Merge branch 'vhost-net-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

drivers/vhost/net.c

@@ -10,7 +10,6 @@
 #include <linux/eventfd.h>
 #include <linux/vhost.h>
 #include <linux/virtio_net.h>
-#include <linux/mmu_context.h>
 #include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -143,7 +142,6 @@ static void handle_tx(struct vhost_net *net)
 		return;
 	}
 
-	use_mm(net->dev.mm);
 	mutex_lock(&vq->mutex);
 	vhost_disable_notify(vq);
 
@@ -208,7 +206,6 @@ static void handle_tx(struct vhost_net *net)
 	}
 
 	mutex_unlock(&vq->mutex);
-	unuse_mm(net->dev.mm);
 }
 
 static int peek_head_len(struct sock *sk)
@@ -313,7 +310,6 @@ static void handle_rx_big(struct vhost_net *net)
 	if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
 		return;
 
-	use_mm(net->dev.mm);
 	mutex_lock(&vq->mutex);
 	vhost_disable_notify(vq);
 	hdr_size = vq->vhost_hlen;
@@ -392,7 +388,6 @@ static void handle_rx_big(struct vhost_net *net)
 	}
 
 	mutex_unlock(&vq->mutex);
-	unuse_mm(net->dev.mm);
 }
 
 /* Expects to be always run from workqueue - which acts as
@@ -424,7 +419,6 @@ static void handle_rx_mergeable(struct vhost_net *net)
 	if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
 		return;
 
-	use_mm(net->dev.mm);
 	mutex_lock(&vq->mutex);
 	vhost_disable_notify(vq);
 	vhost_hlen = vq->vhost_hlen;
@@ -459,7 +453,7 @@ static void handle_rx_mergeable(struct vhost_net *net)
 			move_iovec_hdr(vq->iov, vq->hdr, vhost_hlen, in);
 		else
 			/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
-			 * needed because sendmsg can modify msg_iov. */
+			 * needed because recvmsg can modify msg_iov. */
 			copy_iovec_hdr(vq->iov, vq->hdr, sock_hlen, in);
 		msg.msg_iovlen = in;
 		err = sock->ops->recvmsg(NULL, sock, &msg,
@@ -501,7 +495,6 @@ static void handle_rx_mergeable(struct vhost_net *net)
 	}
 
 	mutex_unlock(&vq->mutex);
-	unuse_mm(net->dev.mm);
 }
 
 static void handle_rx(struct vhost_net *net)

