Re: [RFC 3/6] vduse: add vq group asid support

On Thu, Jun 12, 2025 at 3:25 PM Eugenio Perez Martin wrote: > > On Thu, Jun 12, 2025 at 2:30 AM Jason Wang wrote: > > > > On Fri, Jun 6, 2025 at 7:50 PM Eugenio Pérez wrote: > > > > > > Make one IOTLB domain per address space, and allow the driver to assign

Re: [PATCH v11 2/3] vhost: Reintroduce kthread mode support in vhost

his partially reverts or improves upon: > commit 6e890c5d5021 ("vhost: use vhost_tasks for worker threads") > commit 1cdaafa1b8b4 ("vhost: replace single worker pointer with xarray") > > Signed-off-by: Cindy Lu Acked-by: Jason Wang Thanks

Re: [PATCH v11 3/3] vhost: Add configuration controls for vhost worker's mode

_OWNER_CONTROL to > control the availability of these IOCTLs and parameter, allowing > distributions to disable them if not needed > > - The VHOST_NEW_WORKER functionality requires fork_owner to be set > to true, with validation added to ensure proper configuration > > Signed-off-by: Cindy Lu Acked-by: Jason Wang Thanks

Re: [PATCH v11 1/3] vhost: Add a new parameter in vhost_dev to allow user select kthread

. > > Introduce a new parameter to enable users to choose between kthread and > task mode. > > Signed-off-by: Cindy Lu > --- Acked-by: Jason Wang Thanks

Re: [RFC 5/6] vduse: reset group asid in reset

On Fri, Jun 6, 2025 at 7:50 PM Eugenio Pérez wrote: > > Is the expected behavior with vdpa_sim and mlx. > > Signed-off-by: Eugenio Pérez > --- > drivers/vdpa/vdpa_user/vduse_dev.c | 6 ++ > 1 file changed, 6 insertions(+) > Should we squash this into patch 3? Thanks

Re: [RFC 3/6] vduse: add vq group asid support

On Fri, Jun 6, 2025 at 7:50 PM Eugenio Pérez wrote: > > Make one IOTLB domain per address space, and allow the driver to assign > each ASID to a vq group. Each address space via an dedicated identifier > (ASID). > > During vDPA device allocation, the VDUSE device needs to report the > number of a

Re: [RFC 2/6] vduse: add vq group support

On Mon, Jun 9, 2025 at 2:03 PM Eugenio Perez Martin wrote: > > On Mon, Jun 9, 2025 at 3:55 AM Jason Wang wrote: > > > > On Fri, Jun 6, 2025 at 7:50 PM Eugenio Pérez wrote: > > > > > > The virtqueue group is the minimal set of virtqueues that must share an &

Re: [RFC 1/6] vduse: add v1 API definition

On Mon, Jun 9, 2025 at 2:11 PM Eugenio Perez Martin wrote: > > On Mon, Jun 9, 2025 at 3:50 AM Jason Wang wrote: > > > > On Mon, Jun 9, 2025 at 9:41 AM Jason Wang wrote: > > > > > > On Fri, Jun 6, 2025 at 7:50 PM Eugenio Pérez wrote: > > > > >

Re: [RFC 2/6] vduse: add vq group support

On Fri, Jun 6, 2025 at 7:50 PM Eugenio Pérez wrote: > > The virtqueue group is the minimal set of virtqueues that must share an > address space. And the address space identifier could only be attached > to a specific virtqueue group. The virtqueue is attached to a > virtqueue group for all the l

Re: [RFC 1/6] vduse: add v1 API definition

On Mon, Jun 9, 2025 at 9:41 AM Jason Wang wrote: > > On Fri, Jun 6, 2025 at 7:50 PM Eugenio Pérez wrote: > > > > This allows to define all functions checking the API version set by the > > userland device. > > > > Signed-off-by: Eugenio Pérez > >

Re: [RFC 1/6] vduse: add v1 API definition

On Fri, Jun 6, 2025 at 7:50 PM Eugenio Pérez wrote: > > This allows to define all functions checking the API version set by the > userland device. > > Signed-off-by: Eugenio Pérez It might be worth clarifying how it works. For example, 1) would VDUSE behave differently or if it's just some new

