The virtio devices are converted to PCI-Express
if they are plugged into a PCI-Express bus and
the 'modern' protocol is enabled.

Devices plugged directly into the Root Complex as
Integrated Endpoints remain PCI.
Signed-off-by: NMarcel Apfelbaum <marcel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Guest always get zero when reading queue_enable. This violates
spec. Fixing this by setting the queue_enable to true during any guest
writing and setting it to zero during reset.

Cc: Michael S. Tsirkin <mst@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>

We used to use mmio for notification. This could be slow on some arch
(e.g on x86 without EPT). So this patch introduces pio bar and a pio
notification cap for modern device. This ability is enabled through
property "modern-pio-notify" for virtio pci devices and was disabled
by default. Management can enable when it thinks it was needed.

Benchmarks shows almost no obvious difference compared to legacy
device on machines without ept. Thanks Wenli Quan <wquan@redhat.com>
for the benchmarking.

Cc: Michael S. Tsirkin <mst@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>

We use data match eventfd for 1.0 notification currently. This could
be slow since software decoding is needed for mmio exit. To speed this
up, we can switch to use zero length mmio eventfd for 1.0 notification
since we can examine the queue index directly from the writing
address. KVM kernel module can utilize this by registering it to fast
mmio bus which could be as fast as pio on ept capable machine when
fast mmio is supported by host kernel.

Lots of improvements were seen on a ept capable machine:

Guest RX:(TCP)
size/session/+throughput%/+cpu%/-+per cpu%/
64/1/+1.6807%/[-16.2421%]/[+21.3984%]/
64/2/+0.6091%/[-11.0187%]/[+13.0678%]/
64/4/+0.0553%/[-5.9768%]/[+6.4155%]/
64/8/+0.1206%/[-4.0057%]/[+4.2984%]/
256/1/-0.0031%/[-10.1166%]/[+11.2517%]/
256/2/-0.5058%/[-6.1656%]/+6.0317%]/
...

Guest TX:(TCP)
size/session/+throughput%/+cpu%/-+per cpu%/
64/1/[+18.9183%]/-0.2823%/[+19.2550%]/
64/2/[+13.5714%]/[+2.2675%]/[+11.0533%]/
64/4/[+13.1070%]/[+2.1817%]/[+10.6920%]/
64/8/[+13.0426%]/[+2.0887%]/[+10.7299%]/
256/1/[+36.2761%]/+6.3434%/[+28.1471%]/
...
1024/1/[+44.8873%]/+2.0811%/[+41.9335%]/
...
1024/4/+0.0228%/[-2.2044%]/[+2.2774%]/
...
16384/2/+0.0127%/[-5.0346%]/[+5.3148%]/
...
65535/1/[+0.0062%]/[-4.1183%]/[+4.3017%]/
65535/2/+0.0004%/[-4.2311%]/[+4.4185%]/
65535/4/+0.0107%/[-4.6106%]/[+4.8446%]/
65535/8/-0.0090%/[-5.5178%]/[+5.8306%]/

Latency:(TCP_RR)
size/session/+transaction rate%/+cpu%/-+per cpu%/
64/1/[+6.5248%]/[-9.2882%]/[+17.4322%]/
64/25/[+11.0854%]/[+0.8000%]/[+10.2038%]/
64/50/[+12.1076%]/[+2.4627%]/[+9.4131%]/
256/1/[+5.3677%]/[+10.5669%]/-4.7024%/
256/25/[+5.6402%]/-0.8962%/[+6.5955%]/
256/50/[+5.9685%]/[+1.7766%]/[+4.1188%]/
4096/1/+0.2508%/[-10.4941%]/[+12.0047%]/
4096/25/[+1.8533%]/-0.0273%/+1.8812%/
4096/50/[+1.2156%]/-1.4134%/+2.6667%/

Notes: data with '[]' is the one whose significance is greater than 95%.

Thanks Wenli Quan <wquan@redhat.com> for the benchmarking.

Cc: Michael S. Tsirkin <mst@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>

We don't migrate the followings fields for virtio-pci:

uint32_t dfselect;
uint32_t gfselect;
uint32_t guest_features[2];
struct {
    uint16_t num;
    bool enabled;
    uint32_t desc[2];
    uint32_t avail[2];
    uint32_t used[2];
} vqs[VIRTIO_QUEUE_MAX];

This will confuse driver if migrating during initialization. Solves
this issue by:

- introduce transport specific callbacks to load and store extra
  virtqueue states.
- add a new subsection for virtio to migrate transport specific modern
  device state.
- implement pci specific callbacks.
- add a new property for virtio-pci for whether or not to migrate
  extra state.
- compat the migration for 2.4 and elder machine types

Cc: Michael S. Tsirkin <mst@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>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>

In-kernel ITS emulation on ARM64 will require to supply requester IDs.
These IDs can now be retrieved from the device pointer using new
pci_requester_id() function.

