On Thu, Jan 23, 2025 at 2:54 AM Jason Wang wrote:
>
> On Thu, Jan 23, 2025 at 12:32 AM Eugenio Pérez wrote:
> >
> > We need to move the map and unmap out of virtiofs queue lock. We need to
> > store the unmap sgs to call virtqueue_unmap_sgs, so use the request
> > itself.
> >
> > TODO: We need t
On Thu, Jan 23, 2025 at 2:51 AM Jason Wang wrote:
>
> On Thu, Jan 23, 2025 at 12:32 AM Eugenio Pérez wrote:
> >
> > From: Jason Wang
> >
> > Introduce new virtqueue DMA operations which allows the drivers that
> > want to make use of the premapping API but operate at the sg level.
> >
> > Note t
On Thu, Jan 23, 2025 at 2:50 AM Jason Wang wrote:
>
> On Wed, Jan 22, 2025 at 11:49 PM Stefan Hajnoczi wrote:
> >
> > On Tue, Jan 21, 2025 at 11:33:46AM +0100, Eugenio Pérez wrote:
> > > A VDUSE device that implements virtiofs device works fine just by
> > > adding the device id to the whitelist.
On Thu, Nov 7, 2024 at 2:21 PM Colin Ian King wrote:
>
> The boolean variable has_affinity is true when desc is non-null and
> ops->set_vq_affinity is non-null. Hence the call to create_affinity_masks
> does not need to check for desc being non-null is redundant when
> has_affinity is true, so it
On Tue, Nov 5, 2024 at 7:52 PM Dragos Tatulea wrote:
>
> In the error recovery path of mlx5_vdpa_dev_add(), the cleanup is
> executed and at the end put_device() is called which ends up calling
> mlx5_vdpa_free(). This function will execute the same cleanup all over
> again. Most resources support
On Mon, Sep 9, 2024 at 11:30 AM Dragos Tatulea wrote:
>
>
>
> On 30.08.24 12:58, Dragos Tatulea wrote:
> > This series improves the time of .set_map() operations by parallelizing
> > the MKEY creation and deletion for direct MKEYs. Looking at the top
> > level MKEY creation/deletion functions, the
On Mon, Sep 9, 2024 at 11:33 AM Dragos Tatulea wrote:
>
>
>
> On 16.08.24 11:01, Dragos Tatulea wrote:
> > Currently, commands that qualify as throttled can't be used via the
> > async API. That's due to the fact that the throttle semaphore can sleep
> > but the async API can't.
> >
> > This patch
On Tue, Sep 3, 2024 at 9:48 AM Dragos Tatulea wrote:
>
>
>
> On 03.09.24 09:40, Lei Yang wrote:
> > On Mon, Sep 2, 2024 at 7:05 PM Dragos Tatulea wrote:
> >>
> >> Hi Lei,
> >>
> >> On 02.09.24 12:03, Lei Yang wrote:
> >>> Hi Dragos
> >>>
> >>> QE tested this series with mellanox nic, it failed wi
On Thu, Aug 29, 2024 at 5:23 PM Dragos Tatulea wrote:
>
>
>
> On 29.08.24 17:07, Eugenio Perez Martin wrote:
> > On Wed, Aug 21, 2024 at 1:42 PM Dragos Tatulea wrote:
> >>
> >> Currently, when a new MR is set up, the old MR is deleted. MR deletion
> >>
On Thu, Aug 29, 2024 at 3:54 PM Dragos Tatulea wrote:
>
>
>
> On 29.08.24 15:10, Eugenio Perez Martin wrote:
> > On Wed, Aug 21, 2024 at 1:41 PM Dragos Tatulea wrote:
> >>
> >> Use the async interface to issue MTT MKEY creation.
> >> Extra care is
On Wed, Aug 21, 2024 at 1:42 PM Dragos Tatulea wrote:
>
> Currently, when a new MR is set up, the old MR is deleted. MR deletion
> is about 30-40% the time of MR creation. As deleting the old MR is not
> important for the process of setting up the new MR, this operation
> can be postponed.