Re: [PATCH vhost] vdpa/mlx5: Fix needs_teardown flag calculation

rtain conditions") > Signed-off-by: Dragos Tatulea > Reviewed-by: Shahar Shitrit > Reviewed-by: Si-Wei Liu > Tested-by: Si-Wei Liu > --- Acked-by: Jason Wang Thanks

Re: [PATCH net] virtio-net: drop the multi-buffer XDP packet in zerocopy

On Wed, Jun 4, 2025 at 10:17 PM Bui Quang Minh wrote: > > On 6/4/25 07:37, Jason Wang wrote: > > On Tue, Jun 3, 2025 at 11:07 PM Bui Quang Minh > > wrote: > >> In virtio-net, we have not yet supported multi-buffer XDP packet in > >> zerocopy mode when there i

Re: [PATCH net] virtio-net: drop the multi-buffer XDP packet in zerocopy

On Tue, Jun 3, 2025 at 11:07 PM Bui Quang Minh wrote: > > In virtio-net, we have not yet supported multi-buffer XDP packet in > zerocopy mode when there is a binding XDP program. However, in that > case, when receiving multi-buffer XDP packet, we skip the XDP program > and return XDP_PASS. As a re

Re: [RFC PATCH net-next v2 1/2] virtio-net: support zerocopy multi buffer XDP in mergeable

On Thu, May 29, 2025 at 8:28 PM Bui Quang Minh wrote: > > On 5/29/25 12:59, Jason Wang wrote: > > On Wed, May 28, 2025 at 12:19 AM Bui Quang Minh > > wrote: > >> Currently, in zerocopy mode with mergeable receive buffer, virtio-net > >> does not support m

Re: [PATCH] virtio-mmio: Remove virtqueue list from mmio device

d. > > While at it, fix the virtio_device_for_each_vq() macro to accept an > argument like "&vm_dev->vdev" (which currently fails to build). > > Signed-off-by: Viresh Kumar > --- Acked-by: Jason Wang Btw, virtio-vdpa may need the same optimization. Thanks

Re: [PATCH 1/3] virtio: Fix typo in register_virtio_device() doc comment

error, the caller must call put_device on &@dev->dev (and not kfree), > * as another code path may have obtained a reference to @dev. > * > - * Returns: 0 on suceess, -error on failure > + * Returns: 0 on success, -error on failure > */ > int register_virtio_device(struct virtio_device *dev) > { > -- > 2.47.1 > Acked-by: Jason Wang Thanks

Re: [PATCH] virtio: document ENOSPC

It indicates that some buffers are outstanding and > that > + * the operation can be retried after some buffers have been used. > */ > int virtqueue_add_sgs(struct virtqueue *_vq, > struct scatterlist *sgs[], > -- > MST > Acked-by: Jason Wang Thanks

Re: [RFC PATCH net-next v2 1/2] virtio-net: support zerocopy multi buffer XDP in mergeable

On Wed, May 28, 2025 at 12:19 AM Bui Quang Minh wrote: > > Currently, in zerocopy mode with mergeable receive buffer, virtio-net > does not support multi buffer but a single buffer only. This commit adds > support for multi mergeable receive buffer in the zerocopy XDP path by > utilizing XDP buffe

Re: [PATCH V2 00/19] virtio_ring in order support

On Wed, May 28, 2025 at 8:51 PM Michael S. Tsirkin wrote: > > On Wed, May 28, 2025 at 02:42:15PM +0800, Jason Wang wrote: > > Hello all: > > > > This sereis tries to implement the VIRTIO_F_IN_ORDER to > > virtio_ring. This is done by introducing virtqueue ops so

[PATCH V2 11/19] virtio_ring: switch to use vring_virtqueue for detach_unused_buf variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 12 +--- 1 file changed, 5 insertions(+), 7 dele

[PATCH V2 10/19] virtio_ring: switch to use vring_virtqueue for disable_cb variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 14 +- 1 file changed, 5 insertions(+), 9 dele

[PATCH V2 09/19] virtio_ring: use vring_virtqueue for enable_cb_delayed variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 16 +++- 1 file changed, 7 insertions(+), 9 dele

[PATCH V2 01/19] virtio_ring: rename virtqueue_reinit_xxx to virtqueue_reset_xxx()