This patch adds pci_dev pointer to KVM GSI routing functions and makes
callers passing it.

x86 architecture does not use requester IDs, but hw/i386/kvm/pci-assign.c
also made passing PCI device pointer instead of NULL for consistency with
the rest of the code.
Signed-off-by: NPavel Fedin <p.fedin@samsung.com>
Message-Id: <ce081423ba2394a4efc30f30708fca07656bc500.1444916432.git.p.fedin@samsung.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

When CONFIG_LINUX is off, devices "virtio-keyboard-device",
"virtio-mouse-device", "virtio-tablet-device" and
"virtio-input-host-device" aren't compiled in, yet
"virtio-keyboard-pci", "virtio-mouse-pci", "virtio-tablet-pci" and
"virtio-input-host-pci" still are.  Attempts to introspect them crash,
e.g.

    $ qemu-system-x86_64 -device virtio-tablet-pci,help
    **
    ERROR:/work/armbru/qemu/qom/object.c:333:object_initialize_with_type: assertion failed: (type != NULL)

Broken in commit 710e2d90 and commit 006a5ede.

Fix by compiling the "virtio-FOO-pci" exactly when compiling the
"virtio-FOO-device": compile "virtio-keyboard-device",
"virtio-mouse-device", "virtio-tablet-device" regardless of
CONFIG_LINUX, and compile "virtio-input-host-pci" only for
CONFIG_LINUX.
Reported-by: NPeter Maydell <peter.maydell@linaro.org>
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>
Reviewed-by: NGerd Hoffmann <kraxel@redhat.com>
Message-Id: <1444320700-26260-3-git-send-email-armbru@redhat.com>

And do not issue an error_report in that case.
Signed-off-by: NRichard Henderson <rth@twiddle.net>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NShannon Zhao <zhaoshenglong@huawei.com>
Signed-off-by: NShannon Zhao <shannon.zhao@linaro.org>
Signed-off-by: NMichael Tokarev <mjt@tls.msk.ru>

Use the utility function pow2ceil() for rounding up to the next
largest power of 2, rather than inline calculation.
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Message-id: 1437741192-20955-3-git-send-email-peter.maydell@linaro.org

Each memory_region_add_subregion must be paired with
memory_region_del_subregion.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NPaolo Bonzini <pbonzini@redhat.com>

NOTIFY_ON_EMPTY, ANY_LAYOUT and BAD are only valid on the legacy
interface.

Hide them from modern guests.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Some guests seem to access cfg with an illegal length value.
It's worth fixing them but debugging is easier if
qemu does not crash.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

address_space_rw assumes data is in target format
and byte-swaps it if target is BE and device is LE.
Use fixed-endian LE APIs instead.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

spec says we must, so let's do it!

Note: the implementation is incorrect for BE targets.
Will fix with a patch on top, not a big deal now as
the only user is seabios, used on x86 only.
Tested-by: NGerd Hoffmann <kraxel@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Anticipating for the introduction of new add/remove functions taking
a qemu_irq parameter, let's rename existing ones with a gsi suffix.
Signed-off-by: NEric Auger <eric.auger@linaro.org>
Tested-by: NVikram Sethi <vikrams@codeaurora.org>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NPeter Maydell <peter.maydell@linaro.org>
Signed-off-by: NAlex Williamson <alex.williamson@redhat.com>

This allows to assign host input devices to the guest:

qemu -device virtio-input-host-pci,evdev=/dev/input/event<nr>

The guest gets exclusive access to the input device, so be careful
with assigning the keyboard if you have only one connected to your
machine.
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>

Move properties from virtio-*-pci to virtio-*-device.
Also make better use of QOM and attach common properties
to the abstract parent classes (virtio-input-device and
virtio-input-pci-device).

Switch the hid device instance init functions over to use
virtio_instance_init_common, so we get the properties of the
virtio device aliased properly to the virtio pci proxy.
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>

Overrunning array "proxy->guest_features" of 2 4-byte
elements at element index 2 (byte offset 8) using index
"proxy->gfselect" (which evaluates to 2). Normally, the
Linux kernel driver just read/write '0' or '1' as the
"proxy->gfselect" values, so using '<' instead of '=<' to
make coverity happy and avoid potential harm.

Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: NGonglei <arei.gonglei@huawei.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

This patch adds virtio-pci support for the emulated virtio-input
devices.  Using them is as simple as adding "-device virtio-tablet-pci"
to your command line.  If you want add multiple devices but don't want
waste a pci slot for each you can compose a multifunction device this way:

qemu -device virtio-keyboard-pci,addr=0d.0,multifunction=on \
     -device virtio-tablet-pci,addr=0d.1,multifunction=on
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

This patch adds the virtio-pci support bits for virtio-input-device.
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Initialize the modern bar and the VirtIOPCIRegion fields early, in
realize.  Also add a size field to VirtIOPCIRegion and variables for
pci bars to VirtIOPCIProxy.

This allows virtio-pci subclasses to change things before the
device_plugged callback applies them.  virtio-vga will use that to
arrange regions in a way that virtio-vga is compatible to both stdvga
(in vga mode) and virtio-gpu-pci (in pci mode).
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Now the three struct virtio_pci_caps are identical,
lets drop two of them ;)
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Also fill offset and length automatically,
from VirtIOPCIRegion->offset and region size.
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Add function to map modern virtio regions.
Add offset to VirtIOPCIRegion.
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Add init function for the modern pci regions,
move over the init code.
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

For now just place the MemoryRegion there,
following patches will add more.
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Currently, during host notifier set. We only add eventfd for legacy
bar, this is not correct since:

- Non-transitional device does not have legacy bar, so qemu will crash
  since proxy->bar was not initialized.
- Modern device uses modern bar and notify cap to notify the device,
  we should add eventfd for proxy->notify.

So this patch fixes the above two issues by adding eventfd based on
whether legacy or modern device were supported.
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>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

This patch adds variables for the pci bars (to get rid of the magic
numbers in the code) and moves the modern virtio bar to region 4 so
regions 2+3 are kept free.  virtio-vga wants use them.
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

Add VIRTIO_PCI_FLAG_DISABLE_LEGACY and VIRTIO_PCI_FLAG_DISABLE_MODERN
for VirtIOPCIProxy->flags.  Also add properties for them.  They can be
used to disable modern (virtio 1.0) or legacy (virtio 0.9) modes.

By default only legacy is advertized, modern will be turned on by
default once all remaining spec compilance issues are addressed.
Signed-off-by: NGerd Hoffmann <kraxel@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

virtio 1.0 config space is in LE format for all
devices, use modern wrappers when accessed through
the 1.0 BAR.
Reported-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

This is somewhat functional.  With this, and linux driver from my tree,
I was able to use virtio net as virtio 1.0 device for light browsing.

At the moment, dataplane and vhost code is
still missing.

Based on Cornelia's virtio 1.0 patchset:
    Date: Thu, 11 Dec 2014 14:25:02 +0100
    From: Cornelia Huck <cornelia.huck@de.ibm.com>
    To: virtualization@lists.linux-foundation.org, qemu-devel@nongnu.org
    Cc: rusty@rustcorp.com.au, thuth@linux.vnet.ibm.com, mst@redhat.com,
    Cornelia Huck <cornelia.huck@de.ibm.com>
    Subject: [PATCH RFC v6 00/20] qemu: towards virtio-1 host support
    Message-Id: <1418304322-7546-1-git-send-email-cornelia.huck@de.ibm.com>

which is itself still missing some core bits.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

Easier than duplicating code.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>

We should validate the vq index against nvqs_with_notifiers. Otherwise we may
try to mask or unmask vector for vqs without notifiers (e.g control vq). This
will lead qemu abort on kvm_irqchip_commit_routes() when trying to boot win8.1
guest.

Fixes 851c2a75 ("virtio-pci: speedup MSI-X
masking and unmasking")
Reported-by: NAlex Williamson <alex.williamson@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>

VIRTIO_PCI_QUEUE_MAX is not only used for pci, so rename it be generic.

Cc: Amit Shah <amit.shah@redhat.com>
Cc: Paolo Bonzini <pbonzini@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>

This patch passes error pointer to transport specific device_plugged()
callback. Through this way, device_plugged() can do some transport
specific check and fail. This will be uesd by following patches that
check the number of virtqueues against the transport limitation.

Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Alexander Graf <agraf@suse.de>
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>