>
> Thi
On Wed, Aug 21, 2024 at 1:42 PM Dragos Tatulea wrote:
>
> There's currently not a lot of action happening during
> the init/destroy of MR resources. But more will be added
> in the upcoming patches.
If the series doesn't receive new patches, it is just the next patch :).
>
> Signed-off-by: Drago
On Wed, Aug 21, 2024 at 1:42 PM Dragos Tatulea wrote:
>
> Now that the mr resources have their own namespace in the
> struct, give the lock a clearer name.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin Ratiu
Acked-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/core/mlx5_vdpa.h | 2 +-
On Wed, Aug 21, 2024 at 1:42 PM Dragos Tatulea wrote:
>
> Group all mapping related resources into their own structure.
>
> Upcoming patches will add more members in this new structure.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin Ratiu
Acked-by: Eugenio Pérez
> ---
> drivers/vdpa
On Wed, Aug 21, 2024 at 1:42 PM Dragos Tatulea wrote:
>
> Use the async interface to issue MTT MKEY deletion.
>
> This makes destroy_user_mr() on average 8x times faster.
> This number is also dependent on the size of the MR being
> deleted.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin
On Wed, Aug 21, 2024 at 1:41 PM Dragos Tatulea wrote:
>
> Use the async interface to issue MTT MKEY creation.
> Extra care is taken at the allocation of FW input commands
> due to the MTT tables having variable sizes depending on
> MR.
>
> The indirect MKEY is still created synchronously at the
>
On Fri, Aug 16, 2024 at 11:03 AM Dragos Tatulea wrote:
>
> change_num_qps() is still suspending/resuming VQs one by one.
> This change switches to parallel suspend/resume.
>
> When increasing the number of queues the flow has changed a bit for
> simplicity: the setup_vq() function will always be c
On Fri, Aug 16, 2024 at 11:03 AM Dragos Tatulea wrote:
>
> change_num_qps() has a lot of multiplications by 2 to convert
> the number of VQ pairs to number of VQs. This patch simplifies
> the code by doing the VQP -> VQ count conversion at the beginning
> in a variable.
>
> Signed-off-by: Dragos T
On Fri, Aug 16, 2024 at 11:02 AM Dragos Tatulea wrote:
>
> Switch firmware vq modify command to be issued via the async API to
> allow future parallelization. The new refactored function applies the
> modify on a range of vqs and waits for their execution to complete.
>
> For now the command is st
On Fri, Aug 16, 2024 at 11:02 AM Dragos Tatulea wrote:
>
> Switch firmware vq query command to be issued via the async API to
> allow future parallelization.
>
> For now the command is still serial but the infrastructure is there
> to issue commands in parallel, including ratelimiting the number
>
On Fri, Aug 16, 2024 at 11:02 AM Dragos Tatulea wrote:
>
> Introduce a new function mlx5_vdpa_exec_async_cmds() which
> wraps the mlx5_core async firmware command API in a way
> that will be used to parallelize certain operation in this
> driver.
>
> The wrapper deals with the case when mlx5_cmd_e
On Fri, Aug 2, 2024 at 9:24 AM Dragos Tatulea wrote:
>
> This series parallelizes the mlx5_vdpa device suspend and resume
> operations through the firmware async API. The purpose is to reduce live
> migration downtime.
>
> The series starts with changing the VQ suspend and resume commands
> to the
On Fri, Aug 2, 2024 at 9:24 AM Dragos Tatulea wrote:
>
> Switch firmware vq modify command to be issued via the async API to
> allow future parallelization. The new refactored function applies the
> modify on a range of vqs and waits for their execution to complete.
>
> For now the command is stil
On Fri, Aug 2, 2024 at 9:24 AM Dragos Tatulea wrote:
>
> mlx5_vdpa_err() was missing. This patch adds it and uses it in the
> necessary places.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Tariq Toukan
Acked-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/core/mlx5_vdpa.h | 5 +
> drive
On Wed, Jul 24, 2024 at 9:44 AM Zhu Jun wrote:
>
> The unsigned int should use "%u" instead of "%d".
>
> Signed-off-by: Zhu Jun
Reviewed-by: Eugenio Pérez
Thanks!