To be consistent with virtqueue_reset(). Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index b784aab66867

[PATCH V2 07/19] virtio: switch to use vring_virtqueue for virtqueue_add variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 16 +++- 1 file changed, 7 insertions(+), 9 dele

[PATCH V2 05/19] virtio_ring: switch to use vring_virtqueue for virtqueue_kick_prepare variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 14 ++ 1 file changed, 6 insertions(+), 8 dele

[PATCH V2 06/19] virtio_ring: switch to use vring_virtqueue for virtqueue_add variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 40 +--- 1 file change

[PATCH V2 18/19] virtio_ring: factor out split detaching logic

This patch factors out the split core detaching logic that could be reused by in order feature into a dedicated function. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 18 ++ 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a

[PATCH V2 16/19] virtio_ring: factor out core logic for updating last_used_idx

Factor out the core logic for updating last_used_idx to be reused by the packed in order implementation. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 43 +--- 1 file changed, 25 insertions(+), 18 deletions(-) diff --git a

[PATCH V2 19/19] virtio_ring: add in order support

% PPS improvements from 8.6 Mpps to 9.0 Mpps Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 423 +-- 1 file changed, 402 insertions(+), 21 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 27a9459a0555

[PATCH V2 17/19] virtio_ring: factor out split indirect detaching logic

Factor out the split indirect descriptor detaching logic in order to make it be reused by the in order support. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 63 1 file changed, 35 insertions(+), 28 deletions(-) diff

[PATCH V2 14/19] virtio_ring: determine descriptor flags at one time

Let's determine the last descriptor by counting the number of sg. This would be consistent with packed virtqueue implementation and ease the future in-order implementation. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 25 + 1

[PATCH V2 13/19] virtio_ring: introduce virtqueue ops

uses global array of const ops to allow compiler to avoid indirect branches. Tested with CONFIG_MITIGATION_RETPOLINE, no performance differences were noticed. Suggested-by: Michael S. Tsirkin Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 172 ++- 1

[PATCH V2 15/19] virtio_ring: factor out core logic of buffer detaching

Factor out core logic of buffer detaching and leave the id population to the caller so in order can just call the core logic. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 17 + 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a

[PATCH V2 12/19] virtio_ring: use u16 for last_used_idx in virtqueue_poll_split()

Use u16 for last_used_idx in virtqueue_poll_split() to align with the spec. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index

[PATCH V2 08/19] virtio_ring: switch to use vring_virtqueue for enable_cb_prepare variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 15 ++- 1 file changed, 6 insertions(+), 9 dele

[PATCH V2 03/19] virtio_ring: unify logic of virtqueue_poll() and more_used()

This patch unifies the logic of virtqueue_poll() and more_used() for better code reusing and ease the future in order implementation. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 48 +++- 1 file changed, 20 insertions

[PATCH V2 04/19] virtio_ring: switch to use vring_virtqueue for virtqueue resize variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 14 ++ 1 file changed, 6 insertions(+), 8 dele

[PATCH V2 02/19] virtio_ring: switch to use vring_virtqueue in virtqueue_poll variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Reviewed-by: Xuan Zhuo Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 14 ++ 1 file changed, 6 insertions(+), 8 dele

[PATCH V2 00/19] virtio_ring in order support

with KVM guest testpmd on the host. Changes since V1: - use const global array of function pointers to avoid indirect branches to eliminate retpoline when mitigation is enabled - fix used length calculation when processing used ids in a batch - fix sparse warnings Please review. Thanks Jason

Re: [PATCH 13/19] virtio_ring: introduce virtqueue ops

On Fri, May 16, 2025 at 6:35 PM Michael S. Tsirkin wrote: > > On Fri, May 16, 2025 at 09:30:01AM +0800, Jason Wang wrote: > > On Wed, May 14, 2025 at 10:24 PM Michael S. Tsirkin wrote: > > > > > > On Wed, May 14, 2025 at 10:19:05AM -0400, Michael S. Tsirkin wrote: &

Re: [PATCH v9 4/4] vhost: Add a KConfig knob to enable IOCTL VHOST_FORK_FROM_OWNER

