Patch 06b1297017 ("virtio-net: fix network stall under load")
added double-check to test whether the available buffer size
can satisfy the request or not, in case the guest has added
some buffers to the avail ring simultaneously after the first
check. It will be lucky if the available buffer size becomes
okay after the double-check, then the host can send the packet
to the guest. If the buffer size still can't satisfy the request,
even if the guest has added some buffers, viritio-net would
stall at the host side forever.
The patch enables notification and checks whether the guest has
added some buffers since last check of available buffers when
the available buffers are insufficient. If no buffer is added,
return false, else recheck the available buffers in the loop.
If the available buffers are sufficient, disable notification
and return true.
Changes:
1. Change the return type of virtqueue_get_avail_bytes() from void
to int, it returns an opaque that represents the shadow_avail_idx
of the virtqueue on success, else -1 on error.
2. Add a new API: virtio_queue_enable_notification_and_check(),
it takes an opaque as input arg which is returned from
virtqueue_get_avail_bytes(). It enables notification firstly,
then checks whether the guest has added some buffers since
last check of available buffers or not by virtio_queue_poll(),
return ture if yes.
The patch also reverts patch "06b12970174".
The case below can reproduce the stall.
Guest 0
+--------+
| iperf |
---------------> | server |
Host | +--------+
+--------+ | ...
| iperf |----
| client |---- Guest n
+--------+ | +--------+
| | iperf |
---------------> | server |
+--------+
Boot many guests from qemu with virtio network:
qemu ... -netdev tap,id=net_x \
-device virtio-net-pci-non-transitional,\
iommu_platform=on,mac=xx:xx:xx:xx:xx:xx,netdev=net_x
Each guest acts as iperf server with commands below:
iperf3 -s -D -i 10 -p 8001
iperf3 -s -D -i 10 -p 8002
The host as iperf client:
iperf3 -c guest_IP -p 8001 -i 30 -w 256k -P 20 -t 40000
iperf3 -c guest_IP -p 8002 -i 30 -w 256k -P 20 -t 40000
After some time, the host loses connection to the guest,
the guest can send packet to the host, but can't receive
packet from the host.
It's more likely to happen if SWIOTLB is enabled in the guest,
allocating and freeing bounce buffer takes some CPU ticks,
copying from/to bounce buffer takes more CPU ticks, compared
with that there is no bounce buffer in the guest.
Once the rate of producing packets from the host approximates
the rate of receiveing packets in the guest, the guest would
loop in NAPI.
receive packets ---
| |
v |
free buf virtnet_poll
| |
v |
add buf to avail ring ---
|
| need kick the host?
| NAPI continues
v
receive packets ---
| |
v |
free buf virtnet_poll
| |
v |
add buf to avail ring ---
|
v
... ...
On the other hand, the host fetches free buf from avail
ring, if the buf in the avail ring is not enough, the
host notifies the guest the event by writing the avail
idx read from avail ring to the event idx of used ring,
then the host goes to sleep, waiting for the kick signal
from the guest.
Once the guest finds the host is waiting for kick singal
(in virtqueue_kick_prepare_split()), it kicks the host.
The host may stall forever at the sequences below:
Host Guest
------------ -----------
fetch buf, send packet receive packet ---
... ... |
fetch buf, send packet add buf |
... add buf virtnet_poll
buf not enough avail idx-> add buf |
read avail idx add buf |
add buf ---
receive packet ---
write event idx ... |
wait for kick add buf virtnet_poll
... |
---
no more packet, exit NAPI
In the first loop of NAPI above, indicated in the range of
virtnet_poll above, the host is sending packets while the
guest is receiving packets and adding buffers.
step 1: The buf is not enough, for example, a big packet
needs 5 buf, but the available buf count is 3.
The host read current avail idx.
step 2: The guest adds some buf, then checks whether the
host is waiting for kick signal, not at this time.