> ---
> tools/virtio/ringtest/main.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/tools/virtio/ringte
On Wed, Jun 26, 2024 at 12:28 PM Dragos Tatulea wrote:
>
> Start using the suspend/resume_vq() error return codes previously added.
>
> Reviewed-by: Cosmin Ratiu
> Reviewed-by: Zhu Yanjun
> Signed-off-by: Dragos Tatulea
Reviewed-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c |
On Wed, Jun 26, 2024 at 12:28 PM Dragos Tatulea wrote:
>
> Until now resume_vq() was used only for the suspend/resume scenario.
> This change also allows calling resume_vq() to bring it from Init to
> Ready state (VQ initialization).
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin Ratiu
On Wed, Jun 26, 2024 at 12:28 PM Dragos Tatulea wrote:
>
> Based on the filled flag, create VQs that are filled or blank.
> Blank VQs will be filled in later through VQ modify.
>
> Downstream patches will make use of this to pre-create blank VQs at
> vdpa device creation.
>
s/Downstream/Later/ ?
On Wed, Jun 26, 2024 at 11:27 AM Dragos Tatulea wrote:
>
> On Wed, 2024-06-19 at 17:54 +0200, Eugenio Perez Martin wrote:
> > On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
> > >
> > > Currently, hardware VQs are created right when the vdpa device gets into
On Wed, Jun 26, 2024 at 12:27 PM Dragos Tatulea wrote:
>
> Function is used to set default values, so name it accordingly.
>
> Signed-off-by: Dragos Tatulea
Reviewed-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 10 +-
> 1 file changed, 5 insertions(+), 5 deletions(-)
On Wed, Jun 26, 2024 at 12:27 PM Dragos Tatulea wrote:
>
> The virtio spec says that a vdpa device should start off with one queue
> pair. The driver is already compliant.
>
> This patch moves the initialization to device add and reset times. This
> is done in preparation for the pre-creation of h
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> VQ indices in the range [cur_num_qps, max_vqs) represent queues that
> have not yet been activated. .set_vq_ready should not activate these
> VQs.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin Ratiu
Acked-by: Eugenio Pérez
>
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> The vdpa device can be reset many times in sequence without any
> significant state changes in between. Previously this was not a problem:
> VQs were torn down only on first reset. But after VQ pre-creation was
> introduced, each reset will
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> There are a few conditions under which the hardware VQs need a full
> teardown and setup:
>
> - VQ size changed to something else than default value. Hardware VQ size
> modification is not supported.
>
> - User turns off certain device fe
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> Currently, hardware VQs are created right when the vdpa device gets into
> DRIVER_OK state. That is easier because most of the VQ state is known by
> then.
>
> This patch switches to creating all VQs and their associated resources
> at devi
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> Resume a VQ if it is already created when the number of VQ pairs
> increases. This is done in preparation for VQ pre-creation which is
> coming in a later patch. It is necessary because calling setup_vq() on
> an already created VQ will ret
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> There are a few more places modifying the VQ to Ready directly. Let's
> consolidate them into resume_vq().
>
> The redundant warnings for resume_vq() errors can also be dropped.
>
> There is one special case that needs to be handled for vir
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> Instead of blindly calling suspend/resume_vqs(), make then return error
> codes.
>
> To keep compatibility, keep suspending or resuming VQs on error and
> return the last error code. The assumption here is that the error code
> would be the
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> Otherwise, when virtqueues are moved from INIT to READY the latest mkey
> will not be set appropriately.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin Ratiu
Acked-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c |
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> Currently rqt_size is initialized during device flag configuration.
> That's because it is the earliest moment when device knows if MQ
> (multi queue) is on or off.
>
> Shift this configuration earlier to device creation time. This implies
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea wrote:
>
> The virtqueue size is a pre-requisite for setting up any virtqueue
> resources. For the upcoming optimization of creating virtqueues at
> device add, the virtqueue size has to be configured.
>
> Store the default queue size in struct mlx5_v
On Mon, Jun 17, 2024 at 5:08 PM Dragos Tatulea wrote:
>
> The hardware VQ configuration is mirrored by data in struct
> mlx5_vdpa_virtqueue . Instead of clearing just a few fields at reset,
> fully clear the struct and initialize with the appropriate default
> values.