On Fri, May 16, 2025 at 6:39 PM Michael S. Tsirkin wrote: > > On Fri, May 16, 2025 at 09:31:42AM +0800, Jason Wang wrote: > > On Thu, May 15, 2025 at 2:14 PM Michael S. Tsirkin wrote: > > > > > > On Wed, May 14, 2025 at 10:52:58AM +0800, Jason Wang wrote: > >

Re: [PATCH 13/19] virtio_ring: introduce virtqueue ops

On Wed, May 14, 2025 at 10:24 PM Michael S. Tsirkin wrote: > > On Wed, May 14, 2025 at 10:19:05AM -0400, Michael S. Tsirkin wrote: > > On Wed, Apr 09, 2025 at 12:06:03PM +0800, Jason Wang wrote: > > > On Tue, Apr 8, 2025 at 7:37 PM Michael S. Tsirkin wrote: > > >

Re: [PATCH v9 4/4] vhost: Add a KConfig knob to enable IOCTL VHOST_FORK_FROM_OWNER

On Thu, May 15, 2025 at 2:14 PM Michael S. Tsirkin wrote: > > On Wed, May 14, 2025 at 10:52:58AM +0800, Jason Wang wrote: > > On Tue, May 13, 2025 at 3:09 PM Michael S. Tsirkin wrote: > > > > > > On Tue, May 13, 2025 at 12:08:51PM +0800, Jason Wang wrote: > >

Re: [PATCH v3] virtio: reject shm region if length is zero

o_shm_region *region, u8 id) > { > + if (!region->len) > + return false; > if (!vdev->config->get_shm_region) > return false; > return vdev->config->get_shm_region(vdev, region, id); > -- > 2.34.1 > Acked-by: Jason Wang Thanks

Re: [PATCH] vhost/net: remove zerocopy support

---| > > CAUTION: External Email > > > > |---! > > > > On Tue, Apr 8, 2025 at 8:28 AM Jason Wang wrote: > >> > >> On Tue, Apr 8, 2025 at 9:18 AM Jon Kohler wrote: > >>> > >>> > >>> > >>>> On Apr 6, 202

Re: [PATCH v9 4/4] vhost: Add a KConfig knob to enable IOCTL VHOST_FORK_FROM_OWNER

On Tue, May 13, 2025 at 3:09 PM Michael S. Tsirkin wrote: > > On Tue, May 13, 2025 at 12:08:51PM +0800, Jason Wang wrote: > > On Wed, Apr 30, 2025 at 5:27 PM Michael S. Tsirkin wrote: > > > > > > On Wed, Apr 30, 2025 at 11:34:49AM +0800, Jason Wang wrote: > >

Re: [PATCH v9 4/4] vhost: Add a KConfig knob to enable IOCTL VHOST_FORK_FROM_OWNER

On Wed, Apr 30, 2025 at 5:27 PM Michael S. Tsirkin wrote: > > On Wed, Apr 30, 2025 at 11:34:49AM +0800, Jason Wang wrote: > > On Tue, Apr 29, 2025 at 6:56 PM Michael S. Tsirkin wrote: > > > > > > On Tue, Apr 29, 2025 at 11:39:37AM +0800, Jason Wang wrote: > >

Re: [PATCH v9 4/4] vhost: Add a KConfig knob to enable IOCTL VHOST_FORK_FROM_OWNER

On Tue, Apr 29, 2025 at 6:56 PM Michael S. Tsirkin wrote: > > On Tue, Apr 29, 2025 at 11:39:37AM +0800, Jason Wang wrote: > > On Mon, Apr 21, 2025 at 11:46 AM Jason Wang wrote: > > > > > > On Mon, Apr 21, 2025 at 11:45 AM Jason Wang wrote: > > > > >

Re: [PATCH v9 4/4] vhost: Add a KConfig knob to enable IOCTL VHOST_FORK_FROM_OWNER

On Mon, Apr 21, 2025 at 11:46 AM Jason Wang wrote: > > On Mon, Apr 21, 2025 at 11:45 AM Jason Wang wrote: > > > > On Mon, Apr 21, 2025 at 10:45 AM Cindy Lu wrote: > > > > > > Introduce a new config knob `CONFIG_VHOST_ENABLE_FORK_OWNER_IOCTL`, >

Re: [PATCH v9 4/4] vhost: Add a KConfig knob to enable IOCTL VHOST_FORK_FROM_OWNER