The used ring is not empty, the guest continues
the second loop of NAPI.
step 3: The host writes the avail idx read from avail
ring to used ring as event idx via
virtio_queue_set_notification(q->rx_vq, 1).
step 4: At the end of the second loop of NAPI, recheck
whether kick is needed, as the event idx in the
used ring written by the host is beyound the
range of kick condition, the guest will not
send kick signal to the host.
Fixes: 06b1297017 ("virtio-net: fix network stall under load")
Cc: qemu-stable@nongnu.org
Signed-off-by: Wencheng Yang <east.moutain.yang@gmail.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
with max-bytes set to 0, quota is 0 and so device does not work.
block this to avoid user confusion
Message-Id: <73a89a42d82ec8b47358f25119b87063e4a6ea57.1721818306.git.mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Add a trace point on virtio_iommu_detach_endpoint_from_domain().
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-Id: <20240716094619.1713905-7-eric.auger@redhat.com>
Tested-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
We currently miss the removal of the endpoint in case of detach.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-Id: <20240716094619.1713905-5-eric.auger@redhat.com>
Tested-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
We are currently missing the deallocation of the [host_]resv_regions
in case of hot unplug. Also to make things more simple let's rule
out the case where multiple HostIOMMUDevices would be aliased and
attached to the same IOMMUDevice. This allows to remove the handling
of conflicting Host reserved regions. Anyway this is not properly
supported at guest kernel level. On hotunplug the reserved regions
are reset to the ones set by virtio-iommu property.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-Id: <20240716094619.1713905-4-eric.auger@redhat.com>
Tested-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Now we have switched to PCIIOMMUOps to convey host IOMMU information,
the host reserved regions are transmitted when the PCIe topology is
built. This happens way before the virtio-iommu driver calls the probe
request. So let's remove the probe_done flag that allowed to check
the probe was not done before the IOMMU MR got enabled. Besides this
probe_done flag had a flaw wrt migration since it was not saved/restored.
The only case at risk is if 2 devices were plugged to a
PCIe to PCI bridge and thus aliased. First of all we
discovered in the past this case was not properly supported for
neither SMMU nor virtio-iommu on guest kernel side: see
[RFC] virtio-iommu: Take into account possible aliasing in virtio_iommu_mr()
https://lore.kernel.org/all/20230116124709.793084-1-eric.auger@redhat.com/
If this were supported by the guest kernel, it is unclear what the call
sequence would be from a virtio-iommu driver point of view.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-Id: <20240716094619.1713905-3-eric.auger@redhat.com>
Tested-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This reverts commit 1b889d6e39.
There are different problems with that tentative fix:
- Some resources are left dangling (resv_regions,
host_resv_ranges) and memory subregions are left attached to
the root MR although freed as embedded in the sdev IOMMUDevice.
Finally the sdev->as is not destroyed and associated listeners
are left.
- Even when fixing the above we observe a memory corruption
associated with the deallocation of the IOMMUDevice. This can
be observed when a VFIO device is hotplugged, hot-unplugged
and a system reset is issued. At this stage we have not been
able to identify the root cause (IOMMU MR or as structs beeing
overwritten and used later on?).
- Another issue is HostIOMMUDevice are indexed by non aliased
BDF whereas the IOMMUDevice is indexed by aliased BDF - yes the
current naming is really misleading -. Given the state of the
code I don't think the virtio-iommu device works in non
singleton group case though.
So let's revert the patch for now. This means the IOMMU MR/as survive
the hotunplug. This is what is done in the intel_iommu for instance.
It does not sound very logical to keep those but currently there is
no symetric function to pci_device_iommu_address_space().
probe_done issue will be handled in a subsequent patch. Also
resv_regions and host_resv_regions will be deallocated separately.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-Id: <20240716094619.1713905-2-eric.auger@redhat.com>
Tested-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
A virtio-net device can be added as a SR-IOV VF to another virtio-pci
device that will be the PF.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20240715-sriov-v5-7-3f5539093ffc@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Allow user to attach SR-IOV VF to a virtio-pci PF.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20240715-sriov-v5-6-3f5539093ffc@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Add support for the VIRTIO_F_IN_ORDER feature across a variety of vhost
devices.
