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

5 files changed, 352 insertions, 30 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f442668a1e52..9b3ca103135f 100644
--- a/drivers/vhost/net.c
+++ b/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)
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
new file mode 100644
index 000000000000..099f30230d06
--- /dev/null
+++ b/drivers/vhost/test.c
@@ -0,0 +1,320 @@
+/* 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");
diff --git a/drivers/vhost/test.h b/drivers/vhost/test.h
new file mode 100644
index 000000000000..1fef5df82153
--- /dev/null
+++ b/drivers/vhost/test.h
@@ -0,0 +1,7 @@
+#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
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 94701ff3a23a..38244f59cdd9 100644
--- a/drivers/vhost/vhost.c
+++ b/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);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 073d06ae091f..2af44b7b1f3f 100644
--- a/drivers/vhost/vhost.h
+++ b/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 */