The actual backend is "Chardev", CharBackend is the frontend side of
it (whatever talks to the backend), let's rename it for readability.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Link: https://lore.kernel.org/r/20251022074612.1258413-1-marcandre.lureau@redhat.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
It was deprecated in 9.2, time to remove.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Reviewed-by: Ján Tomko <jtomko@redhat.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Michael Tokarev <mjt@tls.msk.ru>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
This patch adds the ability to map a host unix socket to a guest tcp socket when
using the slirp backend. This feature was added in libslirp version 4.7.0.
A new syntax for unix socket: -hostfwd=unix:hostpath-[guestaddr]:guestport
Signed-off-by: Viktor Kurilko <murlockkinght@gmail.com>
Signed-off-by: Samuel Thibault <samuel.thibault@ens-lyon.org>
Message-ID: <20250808143904.363907-1-murlockkinght@gmail.com>
When any host or guest GSO over UDP tunnel offload is enabled the
virtio net header includes the additional tunnel-related fields,
update the size accordingly.
Push the GSO over UDP tunnel offloads all the way down to the tap
device extending the newly introduced NetFeatures struct, and
eventually enable the associated features.
As per virtio specification, to convert features bit to offload bit,
map the extended features into the reserved range.
Finally, make the vhost backend aware of the exact header layout, to
copy it correctly. The tunnel-related field are present if either
the guest or the host negotiated any UDP tunnel related feature:
add them to the kernel supported features list, to allow qemu
transfer to the backend the needed information.
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <093b4bc68368046bffbcab2202227632d6e4e83b.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tap devices support GSO over UDP tunnel offload. Probe for such
feature in a similar manner to other offloads.
GSO over UDP tunnel needs to be enabled in addition to a "plain"
offload (TSO or USO).
No need to check separately for the outer header checksum offload:
the kernel is going to support both of them or none.
The new features are disabled by default to avoid compat issues,
and could be enabled, after that hw_compat_10_1 will be added,
together with the related compat entries.
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <a987a8a7613cbf33bb2209c7c7f5889b512638a7.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The set_offload() argument list is already pretty long and
we are going to introduce soon a bunch of additional offloads.
Replace the offload arguments with a single struct and update
all the relevant call-sites.
No functional changes intended.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <a9d4dd043b8c71b791e9ff05e17ef06072d9714e.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
net_slirp_register_poll_sock() and net_slirp_unregister_poll_sock()
report WSAEventSelect() failure with error_setg(&error_warn, ...).
error_setg_win32(&error_warn, ...) is undesirable just like
error_setg(&error_fatal, ...) and error_setg(&error_abort, ...) are.
Replace by warn_report().
The failures should probably be errors, but these functions implement
callbacks that cannot fail, exit(1) would be too harsh, and silent
failure we don't want. Thus, warnings.
Cc: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Message-ID: <20250923091000.3180122-7-armbru@redhat.com>
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Instead of open-coded g_unix_set_fd_nonblocking() calls, use
QEMU wrapper qemu_set_blocking().
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
[DB: fix missing closing ) in tap-bsd.c, remove now unused GError var]
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Now we can use qemu_set_blocking() in these cases.
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Use common qemu_set_blocking() instead.
Note that pre-patch the behavior of Win32 and Linux realizations
are inconsistent: we ignore failure for Win32, and assert success
for Linux.
How do we convert the callers?
1. Most of callers call qemu_socket_set_nonblock() on a
freshly created socket fd, in conditions when we may simply
report an error. Seems correct switching to error handling
both for Windows (pre-patch error is ignored) and Linux
(pre-patch we assert success). Anyway, we normally don't
expect errors in these cases.
Still in tests let's use &error_abort for simplicity.
What are exclusions?
2. hw/virtio/vhost-user.c - we are inside #ifdef CONFIG_LINUX,
so no damage in switching to error handling from assertion.
3. io/channel-socket.c: here we convert both old calls to
qemu_socket_set_nonblock() and qemu_socket_set_block() to
one new call. Pre-patch we assert success for Linux in
qemu_socket_set_nonblock(), and ignore all other errors here.
