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>

arch/x86/lguest/Kconfig

@@ -2,6 +2,7 @@ config LGUEST_GUEST
 	bool "Lguest guest support"
 	select PARAVIRT
 	depends on !X86_PAE
+	select VIRTIO_RING
 	help
 	  Lguest is a tiny in-kernel hypervisor.  Selecting this will
 	  allow your kernel to boot under lguest.  This option will increase

drivers/virtio/Kconfig

@@ -1,3 +1,8 @@
 # Virtio always gets selected by whoever wants it.
 config VIRTIO
 	bool
+
+# Similarly the virtio ring implementation.
+config VIRTIO_RING
+	bool
+	depends on VIRTIO

drivers/virtio/Makefile

@@ -1 +1,2 @@
 obj-$(CONFIG_VIRTIO) += virtio.o
+obj-$(CONFIG_VIRTIO_RING) += virtio_ring.o

drivers/virtio/virtio_ring.c

@@ -0,0 +1,313 @@
+/* Virtio ring implementation.
+ *
+ *  Copyright 2007 Rusty Russell IBM Corporation
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include <linux/virtio.h>
+#include <linux/virtio_ring.h>
+#include <linux/device.h>
+
+#ifdef DEBUG
+/* For development, we want to crash whenever the ring is screwed. */
+#define BAD_RING(vq, fmt...)			\
+	do { dev_err(&vq->vq.vdev->dev, fmt); BUG(); } while(0)
+#define START_USE(vq) \
+	do { if ((vq)->in_use) panic("in_use = %i\n", (vq)->in_use); (vq)->in_use = __LINE__; mb(); } while(0)
+#define END_USE(vq) \
+	do { BUG_ON(!(vq)->in_use); (vq)->in_use = 0; mb(); } while(0)
+#else
+#define BAD_RING(vq, fmt...)			\
+	do { dev_err(&vq->vq.vdev->dev, fmt); (vq)->broken = true; } while(0)
+#define START_USE(vq)
+#define END_USE(vq)
+#endif
+
+struct vring_virtqueue
+{
+	struct virtqueue vq;
+
+	/* Actual memory layout for this queue */
+	struct vring vring;
+
+	/* Other side has made a mess, don't try any more. */
+	bool broken;
+
+	/* Number of free buffers */
+	unsigned int num_free;
+	/* Head of free buffer list. */
+	unsigned int free_head;
+	/* Number we've added since last sync. */
+	unsigned int num_added;
+
+	/* Last used index we've seen. */
+	unsigned int last_used_idx;
+
+	/* How to notify other side. FIXME: commonalize hcalls! */
+	void (*notify)(struct virtqueue *vq);
+
+#ifdef DEBUG
+	/* They're supposed to lock for us. */
+	unsigned int in_use;
+#endif
+
+	/* Tokens for callbacks. */
+	void *data[];
+};
+
+#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
+
+static int vring_add_buf(struct virtqueue *_vq,
+			 struct scatterlist sg[],
+			 unsigned int out,
+			 unsigned int in,
+			 void *data)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	unsigned int i, avail, head, uninitialized_var(prev);
+
+	BUG_ON(data == NULL);
+	BUG_ON(out + in > vq->vring.num);
+	BUG_ON(out + in == 0);
+
+	START_USE(vq);
+
+	if (vq->num_free < out + in) {
+		pr_debug("Can't add buf len %i - avail = %i\n",
+			 out + in, vq->num_free);
+		END_USE(vq);
+		return -ENOSPC;
+	}
+
+	/* We're about to use some buffers from the free list. */
+	vq->num_free -= out + in;
+
+	head = vq->free_head;
+	for (i = vq->free_head; out; i = vq->vring.desc[i].next, out--) {
+		vq->vring.desc[i].flags = VRING_DESC_F_NEXT;
+		vq->vring.desc[i].addr = (page_to_pfn(sg_page(sg))<<PAGE_SHIFT)
+			+ sg->offset;
+		vq->vring.desc[i].len = sg->length;
+		prev = i;
+		sg++;
+	}
+	for (; in; i = vq->vring.desc[i].next, in--) {
+		vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+		vq->vring.desc[i].addr = (page_to_pfn(sg_page(sg))<<PAGE_SHIFT)
+			+ sg->offset;
+		vq->vring.desc[i].len = sg->length;
+		prev = i;
+		sg++;
+	}
+	/* Last one doesn't continue. */
+	vq->vring.desc[prev].flags &= ~VRING_DESC_F_NEXT;
+
+	/* Update free pointer */
+	vq->free_head = i;
+
+	/* Set token. */
+	vq->data[head] = data;
+
+	/* Put entry in available array (but don't update avail->idx until they
+	 * do sync).  FIXME: avoid modulus here? */
+	avail = (vq->vring.avail->idx + vq->num_added++) % vq->vring.num;
+	vq->vring.avail->ring[avail] = head;
+
+	pr_debug("Added buffer head %i to %p\n", head, vq);
+	END_USE(vq);
+	return 0;
+}
+
+static void vring_kick(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	START_USE(vq);
+	/* Descriptors and available array need to be set before we expose the
