virtio 1.0 makes all memory structures LE, so
we need APIs to conditionally do a byteswap on BE
architectures.
To make it easier to check code statically,
add virtio specific types for multi-byte integers
in memory.
Add low level wrappers that do a byteswap conditionally, these will be
useful e.g. for vhost. Add high level wrappers that will (in the
future) query device endian-ness and act accordingly.
At the moment, stub them out and assume native endian-ness everywhere.
Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
---
include/linux/virtio_byteorder.h | 29 ++++++++++++++++++++++++
include/linux/virtio_config.h | 16 +++++++++++++
include/uapi/linux/virtio_ring.h | 49 ++++++++++++++++++++--------------------
include/uapi/linux/Kbuild | 1 +
4 files changed, 71 insertions(+), 24 deletions(-)
create mode 100644 include/linux/virtio_byteorder.h
diff --git a/include/linux/virtio_byteorder.h b/include/linux/virtio_byteorder.h
new file mode 100644
index 0000000..7afdd8a
--- /dev/null
+++ b/include/linux/virtio_byteorder.h
@@ -0,0 +1,29 @@
+#ifndef _LINUX_VIRTIO_BYTEORDER_H
+#define _LINUX_VIRTIO_BYTEORDER_H
+#include <linux/types.h>
+#include <uapi/linux/virtio_types.h>
+
+/* Memory accessors for handling virtio in modern little endian and in
+ * compatibility big endian format. */
+
+#define __DEFINE_VIRTIO_XX_TO_CPU(bits) \
+static inline u##bits __virtio##bits##_to_cpu(bool little_endian,
__virtio##bits val) \
+{ \
+ if (little_endian) \
+ return le##bits##_to_cpu((__force __le##bits)val); \
+ else \
+ return (__force u##bits)val; \
+} \
+static inline __virtio##bits __cpu_to_virtio##bits(bool little_endian, u##bits
val) \
+{ \
+ if (little_endian) \
+ return (__force __virtio##bits)cpu_to_le##bits(val); \
+ else \
+ return val; \
+}
+
+__DEFINE_VIRTIO_XX_TO_CPU(16)
+__DEFINE_VIRTIO_XX_TO_CPU(32)
+__DEFINE_VIRTIO_XX_TO_CPU(64)
+
+#endif /* _LINUX_VIRTIO_BYTEORDER */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 7f4ef66..d38d3c2 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -4,6 +4,7 @@
#include <linux/err.h>
#include <linux/bug.h>
#include <linux/virtio.h>
+#include <linux/virtio_byteorder.h>
#include <uapi/linux/virtio_config.h>
/**
@@ -152,6 +153,21 @@ int virtqueue_set_affinity(struct virtqueue *vq, int cpu)
return 0;
}
+/* Memory accessors */
+#define DEFINE_VIRTIO_XX_TO_CPU(bits) \
+static inline u##bits virtio##bits##_to_cpu(struct virtio_device *vdev,
__virtio##bits val) \
+{ \
+ return __virtio##bits##_to_cpu(false, val); \
+} \
+static inline __virtio##bits cpu_to_virtio##bits(struct virtio_device *vdev,
u##bits val) \
+{ \
+ return __cpu_to_virtio##bits(false, val); \
+}
+
+DEFINE_VIRTIO_XX_TO_CPU(16)
+DEFINE_VIRTIO_XX_TO_CPU(32)
+DEFINE_VIRTIO_XX_TO_CPU(64)
+
/* Config space accessors. */
#define virtio_cread(vdev, structname, member, ptr) \
do { \
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index a99f9b7..6c00632 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -32,6 +32,7 @@
*
* Copyright Rusty Russell IBM Corporation 2007. */
#include <linux/types.h>
+#include <linux/virtio_types.h>
/* This marks a buffer as continuing via the next field. */
#define VRING_DESC_F_NEXT 1
@@ -61,32 +62,32 @@
/* Virtio ring descriptors: 16 bytes. These can chain together via
"next". */
struct vring_desc {
/* Address (guest-physical). */
- __u64 addr;
+ __virtio64 addr;
/* Length. */
- __u32 len;
+ __virtio32 len;
/* The flags as indicated above. */
- __u16 flags;
+ __virtio16 flags;
/* We chain unused descriptors via this, too */
- __u16 next;
+ __virtio16 next;
};
struct vring_avail {
- __u16 flags;
- __u16 idx;
- __u16 ring[];
+ __virtio16 flags;
+ __virtio16 idx;
+ __virtio16 ring[];
};
/* u32 is used here for ids for padding reasons. */
struct vring_used_elem {
/* Index of start of used descriptor chain. */
- __u32 id;
+ __virtio32 id;
/* Total length of the descriptor chain which was used (written to) */
- __u32 len;
+ __virtio32 len;
};
struct vring_used {
- __u16 flags;
- __u16 idx;
+ __virtio16 flags;
+ __virtio16 idx;
struct vring_used_elem ring[];
};
@@ -109,25 +110,25 @@ struct vring {
* struct vring_desc desc[num];
*
* // A ring of available descriptor heads with free-running index.
- * __u16 avail_flags;
- * __u16 avail_idx;
- * __u16 available[num];
- * __u16 used_event_idx;
+ * __virtio16 avail_flags;
+ * __virtio16 avail_idx;
+ * __virtio16 available[num];
+ * __virtio16 used_event_idx;
*
* // Padding to the next align boundary.
* char pad[];
*
* // A ring of used descriptor heads with free-running index.
- * __u16 used_flags;
- * __u16 used_idx;
+ * __virtio16 used_flags;
+ * __virtio16 used_idx;
* struct vring_used_elem used[num];
- * __u16 avail_event_idx;
+ * __virtio16 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) (*(__u16
*)&(vr)->used->ring[(vr)->num])
+#define vring_avail_event(vr) (*(__virtio16
*)&(vr)->used->ring[(vr)->num])
static inline void vring_init(struct vring *vr, unsigned int num, void *p,
unsigned long align)
@@ -135,29 +136,29 @@ static inline void vring_init(struct vring *vr, unsigned
int num, void *p,
vr->num = num;
vr->desc = p;
vr->avail = p + num*sizeof(struct vring_desc);
- vr->used = (void *)(((unsigned long)&vr->avail->ring[num] +
sizeof(__u16)
+ vr->used = (void *)(((unsigned long)&vr->avail->ring[num] +
sizeof(__virtio16)
+ align-1) & ~(align - 1));
}
static inline unsigned vring_size(unsigned int num, unsigned long align)
{
- return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num)
+ return ((sizeof(struct vring_desc) * num + sizeof(__virtio16) * (3 + num)
+ align - 1) & ~(align - 1))
- + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num;
+ + sizeof(__virtio16) * 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(__u16 event_idx, __u16 new_idx, __u16 old)
+static inline int vring_need_event(__virtio16 event_idx, __virtio16 new_idx,
__virtio16 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 (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
+ return (__virtio16)(new_idx - event_idx - 1) < (__virtio16)(new_idx - old);
}
#endif /* _UAPI_LINUX_VIRTIO_RING_H */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 6cad974..39c161a 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -419,6 +419,7 @@ header-y += virtio_blk.h
header-y += virtio_config.h
header-y += virtio_console.h
header-y += virtio_ids.h
+header-y += virtio_types.h
header-y += virtio_net.h
header-y += virtio_pci.h
header-y += virtio_ring.h
--
MST