Problem
-------
The expected initial state of the table depends on feature negotiation:
With VIRTIO_NET_F_CTRL_VLAN:
The table must be empty in accordance with the specification.
Without VIRTIO_NET_F_CTRL_VLAN:
The table must be filled to permit all VLAN traffic.
Prior to commit 06b636a1e2 ("virtio-net: do not reset vlan filtering
at set_features"), virtio_net_set_features() always reset the VLAN
table. That commit changed the behavior to skip table reset when
VIRTIO_NET_F_CTRL_VLAN was negotiated, assuming the table would be
properly cleared during device reset and remain stable.
However, this assumption breaks when a driver renegotiates features:
1. Initial negotiation without VIRTIO_NET_F_CTRL_VLAN (table filled)
2. Renegotiation with VIRTIO_NET_F_CTRL_VLAN (table will not be cleared)
The problem was exacerbated by commit 0caed25cd1 ("virtio: Call
set_features during reset"), which triggered virtio_net_set_features()
during device reset, exposing the bug whenever VIRTIO_NET_F_CTRL_VLAN
was negotiated after a device reset.
Solution
--------
Fix the issue by initializing the table when virtio_net_set_features()
is called to change the VIRTIO_NET_F_CTRL_VLAN bit of
vdev->guest_features.
This approach ensures the correct table state regardless of feature
negotiation sequence by performing initialization in
virtio_net_set_features() as QEMU did prior to commit 06b636a1e2
("virtio-net: do not reset vlan filtering at set_features").
This change still preserves the goal of the commit, which was to avoid
resetting the table during migration, by checking whether the
VIRTIO_NET_F_CTRL_VLAN bit of vdev->guest_features is being changed;
vdev->guest_features is set before virtio_net_set_features() gets called
during migration.
It also avoids resetting the table when the driver sets a feature
bitmask with no change for the VIRTIO_NET_F_CTRL_VLAN bit, which makes
the operation idempotent and its semantics cleaner.
Additionally, this change ensures the table is initialized after
feature negotiation and before the DRIVER_OK status bit being set for
compatibility with the Linux driver before commit 50c0ada627f5
("virtio-net: fix race between ndo_open() and virtio_device_ready()"),
which did not ensure to set the DRIVER_OK status bit before modifying
the table.
Fixes: 06b636a1e2 ("virtio-net: do not reset vlan filtering at set_features")
Cc: qemu-stable@nongnu.org
Reported-by: Konstantin Shkolnyy <kshk@linux.ibm.com>
Signed-off-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Tested-by: Konstantin Shkolnyy <kshk@linux.ibm.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Message-Id: <20250727-vlan-v3-1-bbee738619b1@rsg.ci.i.u-tokyo.ac.jp>
Tested-by: Konstantin Shkolnyy <kshk@linux.ibm.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
We use the local variable 'buf' only when we call dma_memory_read(),
and it is always set to &tx_send_buffer[prev_buf_size] immediately
before both of those calls. So remove the variable and pass
tx_send_buffer + prev_buf_size to dma_memory_read().
This fixes in passing a place where we set buf = tx_send_buffer
but never used that value because we always updated buf to
something else later before using it.
Coverity: CID 1534027
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
In gmac_try_send_next_packet() we have code that does "if this block
of data won't fit in the buffer, reallocate it". However, the
condition it uses is
if ((prev_buf_size + tx_buf_len) > sizeof(buf))
where buf is a uint8_t *.
This means that sizeof(buf) is always 8 bytes, and the condition will
almost always be true, so we will reallocate the buffer more often
than we need to.
Correct the condition to test against tx_buffer_size, which is
where we track how big the allocated buffer is.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
After the bug fix in the previous commit, the length and prev_buf_size
variables are identical, except that prev_buf_size is uint32_t and
length is uint16_t. We can therefore unify them. The only place where
the type makes a difference is that we will truncate the packet
at 64K when sending it; this commit preserves that behaviour
by using a local variable when doing the packet send.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
The transmit loop in gmac_try_send_next_packet() is constructed in a
way that means it will send incorrect data if it it sends more than
one packet.
The function assembles the outbound data in a dynamically allocated
block of memory which is pointed to by tx_send_buffer. We track the
first point in this block of memory which is not yet used with the
prev_buf_size offset, initially zero. We track the size of the
packet we're sending with the length variable, also initially zero.
As we read chunks of data out of guest memory, we write them to
tx_send_buffer[prev_buf_size], and then increment both prev_buf_size
and length. (We might dynamically reallocate the buffer if needed.)
When we send a packet, we checksum and send length bytes, starting at
tx_send_buffer, and then we reset length to 0. This gives the right
data for the first packet. But we don't reset prev_buf_size. This
means that if we process more descriptors with further data for the
next packet, that data will continue to accumulate at offset
prev_buf_size, i.e. after the data for the first packet. But when
we transmit that second packet, we send length bytes from
tx_send_buffer, so we will send a packet which has the length of the
second packet but the data of the first one.
