The cached translations are RCU-protected to allow efficient use
when processing virtqueues.
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

In virtio_queue_host_notifier_aio_poll, not all "!virtio_queue_empty()"
cases are making true progress.

Currently the offending one is virtio-scsi event queue, whose handler
does nothing if no event is pending. As a result aio_poll() will spin on
the "non-empty" VQ and take 100% host CPU.

Fix this by reporting actual progress from virtio queue aio handlers.
Reported-by: NEd Swierk <eswierk@skyportsystems.com>
Signed-off-by: NFam Zheng <famz@redhat.com>
Tested-by: NEd Swierk <eswierk@skyportsystems.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>

Current code seems to assume ring size is
always decreased but this is not required by spec:
what spec says is just that size can not exceed
the maximum. Fix it up.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Message-Id: <1484256243-1982-1-git-send-email-mst@redhat.com>
Signed-off-by: NCornelia Huck <cornelia.huck@de.ibm.com>

Add procedure for fast drop of queued packets, acting like
pop and push without mapping the buffers into memory.
Signed-off-by: NYuri Benditovich <yuri.benditovich@daynix.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Bring virtio queue to correct internal  state for host-to-guest
operations when vhost is temporary stopped.
Signed-off-by: NYuri Benditovich <yuri.benditovich@daynix.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Currently, all virtio devices bypass IOMMU completely. This is because
address_space_memory is assumed and used during DMA emulation. This
patch converts the virtio core API to use DMA API. This idea is

- introducing a new transport specific helper to query the dma address
  space. (only pci version is implemented).
- query and use this address space during virtio device guest memory
  accessing when iommu platform (VIRTIO_F_IOMMU_PLATFORM) was enabled
  for this device.

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>
Cc: Amit Shah <amit.shah@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: qemu-block@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>

Dataplane has been omitting forever the step of setting ISR when
an interrupt is raised.  This caused little breakage, because the
specification actually says that ISR may not be updated in MSI mode.

Some versions of the Windows drivers however didn't clear MSI mode
correctly, and proceeded using polling mode (using ISR, not the used
ring index!) for crashdump and hibernation.  If it were just crashdump
and hibernation it would not be a big deal, but recent releases of
Windows do not really shut down, but rather log out and hibernate to
make the next startup faster.  Hence, this manifested as a more serious
hang during shutdown with e.g. Windows 8.1 and virtio-win 1.8.0 RPMs.
Newer versions fixed this, while older versions do not use MSI at all.

The failure has always been there for virtio dataplane, but it became
visible after commits 9ffe337c ("virtio-blk: always use dataplane path
if ioeventfd is active", 2016-10-30) and ad07cd69 ("virtio-scsi: always
use dataplane path if ioeventfd is active", 2016-10-30) made virtio-blk
and virtio-scsi always use the dataplane code under KVM.  The good news
therefore is that it was not a bug in the patches---they were doing
exactly what they were meant for, i.e. shake out remaining dataplane bugs.

The fix is not hard, so it's worth arranging for the broken drivers.
The virtio_should_notify+event_notifier_set pair that is common to
virtio-blk and virtio-scsi dataplane is replaced with a new public
function virtio_notify_irqfd that also sets ISR.  The irqfd emulation
code now need not set ISR anymore, so virtio_irq is removed.
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Tested-by: NFarhan Ali <alifm@linux.vnet.ibm.com>
Tested-by: NAlex Williamson <alex.williamson@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Following the recent refactoring of virtio notifiers [1], more specifically
the patch ed08a2a0 ("virtio: use virtio_bus_set_host_notifier to
start/stop ioeventfd") that uses virtio_bus_set_host_notifier [2]
by default, core virtio code requires 'ioeventfd_started' to be set
to true/false when the host notifiers are configured.

When vhost is stopped and started, however, there is a stop followed by
another start. Since ioeventfd_started was never set to true, the 'stop'
operation triggered by virtio_bus_set_host_notifier() will not result
in a call to virtio_pci_ioeventfd_assign(assign=false). This leaves
the memory regions with stale notifiers and results on the next start
triggering the following assertion:

  kvm_mem_ioeventfd_add: error adding ioeventfd: File exists
  Aborted

This patch reintroduces (hopefully in a cleaner way) the concept
that was present with ioeventfd_disabled before the refactoring.
When ioeventfd_grabbed>0, ioeventfd_started tracks whether ioeventfd
should be enabled or not, but ioeventfd is actually not started at
all until vhost releases the host notifiers.