drivers/vhost/test.c

+/* Copyright (C) 2009 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * test virtio server in host kernel.
+ */
+
+#include <linux/compat.h>
+#include <linux/eventfd.h>
+#include <linux/vhost.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/rcupdate.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+
+#include "test.h"
+#include "vhost.c"
+
+/* Max number of bytes transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others. */
+#define VHOST_TEST_WEIGHT 0x80000
+
+enum {
+	VHOST_TEST_VQ = 0,
+	VHOST_TEST_VQ_MAX = 1,
+};
+
+struct vhost_test {
+	struct vhost_dev dev;
+	struct vhost_virtqueue vqs[VHOST_TEST_VQ_MAX];
+};
+
+/* Expects to be always run from workqueue - which acts as
+ * read-size critical section for our kind of RCU. */
+static void handle_vq(struct vhost_test *n)
+{
+	struct vhost_virtqueue *vq = &n->dev.vqs[VHOST_TEST_VQ];
+	unsigned out, in;
+	int head;
+	size_t len, total_len = 0;
+	void *private;
+
+	private = rcu_dereference_check(vq->private_data, 1);
+	if (!private)
+		return;
+
+	mutex_lock(&vq->mutex);
+	vhost_disable_notify(vq);
+
+	for (;;) {
+		head = vhost_get_vq_desc(&n->dev, vq, vq->iov,
+					 ARRAY_SIZE(vq->iov),
+					 &out, &in,
+					 NULL, NULL);
+		/* On error, stop handling until the next kick. */
+		if (unlikely(head < 0))
+			break;
+		/* Nothing new?  Wait for eventfd to tell us they refilled. */
+		if (head == vq->num) {
+			if (unlikely(vhost_enable_notify(vq))) {
+				vhost_disable_notify(vq);
+				continue;
+			}
+			break;
+		}
+		if (in) {
+			vq_err(vq, "Unexpected descriptor format for TX: "
+			       "out %d, int %d\n", out, in);
+			break;
+		}
+		len = iov_length(vq->iov, out);
+		/* Sanity check */
+		if (!len) {
+			vq_err(vq, "Unexpected 0 len for TX\n");
+			break;
+		}
+		vhost_add_used_and_signal(&n->dev, vq, head, 0);
+		total_len += len;
+		if (unlikely(total_len >= VHOST_TEST_WEIGHT)) {
+			vhost_poll_queue(&vq->poll);
+			break;
+		}
+	}
+
+	mutex_unlock(&vq->mutex);
+}
+
+static void handle_vq_kick(struct vhost_work *work)
+{
+	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
+						  poll.work);
+	struct vhost_test *n = container_of(vq->dev, struct vhost_test, dev);
+
+	handle_vq(n);
+}
+
+static int vhost_test_open(struct inode *inode, struct file *f)
+{
+	struct vhost_test *n = kmalloc(sizeof *n, GFP_KERNEL);
+	struct vhost_dev *dev;
+	int r;
+
+	if (!n)
+		return -ENOMEM;
+
+	dev = &n->dev;
+	n->vqs[VHOST_TEST_VQ].handle_kick = handle_vq_kick;
+	r = vhost_dev_init(dev, n->vqs, VHOST_TEST_VQ_MAX);
+	if (r < 0) {
+		kfree(n);
+		return r;
+	}
+
+	f->private_data = n;
+
+	return 0;
+}
+
+static void *vhost_test_stop_vq(struct vhost_test *n,
+				struct vhost_virtqueue *vq)
+{
+	void *private;
+
+	mutex_lock(&vq->mutex);
+	private = rcu_dereference_protected(vq->private_data,
+					 lockdep_is_held(&vq->mutex));
+	rcu_assign_pointer(vq->private_data, NULL);
+	mutex_unlock(&vq->mutex);
+	return private;
+}
+
+static void vhost_test_stop(struct vhost_test *n, void **privatep)
+{
+	*privatep = vhost_test_stop_vq(n, n->vqs + VHOST_TEST_VQ);
+}
+
+static void vhost_test_flush_vq(struct vhost_test *n, int index)
+{
+	vhost_poll_flush(&n->dev.vqs[index].poll);
+}
+
+static void vhost_test_flush(struct vhost_test *n)
+{
+	vhost_test_flush_vq(n, VHOST_TEST_VQ);
+}
+
+static int vhost_test_release(struct inode *inode, struct file *f)
+{
+	struct vhost_test *n = f->private_data;
+	void  *private;
+
+	vhost_test_stop(n, &private);
+	vhost_test_flush(n);
+	vhost_dev_cleanup(&n->dev);
+	/* We do an extra flush before freeing memory,
+	 * since jobs can re-queue themselves. */
+	vhost_test_flush(n);
+	kfree(n);
+	return 0;