The fix for this is to also clear prev_buf_size after the packet has
been sent -- we never need the data from packet one after we've sent
it, so we can write packet two's data starting at the beginning of
the buffer.
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
virtio,pci,pc: features, fixes, tests
SPCR acpi table can now be disabled
vhost-vdpa can now report hashing capability to guest
PPTT acpi table now tells guest vCPUs are identical
vost-user-blk now shuts down faster
loongarch64 now supports bios-tables-test
intel_iommu now supports ATS
cxl now supports DCD Fabric Management Command Set
arm now supports acpi pci hotplug
fixes, cleanups
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
# -----BEGIN PGP SIGNATURE-----
#
# iQFDBAABCgAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAmh1+7APHG1zdEByZWRo
# YXQuY29tAAoJECgfDbjSjVRpcZ8H/2udpCZ49vjPB8IwQAGdFTw2TWVdxUQFHexQ
# pOsCGyFBNAXqD1bmb8lwWyYVJ08WELyL6xWsQ5tfVPiXpKYYHPHl4rNr/SPoyNcv
# joY++tagudmOki2DU7nfJ+rPIIuigOTUHbv4TZciwcHle6f65s0iKXhR1sL0cj4i
# TS6iJlApSuJInrBBUxuxSUomXk79mFTNKRiXj1k58LRw6JOUEgYvtIW8i+mOUcTg
# h1dZphxEQr/oG+a2pM8GOVJ1AFaBPSfgEnRM4kTX9QuTIDCeMAKUBo/mwOk6PV7z
# ZhSrDPLrea27XKGL++EJm0fFJ/AsHF1dTks2+c0rDrSK+UV87Zc=
# =sktm
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 15 Jul 2025 02:56:48 EDT
# gpg: using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg: issuer "mst@redhat.com"
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full]
# gpg: aka "Michael S. Tsirkin <mst@redhat.com>" [full]
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17 0970 C350 3912 AFBE 8E67
# Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA 8A0D 281F 0DB8 D28D 5469
* tag 'for_upstream' of https://git.kernel.org/pub/scm/virt/kvm/mst/qemu: (97 commits)
hw/cxl: mailbox-utils: 0x5605 - FMAPI Initiate DC Release
hw/cxl: mailbox-utils: 0x5604 - FMAPI Initiate DC Add
hw/cxl: Create helper function to create DC Event Records from extents
hw/cxl: mailbox-utils: 0x5603 - FMAPI Get DC Region Extent Lists
hw/cxl: mailbox-utils: 0x5602 - FMAPI Set DC Region Config
hw/mem: cxl_type3: Add DC Region bitmap lock
hw/cxl: Move definition for dynamic_capacity_uuid and enum for DC event types to header
hw/cxl: mailbox-utils: 0x5601 - FMAPI Get Host Region Config
hw/mem: cxl_type3: Add dsmas_flags to CXLDCRegion struct
hw/cxl: mailbox-utils: 0x5600 - FMAPI Get DCD Info
hw/cxl: fix DC extent capacity tracking
tests: virt: Update expected ACPI tables for virt test
hw/acpi/aml-build: Build a root node in the PPTT table
hw/acpi/aml-build: Set identical implementation flag for PPTT processor nodes
tests: virt: Allow changes to PPTT test table
qtest/bios-tables-test: Generate reference blob for DSDT.acpipcihp
qtest/bios-tables-test: Generate reference blob for DSDT.hpoffacpiindex
tests/qtest/bios-tables-test: Add aarch64 ACPI PCI hotplug test
tests/qtest/bios-tables-test: Prepare for addition of acpi pci hp tests
hw/arm/virt: Let virt support pci hotplug/unplug GED event
...
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Conflicts:
net/vhost-vdpa.c
vhost_vdpa_set_steering_ebpf() was removed, resolve the context
conflict.
By default, virtio-net limits the hash types that will be advertised to
the guest so that all hash types are covered by the offloading
capability the client provides. This change allows to override this
behavior and to advertise hash types that require user-space hash
calculation by specifying "on" for the corresponding properties.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20250530-vdpa-v1-6-5af4109b1c19@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Introduce a boolean is_vhost_user field to the vhost_net
structure. This flag is initialized during vhost_net_init based
on whether the backend is vhost-user.
This refactoring simplifies checks for vhost-user specific behavior,
replacing direct comparisons of 'net->nc->info->type' with the new
flag. It improves readability and encapsulates the backend type
information directly within the vhost_net instance.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
This commit refactors how the maximum transmit queue size for
virtio-net devices is determined, making the mechanism more generic
and extensible.