So, for Windows switch is a bit dangerous: we may get
new errors or crashes(when error_abort is passed) in
cases where we have silently ignored the error before
(was it correct in all such cases, if they were?) Still,
there is no other way to stricter API than take
this risk.
4. util/vhost-user-server - compiled only for Linux (see
util/meson.build), so we are safe, switching from assertion to
&error_abort.
Note: In qga/channel-posix.c we use g_warning(), where g_printerr()
would actually be a better choice. Still let's for now follow
common style of qga, where g_warning() is commonly used to print
such messages, and no call to g_printerr(). Converting everything
to use g_printerr() should better be another series.
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Coverity reported a file descriptor leak (CID 1490785) that happens if
`vhost_vdpa_get_max_queue_pairs()` returns 0, since in that case
net_host_vdpa_init(), which should take ownership of the fd, is never
called.
vhost_vdpa_get_max_queue_pairs() returns 1 if VIRTIO_NET_F_MQ is not
negotiated, or a negative error if the ioctl() fails, or the maximum
number of queue pairs exposed by the device in the config space in the
`max_virtqueue_pairs` field. In the VIRTIO spec we have:
The device MUST set max_virtqueue_pairs to between 1 and 0x8000
inclusive, if it offers VIRTIO_NET_F_MQ.
So, if `vhost_vdpa_get_max_queue_pairs()` returns 0, it's really an
error since the device is violating the VIRTIO spec.
Treat also `queue_pairs == 0` as an error, and jump to the `err` label,
to return a negative value to the caller in any case.
Coverity: CID 1490785
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20250714101156.30024-1-sgarzare@redhat.com>
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org>
Acked-by: Jason Wang <jasowang@redhat.com>
The "err" variable was declared but never used within the
chr_closed_bh() function. This resulted in a dead code
warning (CID 1612365) from Coverity.
Remove the unused variable and the associated error block
to resolve the issue.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
This was flagged by Coverity as a memory illegal access.
Initialize the pointer to NULL at declaration.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
If g_remove() fails, use warn_report() to log an error.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
In passt_vhost_user_start(), if vhost_net_init() fails, the "net"
variable is NULL and execution jumps to the "err:" label.
The cleanup code within this label is conditioned on "if (net)",
which can never be true in this error case. This makes the cleanup
block dead code, as reported by Coverity (CID 1612371).
Refactor the error handling to occur inline, removing the goto and
the unreachable cleanup block.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
The "err" variable was declared but never used within the
net_vhost_user_event() function. This resulted in a dead code
warning (CID 1612372) from Coverity.
Remove the unused variable and the associated error block
to resolve the issue.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
The "err" variable was declared but never used within the
passt_vhost_user_event() function. This resulted in a dead code
warning (CID 1612375) from Coverity.
Remove the unused variable and the associated error block
to resolve the issue.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
net_init_tap intends to return 0 for success and -1 on error. However,
when net_init_tap() succeeds for a multi-queue device, it returns 1,
because of this code where ret becomes 1 when g_unix_set_fd_nonblocking
succeeds:
ret = g_unix_set_fd_nonblocking(fd, true, NULL);
if (!ret) {
... error ...
free_fail:
...
return ret;
Luckily, the only current call site checks for negative, rather than non-zero:
net_client_init1()
if (net_client_init_fun[](...) < 0)
Also, in the unlikely case that g_unix_set_fd_nonblocking fails and returns
false, ret=0 is returned, and net_client_init1 will use a broken interface.
Fix it to be future proof.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Theoretically tap_read_packet() may return size less than
s->host_vnet_hdr_len, and next, we'll work with negative size
(in case of !s->using_vnet_hdr). Let's avoid it.
Don't proceed with size == s->host_vnet_hdr_len as well in case
of !s->using_vnet_hdr, it doesn't make sense.