>
> As clear_vqs_ready() is u
On Mon, Jun 17, 2024 at 5:08 PM Dragos Tatulea wrote:
>
> No need to iterate over max number of VQs.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin Ratiu
Acked-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
>
On Mon, Jun 17, 2024 at 5:08 PM Dragos Tatulea wrote:
>
> Use the dedicated suspend_vqs() function instead.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin Ratiu
Reviewed-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 7 +--
> 1 file changed, 1 insertion(+), 6 dele
On Mon, Jun 17, 2024 at 5:08 PM Dragos Tatulea wrote:
>
> The check is done inside teardown_vq().
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin Ratiu
Reviewed-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 10 ++
> 1 file changed, 2 insertions(+), 8 deletions
On Mon, Jun 17, 2024 at 5:08 PM Dragos Tatulea wrote:
Patch message suggestion:
Originally, the second loop initialized the CVQ. But (acde3929492b
("vdpa/mlx5: Use consistent RQT size") initialized all the queues in
the first loop, so the second iteration in ...
>
> The second iteration in init_
On Mon, Jun 17, 2024 at 5:08 PM Dragos Tatulea wrote:
>
> ... by changing the setup_vq_resources() parameter.
s/parameter/parameter type/ ?
Either way,
Acked-by: Eugenio Pérez
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Cosmin Ratiu
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 10 +
On Mon, Jun 17, 2024 at 5:08 PM Dragos Tatulea wrote:
>
> setup_driver()/teardown_driver() are a bit vague. These functions are
> used for virtqueue resources.
>
> Same for alloc_resources()/teardown_resources(): they represent fixed
> resources that are meant to exist during the device lifetime.
On Wed, May 15, 2024 at 5:05 PM Michael S. Tsirkin wrote:
>
> There are two issues around seqpacket_allow:
> 1. seqpacket_allow is not initialized when socket is
>created. Thus if features are never set, it will be
>read uninitialized.
> 2. if VIRTIO_VSOCK_F_SEQPACKET is set and then clear
On Tue, Apr 2, 2024 at 11:21 PM Michael S. Tsirkin wrote:
>
> VDPA_GET_VRING_SIZE by mistake uses the already occupied
> ioctl # 0x80 and we never noticed - it happens to work
> because the direction and size are different, but confuses
> tools such as perf which like to look at just the number,
>
On Mon, Feb 19, 2024 at 2:09 AM Lei Yang wrote:
>
> QE tested this patch's V2, qemu no longer print error messages
> "qemu-system-x86_64: Insufficient written data (0)" after
> enable/disable multi queues multi times inside guest. Both "x-svq=on
> '' and without it are all test pass.
>
> Tested-by
On Wed, Feb 14, 2024 at 8:52 PM Steven Sistare
wrote:
>
> On 2/14/2024 2:39 PM, Eugenio Perez Martin wrote:
> > On Wed, Feb 14, 2024 at 6:50 PM Steven Sistare
> > wrote:
> >>
> >> On 2/13/2024 11:10 AM, Eugenio Perez Martin wrote:
> >>> On Mon, Feb
On Wed, Feb 14, 2024 at 6:50 PM Steven Sistare
wrote:
>
> On 2/13/2024 11:10 AM, Eugenio Perez Martin wrote:
> > On Mon, Feb 12, 2024 at 6:16 PM Steve Sistare
> > wrote:
> >>
> >> Flush to guarantee no workers are running when suspend returns.
&g
On Mon, Feb 12, 2024 at 6:16 PM Steve Sistare wrote:
>
> Flush to guarantee no workers are running when suspend returns.
>
> Signed-off-by: Steve Sistare
> ---
> drivers/vdpa/vdpa_sim/vdpa_sim.c | 13 +
> 1 file changed, 13 insertions(+)
>
> diff --git a/drivers/vdpa/vdpa_sim/vdpa_si
On Mon, Feb 12, 2024 at 6:16 PM Steve Sistare wrote:
>
> Flush to guarantee no workers are running when suspend returns.
