diff options
-rw-r--r-- | hw/net/vhost_net.c | 2 | ||||
-rw-r--r-- | include/hw/virtio/dataplane/vring.h | 2 | ||||
-rw-r--r-- | include/hw/virtio/virtio_ring.h | 167 | ||||
-rw-r--r-- | linux-headers/linux/vhost.h | 2 |
4 files changed, 170 insertions, 3 deletions
diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 77bb93e..4e3a061 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -28,7 +28,6 @@ #include <sys/socket.h> #include <linux/kvm.h> #include <fcntl.h> -#include <linux/virtio_ring.h> #include <netpacket/packet.h> #include <net/ethernet.h> #include <net/if.h> @@ -36,6 +35,7 @@ #include <stdio.h> +#include "hw/virtio/virtio_ring.h" #include "hw/virtio/vhost.h" #include "hw/virtio/virtio-bus.h" diff --git a/include/hw/virtio/dataplane/vring.h b/include/hw/virtio/dataplane/vring.h index af73ee2..d3e086a 100644 --- a/include/hw/virtio/dataplane/vring.h +++ b/include/hw/virtio/dataplane/vring.h @@ -17,8 +17,8 @@ #ifndef VRING_H #define VRING_H -#include <linux/virtio_ring.h> #include "qemu-common.h" +#include "hw/virtio/virtio_ring.h" #include "hw/virtio/virtio.h" typedef struct { diff --git a/include/hw/virtio/virtio_ring.h b/include/hw/virtio/virtio_ring.h new file mode 100644 index 0000000..8f58bc9 --- /dev/null +++ b/include/hw/virtio/virtio_ring.h @@ -0,0 +1,167 @@ +#ifndef _LINUX_VIRTIO_RING_H +#define _LINUX_VIRTIO_RING_H +/* + * This file is copied from /usr/include/linux while converting __uNN types + * to uXX_t, __inline__ to inline, and tab to spaces. + * */ + +/* An interface for efficient virtio implementation, currently for use by KVM + * and lguest, but hopefully others soon. Do NOT change this since it will + * break existing servers and clients. + * + * This header is BSD licensed so anyone can use the definitions to implement + * compatible drivers/servers. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * Copyright Rusty Russell IBM Corporation 2007. */ + +/* This marks a buffer as continuing via the next field. */ +#define VRING_DESC_F_NEXT 1 +/* This marks a buffer as write-only (otherwise read-only). */ +#define VRING_DESC_F_WRITE 2 +/* This means the buffer contains a list of buffer descriptors. */ +#define VRING_DESC_F_INDIRECT 4 + +/* The Host uses this in used->flags to advise the Guest: don't kick me when + * you add a buffer. It's unreliable, so it's simply an optimization. Guest + * will still kick if it's out of buffers. */ +#define VRING_USED_F_NO_NOTIFY 1 +/* The Guest uses this in avail->flags to advise the Host: don't interrupt me + * when you consume a buffer. It's unreliable, so it's simply an + * optimization. */ +#define VRING_AVAIL_F_NO_INTERRUPT 1 + +/* We support indirect buffer descriptors */ +#define VIRTIO_RING_F_INDIRECT_DESC 28 + +/* The Guest publishes the used index for which it expects an interrupt + * at the end of the avail ring. Host should ignore the avail->flags field. */ +/* The Host publishes the avail index for which it expects a kick + * at the end of the used ring. Guest should ignore the used->flags field. */ +#define VIRTIO_RING_F_EVENT_IDX 29 + +/* Virtio ring descriptors: 16 bytes. These can chain together via "next". */ +struct vring_desc { + /* Address (guest-physical). */ + uint64_t addr; + /* Length. */ + uint32_t len; + /* The flags as indicated above. */ + uint16_t flags; + /* We chain unused descriptors via this, too */ + uint16_t next; +}; + +struct vring_avail { + uint16_t flags; + uint16_t idx; + uint16_t ring[]; +}; + +/* u32 is used here for ids for padding reasons. */ +struct vring_used_elem { + /* Index of start of used descriptor chain. */ + uint32_t id; + /* Total length of the descriptor chain which was used (written to) */ + uint32_t len; +}; + +struct vring_used { + uint16_t flags; + uint16_t idx; + struct vring_used_elem ring[]; +}; + +struct vring { + unsigned int num; + + struct vring_desc *desc; + + struct vring_avail *avail; + + struct vring_used *used; +}; + +/* The standard layout for the ring is a continuous chunk of memory which looks + * like this. We assume num is a power of 2. + * + * struct vring + * { + * // The actual descriptors (16 bytes each) + * struct vring_desc desc[num]; + * + * // A ring of available descriptor heads with free-running index. + * uint16_t avail_flags; + * uint16_t avail_idx; + * uint16_t available[num]; + * uint16_t used_event_idx; + * + * // Padding to the next align boundary. + * char pad[]; + * + * // A ring of used descriptor heads with free-running index. + * uint16_t used_flags; + * uint16_t used_idx; + * struct vring_used_elem used[num]; + * uint16_t avail_event_idx; + * }; + */ +/* We publish the used event index at the end of the available ring, and vice + * versa. They are at the end for backwards compatibility. */ +#define vring_used_event(vr) ((vr)->avail->ring[(vr)->num]) +#define vring_avail_event(vr) (*(uint16_t *)&(vr)->used->ring[(vr)->num]) + +static inline void vring_init(struct vring *vr, unsigned int num, void *p, + unsigned long align) +{ + vr->num = num; + vr->desc = p; + vr->avail = p + num*sizeof(struct vring_desc); + vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(uint16_t) + + align-1) & ~(align - 1)); +} + +static inline unsigned vring_size(unsigned int num, unsigned long align) +{ + return ((sizeof(struct vring_desc) * num + sizeof(uint16_t) * (3 + num) + + align - 1) & ~(align - 1)) + + sizeof(uint16_t) * 3 + sizeof(struct vring_used_elem) * num; +} + +/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */ +/* Assuming a given event_idx value from the other size, if + * we have just incremented index from old to new_idx, + * should we trigger an event? */ +static inline int vring_need_event(uint16_t event_idx, uint16_t new_idx, uint16_t old) +{ + /* Note: Xen has similar logic for notification hold-off + * in include/xen/interface/io/ring.h with req_event and req_prod + * corresponding to event_idx + 1 and new_idx respectively. + * Note also that req_event and req_prod in Xen start at 1, + * event indexes in virtio start at 0. */ + return (uint16_t)(new_idx - event_idx - 1) < (uint16_t)(new_idx - old); +} + +#endif /* _LINUX_VIRTIO_RING_H */ diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h index c656f61..bb5df43 100644 --- a/linux-headers/linux/vhost.h +++ b/linux-headers/linux/vhost.h @@ -14,7 +14,7 @@ #include <linux/ioctl.h> #include <linux/virtio_config.h> -#include <linux/virtio_ring.h> +#include "hw/virtio/virtio_ring.h" struct vhost_vring_state { unsigned int index; |