Tested-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Extend 'inhibit=on' setting with the option to specify a pinned XSK map
path along with a starting index (default 0) to push the created XSK
sockets into. Example usage:
# ./build/qemu-system-x86_64 [...] \
-netdev af-xdp,ifname=enp2s0f0np0,id=net0,mode=native,queues=2,start-queue=14,inhibit=on,map-path=/sys/fs/bpf/xsks_map,map-start-index=14 \
-device virtio-net-pci,netdev=net0 [...]
This is useful for the case where an existing XDP program with XSK map
is present on the AF_XDP supported phys device and the XSK map is not
yet populated. For example, the former could have been pre-loaded onto
the netdevice by a control plane, which later launches QEMU to populate
it with XSK sockets.
Normally, the main idea behind 'inhibit=on' is that the QEMU instance
doesn't need to have a lot of privileges to use the pre-loaded program
and the pre-created sockets, but this mentioned use-case here is different
where QEMU still needs privileges to create the sockets.
The 'map-start-index' parameter is optional and defaults to 0. It allows
flexible placement of the XSK sockets, and is up to the user to specify
when the XDP program with XSK map was already preloaded. In the simplest
case the queue-to-map-slot mapping is just 1:1 based on ctx->rx_queue_index
but the user might as well have a different scheme (or smaller map size,
e.g. ctx->rx_queue_index % max_size) to push the inbound traffic to one
of the XSK sockets.
Note that the bpf_xdp_query_id() is now only tested for 'inhibit=off'
since only in the latter case the libxdp takes care of installing the
XDP program which was installed based on the s->xdp_flags pointing to
either driver or skb mode. For 'inhibit=on' we don't make any assumptions
and neither go down the path of probing all possible options in which
way the user installed the XDP program.
Reviewed-by: Ilya Maximets <i.maximets@ovn.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Ilya Maximets <i.maximets@ovn.org>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Anton Protopopov <aspsk@isovalent.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
While testing, it turned out that upon error in the queue creation loop,
we never trigger the af_xdp_cleanup() handler. This is because we pass
errp instead of a local err pointer into the various AF_XDP setup functions
instead of a scheme like:
bool fn(..., Error **errp)
{
Error *err = NULL;
foo(arg, &err);
if (err) {
handle the error...
error_propagate(errp, err);
return false;
}
...
}
The same is true for the attachment probing with bpf_xdp_query_id(). With a
conversion into the above format, the af_xdp_cleanup() handler is called as
expected. Note the error_propagate() handles a NULL err internally.
Fixes: cb039ef3d9 ("net: add initial support for AF_XDP network backend")
Reviewed-by: Ilya Maximets <i.maximets@ovn.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Ilya Maximets <i.maximets@ovn.org>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Anton Protopopov <aspsk@isovalent.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
There are two issues with the XDP program removal in af_xdp_cleanup():
1) Starting from libxdp 1.3.0 [0] the XDP program gets automatically
detached when we call xsk_socket__delete() for the last successfully
configured queue. libxdp internally keeps track of that. For QEMU
we require libxdp >= 1.4.0. Given QEMU is not loading the program,
lets also not attempt to remove it and delegate this instead.
2) The removal logic is incorrect anyway because we are setting n_queues
into the last queue that never has xdp_flags on failure, so the logic
is always skipped since the non-zero test for s->xdp_flags in
af_xdp_cleanup() fails.
Fixes: cb039ef3d9 ("net: add initial support for AF_XDP network backend")
Suggested-by: Ilya Maximets <i.maximets@ovn.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Ilya Maximets <i.maximets@ovn.org>
Cc: Ilya Maximets <i.maximets@ovn.org>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Anton Protopopov <aspsk@isovalent.com>
Link: 38c2914988 [0]
Signed-off-by: Jason Wang <jasowang@redhat.com>
It is no longer used.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20250530-vdpa-v1-5-5af4109b1c19@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Retrieve peer hashing capability instead of hardcoding.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20250530-vdpa-v1-4-5af4109b1c19@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Report hashing capability so that virtio-net can deliver the correct
capability information to the guest.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20250530-vdpa-v1-2-5af4109b1c19@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This commit adds support for the vhost-user interface to the passt
network backend, enabling high-performance, accelerated networking for
guests using passt.