>
> Signed-off-by: Steve Sistare
Acked-by: Eugenio Pérez
Should this have a Fixes tag?
> ---
> drivers/vhost/vdpa.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --g
On Tue, Feb 13, 2024 at 3:26 PM Steve Sistare wrote:
>
> If a vdpa device is not in state DRIVER_OK, then there is no driver state
> to preserve, so no need to call the suspend and resume driver ops.
>
> Suggested-by: Eugenio Perez Martin "
> Signed-off-by: Steve Sistare
On Tue, Feb 13, 2024 at 8:49 AM Eugenio Perez Martin
wrote:
>
> On Mon, Feb 12, 2024 at 9:20 AM Michael S. Tsirkin wrote:
> >
> > On Fri, Feb 09, 2024 at 02:29:59PM -0800, Steve Sistare wrote:
> > > Calling suspend or resume requires VIRTIO_CONFIG_S_DRIVER_OK,
On Mon, Feb 12, 2024 at 9:20 AM Michael S. Tsirkin wrote:
>
> On Fri, Feb 09, 2024 at 02:29:59PM -0800, Steve Sistare wrote:
> > Calling suspend or resume requires VIRTIO_CONFIG_S_DRIVER_OK, for all
> > vdpa devices.
> >
> > Suggested-by: Eugenio Perez Martin &quo
On Tue, Feb 6, 2024 at 3:52 PM Stefano Garzarella wrote:
>
> If VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK is not negotiated, we expect
> the driver to enable virtqueue before setting DRIVER_OK. If the driver
> tries anyway, better to fail right away as soon as we get the ioctl.
> Let's also update th
On Mon, Jan 22, 2024 at 11:22 AM Stefano Garzarella wrote:
>
> On Wed, Jan 17, 2024 at 11:23:23AM -0800, Steve Sistare wrote:
> >vdpasim_do_reset sets running to true, which is wrong, as it allows
> >vdpasim_kick_vq to post work requests before the device has been
> >configured. To fix, do not se
On Wed, Jan 10, 2024 at 9:40 PM Steve Sistare wrote:
>
> To pass ownership of a live vdpa device to a new process, the user
> suspends the device, calls VHOST_NEW_OWNER to change the mm, and calls
> VHOST_IOTLB_REMAP to change the user virtual addresses to match the new
> mm. Flush workers in sus
On Wed, Jan 10, 2024 at 9:40 PM Steve Sistare wrote:
>
> vdpasim_do_reset sets running to true, which is wrong, as it allows
> vdpasim_kick_vq to post work requests before the device has been
> configured. To fix, do not set running until VIRTIO_CONFIG_S_FEATURES_OK
> is set.
>
> Signed-off-by: S
On Wed, Jan 10, 2024 at 9:40 PM Steve Sistare wrote:
>
> When device ownership is passed to a new process via VHOST_NEW_OWNER,
> some devices need to know the new userland addresses of the dma mappings.
> Define the new iotlb message type VHOST_IOTLB_REMAP to update the uaddr
> of a mapping. The
On Tue, Jan 9, 2024 at 12:11 PM Maxime Coquelin
wrote:
>
> Virtio-net driver control queue implementation is not safe
> when used with VDUSE. If the VDUSE application does not
> reply to control queue messages, it currently ends up
> hanging the kernel thread sending this command.
>
> Some work is
On Thu, Jan 4, 2024 at 4:39 PM Maxime Coquelin
wrote:
>
> This patch adds Virtio-net device type to the supported
> devices types.
>
> Initialization fails if the device does not support
> VIRTIO_F_VERSION_1 feature, in order to guarantee the
> configuration space is read-only. It also fails with
On Fri, Jan 5, 2024 at 9:12 AM Maxime Coquelin
wrote:
>
>
>
> On 1/5/24 03:45, Jason Wang wrote:
> > On Thu, Jan 4, 2024 at 11:38 PM Maxime Coquelin
> > wrote:
> >>
> >> Virtio-net driver control queue implementation is not safe
> >> when used with VDUSE. If the VDUSE application does not
> >> re
On Thu, Jan 4, 2024 at 4:38 PM Maxime Coquelin
wrote:
>
> This patch is preliminary work to enable network device
> type support to VDUSE.