The inclusion of VIRTIO_F_IN_ORDER in the feature bits arrays for these
devices ensures that the backend is capable of offering and providing
support for this feature, and that it can be disabled if the backend
does not support it.
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20240710125522.4168043-6-jonah.palmer@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Add VIRTIO_F_IN_ORDER feature support for the virtqueue_flush operation.
The goal of the virtqueue_ordered_flush operation when the
VIRTIO_F_IN_ORDER feature has been negotiated is to write elements to
the used/descriptor ring in-order and then update used_idx.
The function iterates through the VirtQueueElement used_elems array
in-order starting at vq->used_idx. If the element is valid (filled), the
element is written to the used/descriptor ring. This process continues
until we find an invalid (not filled) element.
For packed VQs, the first entry (at vq->used_idx) is written to the
descriptor ring last so the guest doesn't see any invalid descriptors.
If any elements were written, the used_idx is updated.
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20240710125522.4168043-5-jonah.palmer@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Add VIRTIO_F_IN_ORDER feature support for the virtqueue_fill operation.
The goal of the virtqueue_ordered_fill operation when the
VIRTIO_F_IN_ORDER feature has been negotiated is to search for this
now-used element, set its length, and mark the element as filled in
the VirtQueue's used_elems array.
By marking the element as filled, it will indicate that this element has
been processed and is ready to be flushed, so long as the element is
in-order.
Reviewed-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20240710125522.4168043-4-jonah.palmer@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Add VIRTIO_F_IN_ORDER feature support in virtqueue_split_pop and
virtqueue_packed_pop.
VirtQueueElements popped from the available/descritpor ring are added to
the VirtQueue's used_elems array in-order and in the same fashion as
they would be added the used and descriptor rings, respectively.
This will allow us to keep track of the current order, what elements
have been written, as well as an element's essential data after being
processed.
Reviewed-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20240710125522.4168043-3-jonah.palmer@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Currently, if the function fails during the key_len check, the op_code
does not have a proper value, causing virtio_crypto_free_create_session_req
not to free the memory correctly, leading to a memory leak.
By setting the op_code before performing any checks, we ensure that
virtio_crypto_free_create_session_req has the correct context to
perform cleanup operations properly, thus preventing memory leaks.
ASAN log:
==3055068==ERROR: LeakSanitizer: detected memory leaks
Direct leak of 512 byte(s) in 1 object(s) allocated from:
#0 0x5586a75e6ddd in malloc llvm/compiler-rt/lib/asan/asan_malloc_linux.cpp:129:3
#1 0x7fb6b63b6738 in g_malloc (/lib/x86_64-linux-gnu/libglib-2.0.so.0+0x5e738)
#2 0x5586a864bbde in virtio_crypto_handle_ctrl hw/virtio/virtio-crypto.c:407:19
#3 0x5586a94fc84c in virtio_queue_notify_vq hw/virtio/virtio.c:2277:9
#4 0x5586a94fc0a2 in virtio_queue_host_notifier_read hw/virtio/virtio.c:3641:9
Signed-off-by: Zheyu Ma <zheyuma97@gmail.com>
Message-Id: <20240702211835.3064505-1-zheyuma97@gmail.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The error message is actually expressive, considering QEMU only. But
when called from Libvirt, talking about "size" can be confusing, because
in Libvirt "size" translates to the memory backend size in QEMU (maximum
size) and "current" translates to the QEMU "size" property.
Let's simply avoid talking about the "size" property and spell out that
some device memory is still plugged.
