similar to: [PATCH] vhost: error handling fix

vhost_dev_set_owner() is an example of why come-from labels are bad style. devel/drivers/vhost/vhost.c 473 /* Caller should have device mutex */ 474 long vhost_dev_set_owner(struct vhost_dev *dev) 475 { 476 struct task_struct *worker; 477 int err; 478 479 /* Is there an owner already? */ 480 if (vhost_dev_has_owner(dev)) { 481

vDPA device currently relays the eventfd via vhost worker. This is inefficient due the latency of wakeup and scheduling, so this patch tries to introduce a use_worker attribute for the vhost device. When use_worker is not set with vhost_dev_init(), vhost won't try to allocate a worker thread and the vhost_poll will be processed directly in the wakeup function. This help for vDPA since it

Since 2.6.36-rc1, non-root users of vhost-net fail to attach if they are in any cgroups. This is a regression, and libvirt actually uses this functionality, as it runs qemu with reduced priveledges. The bug is that when qemu uses vhost, vhost wants to attach its thread to all cgroups that qemu has. But we got the API backwards, so a non-priveledged process (qemu) tried to control the priveledged

Since 2.6.36-rc1, non-root users of vhost-net fail to attach if they are in any cgroups. This is a regression, and libvirt actually uses this functionality, as it runs qemu with reduced priveledges. The bug is that when qemu uses vhost, vhost wants to attach its thread to all cgroups that qemu has. But we got the API backwards, so a non-priveledged process (qemu) tried to control the priveledged

I saw WARN_ON(!list_empty(&dev->work_list)) trigger so our custom flush is not as airtight as need be. This patch switches to a simple atomic counter + srcu instead of the custom locked queue + flush implementation. This will slow down the setup ioctls, which should not matter - it's slow path anyway. We use the expedited flush to at least make sure it has a sane time bound. Works

I saw WARN_ON(!list_empty(&dev->work_list)) trigger so our custom flush is not as airtight as need be. This patch switches to a simple atomic counter + srcu instead of the custom locked queue + flush implementation. This will slow down the setup ioctls, which should not matter - it's slow path anyway. We use the expedited flush to at least make sure it has a sane time bound. Works

On Mon, Aug 22, 2016 at 08:16:17AM -0600, Jonathan Corbet wrote: > On Mon, 22 Aug 2016 16:57:46 +0300 > "Michael S. Tsirkin" <mst at redhat.com> wrote: > > > commit commit ea04036032edda6f771c1381d03832d2ed0f6c31 ("CodingStyle: > > add some more error handling guidelines") suggests never naming goto > > labels after the goto location - that is

On Mon, Aug 22, 2016 at 08:16:17AM -0600, Jonathan Corbet wrote: > On Mon, 22 Aug 2016 16:57:46 +0300 > "Michael S. Tsirkin" <mst at redhat.com> wrote: > > > commit commit ea04036032edda6f771c1381d03832d2ed0f6c31 ("CodingStyle: > > add some more error handling guidelines") suggests never naming goto > > labels after the goto location - that is

It was noticed that the copy_user() friends that was used to access virtqueue metdata tends to be very expensive for dataplane implementation like vhost since it involves lots of software checks, speculation barrier, hardware feature toggling (e.g SMAP). The extra cost will be more obvious when transferring small packets since the time spent on metadata accessing become significant.. This patch

It was noticed that the copy_user() friends that was used to access virtqueue metdata tends to be very expensive for dataplane implementation like vhost since it involves lots of software checks, speculation barrier, hardware feature toggling (e.g SMAP). The extra cost will be more obvious when transferring small packets since the time spent on metadata accessing become significant.. This patch

It was reported that metadata acceleration introduces several issues, so this patch reverts commit ff466032dc9e5a61217f22ea34b2df932786bbfc, 73f628ec9e6bcc45b77c53fe6d0c0ec55eaf82af and 0b4a7092ffe568a55bf8f3cefdf79ff666586d91. We will rework it on the next version. Cc: Jason Gunthorpe <jgg at mellanox.com> Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vhost.c

On Thu, Oct 17, 2019 at 07:44:15PM +0200, Andrey Konovalov wrote: > This patch adds kcov_remote_start/kcov_remote_stop annotations to the > vhost_worker function, which is responsible for processing vhost works. > Since vhost_worker is spawned when a vhost device instance is created, > the common kcov handle is used for kcov_remote_start/stop annotations. > > Signed-off-by:

On Tue, Oct 22, 2019 at 6:46 PM Andrey Konovalov <andreyknvl at google.com> wrote: > > This patch adds kcov_remote_start()/kcov_remote_stop() annotations to the > vhost_worker() function, which is responsible for processing vhost works. > Since vhost_worker() threads are spawned per vhost device instance > the common kcov handle is used for kcov_remote_start()/stop()

On Sat, Dec 29, 2018 at 08:46:56PM +0800, Jason Wang wrote: > It was noticed that the copy_user() friends that was used to access > virtqueue metdata tends to be very expensive for dataplane > implementation like vhost since it involves lots of software checks, > speculation barrier, hardware feature toggling (e.g SMAP). The > extra cost will be more obvious when transferring small

We flush under vq mutex when changing backends. This creates a deadlock as workqueue being flushed needs this lock as well. https://bugzilla.redhat.com/show_bug.cgi?id=612421 Drop the vq mutex before flush: we have the device mutex which is sufficient to prevent another ioctl from touching the vq. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- drivers/vhost/net.c | 5 +++++

We flush under vq mutex when changing backends. This creates a deadlock as workqueue being flushed needs this lock as well. https://bugzilla.redhat.com/show_bug.cgi?id=612421 Drop the vq mutex before flush: we have the device mutex which is sufficient to prevent another ioctl from touching the vq. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- drivers/vhost/net.c | 5 +++++

On Wed, Oct 23, 2019 at 3:35 PM Andrey Konovalov <andreyknvl at google.com> wrote: > > On Wed, Oct 23, 2019 at 10:36 AM Dmitry Vyukov <dvyukov at google.com> wrote: > > > > On Tue, Oct 22, 2019 at 6:46 PM Andrey Konovalov <andreyknvl at google.com> wrote: > > > > > > This patch adds kcov_remote_start()/kcov_remote_stop() annotations to the >

On 2019/9/8 ??7:05, Michael S. Tsirkin wrote: > On Thu, Sep 05, 2019 at 08:27:36PM +0800, Jason Wang wrote: >> This is a rework on the commit 7f466032dc9e ("vhost: access vq >> metadata through kernel virtual address"). >> >> It was noticed that the copy_to/from_user() friends that was used to >> access virtqueue metdata tends to be very expensive for

It was noticed that the copy_user() friends that was used to access virtqueue metdata tends to be very expensive for dataplane implementation like vhost since it involves lots of software checks, speculation barrier, hardware feature toggling (e.g SMAP). The extra cost will be more obvious when transferring small packets since the time spent on metadata accessing become more significant. This

Qemu supports up to UIO_MAXIOV s/g so we have to match that because guest drivers may rely on this. Allocate indirect and log arrays dynamically to avoid using too much contigious memory and make the length of hdr array to match the header length since each iovec entry has a least one byte. Test with copying large files w/ and w/o migration in both linux and windows guests. Signed-off-by: Jason