Previously, virtio_net_max_tx_queue_size() contained hardcoded
checks for specific network backend types (vhost-user and
vhost-vdpa) to determine their supported maximum queue size. This
created direct dependencies and would require modifications for
every new backend that supports variable queue sizes.
To improve flexibility, a new max_tx_queue_size field is added
to the vhost_net structure. This allows each network backend
to advertise its supported maximum transmit queue size directly.
The virtio_net_max_tx_queue_size() function now retrieves the max
TX queue size from the vhost_net struct, if available and set.
Otherwise, it defaults to VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
This commit introduces a save_acked_features function pointer to
vhost_net and converts the vhost_net function into a generic dispatcher.
The vhost-user backend provides the callback, making its function static.
With this change, no other module has a direct dependency on the
vhost-user implementation.
This cleanup allows for the complete removal of the net/vhost-user.h
header file.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
This patch continues the effort to decouple the generic vhost layer
from specific network backend implementations.
Previously, the vhost_net initialization code contained a hardcoded
check for the vhost-user client type to retrieve its acked features
by calling vhost_user_get_acked_features(). This exposed an
internal vhost-user function in a public header and coupled the two
modules.
The vhost-user backend is updated to provide a callback, and its
getter function is now static. The call site in vhost_net.c is
simplified to use the new generic helper, removing the type check and
the direct dependency.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Previously, the vhost_net_get_feature_bits() function in
hw/net/vhost_net.c used a large switch statement to determine
the appropriate feature bits based on the NetClientDriver type.
This created unnecessary coupling between the generic vhost layer
and specific network backends (like TAP, vhost-user, and
vhost-vdpa).
This patch moves the definition of vhost feature bits directly into the
vhost_net structure for each relevant network client.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
The get_vhost_net() function previously contained a large switch
statement to find the VHostNetState pointer based on the net
client's type. This created a tight coupling, requiring the generic
vhost layer to be aware of every specific backend that supported
vhost, such as tap, vhost-user, and vhost-vdpa.
This approach is not scalable and requires modifying a central function
for any new backend. It also forced each backend to expose its internal
getter function in a public header file.
This patch refactors the logic by introducing a new get_vhost_net
function pointer to the NetClientInfo struct. The central
get_vhost_net() function is now a simple, generic dispatcher that
invokes the callback provided by the net client.
Each backend now implements its own private getter and registers it in
its NetClientInfo.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
This is a cosmetic change with no functional impact.
The function vhost_set_vring_enable() is specific to vhost_net and
is used outside of vhost_net.c (specifically, in
hw/net/virtio-net.c). To prevent confusion with other similarly named
vhost functions, such as the one found in cryptodev-vhost.c, it has
been renamed to vhost_net_set_vring_enable(). This clarifies that the
function belongs to the vhost_net module.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
virtio_net_pre_load_queues() inspects vdev->guest_features to tell if
VIRTIO_NET_F_RSS or VIRTIO_NET_F_MQ is enabled to infer the required
number of queues. This works for VIRTIO_NET_F_MQ but it doesn't for
VIRTIO_NET_F_RSS because only the lowest 32 bits of vdev->guest_features
is set at the point and VIRTIO_NET_F_RSS uses bit 60 while
VIRTIO_NET_F_MQ uses bit 22.
Instead of inferring the required number of queues from
vdev->guest_features, use the number loaded from the vm state. This
change also has a nice side effect to remove a duplicate peer queue
pair change by circumventing virtio_net_set_multiqueue().
Also update the comment in include/hw/virtio/virtio.h to prevent an
implementation of pre_load_queues() from refering to any fields being
loaded during migration by accident in the future.
Fixes: 8c49756825 ("virtio-net: Add only one queue pair when realizing")
Tested-by: Lei Yang <leiyang@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
The 'xgmac_enet_send' method has a 8k byte array used for copying
data between guest and host. Skip the automatic zero-init of this
array to eliminate the performance overhead in the I/O hot path.
The 'frame' buffer will be fully initialized when reading guest
memory to fetch the data to send.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-23-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The 'virtio_net_receive_rcu' method has three arrays with
VIRTQUEUE_MAX_SIZE elements, which are apprixmately 32k in
size used for copying data between guest and host. Skip the
automatic zero-init of these arrays to eliminate the
performance overhead in the I/O hot path.
The three arrays will be selectively initialized as required
when processing network buffers.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-22-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The 'tulip_setup_frame' method has a 4k byte array used for copynig
DMA data from the device. Skip the automatic zero-init of this array
to eliminate the performance overhead in the I/O hot path.
The 'buf' array will be fully initialized when reading data from the
device.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-21-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The 'rtl8139_transmit_one' method has a 8k byte array used for
copying data between guest and host. Skip the automatic zero-init
of this array to eliminate the performance overhead in the I/O
hot path.
The 'txbuffer' will be fully initialized when reading PCI DMA
buffers.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-20-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