+}
+
+static long vhost_test_run(struct vhost_test *n, int test)
+{
+	void *priv, *oldpriv;
+	struct vhost_virtqueue *vq;
+	int r, index;
+
+	if (test < 0 || test > 1)
+		return -EINVAL;
+
+	mutex_lock(&n->dev.mutex);
+	r = vhost_dev_check_owner(&n->dev);
+	if (r)
+		goto err;
+
+	for (index = 0; index < n->dev.nvqs; ++index) {
+		/* Verify that ring has been setup correctly. */
+		if (!vhost_vq_access_ok(&n->vqs[index])) {
+			r = -EFAULT;
+			goto err;
+		}
+	}
+
+	for (index = 0; index < n->dev.nvqs; ++index) {
+		vq = n->vqs + index;
+		mutex_lock(&vq->mutex);
+		priv = test ? n : NULL;
+
+		/* start polling new socket */
+		oldpriv = rcu_dereference_protected(vq->private_data,
+						    lockdep_is_held(&vq->mutex));
+		rcu_assign_pointer(vq->private_data, priv);
+
+		mutex_unlock(&vq->mutex);
+
+		if (oldpriv) {
+			vhost_test_flush_vq(n, index);
+		}
+	}
+
+	mutex_unlock(&n->dev.mutex);
+	return 0;
+
+err:
+	mutex_unlock(&n->dev.mutex);
+	return r;
+}
+
+static long vhost_test_reset_owner(struct vhost_test *n)
+{
+	void *priv = NULL;
+	long err;
+	mutex_lock(&n->dev.mutex);
+	err = vhost_dev_check_owner(&n->dev);
+	if (err)
+		goto done;
+	vhost_test_stop(n, &priv);
+	vhost_test_flush(n);
+	err = vhost_dev_reset_owner(&n->dev);
+done:
+	mutex_unlock(&n->dev.mutex);
+	return err;
+}
+
+static int vhost_test_set_features(struct vhost_test *n, u64 features)
+{
+	mutex_lock(&n->dev.mutex);
+	if ((features & (1 << VHOST_F_LOG_ALL)) &&
+	    !vhost_log_access_ok(&n->dev)) {
+		mutex_unlock(&n->dev.mutex);
+		return -EFAULT;
+	}
+	n->dev.acked_features = features;
+	smp_wmb();
+	vhost_test_flush(n);
+	mutex_unlock(&n->dev.mutex);
+	return 0;
+}
+
+static long vhost_test_ioctl(struct file *f, unsigned int ioctl,
+			     unsigned long arg)
+{
+	struct vhost_test *n = f->private_data;
+	void __user *argp = (void __user *)arg;
+	u64 __user *featurep = argp;
+	int test;
+	u64 features;
+	int r;
+	switch (ioctl) {
+	case VHOST_TEST_RUN:
+		if (copy_from_user(&test, argp, sizeof test))
+			return -EFAULT;
+		return vhost_test_run(n, test);
+	case VHOST_GET_FEATURES:
+		features = VHOST_FEATURES;
+		if (copy_to_user(featurep, &features, sizeof features))
+			return -EFAULT;
+		return 0;
+	case VHOST_SET_FEATURES:
+		if (copy_from_user(&features, featurep, sizeof features))
+			return -EFAULT;
+		if (features & ~VHOST_FEATURES)
+			return -EOPNOTSUPP;
+		return vhost_test_set_features(n, features);
+	case VHOST_RESET_OWNER:
+		return vhost_test_reset_owner(n);
+	default:
+		mutex_lock(&n->dev.mutex);
+		r = vhost_dev_ioctl(&n->dev, ioctl, arg);
+		vhost_test_flush(n);
+		mutex_unlock(&n->dev.mutex);
+		return r;
+	}
+}
+
+#ifdef CONFIG_COMPAT
+static long vhost_test_compat_ioctl(struct file *f, unsigned int ioctl,
+				   unsigned long arg)
+{
+	return vhost_test_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+static const struct file_operations vhost_test_fops = {
+	.owner          = THIS_MODULE,
+	.release        = vhost_test_release,
+	.unlocked_ioctl = vhost_test_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = vhost_test_compat_ioctl,
+#endif
+	.open           = vhost_test_open,
+	.llseek		= noop_llseek,
+};
+
+static struct miscdevice vhost_test_misc = {
+	MISC_DYNAMIC_MINOR,
+	"vhost-test",
+	&vhost_test_fops,
+};
+
+static int vhost_test_init(void)
+{
+	return misc_register(&vhost_test_misc);
+}
+module_init(vhost_test_init);
+
+static void vhost_test_exit(void)
+{
+	misc_deregister(&vhost_test_misc);
+}
+module_exit(vhost_test_exit);
+
+MODULE_VERSION("0.0.1");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Michael S. Tsirkin");
+MODULE_DESCRIPTION("Host kernel side for virtio simulator");