[1] http://lists.nongnu.org/archive/html/qemu-devel/2016-10/msg07748.html
[2] http://lists.nongnu.org/archive/html/qemu-devel/2016-10/msg07760.htmlReported-by: NFelipe Franciosi <felipe@nutanix.com>
Reported-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Reported-by: NAlex Williamson <alex.williamson@redhat.com>
Fixes: ed08a2a0 ("virtio: use virtio_bus_set_host_notifier to start/stop ioeventfd")
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Tested-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Tested-by: NFarhan Ali <alifm@linux.vnet.ibm.com>
Tested-by: NAlex Williamson <alex.williamson@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

These are not used anymore.
Signed-off-by: NGreg Kurz <groug@kaod.org>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Legacy features are those that transitional devices only
expose on the legacy interface.
Allow different ones per device class.

Cc: qemu-stable@nongnu.org # dependency for the next patch
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>

The function does not fully initialize the returned VirtQueueElement and should
be used only internally from the virtio module.
Signed-off-by: NLadi Prosek <lprosek@redhat.com>
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 function undoes the effect of virtqueue_pop and doesn't do anything
destructive or irreversible so virtqueue_unpop is a more fitting name.
Signed-off-by: NLadi Prosek <lprosek@redhat.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Of the three possible parameter combinations for
virtio_queue_set_host_notifier_fd_handler:

- assign=true/set_handler=true is only called from
  virtio_device_start_ioeventfd

- assign=false/set_handler=false is called from
  set_host_notifier_internal but it only does something when
  reached from virtio_device_stop_ioeventfd_impl; otherwise
  there is no EventNotifier set on qemu_get_aio_context().

- assign=true/set_handler=false is called from
  set_host_notifier_internal, but it is not doing anything:
  with the new start_ioeventfd and stop_ioeventfd methods,
  there is never an EventNotifier set on qemu_get_aio_context()
  at this point.  This is enforced by the assertion in
  virtio_bus_set_host_notifier.
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

This reverts commit 872dd82c.
virtio_add_queue_aio is unused.
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

This will be used to forbid iothread configuration when the
proxy does not allow using ioeventfd.  To simplify the implementation,
change the direction of the ioeventfd_disabled callback too.
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Allow customization of the start and stop of ioeventfd.  This will
allow direct start of dataplane without passing through the default
ioeventfd handlers, which in turn allows using the dataplane logic
instead of virtio_add_queue_aio.  It will also enable some code
simplification, because the sole entry point to ioeventfd setup
will be virtio_bus_set_host_notifier.
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Provide a vmsd pointer for VirtIO devices to use instead of the
load/save methods.

We'll eventually kill off the load/save methods.
Signed-off-by: NDr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Now all the usages of the old version of VMSTATE_VIRTIO_DEVICE are gone,
so we can get rid of the conditionals, and the old macro.
Signed-off-by: NHalil Pasic <pasic@linux.vnet.ibm.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

In most cases the functions passed to VMSTATE_VIRTIO_DEVICE
only call the virtio_load and virtio_save wrappers. Some include some
pre- and post- massaging too. The massaging is better expressed
as such in the VMStateDescription.

Let us prepare for changing the semantic of the VMSTATE_VIRTIO_DEVICE
macro so that it is more similar to the other VMSTATE_*_DEVICE macros
in a sense that it is a field definition.

The preprocessor conditionals are going to be removed as soon as
every usage is converted to the new semantic.
Signed-off-by: NHalil Pasic <pasic@linux.vnet.ibm.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

During device reset or similar situations a VirtQueueElement needs to be
freed without pushing it onto the used ring or rewinding the virtqueue.
Extract a new function to do this.

Later patches add virtio_detach_element() calls to existing device so
that scatter-gather lists are unmapped and vq->inuse goes back to zero
during device reset.  Currently some devices don't bother and simply
call g_free(elem) which is not a clean way to throw away a
VirtQueueElement.
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>
Acked-by: NGreg Kurz <groug@kaod.org>
Reviewed-by: NLadi Prosek <lprosek@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

QEMU prints an error message and exits when the device enters an invalid
state.  Terminating the process is heavy-handed.  The guest may still be
able to function even if there is a bug in a virtio guest driver.

Moreover, exiting is a bug in nested virtualization where a nested guest
could DoS other nested guests by killing a pass-through virtio device.
I don't think this configuration is possible today but it is likely in
the future.

If the broken flag is set, do not process virtqueues or write back used
descriptors.  The broken flag can be cleared again by resetting the
device.
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.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>

virtqueue_discard() requires a VirtQueueElement but virtio-balloon does
not migrate its in-use element.  Introduce a new function that is
similar to virtqueue_discard() but doesn't require a VirtQueueElement.

This will allow virtio-balloon to access element again after migration
with the usual proviso that the guest may have modified the vring since
last time.

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Roman Kagan <rkagan@virtuozzo.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: NLadi Prosek <lprosek@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

To make conversion of virtio devices to VMState simple
at first add a helper function for the simple virtio_save
case and a helper macro that defines the VMState structure.
These will probably go away or change as more of the virtio
code gets converted.
Signed-off-by: NDr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Using this function instead of virtio_add_queue marks the vq as aio
based. This differentiation will be useful in later patches.