On Mon, Apr 21, 2025 at 11:45 AM Jason Wang wrote: > > On Mon, Apr 21, 2025 at 10:45 AM Cindy Lu wrote: > > > > Introduce a new config knob `CONFIG_VHOST_ENABLE_FORK_OWNER_IOCTL`, > > to control the availability of the `VHOST_FORK_FROM_OWNER` ioctl. > > When CONFIG

Re: [PATCH v9 4/4] vhost: Add a KConfig knob to enable IOCTL VHOST_FORK_FROM_OWNER

On Mon, Apr 21, 2025 at 10:45 AM Cindy Lu wrote: > > Introduce a new config knob `CONFIG_VHOST_ENABLE_FORK_OWNER_IOCTL`, > to control the availability of the `VHOST_FORK_FROM_OWNER` ioctl. > When CONFIG_VHOST_ENABLE_FORK_OWNER_IOCTL is set to n, the ioctl > is disabled, and any attempt to use it w

Re: [PATCH v9 3/4] vhost: add VHOST_FORK_FROM_OWNER ioctl and validate inherit_owner

VHOST_SET_OWNER, as the worker > will be created in the VHOST_SET_OWNER function. > > In addition, the VHOST_NEW_WORKER requires the inherit_owner > setting to be true. So we need to add a check for this. > > Signed-off-by: Cindy Lu Acked-by: Jason Wang Thanks

Re: [PATCH v9 2/4] vhost: Reintroduce kthread mode support in vhost

On Mon, Apr 21, 2025 at 10:45 AM Cindy Lu wrote: > > This patch reintroduces kthread mode support in vhost, > It also introduces struct vhost_worker_ops to abstract > worker create/stop/wakeup operations. > > * Bring back the original vhost_worker() implementation, > and renamed to vhost_run_wor

Re: [PATCH v9 1/4] vhost: Add a new parameter in vhost_dev to allow user select kthread

gt; API support. > > Introduce a new parameter to enable users to choose between kthread and > task mode. > > By default, this parameter is set to true, so the default behavior > remains unchanged by this patch. > > Signed-off-by: Cindy Lu Acked-by: Jason Wang Thanks

Re: [PATCH v3 4/9] vhost: modify vhost_log_write() for broader users

all pages of > vring descriptors, or only pages that are tainted by the driver. > > In addition, removes BUG(). > > Suggested-by: Joao Martins > Signed-off-by: Dongli Zhang Acked-by: Jason Wang Thanks

Re: [PATCH v4 1/4] virtio-net: disable delayed refill when pausing rx

fixes up the > virtnet_rx_resume to disable future and cancel all inflights delayed > refill_work before calling napi_disable() to pause the rx. > > Fixes: 413f0271f396 ("net: protect NAPI enablement with netdev_lock()") > Acked-by: Michael S. Tsirkin > Signed-off-by: Bu

Re: [PATCH v3 3/3] selftests: net: add a virtio_net deadlock selftest

On Wed, Apr 16, 2025 at 2:54 PM Bui Quang Minh wrote: > > On 4/16/25 11:27, Jakub Kicinski wrote: > > On Tue, 15 Apr 2025 14:43:41 +0700 Bui Quang Minh wrote: > >> +def setup_xsk(cfg, xdp_queue_id = 0) -> bkg: > >> +# Probe for support > >> +xdp = cmd(f'{cfg.net_lib_dir / "xdp_helper"} - -

Re: [PATCH 13/19] virtio_ring: introduce virtqueue ops

On Tue, Apr 8, 2025 at 7:37 PM Michael S. Tsirkin wrote: > > On Tue, Apr 08, 2025 at 03:02:35PM +0800, Jason Wang wrote: > > On Mon, Apr 7, 2025 at 4:20 PM Michael S. Tsirkin wrote: > > > > > > On Mon, Mar 24, 2025 at 02:01:21PM +0800, Jason Wang wrote: > >

Re: [PATCH] vhost/net: remove zerocopy support

On Tue, Apr 8, 2025 at 9:18 AM Jon Kohler wrote: > > > > > On Apr 6, 2025, at 7:14 PM, Jason Wang wrote: > > > > !---| &