drivers/vhost/test.h

+#ifndef LINUX_VHOST_TEST_H
+#define LINUX_VHOST_TEST_H
+
+/* Start a given test on the virtio null device. 0 stops all tests. */
+#define VHOST_TEST_RUN _IOW(VHOST_VIRTIO, 0x31, int)
+
+#endif

drivers/vhost/vhost.c

@@ -15,6 +15,7 @@
 #include <linux/vhost.h>
 #include <linux/virtio_net.h>
 #include <linux/mm.h>
+#include <linux/mmu_context.h>
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
 #include <linux/rcupdate.h>
@@ -29,8 +30,6 @@
 #include <linux/if_packet.h>
 #include <linux/if_arp.h>
 
-#include <net/sock.h>
-
 #include "vhost.h"
 
 enum {
@@ -157,7 +156,6 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->avail_idx = 0;
 	vq->last_used_idx = 0;
 	vq->used_flags = 0;
-	vq->used_flags = 0;
 	vq->log_used = false;
 	vq->log_addr = -1ull;
 	vq->vhost_hlen = 0;
@@ -178,6 +176,8 @@ static int vhost_worker(void *data)
 	struct vhost_work *work = NULL;
 	unsigned uninitialized_var(seq);
 
+	use_mm(dev->mm);
+
 	for (;;) {
 		/* mb paired w/ kthread_stop */
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -192,7 +192,7 @@ static int vhost_worker(void *data)
 		if (kthread_should_stop()) {
 			spin_unlock_irq(&dev->work_lock);
 			__set_current_state(TASK_RUNNING);
-			return 0;
+			break;
 		}
 		if (!list_empty(&dev->work_list)) {
 			work = list_first_entry(&dev->work_list,
@@ -210,6 +210,8 @@ static int vhost_worker(void *data)
 			schedule();
 
 	}
+	unuse_mm(dev->mm);
+	return 0;
 }
 
 /* Helper to allocate iovec buffers for all vqs. */
@@ -402,15 +404,14 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 	kfree(rcu_dereference_protected(dev->memory,
 					lockdep_is_held(&dev->mutex)));
 	RCU_INIT_POINTER(dev->memory, NULL);
-	if (dev->mm)
-		mmput(dev->mm);
-	dev->mm = NULL;
-
 	WARN_ON(!list_empty(&dev->work_list));
 	if (dev->worker) {
 		kthread_stop(dev->worker);
 		dev->worker = NULL;
 	}
+	if (dev->mm)
+		mmput(dev->mm);
+	dev->mm = NULL;
 }
 
 static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
@@ -881,14 +882,15 @@ static int set_bit_to_user(int nr, void __user *addr)
 static int log_write(void __user *log_base,
 		     u64 write_address, u64 write_length)
 {
+	u64 write_page = write_address / VHOST_PAGE_SIZE;
 	int r;
 	if (!write_length)
 		return 0;
-	write_address /= VHOST_PAGE_SIZE;
+	write_length += write_address % VHOST_PAGE_SIZE;
 	for (;;) {
 		u64 base = (u64)(unsigned long)log_base;
-		u64 log = base + write_address / 8;
-		int bit = write_address % 8;
+		u64 log = base + write_page / 8;
+		int bit = write_page % 8;
 		if ((u64)(unsigned long)log != log)
 			return -EFAULT;
 		r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
@@ -897,7 +899,7 @@ static int log_write(void __user *log_base,
 		if (write_length <= VHOST_PAGE_SIZE)
 			break;
 		write_length -= VHOST_PAGE_SIZE;
-		write_address += VHOST_PAGE_SIZE;
+		write_page += 1;
 	}
 	return r;
 }
@@ -1092,7 +1094,7 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 
 	/* Check it isn't doing very strange things with descriptor numbers. */
 	last_avail_idx = vq->last_avail_idx;
-	if (unlikely(get_user(vq->avail_idx, &vq->avail->idx))) {
+	if (unlikely(__get_user(vq->avail_idx, &vq->avail->idx))) {
 		vq_err(vq, "Failed to access avail idx at %p\n",
 		       &vq->avail->idx);
 		return -EFAULT;
@@ -1113,8 +1115,8 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 
 	/* Grab the next descriptor number they're advertising, and increment
 	 * the index we've seen. */
-	if (unlikely(get_user(head,
-			      &vq->avail->ring[last_avail_idx % vq->num]))) {
+	if (unlikely(__get_user(head,
+				&vq->avail->ring[last_avail_idx % vq->num]))) {
 		vq_err(vq, "Failed to read head: idx %d address %p\n",
 		       last_avail_idx,
 		       &vq->avail->ring[last_avail_idx % vq->num]);
@@ -1213,17 +1215,17 @@ int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
 	/* The virtqueue contains a ring of used buffers.  Get a pointer to the
 	 * next entry in that used ring. */
 	used = &vq->used->ring[vq->last_used_idx % vq->num];
-	if (put_user(head, &used->id)) {
+	if (__put_user(head, &used->id)) {
 		vq_err(vq, "Failed to write used id");
 		return -EFAULT;
 	}
-	if (put_user(len, &used->len)) {
+	if (__put_user(len, &used->len)) {
 		vq_err(vq, "Failed to write used len");
 		return -EFAULT;
 	}
 	/* Make sure buffer is written before we update index. */
 	smp_wmb();
-	if (put_user(vq->last_used_idx + 1, &vq->used->idx)) {
+	if (__put_user(vq->last_used_idx + 1, &vq->used->idx)) {
 		vq_err(vq, "Failed to increment used idx");
 		return -EFAULT;
 	}
@@ -1255,7 +1257,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 
 	start = vq->last_used_idx % vq->num;
 	used = vq->used->ring + start;
-	if (copy_to_user(used, heads, count * sizeof *used)) {
+	if (__copy_to_user(used, heads, count * sizeof *used)) {
 		vq_err(vq, "Failed to write used");
 		return -EFAULT;
 	}
@@ -1316,7 +1318,7 @@ void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	 * interrupts. */
 	smp_mb();
 