Distinguish between virtqueue processing in the iohandler context and main loop
AioContext.  iohandler context is isolated from AioContexts and therefore does
not run during aio_poll().
Signed-off-by: NFam Zheng <famz@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>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>

The function pointer signature has been repeated a few times, using a
typedef may make coding easier.
Signed-off-by: NFam Zheng <famz@redhat.com>
Reviewed-by: NStefan Hajnoczi <stefanha@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>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>

Cleaned up with scripts/clean-header-guards.pl.
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>
Reviewed-by: NRichard Henderson <rth@twiddle.net>

The virtio_queue_get_id() function is the lesser used duplicate of
virtio_get_queue_index().  Use the latter instead.
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>
Message-id: 1463767461-17922-1-git-send-email-stefanha@redhat.com

Eliminating the reentrancy is actually a nice thing that we can do
with the API that Michael proposed, so let's make it first class.
This also hides the complex assign/set_handler conventions from
callers of virtio_queue_aio_set_host_notifier_handler, which in
fact was always called with assign=true.
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

In addition to handling IO in vcpu thread and in io thread, blk dataplane
introduces yet another mode: handling it by AioContext.

Currently, this reuses the same handler as previous modes,
which triggers races as these were not designed to be reentrant.
Add instead a separate handler just for aio; this will make
it possible to disable regular handlers when dataplane is active.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Acked-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Virtio dataplane needs to trigger the irq manually through the
guest notifier.  Export virtio_should_notify so that it can be
used around event_notifier_set.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Acked-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: NFam Zheng <famz@redhat.com>
Acked-by: NStefan Hajnoczi <stefanha@redhat.com>

This is used to register ioeventfd with a dataplane thread.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NFam Zheng <famz@redhat.com>
Acked-by: NStefan Hajnoczi <stefanha@redhat.com>

Since guest_mask_notifier can not be used in vhost-user mode due
to buffering implied by unix control socket, force
use_mask_notifier on virtio devices of vhost-user interfaces, and
send correct callfd to the guest at vhost start.

Using guest_notifier_mask function in vhost-user case may
break interrupt mask paradigm, because mask/unmask is not
really done when returning from guest_notifier_mask call, instead
message is posted in a unix socket, and processed later.

Add an option boolean flag 'use_mask_notifier' to disable the use
of guest_notifier_mask in virtio pci.
Signed-off-by: NDidier Pallard <didier.pallard@6wind.com>
Signed-off-by: NVictor Kaplansky <victork@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Allocate the arrays for in_addr/out_addr/in_sg/out_sg outside the
VirtQueueElement.  For now, virtqueue_pop and vring_pop keep
allocating a very large VirtQueueElement.
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Move allocation to virtio functions also when loading/saving a
VirtQueueElement.  This will also let the load/save functions
keep backwards compatibility when the VirtQueueElement layout
is changed.
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

The return code of virtqueue_pop/vring_pop is unused except to check for
errors or 0.  We can thus easily move allocation inside the functions
and just return a pointer to the VirtQueueElement.

The advantage is that we will be able to allocate only the space that
is needed for the actual size of the s/g list instead of the full
VIRTQUEUE_MAX_SIZE items.  Currently VirtQueueElement takes about 48K
of memory, and this kind of allocation puts a lot of stress on malloc.
By cutting the size by two or three orders of magnitude, malloc can
use much more efficient algorithms.

The patch is pretty large, but changes to each device are testable
more or less independently.  Splitting it would mostly add churn.
Signed-off-by: NPaolo Bonzini <pbonzini@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>

Deprecated in favor of virtqueue_map.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NIgor Mammedov <imammedo@redhat.com>

virtio_map_sg currently fails if one of the entries it's mapping is
contigious in GPA but not HVA address space.  Introduce virtio_map which
handles this by splitting sg entries.

This new API generally turns out to be a good idea since it's harder to
misuse: at least in one case the existing one was used incorrectly.

This will still fail if there's no space left in the sg, but luckily max
queue size in use is currently 256, while max sg size is 1024, so we
should be OK even is all entries happen to cross a single DIMM boundary.

Won't work well with very small DIMM sizes, unfortunately:
e.g. this will fail with 4K DIMMs where a single
request might span a large number of DIMMs.

Let's hope these are uncommon - at least we are not breaking things.

Note: virtio-scsi calls virtio_map_sg on data loaded from network, and
validates input, asserting on failure.  Copy the validating code here -
it will be dropped from virtio-scsi in a follow-up patch.
Reported-by: NIgor Mammedov <imammedo@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: NIgor Mammedov <imammedo@redhat.com>

This patch introduces virtqueue_discard() to discard a descriptor and
unmap the sgs. This will be used by the patch that will discard
descriptor when packet is truncated.

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>