Re: [PATCH 13/19] virtio_ring: introduce virtqueue ops

On Mon, Apr 7, 2025 at 4:20 PM Michael S. Tsirkin wrote: > > On Mon, Mar 24, 2025 at 02:01:21PM +0800, Jason Wang wrote: > > This patch introduces virtqueue ops which is a set of the callbacks > > that will be called for different queue layout or features. This would > >

Re: [PATCH] virtio-net: disable delayed refill when pausing rx

On Mon, Apr 7, 2025 at 10:27 AM Bui Quang Minh wrote: > > On 4/7/25 08:03, Xuan Zhuo wrote: > > On Fri, 4 Apr 2025 16:39:03 +0700, Bui Quang Minh > > wrote: > >> When pausing rx (e.g. set up xdp, xsk pool, rx resize), we call > >> napi_disable() on the receive queue's napi. In delayed refill_wo

Re: [PATCH] vhost/net: Defer TX queue re-enable until after sendmsg

Datagrams/second: ~650k (~1.7x increase) > Interval Transfer Bitrate Lost/Total Datagrams > 0.00-30.00 sec 26.4 GBytes 7.55 Gbits/sec 0/19554720 (0%) sender > > Signed-off-by: Jon Kohler Acked-by: Jason Wang Thanks

Re: [PATCH] vhost/net: remove zerocopy support

On Fri, Apr 4, 2025 at 10:24 PM Jon Kohler wrote: > > Commit 098eadce3c62 ("vhost_net: disable zerocopy by default") disabled > the module parameter for the handle_tx_zerocopy path back in 2019, > nothing that many downstream distributions (e.g., RHEL7 and later) had > already done the same. > > B

[PATCH 18/19] virtio_ring: factor out split indirect detaching logic

Factor out the split indirect descriptor detaching logic in order to make it be reused by the in order support. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 63 1 file changed, 35 insertions(+), 28 deletions(-) diff --git a/drivers/virtio

Re: [PATCH net-next 3/4] virtio_net: Use new RSS config structs

On Fri, Mar 21, 2025 at 2:35 PM Akihiko Odaki wrote: > > On 2025/03/21 9:35, Jason Wang wrote: > > On Thu, Mar 20, 2025 at 1:36 PM Akihiko Odaki > > wrote: > >> > >> On 2025/03/20 10:50, Jason Wang wrote: > >>> On Wed, Mar 19, 2025 at 12:48 PM Ak

[PATCH 11/19] virtio_ring: switch to use vring_virtqueue for detach_unused_buf variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 12 +--- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/dr

[PATCH 19/19] virtio_ring: add in order support

PPS. No obvious changes in other test cases. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 451 +-- 1 file changed, 434 insertions(+), 17 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 0fad8e8419c8

[PATCH 16/19] virtio_ring: factor out core logic for updating last_used_idx

Factor out the core logic for updating last_used_idx to be reused by the packed in order implementation. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 43 +--- 1 file changed, 25 insertions(+), 18 deletions(-) diff --git a/drivers/virtio

[PATCH 17/19] virtio_ring: move next_avail_idx to vring_virtqueue

This variable is used by packed virtqueue now, moving it to vring_virtqueue to make it possible to be reused by split virtqueue in-order implementation. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 22 +++--- 1 file changed, 11 insertions(+), 11 deletions

[PATCH 14/19] virtio_ring: determine descriptor flags at one time

Let's determine the last descriptor by counting the number of sg. This would be consistent with packed virtqueue implementation and ease the future in-order implementation. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 25 + 1 file changed, 13 inser

[PATCH 15/19] virtio_ring: factor out core logic of buffer detaching

Factor out core logic of buffer detaching and leave the id population to the caller so in order can just call the core logic. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 17 + 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/virtio

[PATCH 13/19] virtio_ring: introduce virtqueue ops

This patch introduces virtqueue ops which is a set of the callbacks that will be called for different queue layout or features. This would help to avoid branches for split/packed and will ease the future implementation like in order. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c

[PATCH 12/19] virtio_ring: use u16 for last_used_idx in virtqueue_poll_split()

Use u16 for last_used_idx in virtqueue_poll_split() to align with the spec. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 19aa24d62d20..a2884eae14d9