>
> As VIRTIO_BLK_F_CONFIG_WCE shares the same value as
> VIRTIO_NET_F_HOST_TSO4, we need to restrict its check
> to Virtio-blk device type.
>
> Acked-by: Jaso
On Wed, Jan 3, 2024 at 11:00 AM Yunsheng Lin wrote:
>
> introduce vhost_net_test basing on virtio_test to test
> vhost_net changing in the kernel.
>
> Signed-off-by: Yunsheng Lin
> ---
> tools/virtio/Makefile | 8 +-
> tools/virtio/vhost_net_test.c | 574 +++
On Thu, Dec 21, 2023 at 4:07 PM Dragos Tatulea wrote:
>
> On Thu, 2023-12-21 at 15:55 +0100, Eugenio Perez Martin wrote:
> > On Thu, Dec 21, 2023 at 3:38 PM Dragos Tatulea wrote:
> > >
> > > On Thu, 2023-12-21 at 13:08 +0100, Eugenio Perez Martin wrote:
> >
On Thu, Dec 21, 2023 at 3:38 PM Dragos Tatulea wrote:
>
> On Thu, 2023-12-21 at 13:08 +0100, Eugenio Perez Martin wrote:
> > On Thu, Dec 21, 2023 at 12:52 PM Dragos Tatulea wrote:
> > >
> > > On Thu, 2023-12-21 at 08:46 +0100, Eugenio Perez Martin wrote:
> >
On Thu, Dec 21, 2023 at 12:52 PM Dragos Tatulea wrote:
>
> On Thu, 2023-12-21 at 08:46 +0100, Eugenio Perez Martin wrote:
> > On Thu, Dec 21, 2023 at 3:03 AM Jason Wang wrote:
> > >
> > > On Wed, Dec 20, 2023 at 9:32 PM Eugenio Perez Martin
> > > wrote:
&g
On Thu, Dec 21, 2023 at 3:03 AM Jason Wang wrote:
>
> On Wed, Dec 20, 2023 at 9:32 PM Eugenio Perez Martin
> wrote:
> >
> > On Wed, Dec 20, 2023 at 5:06 AM Jason Wang wrote:
> > >
> > > On Wed, Dec 20, 2023 at 11:46 AM Jason Wang wrote:
> > >
On Tue, Dec 19, 2023 at 7:10 PM Dragos Tatulea wrote:
>
> Virtqueue state change during DRIVE_OK is not supported by the virtio
> standard. Allow this op in DRIVER_OK only for devices that support
> changing the state during DRIVER_OK if the device is suspended.
>
> Signed-off-by: Dragos Tatulea
On Tue, Dec 19, 2023 at 7:09 PM Dragos Tatulea wrote:
>
> Virtqueue address change during DRIVE_OK is not supported by the virtio
> standard. Allow this op in DRIVER_OK only for devices that support
> changing the address during DRIVER_OK if the device is suspended.
>
> Signed-off-by: Dragos Tatul
On Tue, Dec 19, 2023 at 7:09 PM Dragos Tatulea wrote:
>
> If userland sets this feature, allow it.
>
> Signed-off-by: Dragos Tatulea
> Suggested-by: Eugenio Pérez
Acked-by: Eugenio Pérez
> ---
> drivers/vhost/vdpa.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/vhost/vdpa.
On Tue, Dec 19, 2023 at 7:09 PM Dragos Tatulea wrote:
>
> If userland sets this feature, allow it.
>
> Signed-off-by: Dragos Tatulea
> Suggested-by: Eugenio Pérez
Acked-by: Eugenio Pérez
> ---
> drivers/vhost/vdpa.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/vhost/vdpa.