-	if (get_user(flags, &vq->avail->flags)) {
+	if (__get_user(flags, &vq->avail->flags)) {
 		vq_err(vq, "Failed to get flags");
 		return;
 	}
@@ -1367,7 +1369,7 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 	/* They could have slipped one in as we were doing that: make
 	 * sure it's written, then check again. */
 	smp_mb();
-	r = get_user(avail_idx, &vq->avail->idx);
+	r = __get_user(avail_idx, &vq->avail->idx);
 	if (r) {
 		vq_err(vq, "Failed to check avail idx at %p: %d\n",
 		       &vq->avail->idx, r);

drivers/vhost/vhost.h

@@ -102,7 +102,7 @@ struct vhost_virtqueue {
 	 * flush the vhost_work instead of synchronize_rcu. Therefore readers do
 	 * not need to call rcu_read_lock/rcu_read_unlock: the beginning of
 	 * vhost_work execution acts instead of rcu_read_lock() and the end of
-	 * vhost_work execution acts instead of rcu_read_lock().
+	 * vhost_work execution acts instead of rcu_read_unlock().
 	 * Writers use virtqueue mutex. */
 	void __rcu *private_data;
 	/* Log write descriptors */

tools/virtio/Makefile

+all: test mod
+test: virtio_test
+virtio_test: virtio_ring.o virtio_test.o
+CFLAGS += -g -O2 -Wall -I. -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow  -MMD
+vpath %.c ../../drivers/virtio
+mod:
+	${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test
+.PHONY: all test mod clean
+clean:
+	${RM} *.o vhost_test/*.o vhost_test/.*.cmd \
+              vhost_test/Module.symvers vhost_test/modules.order *.d
+-include *.d