The passt backend can now operate in a vhost-user mode, where it
communicates with the guest's virtio-net device over a socket pair
using the vhost-user protocol. This offloads the datapath from the
main QEMU loop, significantly improving network performance.
When the vhost-user=on option is used with -netdev passt, the new
vhost initialization path is taken instead of the standard
stream-based connection.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
This commit introduces support for passt as a new network backend.
passt is an unprivileged, user-mode networking solution that provides
connectivity for virtual machines by launching an external helper process.
The implementation reuses the generic stream data handling logic. It
launches the passt binary using GSubprocess, passing it a file
descriptor from a socketpair() for communication. QEMU connects to
the other end of the socket pair to establish the network data stream.
The PID of the passt daemon is tracked via a temporary file to
ensure it is terminated when QEMU exits.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@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>
The code to set the link status is currently located in
qmp_set_link(). This function identifies the device by name,
searches for the corresponding NetClientState, and then updates
the link status.
In some parts of the code, such as vhost-user.c, the
NetClientState are already available. Calling qmp_set_link()
from these locations leads to a redundant search for the clients.
This patch refactors the logic by introducing a new function,
net_client_set_link(), which accepts a NetClientState array
directly. qmp_set_link() is simplified to be a wrapper that
performs the client search and then calls the new function.
The vhost-user implementation is updated to use net_client_set_link()
directly, thereby eliminating the unnecessary client lookup.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
To prepare for the implementation of '-net passt', this patch moves
the generic stream handling functions from net/stream.c into new
net/stream_data.c and net/stream_data.h files.
This refactoring introduces a NetStreamData struct that encapsulates
the generic fields and logic previously in NetStreamState. The
NetStreamState now embeds NetStreamData and delegates the core
stream operations to the new generic functions.
To maintain flexibility for different users of this generic code,
callbacks for send and listen operations are now passed via
function pointers within the NetStreamData struct. This allows
callers to provide their own specific implementations while reusing
the common connection and data transfer logic.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
s->pool has n_descs elements so maximum i should be
n_descs - 1. Fix the upper bound.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Fixes: cb039ef3d9 ("net: add initial support for AF_XDP network backend")
Cc: qemu-stable@nongnu.org
Reviewed-by: Ilya Maximets <i.maximets@ovn.org>
Signed-off-by: Anastasia Belova <nabelova31@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
The 'net_stream_send' method has a 68k 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 'buf1' array will be fully initialized when reading data off
the network socket.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-32-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The 'net_socket_send' method has a 68k 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 'buf1' array will be fully initialized when reading data off
the network socket.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-31-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
As we are moving to keep the mapping through all the vdpa device life
instead of resetting it at VirtIO reset, we need to move all its
dependencies to the initialization too. In particular devices with
x-svq=on need a valid iova_tree from the beginning.
Simplify the code also consolidating the two creation points: the first
data vq in case of SVQ active and CVQ start in case only CVQ uses it.
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Si-Wei Liu <si-wei.liu@oracle.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Suggested-by: Si-Wei Liu <si-wei.liu@oracle.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20250522145839.59974-7-jonah.palmer@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
To map the guest memory while it is migrating we need to create the
iova_tree, as long as the destination uses x-svq=on. Checking to not
override it.
The function vhost_vdpa_net_client_stop clear it if the device is
stopped. If the guest starts the device again, the iova tree is
recreated by vhost_vdpa_net_data_start_first or vhost_vdpa_net_cvq_start
if needed, so old behavior is kept.
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Si-Wei Liu <si-wei.liu@oracle.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Message-Id: <20250522145839.59974-2-jonah.palmer@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Mechanical change using gsed, then style manually adapted
to pass checkpatch.pl script.