On Tue, Dec 19, 2023 at 7:09 PM Dragos Tatulea wrote:
>
> The virtio spec doesn't allow changing virtqueue state after
> DRIVER_OK. Some devices do support this operation when the device is
> suspended. The VHOST_BACKEND_F_CHANGEABLE_VQ_STATE_IN_SUSPEND flag
> advertises this support as a backend
On Tue, Dec 19, 2023 at 7:09 PM Dragos Tatulea wrote:
>
> The virtio spec doesn't allow changing virtqueue addresses after
> DRIVER_OK. Some devices do support this operation when the device is
> suspended. The VHOST_BACKEND_F_CHANGEABLE_VQ_ADDR_IN_SUSPEND flag
> advertises this support as a backe
On Wed, Dec 20, 2023 at 5:06 AM Jason Wang wrote:
>
> On Wed, Dec 20, 2023 at 11:46 AM Jason Wang wrote:
> >
> > On Wed, Dec 20, 2023 at 2:09 AM Dragos Tatulea wrote:
> > >
> > > The virtio spec doesn't allow changing virtqueue addresses after
> > > DRIVER_OK. Some devices do support this operat
On Tue, Dec 19, 2023 at 12:16 PM Dragos Tatulea wrote:
>
> On Tue, 2023-12-19 at 08:24 +0100, Eugenio Perez Martin wrote:
> > On Mon, Dec 18, 2023 at 2:58 PM Dragos Tatulea wrote:
> > >
> > > On Mon, 2023-12-18 at 13:06 +0100, Eugenio Perez Martin wrote:
> >
On Mon, Dec 18, 2023 at 2:58 PM Dragos Tatulea wrote:
>
> On Mon, 2023-12-18 at 13:06 +0100, Eugenio Perez Martin wrote:
> > On Mon, Dec 18, 2023 at 11:52 AM Dragos Tatulea wrote:
> > >
> > > On Mon, 2023-12-18 at 11:16 +0100, Eugenio Perez Martin wrote:
> >
On Mon, Dec 18, 2023 at 11:52 AM Dragos Tatulea wrote:
>
> On Mon, 2023-12-18 at 11:16 +0100, Eugenio Perez Martin wrote:
> > On Sat, Dec 16, 2023 at 12:03 PM Dragos Tatulea wrote:
> > >
> > > On Fri, 2023-12-15 at 18:56 +0100, Eugenio Perez Martin wrote:
> >
On Sat, Dec 16, 2023 at 12:03 PM Dragos Tatulea wrote:
>
> On Fri, 2023-12-15 at 18:56 +0100, Eugenio Perez Martin wrote:
> > On Fri, Dec 15, 2023 at 3:13 PM Dragos Tatulea wrote:
> > >
> > > On Fri, 2023-12-15 at 12:35 +, Dragos Tatulea wrote:
> > &
On Fri, Dec 15, 2023 at 3:13 PM Dragos Tatulea wrote:
>
> On Fri, 2023-12-15 at 12:35 +, Dragos Tatulea wrote:
> > On Thu, 2023-12-14 at 19:30 +0100, Eugenio Perez Martin wrote:
> > > On Thu, Dec 14, 2023 at 4:51 PM Dragos Tatulea
> > > wrote:
> > >
gt; > > On 12/12/2023 11:21 AM, Eugenio Perez Martin wrote:
> > > > > On Tue, Dec 5, 2023 at 11:46 AM Dragos Tatulea
> > > > > wrote:
> > > > > > Addresses get set by .set_vq_address. hw vq addresses will be
> > > >
On Tue, Dec 5, 2023 at 11:47 AM Dragos Tatulea wrote:
>
> Instead of tearing down and setting up vq resources, use vq
> suspend/resume during .set_map to speed things up a bit.
>
> The vq mr is updated with the new mapping while the vqs are suspended.
>
> If the device doesn't support resumable vq
On Tue, Dec 5, 2023 at 11:46 AM Dragos Tatulea wrote:
>
> Addresses get set by .set_vq_address. hw vq addresses will be updated on
> next modify_virtqueue.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Gal Pressman
> Acked-by: Eugenio Pérez
I'm kind of ok with this patch and the next one ab
On Tue, Dec 5, 2023 at 11:47 AM Dragos Tatulea wrote:
>
> Track allocated mrs in a list and show warning when leaks are detected
> on device free or reset.