Message-ID: <20240416141426.588544-1-david@redhat.com>
Tested-by: Mario Casquero <mcasquer@redhat.com>
Cc: Liang Cong <lcong@redhat.com>
Cc: Mario Casquero <mcasquer@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
In 94df5b2180 ("virtio-iommu: Fix 64kB host page size VFIO device
assignment"), in case of bypass mode, we transiently enabled the
IOMMU MR to allow the set_page_size_mask() to be called and pass
information about the page size mask constraint of cold plugged
VFIO devices. Now we do not use the IOMMU MR callback anymore, we
can just get rid of this hack.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Everything is now in place to use the Host IOMMU Device callbacks
to retrieve the page size mask usable with a given assigned device.
This new method brings the advantage to pass the info much earlier
to the virtual IOMMU and before the IOMMU MR gets enabled. So let's
remove the call to memory_region_iommu_set_page_size_mask in
vfio common.c and remove the single implementation of the IOMMU MR
callback in the virtio-iommu.c
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Retrieve the Host IOMMU Device page size mask when this latter is set.
This allows to get the information much sooner than when relying on
IOMMU MR set_page_size_mask() call, whcih happens when the IOMMU MR
gets enabled. We introduce check_page_size_mask() helper whose code
is inherited from current virtio_iommu_set_page_size_mask()
implementation. This callback will be removed in a subsequent patch.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
The error handle argument is not used anywhere. let's remove it.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
In case no IOMMUPciBus/IOMMUDevice are found we need to properly
set the error handle and return.
Fixes : Coverity CID 1549006
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Fixes: cf2647a76e ("virtio-iommu: Compute host reserved regions")
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
When a VFIO device is hoplugged in a VM using virtio-iommu, IOMMUPciBus
and IOMMUDevice cache entries are created in the .get_address_space()
handler of the machine IOMMU device. However, these entries are never
destroyed, not even when the VFIO device is detached from the machine.
This can lead to an assert if the device is reattached again.
When reattached, the .get_address_space() handler reuses an
IOMMUDevice entry allocated when the VFIO device was first attached.
virtio_iommu_set_host_iova_ranges() is called later on from the
.set_iommu_device() handler an fails with an assert on 'probe_done'
because the device appears to have been already probed when this is
not the case.
The IOMMUDevice entry is allocated in pci_device_iommu_address_space()
called from under vfio_realize(), the VFIO PCI realize handler. Since
pci_device_unset_iommu_device() is called from vfio_exitfn(), a sub
function of the PCIDevice unrealize() handler, it seems that the
.unset_iommu_device() handler is the best place to release resources
allocated at realize time. Clear the IOMMUDevice cache entry there to
fix hotplug.
Fixes: 817ef10da2 ("virtio-iommu: Implement set|unset]_iommu_device() callbacks")
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Message-Id: <20240701101453.203985-1-clg@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Commit d152cdd6f6 ("virtio: use virtio accessor to access packed event")
switched using of address_space_read_cached() to virito_lduw_phys_cached()
to access packed descriptor event.
When we used address_space_read_cached(), we needed to call
virtio_tswap16s() to handle the endianess of the field, but
virito_lduw_phys_cached() already handles it internally, so we no longer
need to call virtio_tswap16s() (as the commit had done for `off_wrap`,
but forgot for `flags`).
Fixes: d152cdd6f6 ("virtio: use virtio accessor to access packed event")
Cc: jasowang@redhat.com
Cc: qemu-stable@nongnu.org
Reported-by: Xoykie <xoykie@gmail.com>
Link: https://lore.kernel.org/qemu-devel/CAFU8RB_pjr77zMLsM0Unf9xPNxfr_--Tjr49F_eX32ZBc5o2zQ@mail.gmail.com
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20240701075208.19634-1-sgarzare@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Eugenio Pérez <eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The VHOST_USER_SET_LOG_BASE requests should be categorized into
non-vring specific messages, and should be sent only once.
If send more than once, dpdk will munmap old log_addr which may has been used and cause segmentation fault.