tools/virtio/linux/device.h

+#ifndef LINUX_DEVICE_H
+#endif

tools/virtio/linux/slab.h

+#ifndef LINUX_SLAB_H
+#endif

tools/virtio/linux/virtio.h

+#ifndef LINUX_VIRTIO_H
+#define LINUX_VIRTIO_H
+
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+
+#include <linux/types.h>
+#include <errno.h>
+
+typedef unsigned long long dma_addr_t;
+
+struct scatterlist {
+	unsigned long	page_link;
+	unsigned int	offset;
+	unsigned int	length;
+	dma_addr_t	dma_address;
+};
+
+struct page {
+	unsigned long long dummy;
+};
+
+#define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond))
+
+/* Physical == Virtual */
+#define virt_to_phys(p) ((unsigned long)p)
+#define phys_to_virt(a) ((void *)(unsigned long)(a))
+/* Page address: Virtual / 4K */
+#define virt_to_page(p) ((struct page*)((virt_to_phys(p) / 4096) * \
+					sizeof(struct page)))
+#define offset_in_page(p) (((unsigned long)p) % 4096)
+#define sg_phys(sg) ((sg->page_link & ~0x3) / sizeof(struct page) * 4096 + \
+		     sg->offset)
+static inline void sg_mark_end(struct scatterlist *sg)
+{
+	/*
+	 * Set termination bit, clear potential chain bit
+	 */
+	sg->page_link |= 0x02;
+	sg->page_link &= ~0x01;
+}
+static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents)
+{
+	memset(sgl, 0, sizeof(*sgl) * nents);
+	sg_mark_end(&sgl[nents - 1]);
+}
+static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
+{
+	unsigned long page_link = sg->page_link & 0x3;
+
+	/*
+	 * In order for the low bit stealing approach to work, pages
+	 * must be aligned at a 32-bit boundary as a minimum.
+	 */
+	BUG_ON((unsigned long) page & 0x03);
+	sg->page_link = page_link | (unsigned long) page;
+}
+
+static inline void sg_set_page(struct scatterlist *sg, struct page *page,
+			       unsigned int len, unsigned int offset)
+{
+	sg_assign_page(sg, page);
+	sg->offset = offset;
+	sg->length = len;
+}
+
+static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
+			      unsigned int buflen)
+{
+	sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
+}
+
+static inline void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen)
+{
+	sg_init_table(sg, 1);
+	sg_set_buf(sg, buf, buflen);
+}
+
+typedef __u16 u16;
+
+typedef enum {
+	GFP_KERNEL,
+	GFP_ATOMIC,
+} gfp_t;
+typedef enum {
+	IRQ_NONE,
+	IRQ_HANDLED
+} irqreturn_t;
+
+static inline void *kmalloc(size_t s, gfp_t gfp)
+{
+	return malloc(s);
+}
+
+static inline void kfree(void *p)
+{
+	free(p);
+}
+
+#define container_of(ptr, type, member) ({			\
+	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
+	(type *)( (char *)__mptr - offsetof(type,member) );})
+
+#define uninitialized_var(x) x = x
+
+# ifndef likely
+#  define likely(x)	(__builtin_expect(!!(x), 1))
+# endif
+# ifndef unlikely
+#  define unlikely(x)	(__builtin_expect(!!(x), 0))
+# endif
+
+#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#ifdef DEBUG
+#define pr_debug(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#else
+#define pr_debug(format, ...) do {} while (0)
+#endif
+#define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+
+/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
+#define list_add_tail(a, b) do {} while (0)
+#define list_del(a) do {} while (0)
+
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BITS_PER_BYTE		8
+#define BITS_PER_LONG (sizeof(long) * BITS_PER_BYTE)
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+/* TODO: Not atomic as it should be:
+ * we don't use this for anything important. */
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+        return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+/* The only feature we care to support */
+#define virtio_has_feature(dev, feature) \
+	test_bit((feature), (dev)->features)
+/* end of stubs */
+
+struct virtio_device {
+	void *dev;
+	unsigned long features[1];
+};
+
+struct virtqueue {
+	/* TODO: commented as list macros are empty stubs for now.
+	 * Broken but enough for virtio_ring.c
+	 * struct list_head list; */
+	void (*callback)(struct virtqueue *vq);
+	const char *name;
+	struct virtio_device *vdev;
+	void *priv;
+};
+
+#define EXPORT_SYMBOL_GPL(__EXPORT_SYMBOL_GPL_name) \
+	void __EXPORT_SYMBOL_GPL##__EXPORT_SYMBOL_GPL_name() { \
+}
+#define MODULE_LICENSE(__MODULE_LICENSE_value) \
+	const char *__MODULE_LICENSE_name = __MODULE_LICENSE_value
+
+#define CONFIG_SMP
+
+#if defined(__i386__) || defined(__x86_64__)
+#define barrier() asm volatile("" ::: "memory")
+#define mb() __sync_synchronize()
+
+#define smp_mb()	mb()
+# define smp_rmb()	barrier()
+# define smp_wmb()	barrier()
+#else
+#error Please fill in barrier macros
+#endif
+
+/* Interfaces exported by virtio_ring. */
+int virtqueue_add_buf_gfp(struct virtqueue *vq,
+			  struct scatterlist sg[],
+			  unsigned int out_num,
+			  unsigned int in_num,
+			  void *data,
+			  gfp_t gfp);
+
+static inline int virtqueue_add_buf(struct virtqueue *vq,
+				    struct scatterlist sg[],
+				    unsigned int out_num,
+				    unsigned int in_num,
+				    void *data)
+{
+	return virtqueue_add_buf_gfp(vq, sg, out_num, in_num, data, GFP_ATOMIC);
+}
+
+void virtqueue_kick(struct virtqueue *vq);
+
+void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len);
+
+void virtqueue_disable_cb(struct virtqueue *vq);
+
+bool virtqueue_enable_cb(struct virtqueue *vq);
+
+void *virtqueue_detach_unused_buf(struct virtqueue *vq);
+struct virtqueue *vring_new_virtqueue(unsigned int num,
+				      unsigned int vring_align,
+				      struct virtio_device *vdev,
+				      void *pages,
+				      void (*notify)(struct virtqueue *vq),
+				      void (*callback)(struct virtqueue *vq),
+				      const char *name);
+void vring_del_virtqueue(struct virtqueue *vq);
+
+#endif

