg. AUTONEG_COMPLETE during autoneg_timer() only
    if we actually brought the link up.
  - group all checks for "can we, and should we autonegotiate?"
    together for more clarity.
Signed-off-by: NGabriel Somlo <somlo@cmu.edu>
Reviewed-by: NAlexander Graf <agraf@suse.de>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

The supplied chardev id will be inspected for supported options. Only
a socket backend, with a set path (i.e. a Unix socket) and optionally
the server parameter set, will be allowed. Other options (nowait, telnet)
will make the chardev unusable and the netdev will not be initialised.

Additional checks for validity:
  - requires `-numa node,memdev=..`
  - requires `-device virtio-net-*`

The `vhostforce` option is used to force vhost-net when we deal with
non-MSIX guests.
Signed-off-by: NAntonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: NNikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Acked-by: NLuiz Capitulino <lcapitulino@redhat.com>
Reviewed-by: NEric Blake <eblake@redhat.com>

Handle the feature bits negotiation when using vhost-user. Allow
the underlying implementation to have a finer control over all the
bits except the VIRTIO_NET_F_MAC.
Signed-off-by: NNikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Use vhost_set_backend_type to initialise a proper vhost_ops structure.
In vhost_net_init and vhost_net_start_one call conditionally TAP related
initialisation depending on the vhost backend type.
Signed-off-by: NAntonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: NNikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Decouple vhost from the Linux kernel by introducing vhost_ops. The
intention is to provide different backends - a 'kernel' backend based on
the ioctl interface, and an 'user' backend based on a UNIX domain socket
and shared memory interface.
Signed-off-by: NAntonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: NNikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

vhost_dev_init will replace devfd and devpath with a single opaque argument.
This is initialised with a file descriptor. When TAP is used (through
vhost_net), open /dev/vhost-net and pass the fd as an opaque parameter in
VhostNetOptions. The same applies to vhost-scsi - open /dev/vhost-scsi and
pass the fd.
Signed-off-by: NAntonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: NNikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

This decouples virtio-net from the TAP netdev backend and allows support
for other backends to be implemented.
Signed-off-by: NAntonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: NNikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

The poll callback needs to be called when bringing up or down
the vhost_net instance. As it is not mandatory for an NetClient
to implement it, invoke it only when it is set.
Signed-off-by: NAntonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: NNikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Generalize the features get/ack to be used for both vhost-net and vhost-scsi.
In vhost-net add vhost_net_get_feature_bits to select the feature bit set
depending on the NetClient kind.
Signed-off-by: NNikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

It's hard to track all mac addresses and their configurations (e.g
vlan or ipv6) in qemu. Without this information, it's impossible to
build proper garp packet after migration. The only possible solution
to this is let guest (who knows all configurations) to do this.

So, this patch introduces a new readonly config status bit of virtio-net,
VIRTIO_NET_S_ANNOUNCE which is used to notify guest to announce
presence of its link through config update interrupt.When guest has
done the announcement, it should ack the notification through
VIRTIO_NET_CTRL_ANNOUNCE_ACK cmd. This feature is negotiated by a new
feature bit VIRTIO_NET_F_ANNOUNCE (which has already been supported by
Linux guest).

During load, a counter of announcing rounds is set so that after the vm is
running it can trigger rounds of config interrupts to notify the guest to build
and send the correct garps.

Cc: Liuyongan <liuyongan@huawei.com>
Cc: Amos Kong <akong@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NMarkus Armbruster <armbru@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NEric Blake <eblake@redhat.com>

Signed-off-by: NMarkus Armbruster <armbru@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NEric Blake <eblake@redhat.com>

IRQ are lowered when ievent bit is cleared, so irq_pulse makes no sense
here...
Signed-off-by: NFabien Chouteau <chouteau@adacore.com>
Signed-off-by: NAlexander Graf <agraf@suse.de>

After previous Peter patch, they are redundant.  This way we don't
assign them except when needed.  Once there, there were lots of case
where the ".fields" indentation was wrong:

     .fields = (VMStateField []) {
and
     .fields =      (VMStateField []) {

Change all the combinations to:

     .fields = (VMStateField[]){

The biggest problem (appart from aesthetics) was that checkpatch complained
when we copy&pasted the code from one place to another.
Signed-off-by: NJuan Quintela <quintela@redhat.com>
Acked-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

After previous Peter patch, they are redundant.  This way we don't
assign them except when needed.  Once there, there were lots of case
where the ".fields" indentation was wrong:

     .fields = (VMStateField []) {
and
     .fields =      (VMStateField []) {

Change all the combinations to:

     .fields = (VMStateField[]){

The biggest problem (appart from aesthetics) was that checkpatch complained
when we copy&pasted the code from one place to another.
Signed-off-by: NJuan Quintela <quintela@redhat.com>
Acked-by: NAlexey Kardashevskiy <aik@ozlabs.ru>

The ne2000-isa device defines a VMState struct for migration, but
we forgot to actually register it. Correct this deficiency by
setting dc->vmsd.
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>
Signed-off-by: NMichael Tokarev <mjt@tls.msk.ru>

Just use desc instead.
Signed-off-by: NPeter Crosthwaite <peter.crosthwaite@xilinx.com>
Signed-off-by: NMichael Tokarev <mjt@tls.msk.ru>

Fix some typos in comments.
Signed-off-by: NPeter Crosthwaite <peter.crosthwaite@xilinx.com>
Signed-off-by: NMichael Tokarev <mjt@tls.msk.ru>

Add a debug printf for TX descriptor fetching. This is helpful to anyone
needing to debug TX ring buffer traversal. It is also now consistent with
the RX code which has a similar printf.
Signed-off-by: NPeter Crosthwaite <peter.crosthwaite@xilinx.com>
Signed-off-by: NMichael Tokarev <mjt@tls.msk.ru>