aboutsummaryrefslogtreecommitdiff
path: root/include/linux/virtio_ring.h
blob: e338730c2660f9e6efb593858bc672c486c8f996 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
#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.
 *
 * 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. */
#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 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). */
	__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.  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.
 *	__u16 avail_flags;
 *	__u16 avail_idx;
 *	__u16 available[num];
 *	__u16 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;
 *	struct vring_used_elem used[num];
 *	__u16 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])

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(__u16)
		+ 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)
		 + align - 1) & ~(align - 1))
		+ sizeof(__u16) * 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)
{
	/* 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);
}

#ifdef __KERNEL__
#include <linux/irqreturn.h>
struct virtio_device;
struct virtqueue;

struct virtqueue *vring_new_virtqueue(unsigned int num,
				      unsigned int vring_align,
				      struct virtio_device *vdev,
				      bool weak_barriers,
				      void *pages,
				      void (*notify)(struct virtqueue *vq),
				      void (*callback)(struct virtqueue *vq),
				      const char *name);
void vring_del_virtqueue(struct virtqueue *vq);
/* Filter out transport-specific feature bits. */
void vring_transport_features(struct virtio_device *vdev);

irqreturn_t vring_interrupt(int irq, void *_vq);
#endif /* __KERNEL__ */
#endif /* _LINUX_VIRTIO_RING_H */