>
> Signed-off-by: Dragos Tatulea
> Reviewed-by: Gal Pressman
Acked-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/core/mlx5_vdpa.h | 2 ++
On Tue, Dec 5, 2023 at 11:47 AM Dragos Tatulea wrote:
>
> Deleting the old mr during mr update (.set_map) and then modifying the
> vqs with the new mr is not a good flow for firmware. The firmware
> expects that mkeys are deleted after there are no more vqs referencing
> them.
>
> Introduce refere
On Fri, Dec 1, 2023 at 11:50 AM Dragos Tatulea wrote:
>
> .set_vq_state will set the indices and mark the fields to be modified in
> the hw vq.
>
> Signed-off-by: Dragos Tatulea
Acked-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 8
> include/linux/mlx5/mlx5_ifc_vdpa
On Fri, Dec 1, 2023 at 11:50 AM Dragos Tatulea wrote:
>
> Implement vdpa vq and device resume if capability detected. Add support
> for suspend -> ready state change.
>
> Signed-off-by: Dragos Tatulea
Acked-by: Eugenio Pérez
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 67 +
On Fri, Dec 1, 2023 at 11:49 AM Dragos Tatulea wrote:
>
> Add a bitmask variable that tracks hw vq field changes that
> are supposed to be modified on next hw vq change command.
>
> This will be useful to set multiple vq fields when resuming the vq.
>
> The state needs to remain as a parameter as
On Fri, Dec 1, 2023 at 11:49 AM Dragos Tatulea wrote:
>
> mlx5_vdpa_destroy_mr contains more logic than _mlx5_vdpa_destroy_mr.
> There is no reason for this to be the case. All the logic can go into
> the unlocked variant.
>
> Using the unlocked version is needed in a follow-up patch. And it also
On Tue, Jan 12, 2021 at 4:12 AM Jason Wang wrote:
>
>
> On 2021/1/11 下午8:26, Eli Cohen wrote:
> > On Wed, Dec 16, 2020 at 02:48:18PM +0800, Jason Wang wrote:
> >> This patch introduces the control virtqueue support for vDPA
> >> simulator. This is a requirement for supporting advanced features lik
On Thu, Sep 24, 2020 at 5:24 AM Jason Wang wrote:
>
> This patch introduces the support of ASID based IOTLB by tagging IOTLB
> with a unique ASID. This is a must for supporting ASID based vhost
> IOTLB API by the following patches.
>
> IOTLB were stored in a hlist and new IOTLB will be allocated w
On Thu, Sep 24, 2020 at 5:23 AM Jason Wang wrote:
>
> This patch introduces virtqueue groups to vDPA device. The virtqueue
> group is the minimal set of virtqueues that must share an address
> space. And the adddress space identifier could only be attached to
> a specific virtqueue group.
>
> A ne
On Thu, Sep 24, 2020 at 5:25 AM Jason Wang wrote:
>
> This patch extends the vhost-vdpa to support ASID based IOTLB API. The
> vhost-vdpa device will allocated multple IOTLBs for vDPA device that
> supports multiple address spaces. The IOTLBs and vDPA device memory
> mappings is determined and mai
On Tue, Jul 21, 2020 at 4:55 AM Jason Wang wrote:
>
>
> On 2020/7/20 下午7:16, Eugenio Pérez wrote:
> > On Mon, Jul 20, 2020 at 11:27 AM Michael S. Tsirkin wrote:
> >> On Thu, Jul 16, 2020 at 07:16:27PM +0200, Eugenio Perez Martin wrote:
> >>> On Fri, Jul 10
On Mon, Jul 20, 2020 at 10:55 AM Jason Wang wrote:
>
>
> On 2020/7/17 上午1:16, Eugenio Perez Martin wrote:
> > On Fri, Jul 10, 2020 at 7:58 AM Michael S. Tsirkin wrote:
> >> On Fri, Jul 10, 2020 at 07:39:26AM +0200, Eugenio Perez Martin wrote:
> >>>>> H
On Fri, Jul 10, 2020 at 7:58 AM Michael S. Tsirkin wrote:
>
> On Fri, Jul 10, 2020 at 07:39:26AM +0200, Eugenio Perez Martin wrote:
> > > > How about playing with the batch size? Make it a mod parameter instead
> > > > of the hard coded 64, and
1 - 100 of 122 matches
Mail list logo