tools/virtio/vhost_test/Makefile

+obj-m += vhost_test.o
+EXTRA_CFLAGS += -Idrivers/vhost

tools/virtio/vhost_test/vhost_test.c

+#include "test.c"

tools/virtio/virtio_test.c

+#define _GNU_SOURCE
+#include <getopt.h>
+#include <string.h>
+#include <poll.h>
+#include <sys/eventfd.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <fcntl.h>
+#include <linux/vhost.h>
+#include <linux/virtio.h>
+#include <linux/virtio_ring.h>
+#include "../../drivers/vhost/test.h"
+
+struct vq_info {
+	int kick;
+	int call;
+	int num;
+	int idx;
+	void *ring;
+	/* copy used for control */
+	struct vring vring;
+	struct virtqueue *vq;
+};
+
+struct vdev_info {
+	struct virtio_device vdev;
+	int control;
+	struct pollfd fds[1];
+	struct vq_info vqs[1];
+	int nvqs;
+	void *buf;
+	size_t buf_size;
+	struct vhost_memory *mem;
+};
+
+void vq_notify(struct virtqueue *vq)
+{
+	struct vq_info *info = vq->priv;
+	unsigned long long v = 1;
+	int r;
+	r = write(info->kick, &v, sizeof v);
+	assert(r == sizeof v);
+}
+
+void vq_callback(struct virtqueue *vq)
+{
+}
+
+
+void vhost_vq_setup(struct vdev_info *dev, struct vq_info *info)
+{
+	struct vhost_vring_state state = { .index = info->idx };
+	struct vhost_vring_file file = { .index = info->idx };
+	unsigned long long features = dev->vdev.features[0];
+	struct vhost_vring_addr addr = {
+		.index = info->idx,
+		.desc_user_addr = (uint64_t)(unsigned long)info->vring.desc,
+		.avail_user_addr = (uint64_t)(unsigned long)info->vring.avail,
+		.used_user_addr = (uint64_t)(unsigned long)info->vring.used,
+	};
+	int r;
+	r = ioctl(dev->control, VHOST_SET_FEATURES, &features);
+	assert(r >= 0);
+	state.num = info->vring.num;
+	r = ioctl(dev->control, VHOST_SET_VRING_NUM, &state);
+	assert(r >= 0);
+	state.num = 0;
+	r = ioctl(dev->control, VHOST_SET_VRING_BASE, &state);
+	assert(r >= 0);
+	r = ioctl(dev->control, VHOST_SET_VRING_ADDR, &addr);
+	assert(r >= 0);
+	file.fd = info->kick;
+	r = ioctl(dev->control, VHOST_SET_VRING_KICK, &file);
+	assert(r >= 0);
+	file.fd = info->call;
+	r = ioctl(dev->control, VHOST_SET_VRING_CALL, &file);
+	assert(r >= 0);
+}
+
+static void vq_info_add(struct vdev_info *dev, int num)
+{
+	struct vq_info *info = &dev->vqs[dev->nvqs];
+	int r;
+	info->idx = dev->nvqs;
+	info->kick = eventfd(0, EFD_NONBLOCK);
+	info->call = eventfd(0, EFD_NONBLOCK);
+	r = posix_memalign(&info->ring, 4096, vring_size(num, 4096));
+	assert(r >= 0);
+	memset(info->ring, 0, vring_size(num, 4096));
+	vring_init(&info->vring, num, info->ring, 4096);
+	info->vq = vring_new_virtqueue(info->vring.num, 4096, &dev->vdev, info->ring,
+				       vq_notify, vq_callback, "test");
+	assert(info->vq);
+	info->vq->priv = info;
+	vhost_vq_setup(dev, info);
+	dev->fds[info->idx].fd = info->call;
+	dev->fds[info->idx].events = POLLIN;
+	dev->nvqs++;
+}
+
+static void vdev_info_init(struct vdev_info* dev, unsigned long long features)
+{
+	int r;
+	memset(dev, 0, sizeof *dev);
+	dev->vdev.features[0] = features;
+	dev->vdev.features[1] = features >> 32;
+	dev->buf_size = 1024;
+	dev->buf = malloc(dev->buf_size);
+	assert(dev->buf);
+        dev->control = open("/dev/vhost-test", O_RDWR);