[PATCH 08/19] virtio_ring: switch to use vring_virtqueue for enable_cb_prepare variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 15 ++- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/dr

[PATCH 05/19] virtio_ring: switch to use vring_virtqueue for virtqueue_kick_prepare variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 14 ++ 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/dr

[PATCH 10/19] virtio_ring: switch to use vring_virtqueue for disable_cb variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 14 +- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/dr

[PATCH 09/19] virtio_ring: use vring_virtqueue for enable_cb_delayed variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 16 +++- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/dr

[PATCH 07/19] virtio: switch to use vring_virtqueue for virtqueue_add variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 16 +++- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/dr

[PATCH 06/19] virtio_ring: switch to use vring_virtqueue for virtqueue_add variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 40 +--- 1 file changed, 19 insertions(+), 21 dele

[PATCH 04/19] virtio_ring: switch to use vring_virtqueue for virtqueue resize variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 14 ++ 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/dr

[PATCH 02/19] virtio_ring: switch to use vring_virtqueue in virtqueue_poll variants

Those variants are used internally so let's switch to use vring_virtqueue as parameter to be consistent with other internal virtqueue helpers. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 14 ++ 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/dr

[PATCH 03/19] virtio_ring: unify logic of virtqueue_poll() and more_used()

This patch unifies the logic of virtqueue_poll() and more_used() for better code reusing and ease the future in order implementation. Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 48 +++- 1 file changed, 20 insertions(+), 28 deletions(-) diff

[PATCH 01/19] virtio_ring: rename virtqueue_reinit_xxx to virtqueue_reset_xxx()

To be consistent with virtqueue_reset(). Signed-off-by: Jason Wang --- drivers/virtio/virtio_ring.c | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index fdd2d2b07b5a..1bdfd5d617a7 100644 --- a/drivers

[PATCH 00/19] virtio_ring in order support

+ testpmd on the host. Please review. Thanks Jason Wang (19): virtio_ring: rename virtqueue_reinit_xxx to virtqueue_reset_xxx() virtio_ring: switch to use vring_virtqueue in virtqueue_poll variants virtio_ring: unify logic of virtqueue_poll() and more_used() virtio_ring: switch to use

Re: [PATCH net-next v2 3/4] virtio_net: Use new RSS config structs

Lei Yang > Acked-by: Michael S. Tsirkin > --- > drivers/net/virtio_net.c | 117 > +-- > 1 file changed, 43 insertions(+), 74 deletions(-) > Though I still think hash config should use a separate helper, it could be done in the future. So Acked-by: Jason Wang Thanks

Re: [PATCH net-next 3/4] virtio_net: Use new RSS config structs

On Thu, Mar 20, 2025 at 1:36 PM Akihiko Odaki wrote: > > On 2025/03/20 10:50, Jason Wang wrote: > > On Wed, Mar 19, 2025 at 12:48 PM Akihiko Odaki > > wrote: > >> > >> On 2025/03/19 10:43, Jason Wang wrote: > >>> On Tue, Mar 18, 2025 at 5:57 PM Ak

Re: [PATCH net-next 3/4] virtio_net: Use new RSS config structs

On Wed, Mar 19, 2025 at 12:48 PM Akihiko Odaki wrote: > > On 2025/03/19 10:43, Jason Wang wrote: > > On Tue, Mar 18, 2025 at 5:57 PM Akihiko Odaki > > wrote: > >> > >> The new RSS configuration structures allow easily constructing data for > >> V

Re: [PATCH v2 03/10] vhost-scsi: Fix vhost_scsi_send_status()

On Thu, Mar 20, 2025 at 1:54 AM Dongli Zhang wrote: > > Hi Jason, > > On 3/17/25 5:48 PM, Jason Wang wrote: > > On Tue, Mar 18, 2025 at 7:52 AM Dongli Zhang > > wrote: > >> > >> Although the support of VIRTIO_F_ANY_LAYOUT + VIRTIO_F_VERSION_1 was > &

Re: [PATCH v2 04/10] vhost: modify vhost_log_write() for broader users

On Thu, Mar 20, 2025 at 12:38 AM Dongli Zhang wrote: > > Hi Jason, > > On 3/17/25 6:12 PM, Jason Wang wrote: > > On Tue, Mar 18, 2025 at 7:51 AM Dongli Zhang > > wrote: > >> > >> Currently, the only user of vhost_log_write() is vhost-net. The 'le