Signed-off-by: BillXiang <xiangwencheng@dayudpu.com>
Message-Id: <20240613065150.3100-1-xiangwencheng@dayudpu.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This fixes LeakSanitizer warnings.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20240627-san-v2-7-750bb0946dbd@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
In current code, when guest does S3, virtio-gpu are reset due to the
bit No_Soft_Reset is not set. After resetting, the display resources
of virtio-gpu are destroyed, then the display can't come back and only
show blank after resuming.
Implement No_Soft_Reset bit of PCI_PM_CTRL register, then guest can check
this bit, if this bit is set, the devices resetting will not be done, and
then the display can work after resuming.
No_Soft_Reset bit is implemented for all virtio devices, and was tested
only on virtio-gpu device. Set it false by default for safety.
Signed-off-by: Jiqian Chen <Jiqian.Chen@amd.com>
Message-Id: <20240606102205.114671-3-Jiqian.Chen@amd.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
In function kvm_virtio_pci_vector_use_one(), the function will only use
the irqfd/vector for itself. Therefore, in the undo label, the failing
process is incorrect.
To fix this, we can just remove this label.
Fixes: f9a09ca3ea ("vhost: add support for configure interrupt")
Cc: qemu-stable@nongnu.org
Signed-off-by: Cindy Lu <lulu@redhat.com>
Message-Id: <20240528084840.194538-1-lulu@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
When the vhost-user is reconnecting to the backend, and if the vhost-user fails
at the get_features in vhost_dev_init(), then the reconnect will fail
and it will not be retriggered forever.
The reason is:
When the vhost-user fail at get_features, the vhost_dev_cleanup will be called
immediately.
vhost_dev_cleanup calls 'memset(hdev, 0, sizeof(struct vhost_dev))'.
The reconnect path is:
vhost_user_blk_event
vhost_user_async_close(.. vhost_user_blk_disconnect ..)
qemu_chr_fe_set_handlers <----- clear the notifier callback
schedule vhost_user_async_close_bh
The vhost->vdev is null, so the vhost_user_blk_disconnect will not be
called, then the event fd callback will not be reinstalled.
We need to ensure that even if vhost_dev_init initialization fails, the event
handler still needs to be reinstalled when s->connected is false.
All vhost-user devices have this issue, including vhost-user-blk/scsi.
Fixes: 71e076a07d ("hw/virtio: generalise CHR_EVENT_CLOSED handling")
Signed-off-by: Li Feng <fengli@smartx.com>
Message-Id: <20240516025753.130171-3-fengli@smartx.com>
Reviewed-by: Raphael Norwitz <raphael@enfabrica.net>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This reverts commit f02a4b8e64.
Since the current patch cannot completely fix the lost reconnect
problem, there is a scenario that is not considered:
- When the virtio-blk driver is removed from the guest os,
s->connected has no chance to be set to false, resulting in
subsequent reconnection not being executed.
The next patch will completely fix this issue with a better approach.
Signed-off-by: Li Feng <fengli@smartx.com>
Message-Id: <20240516025753.130171-2-fengli@smartx.com>
Reviewed-by: Raphael Norwitz <raphael@enfabrica.net>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Fix bug imported by 27ce0f3afc ("fix Power Management Control Register for PCI Express virtio devices"
After this change, observe that QEMU may erroneously clear the power status of the device,
or may erroneously clear non writable registers, such as NO_SOFT_RESET, etc.
Only state of PM_CTRL is writable.
Only when flag VIRTIO_PCI_FLAG_INIT_PM is set, need to reset state.
Fixes: 27ce0f3afc ("fix Power Management Control Register for PCI Express virtio devices"
Signed-off-by: Jiqian Chen <Jiqian.Chen@amd.com>
Message-Id: <20240515073526.17297-2-Jiqian.Chen@amd.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The virtio-1.3 specification
<https://docs.oasis-open.org/virtio/virtio/v1.3/virtio-v1.3.html> writes:
2.8.6 Next Flag: Descriptor Chaining
Buffer ID is included in the last descriptor in the list.