+	assert(dev->control >= 0);
+	r = ioctl(dev->control, VHOST_SET_OWNER, NULL);
+	assert(r >= 0);
+	dev->mem = malloc(offsetof(struct vhost_memory, regions) +
+			  sizeof dev->mem->regions[0]);
+	assert(dev->mem);
+	memset(dev->mem, 0, offsetof(struct vhost_memory, regions) +
+                          sizeof dev->mem->regions[0]);
+	dev->mem->nregions = 1;
+	dev->mem->regions[0].guest_phys_addr = (long)dev->buf;
+	dev->mem->regions[0].userspace_addr = (long)dev->buf;
+	dev->mem->regions[0].memory_size = dev->buf_size;
+	r = ioctl(dev->control, VHOST_SET_MEM_TABLE, dev->mem);
+	assert(r >= 0);
+}
+
+/* TODO: this is pretty bad: we get a cache line bounce
+ * for the wait queue on poll and another one on read,
+ * plus the read which is there just to clear the
+ * current state. */
+static void wait_for_interrupt(struct vdev_info *dev)
+{
+	int i;
+	unsigned long long val;
+	poll(dev->fds, dev->nvqs, -1);
+	for (i = 0; i < dev->nvqs; ++i)
+		if (dev->fds[i].revents & POLLIN) {
+			read(dev->fds[i].fd, &val, sizeof val);
+		}
+}
+
+static void run_test(struct vdev_info *dev, struct vq_info *vq, int bufs)
+{
+	struct scatterlist sl;
+	long started = 0, completed = 0;
+	long completed_before;
+	int r, test = 1;
+	unsigned len;
+	long long spurious = 0;
+	r = ioctl(dev->control, VHOST_TEST_RUN, &test);
+	assert(r >= 0);
+	for (;;) {
+		virtqueue_disable_cb(vq->vq);
+		completed_before = completed;
+		do {
+			if (started < bufs) {
+				sg_init_one(&sl, dev->buf, dev->buf_size);
+				r = virtqueue_add_buf(vq->vq, &sl, 1, 0,
+						      dev->buf + started);
+				if (likely(r >= 0)) {
+					++started;
+					virtqueue_kick(vq->vq);
+				}
+			} else
+				r = -1;
+
+			/* Flush out completed bufs if any */
+			if (virtqueue_get_buf(vq->vq, &len)) {
+				++completed;
+				r = 0;
+			}
+
+		} while (r >= 0);
+		if (completed == completed_before)
+			++spurious;
+		assert(completed <= bufs);
+		assert(started <= bufs);
+		if (completed == bufs)
+			break;
+		if (virtqueue_enable_cb(vq->vq)) {
+			wait_for_interrupt(dev);
+		}
+	}
+	test = 0;
+	r = ioctl(dev->control, VHOST_TEST_RUN, &test);
+	assert(r >= 0);
+	fprintf(stderr, "spurious wakeus: 0x%llx\n", spurious);
+}
+
+const char optstring[] = "h";
+const struct option longopts[] = {
+	{
+		.name = "help",
+		.val = 'h',
+	},
+	{
+		.name = "indirect",
+		.val = 'I',
+	},
+	{
+		.name = "no-indirect",
+		.val = 'i',
+	},
+	{
+	}
+};
+
+static void help()
+{
+	fprintf(stderr, "Usage: virtio_test [--help] [--no-indirect]\n");
+}
+
+int main(int argc, char **argv)
+{
+	struct vdev_info dev;
+	unsigned long long features = 1ULL << VIRTIO_RING_F_INDIRECT_DESC;
+	int o;
+
+	for (;;) {
+		o = getopt_long(argc, argv, optstring, longopts, NULL);
+		switch (o) {
+		case -1:
+			goto done;
+		case '?':
+			help();
+			exit(2);
+		case 'h':
+			help();
+			goto done;
+		case 'i':
+			features &= ~(1ULL << VIRTIO_RING_F_INDIRECT_DESC);
+			break;
+		default:
+			assert(0);
+			break;
+		}
+	}
+
+done:
+	vdev_info_init(&dev, features);
+	vq_info_add(&dev, 256);
+	run_test(&dev, &dev.vqs[0], 0x100000);
+	return 0;
+}