aboutsummaryrefslogtreecommitdiff
path: root/include/linux
diff options
context:
space:
mode:
authorRusty Russell <rusty@rustcorp.com.au>2007-10-22 11:03:40 +1000
committerRusty Russell <rusty@rustcorp.com.au>2007-10-23 15:49:55 +1000
commit0a8a69dd77ddbd4513b21363021ecde7e1025502 (patch)
treeed6d8f0756835390b4c0d9a172422f2e42a65523 /include/linux
parentb01d9f2863349b0e041b90c3c86a998ee0fed2b0 (diff)
Virtio helper routines for a descriptor ringbuffer implementation
These helper routines supply most of the virtqueue_ops for hypervisors which want to use a ring for virtio. Unlike the previous lguest implementation: 1) The rings are variable sized (2^n-1 elements). 2) They have an unfortunate limit of 65535 bytes per sg element. 3) The page numbers are always 64 bit (PAE anyone?) 4) They no longer place used[] on a separate page, just a separate cacheline. 5) We do a modulo on a variable. We could be tricky if we cared. 6) Interrupts and notifies are suppressed using flags within the rings. Users need only get the ring pages and provide a notify hook (KVM wants the guest to allocate the rings, lguest does it sanely). Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Cc: Dor Laor <dor.laor@qumranet.com>
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/virtio_ring.h119
1 files changed, 119 insertions, 0 deletions
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
new file mode 100644
index 00000000000..ac69e7bb5a1
--- /dev/null
+++ b/include/linux/virtio_ring.h
@@ -0,0 +1,119 @@
+#ifndef _LINUX_VIRTIO_RING_H
+#define _LINUX_VIRTIO_RING_H
+/* 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.
+ *
+ * Copyright Rusty Russell IBM Corporation 2007. */
+#include <linux/types.h>
+
+/* 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 don't notify other side when buffer added. */
+#define VRING_USED_F_NO_NOTIFY 1
+/* This means don't interrupt guest when buffer consumed. */
+#define VRING_AVAIL_F_NO_INTERRUPT 1
+
+/* Virtio ring descriptors: 16 bytes. These can chain together via "next". */
+struct vring_desc
+{
+ /* Address (guest-physical). */
+ __u64 addr;
+ /* Length. */
+ __u32 len;
+ /* The flags as indicated above. */
+ __u16 flags;
+ /* We chain unused descriptors via this, too */
+ __u16 next;
+};
+
+struct vring_avail
+{
+ __u16 flags;
+ __u16 idx;
+ __u16 ring[];
+};
+
+/* u32 is used here for ids for padding reasons. */
+struct vring_used_elem
+{
+ /* Index of start of used descriptor chain. */
+ __u32 id;
+ /* Total length of the descriptor chain which was used (written to) */
+ __u32 len;
+};
+
+struct vring_used
+{
+ __u16 flags;
+ __u16 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. The used fields will be aligned to a "num+1" boundary.
+ *
+ * struct vring
+ * {
+ * // The actual descriptors (16 bytes each)
+ * struct vring_desc desc[num];
+ *
+ * // A ring of available descriptor heads with free-running index.
+ * __u16 avail_flags;
+ * __u16 avail_idx;
+ * __u16 available[num];
+ *
+ * // Padding so a correctly-chosen num value will cache-align used_idx.
+ * char pad[sizeof(struct vring_desc) - sizeof(avail_flags)];
+ *
+ * // A ring of used descriptor heads with free-running index.
+ * __u16 used_flags;
+ * __u16 used_idx;
+ * struct vring_used_elem used[num];
+ * };
+ */
+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);
+ vr->used = p + (num+1)*(sizeof(struct vring) + sizeof(__u16));
+}
+
+static inline unsigned vring_size(unsigned int num)
+{
+ return (num + 1) * (sizeof(struct vring_desc) + sizeof(__u16))
+ + sizeof(__u32) + num * sizeof(struct vring_used_elem);
+}
+
+#ifdef __KERNEL__
+#include <linux/irqreturn.h>
+struct virtio_device;
+struct virtqueue;
+
+struct virtqueue *vring_new_virtqueue(unsigned int num,
+ struct virtio_device *vdev,
+ void *pages,
+ void (*notify)(struct virtqueue *vq),
+ bool (*callback)(struct virtqueue *vq));
+void vring_del_virtqueue(struct virtqueue *vq);
+
+irqreturn_t vring_interrupt(int irq, void *_vq);
+#endif /* __KERNEL__ */
+#endif /* _LINUX_VIRTIO_RING_H */