Re: [PATCH net-next 4/4] virtio_net: Allocate rss_hdr with devres

ze") > Signed-off-by: Akihiko Odaki > --- > drivers/net/virtio_net.c | 10 -- > 1 file changed, 4 insertions(+), 6 deletions(-) Acked-by: Jason Wang Thanks

Re: [PATCH net-next 3/4] virtio_net: Use new RSS config structs

On Tue, Mar 18, 2025 at 5:57 PM Akihiko Odaki wrote: > > The new RSS configuration structures allow easily constructing data for > VIRTIO_NET_CTRL_MQ_RSS_CONFIG as they strictly follow the order of data > for the command. > > Signed-off-by: Akihiko Odaki > --- > drivers/net/virtio_net.c | 117 >

Re: [PATCH net-next 2/4] virtio_net: Fix endian with virtio_net_ctrl_rss

Signed-off-by: Akihiko Odaki Acked-by: Jason Wang Thanks

Re: [PATCH net-next 1/4] virtio_net: Split struct virtio_net_rss_config

On Tue, Mar 18, 2025 at 5:57 PM Akihiko Odaki wrote: > > struct virtio_net_rss_config was less useful in actual code because of a > flexible array placed in the middle. Add new structures that split it > into two to avoid having a flexible array in the middle. > > Sugges

Re: [PATCH v2 04/10] vhost: modify vhost_log_write() for broader users

On Tue, Mar 18, 2025 at 7:51 AM Dongli Zhang wrote: > > Currently, the only user of vhost_log_write() is vhost-net. The 'len' > argument prevents logging of pages that are not tainted by the RX path. > > Adjustments are needed since more drivers (i.e. vhost-scsi) begin using > vhost_log_write(). S

Re: [PATCH v2 02/10] vhost-scsi: Fix vhost_scsi_send_bad_target()

vhost/scsi.c | 48 ++++++------ > 1 file changed, 37 insertions(+), 11 deletions(-) > Acked-by: Jason Wang Thanks

Re: [PATCH v2 03/10] vhost-scsi: Fix vhost_scsi_send_status()

csi *vs, struct > vhost_virtqueue *vq) > else if (ret == -EIO) > vhost_scsi_send_bad_target(vs, vq, &vc, TYPE_IO_CMD); > else if (ret == -ENOMEM) > - vhost_scsi_send_status(vs, vq, vc.head, vc.out, > + vhost_scsi_send_status(vs, vq, &vc, >SAM_STAT_TASK_SET_FULL); > } while (likely(!vhost_exceeds_weight(vq, ++c, 0))); > out: > -- > 2.39.3 > Acked-by: Jason Wang Thanks

Re: [PATCH v2 01/10] vhost-scsi: protect vq->log_used with vq->mutex

; Assuming the VMM is QEMU. The vq->log_base is from QEMU userpace and can be > reclaimed via gfree(). As a result, this causes invalid memory writes to > QEMU userspace. > > The control queue path has the same issue. > > Signed-off-by: Dongli Zhang > --- Acked-by: Jason Wang Thanks

Re: [PATCH v2] virtio_ring: Fix data race by tagging event_triggered as racy for KCSAN

ng_virtqueue *vq = to_vvq(_vq); > > if (vq->event_triggered) > - vq->event_triggered = false; > + data_race(vq->event_triggered = false); > > return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) : > virtqueue_enable_cb_delayed_split(_vq); > -- > 2.25.1 > Acked-by: Jason Wang Thanks

Re: [PATCH v5] can: virtio: Initial virtio CAN driver.

On Wed, Mar 12, 2025 at 9:36 PM Marc Kleine-Budde wrote: > > On 12.03.2025 14:28:10, Matias Ezequiel Vara Larsen wrote: > > On Wed, Mar 12, 2025 at 11:41:26AM +0100, Marc Kleine-Budde wrote: > > > On 12.03.2025 11:31:12, Matias Ezequiel Vara Larsen wrote: > > > > On Thu, Feb 01, 2024 at 07:57:45PM

  1   2   3   4   5   6   7   8   9   10   >