search for: ce2c68

Hi, This patchset allows vhost_net to be used with legacy virtio when guest and host have a different endianness. It is based on previous work by C?dric Le Goater: https://www.mail-archive.com/kvm-ppc at vger.kernel.org/msg09848.html As suggested by MST: - the API now asks for a specific format (big endian) instead of the hint whether byteswap is needed or not (patch 1) - rebased on top of

Hi, This patchset allows vhost_net to be used with legacy virtio when guest and host have a different endianness. It is based on previous work by C?dric Le Goater: https://www.mail-archive.com/kvm-ppc at vger.kernel.org/msg09848.html As suggested by MST: - the API now asks for a specific format (big endian) instead of the hint whether byteswap is needed or not (patch 1) - rebased on top of

...ditionnal overhead to fixed endian architectures: that is all architectures except arm and ppc64. This was addressed in QEMU with a TARGET_IS_BIENDIAN macro. Please give an advice about how to address this in the vhost code. Thanks. diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index ce2c68e..21e7d6a 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -176,34 +176,42 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) return vq->acked_features & (1ULL << bit); } +static inline bool vhost_is_little_endian(struct vhost_virtqueue *...

...er *)(unsigned long)a.used_user_addr; + vq->legacy_big_endian = + !!(a.flags & (0x1 << VHOST_VRING_F_LEGACY_BIG_ENDIAN)); break; case VHOST_SET_VRING_KICK: if (copy_from_user(&f, argp, sizeof f)) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 8c1c792..ce2c68e 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -106,6 +106,9 @@ struct vhost_virtqueue { /* Log write descriptors */ void __user *log_base; struct vhost_log *log; + + /* We need to know the device endianness with legacy virtio. */ + bool legacy_big_endian; }; struct vh...

...ditionnal overhead to fixed endian architectures: that is all architectures except arm and ppc64. This was addressed in QEMU with a TARGET_IS_BIENDIAN macro. Please give an advice about how to address this in the vhost code. Thanks. diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index ce2c68e..21e7d6a 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -176,34 +176,42 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) return vq->acked_features & (1ULL << bit); } +static inline bool vhost_is_little_endian(struct vhost_virtqueue *...

...er *)(unsigned long)a.used_user_addr; + vq->legacy_big_endian = + !!(a.flags & (0x1 << VHOST_VRING_F_LEGACY_BIG_ENDIAN)); break; case VHOST_SET_VRING_KICK: if (copy_from_user(&f, argp, sizeof f)) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 8c1c792..ce2c68e 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -106,6 +106,9 @@ struct vhost_virtqueue { /* Log write descriptors */ void __user *log_base; struct vhost_log *log; + + /* We need to know the device endianness with legacy virtio. */ + bool legacy_big_endian; }; struct vh...