If the feature (_F_INDIRECT_DESC) has been negotiated, install only
one descriptor in the virtqueue.
Therefor the buffer id should be obtained from the first descriptor.
In descriptor chaining scenarios, the buffer id should be obtained
from the last descriptor.
Fixes: 86044b24e8 ("virtio: basic packed virtqueue support")
Signed-off-by: Wafer <wafer@jaguarmicro.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20240510072753.26158-2-wafer@jaguarmicro.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Not having VIRTIO_F_RING_PACKED in feature_bits[] is a problem when the
vhost-vsock device does not offer the feature bit VIRTIO_F_RING_PACKED
but the in QEMU device is configured to try to use the packed layout
(the virtio property "packed" is on).
As of today, the Linux kernel vhost-vsock device does not support the
packed queue layout (as vhost does not support packed), and does not
offer VIRTIO_F_RING_PACKED. Thus when for example a vhost-vsock-ccw is
used with packed=on, VIRTIO_F_RING_PACKED ends up being negotiated,
despite the fact that the device does not actually support it, and
one gets to keep the pieces.
Fixes: 74b3e46630 ("virtio: add property to enable packed virtqueue")
Reported-by: Marc Hartmayer <mhartmay@linux.ibm.com>
Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
Message-Id: <20240429113334.2454197-1-pasic@linux.ibm.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Add support for the VIRTIO_F_NOTIFICATION_DATA feature across a variety
of vhost devices.
The inclusion of VIRTIO_F_NOTIFICATION_DATA in the feature bits arrays
for these devices ensures that the backend is capable of offering and
providing support for this feature, and that it can be disabled if the
backend does not support it.
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20240315165557.26942-6-jonah.palmer@oracle.com>
Acked-by: Srujana Challa <schalla@marvell.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Add support to virtio-mmio devices for handling the extra data sent from
the driver to the device when the VIRTIO_F_NOTIFICATION_DATA transport
feature has been negotiated.
The extra data that's passed to the virtio-mmio device when this feature
is enabled varies depending on the device's virtqueue layout.
The data passed to the virtio-mmio device is in the same format as the
data passed to virtio-pci devices.
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20240315165557.26942-4-jonah.palmer@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Prevent the realization of a virtio device that attempts to use the
VIRTIO_F_NOTIFICATION_DATA transport feature without disabling
ioeventfd.
Due to ioeventfd not being able to carry the extra data associated with
this feature, having both enabled is a functional mismatch and therefore
Qemu should not continue the device's realization process.
Although the device does not yet know if the feature will be
successfully negotiated, many devices using this feature wont actually
work without this extra data and would fail FEATURES_OK anyway.
If ioeventfd is able to work with the extra notification data in the
future, this compatibility check can be removed.
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20240315165557.26942-3-jonah.palmer@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Add support to virtio-pci devices for handling the extra data sent
from the driver to the device when the VIRTIO_F_NOTIFICATION_DATA
transport feature has been negotiated.
The extra data that's passed to the virtio-pci device when this
feature is enabled varies depending on the device's virtqueue
layout.
In a split virtqueue layout, this data includes:
- upper 16 bits: shadow_avail_idx
- lower 16 bits: virtqueue index
In a packed virtqueue layout, this data includes:
- upper 16 bits: 1-bit wrap counter & 15-bit shadow_avail_idx
- lower 16 bits: virtqueue index
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20240315165557.26942-2-jonah.palmer@oracle.com>
Reviewed-by: Eugenio Pérez <eperezma@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
On setups with one or more virtio-net devices with vhost on,
dirty tracking iteration increases cost the bigger the number
amount of queues are set up e.g. on idle guests migration the
following is observed with virtio-net with vhost=on:
48 queues -> 78.11% [.] vhost_dev_sync_region.isra.13
8 queues -> 40.50% [.] vhost_dev_sync_region.isra.13
1 queue -> 6.89% [.] vhost_dev_sync_region.isra.13
2 devices, 1 queue -> 18.60% [.] vhost_dev_sync_region.isra.14
With high memory rates the symptom is lack of convergence as soon
as it has a vhost device with a sufficiently high number of queues,
the sufficient number of vhost devices.
