search for: ca3ad41

...() and friends, make it pull in asm/barrier.h itself, not rely on other headers to do it. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- include/linux/virtio_ring.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index ca3ad41..b300787 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -1,6 +1,7 @@ #ifndef _LINUX_VIRTIO_RING_H #define _LINUX_VIRTIO_RING_H +#include <asm/barrier.h> #include <linux/irqreturn.h> #include <uapi/linux/virtio_ring.h> -- MST

...() and friends, make it pull in asm/barrier.h itself, not rely on other headers to do it. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- include/linux/virtio_ring.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index ca3ad41..b300787 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -1,6 +1,7 @@ #ifndef _LINUX_VIRTIO_RING_H #define _LINUX_VIRTIO_RING_H +#include <asm/barrier.h> #include <linux/irqreturn.h> #include <uapi/linux/virtio_ring.h> -- MST

...bool weak_barriers, void *pages, - void (*notify)(struct virtqueue *), + int (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name) { diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index ca3ad41..74fa580 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -70,7 +70,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, struct virtio_device *vdev, bool weak_barriers, void *pages, - void (*notify)(struct virtqueue *v...

Rusty, here is just patch 1 (using bool as return value in notify API). Thanks. Heinz Graalfs (9): virtio_ring: change host notification API virtio_ring: let virtqueue_{kick()/notify()} return a bool virtio_net: verify if virtqueue_kick() succeeded virtio_test: verify if virtqueue_kick() succeeded virtio_ring: add new function virtqueue_is_broken() virtio_blk: verify if queue is

Rusty, here is just patch 1 (using bool as return value in notify API). Thanks. Heinz Graalfs (9): virtio_ring: change host notification API virtio_ring: let virtqueue_{kick()/notify()} return a bool virtio_net: verify if virtqueue_kick() succeeded virtio_test: verify if virtqueue_kick() succeeded virtio_ring: add new function virtqueue_is_broken() virtio_blk: verify if queue is

Hi, this patch-set solves a hang situation when a vlan network device is hot-unplugged from a KVM guest. On System z there exists no handshake mechanism between host and guest when a device is hot-unplugged. The device is removed and no further I/O is possible. The guest is notified about the hard removal with a CRW machine check. As per architecture, the host must repond to any I/O operation

Hi, this patch-set solves a hang situation when a vlan network device is hot-unplugged from a KVM guest. On System z there exists no handshake mechanism between host and guest when a device is hot-unplugged. The device is removed and no further I/O is possible. The guest is notified about the hard removal with a CRW machine check. As per architecture, the host must repond to any I/O operation

...q->vring) = vq->last_used_idx + bufs; - virtio_mb(vq); + virtio_mb(vq->weak_barriers); if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) { END_USE(vq); return false; diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 63c6ea1..ca3ad41 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -4,6 +4,63 @@ #include <linux/irqreturn.h> #include <uapi/linux/virtio_ring.h> +/* + * Barriers in virtio are tricky. Non-SMP virtio guests can't assume + * they're not on an SMP host system, so t...

...q->vring) = vq->last_used_idx + bufs; - virtio_mb(vq); + virtio_mb(vq->weak_barriers); if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) { END_USE(vq); return false; diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 63c6ea1..ca3ad41 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -4,6 +4,63 @@ #include <linux/irqreturn.h> #include <uapi/linux/virtio_ring.h> +/* + * Barriers in virtio are tricky. Non-SMP virtio guests can't assume + * they're not on an SMP host system, so t...

This introduces vringh, which are generic accessors for virtio rings (host side). There's a host-side implementation in vhost, but it assumes that the rings are in userspace, and is tied to the vhost implementation. I have patches to adapt it to use vringh, but I'm pushing this in the next merge window for Sjur, who has CAIF patches which need it. This also includes a test program in

This introduces vringh, which are generic accessors for virtio rings (host side). There's a host-side implementation in vhost, but it assumes that the rings are in userspace, and is tied to the vhost implementation. I have patches to adapt it to use vringh, but I'm pushing this in the next merge window for Sjur, who has CAIF patches which need it. This also includes a test program in