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20250424194905.82506-4-philmd@linaro.org>
A few functions now end with a label. The next commit will clean them
up.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20250407082643.2310002-3-armbru@redhat.com>
[Straightforward conflict with commit 988ad4cceb (hw/loongarch/virt:
Fix cpuslot::cpu set at last in virt_cpu_plug()) resolved]
Tracked down with scripts/coccinelle/err-bad-newline.cocci.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-ID: <20250312143504.1659061-1-armbru@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Song Gao <gaosong@loongson.cn>
Add .set_vnet_le() function that always returns success, assuming that
vDPA h/w always implements LE data format. Otherwise, QEMU disables vDPA and
outputs the message:
"backend does not support LE vnet headers; falling back on userspace virtio"
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Konstantin Shkolnyy <kshk@linux.ibm.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
ipvtap and macvtap create a file for each interface unlike tuntap, which
creates one file shared by all interfaces. Try to open a file dedicated
to the interface first for ipvtap and macvtap.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Commit a0d7215e33 ("vhost-vdpa: do not cleanup the vdpa/vhost-net
structures if peer nic is present") effectively delayed the backend
cleanup, allowing the frontend or the guest to access it resources as
long as the frontend is still visible to the guest.
However it does not clean up the resources until the qemu process is
over. This causes an effective leak if the device is deleted with
device_del, as there is no way to close the vdpa device. This makes
impossible to re-add that device to this or other QEMU instances until
the first instance of QEMU is finished.
Move the cleanup from qemu_cleanup to the NIC deletion and to
net_cleanup.
Fixes: a0d7215e33 ("vhost-vdpa: do not cleanup the vdpa/vhost-net structures if peer nic is present")
Reported-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
This change is used in later commits so we can avoid the removal of the
netclient if it is delayed.
No functional change intended.
Reviewed-by: Si-Wei Liu <si-wei.liu@oracle.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
The netdev reports NETDEV_VHOST_USER_CONNECTED event when
the chardev is connected, and NETDEV_VHOST_USER_DISCONNECTED
when it is disconnected.
The NETDEV_VHOST_USER_CONNECTED event includes the chardev id.
This allows a system manager like libvirt to detect when the server
fails.
For instance with passt:
{ 'execute': 'qmp_capabilities' }
{ "return": { } }
[killing passt here]
{ "timestamp": { "seconds": 1739538634, "microseconds": 920450 },
"event": "NETDEV_VHOST_USER_DISCONNECTED",
"data": { "netdev-id": "netdev0" } }
[automatic reconnection with reconnect-ms]
{ "timestamp": { "seconds": 1739538638, "microseconds": 354181 },
"event": "NETDEV_VHOST_USER_CONNECTED",
"data": { "netdev-id": "netdev0", "chardev-id": "chr0" } }
Tested-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Message-Id: <20250217092550.1172055-1-lvivier@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Creates and supports a GPA->IOVA tree and a partial IOVA->HVA tree by
splitting up guest-backed memory maps and host-only memory maps from the
full IOVA->HVA tree. That is, any guest-backed memory maps are now
stored in the GPA->IOVA tree and host-only memory maps stay in the
IOVA->HVA tree.
Also propagates the GPAs (in_addr/out_addr) of a VirtQueueElement to
vhost_svq_translate_addr() to translate GPAs to IOVAs via the GPA->IOVA
tree (when descriptors are backed by guest memory). For descriptors
backed by host-only memory, the existing partial SVQ IOVA->HVA tree is
used.
GPAs are unique in the guest's address space, ensuring unambiguous IOVA
translations. This avoids the issue where different GPAs map to the same
HVA, causing the original HVA->IOVA translation to potentially return an
IOVA associated with the wrong intended GPA.
Signed-off-by: Jonah Palmer <jonah.palmer@oracle.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20250217144936.3589907-3-jonah.palmer@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Marc-André Lureau
Vladimir Sementsov-Ogievskiy
Viktor Kurilko
Paolo Abeni
Markus Armbruster
Stefano Garzarella
Laurent Vivier
Steve Sistare
Daniel Borkmann
Akihiko Odaki
Anastasia Belova
Daniel P. Berrangé
Eugenio Pérez
Philippe Mathieu-Daudé
Konstantin Shkolnyy
Jonah Palmer