On every migration iteration (every 100msecs) it will redundantly
query the *shared log* the number of queues configured with vhost
that exist in the guest. For the virtqueue data, this is necessary,
but not for the memory sections which are the same. So essentially
we end up scanning the dirty log too often.
To fix that, select a vhost device responsible for scanning the
log with regards to memory sections dirty tracking. It is selected
when we enable the logger (during migration) and cleared when we
disable the logger. If the vhost logger device goes away for some
reason, the logger will be re-selected from the rest of vhost
devices.
After making mem-section logger a singleton instance, constant cost
of 7%-9% (like the 1 queue report) will be seen, no matter how many
queues or how many vhost devices are configured:
48 queues -> 8.71% [.] vhost_dev_sync_region.isra.13
2 devices, 8 queues -> 7.97% [.] vhost_dev_sync_region.isra.14
Co-developed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Message-Id: <1710448055-11709-2-git-send-email-si-wei.liu@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
There could be a mix of both vhost-user and vhost-kernel clients
in the same QEMU process, where separate vhost loggers for the
specific vhost type have to be used. Make the vhost logger per
backend type, and have them properly reference counted.
Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Message-Id: <1710448055-11709-1-git-send-email-si-wei.liu@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Now that we use PCIIOMMUOps to convey information about usable IOVA
ranges we do not to implement the iommu_set_iova_ranges IOMMU MR
callback.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Compute the host reserved regions in virtio_iommu_set_iommu_device().
The usable IOVA regions are retrieved from the HostIOMMUDevice.
The virtio_iommu_set_host_iova_ranges() helper turns usable regions
into complementary reserved regions while testing the inclusion
into existing ones. virtio_iommu_set_host_iova_ranges() reuse the
implementation of virtio_iommu_set_iova_ranges() which will be
removed in subsequent patches. rebuild_resv_regions() is just moved.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Implement PCIIOMMUOPs [set|unset]_iommu_device() callbacks.
In set(), the HostIOMMUDevice handle is stored in a hash
table indexed by PCI BDF. The object will allow to retrieve
information related to the physical IOMMU.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
'legacy_align' is always NULL, remove it, simplifying
memory_device_pre_plug().
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20240617071118.60464-16-philmd@linaro.org>
Generalize the current 1 byte unit and 4 byte blocking
within the output.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20240412073346.458116-5-richard.henderson@linaro.org>
Allocate a new, or append to an existing GString instead of
using a fixed sized buffer. Require the caller to determine
the length of the line -- do not bound len here.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20240412073346.458116-4-richard.henderson@linaro.org>
Split out asciidump_line as a separate function, local to hexdump.c,
for use by qemu_hexdump. Use "%-*s" to generate the alignment
between the hex and the ascii, rather than explicit spaces.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20240412073346.458116-3-richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Require that the caller output the offset and increment bufptr.
Use QEMU_HEXDUMP_LINE_BYTES in vhost_vdpa_dump_config instead
of raw integer.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20240412073346.458116-2-richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Let the callers do the reporting. This will be useful in
vfio_iommu_map_dirty_notify().
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Avihai Horon <avihaih@nvidia.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
We usually check target endianess before swapping values,
so target_words_bigendian() declaration makes sense in
"exec/tswap.h" with the target swapping helpers.
Remove "hw/core/cpu.h" when it was only included to get
the target_words_bigendian() declaration.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Anton Johansson <anjo@rev.ng>
Message-Id: <20231212123401.37493-16-philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