+	 * new available array entries. */
+	wmb();
+
+	vq->vring.avail->idx += vq->num_added;
+	vq->num_added = 0;
+
+	/* Need to update avail index before checking if we should notify */
+	mb();
+
+	if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
+		/* Prod other side to tell it about changes. */
+		vq->notify(&vq->vq);
+
+	END_USE(vq);
+}
+
+static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
+{
+	unsigned int i;
+
+	/* Clear data ptr. */
+	vq->data[head] = NULL;
+
+	/* Put back on free list: find end */
+	i = head;
+	while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
+		i = vq->vring.desc[i].next;
+		vq->num_free++;
+	}
+
+	vq->vring.desc[i].next = vq->free_head;
+	vq->free_head = head;
+	/* Plus final descriptor */
+	vq->num_free++;
+}
+
+/* FIXME: We need to tell other side about removal, to synchronize. */
+static void vring_shutdown(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	unsigned int i;
+
+	for (i = 0; i < vq->vring.num; i++)
+		detach_buf(vq, i);
+}
+
+static inline bool more_used(const struct vring_virtqueue *vq)
+{
+	return vq->last_used_idx != vq->vring.used->idx;
+}
+
+static void *vring_get_buf(struct virtqueue *_vq, unsigned int *len)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	void *ret;
+	unsigned int i;
+
+	START_USE(vq);
+
+	if (!more_used(vq)) {
+		pr_debug("No more buffers in queue\n");
+		END_USE(vq);
+		return NULL;
+	}
+
+	i = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].id;
+	*len = vq->vring.used->ring[vq->last_used_idx%vq->vring.num].len;
+
+	if (unlikely(i >= vq->vring.num)) {
+		BAD_RING(vq, "id %u out of range\n", i);
+		return NULL;
+	}
+	if (unlikely(!vq->data[i])) {
+		BAD_RING(vq, "id %u is not a head!\n", i);
+		return NULL;
+	}
+
+	/* detach_buf clears data, so grab it now. */
+	ret = vq->data[i];
+	detach_buf(vq, i);
+	vq->last_used_idx++;
+	END_USE(vq);
+	return ret;
+}
+
+static bool vring_restart(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	START_USE(vq);
+	BUG_ON(!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT));
+
+	/* We optimistically turn back on interrupts, then check if there was
+	 * more to do. */
+	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	mb();
+	if (unlikely(more_used(vq))) {
+		vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+
+irqreturn_t vring_interrupt(int irq, void *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (!more_used(vq)) {
+		pr_debug("virtqueue interrupt with no work for %p\n", vq);
+		return IRQ_NONE;
+	}
+
+	if (unlikely(vq->broken))
+		return IRQ_HANDLED;
+
+	pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback);
+	if (vq->vq.callback && !vq->vq.callback(&vq->vq))
+		vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+
+	return IRQ_HANDLED;
+}
+
+static struct virtqueue_ops vring_vq_ops = {
+	.add_buf = vring_add_buf,
+	.get_buf = vring_get_buf,
+	.kick = vring_kick,
+	.restart = vring_restart,
+	.shutdown = vring_shutdown,
+};
+
+struct virtqueue *vring_new_virtqueue(unsigned int num,
+				      struct virtio_device *vdev,
+				      void *pages,
+				      void (*notify)(struct virtqueue *),
+				      bool (*callback)(struct virtqueue *))
+{
+	struct vring_virtqueue *vq;
+	unsigned int i;
+
+	vq = kmalloc(sizeof(*vq) + sizeof(void *)*num, GFP_KERNEL);
+	if (!vq)
+		return NULL;
+
+	vring_init(&vq->vring, num, pages);
+	vq->vq.callback = callback;
+	vq->vq.vdev = vdev;
+	vq->vq.vq_ops = &vring_vq_ops;
+	vq->notify = notify;
+	vq->broken = false;
+	vq->last_used_idx = 0;
+	vq->num_added = 0;
+#ifdef DEBUG
+	vq->in_use = false;
+#endif
+
+	/* No callback?  Tell other side not to bother us. */
+	if (!callback)
+		vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+
+	/* Put everything in free lists. */
+	vq->num_free = num;
+	vq->free_head = 0;
+	for (i = 0; i < num-1; i++)
+		vq->vring.desc[i].next = i+1;
+
+	return &vq->vq;
+}
+
+void vring_del_virtqueue(struct virtqueue *vq)
+{
+	kfree(to_vvq(vq));
+}
+

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 */