Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio/vhost updates from Michael Tsirkin:
 "New features, performance improvements, cleanups:

   - basic polling support for vhost
   - rework virtio to optionally use DMA API, fixing it on Xen
   - balloon stats gained a new entry
   - using the new napi_alloc_skb speeds up virtio net
   - virtio blk stats can now be read while another VCPU is busy
     inflating or deflating the balloon

  plus misc cleanups in various places"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_net: replace netdev_alloc_skb_ip_align() with napi_alloc_skb()
  vhost_net: basic polling support
  vhost: introduce vhost_vq_avail_empty()
  vhost: introduce vhost_has_work()
  virtio_balloon: Allow to resize and update the balloon stats in parallel
  virtio_balloon: Use a workqueue instead of "vballoon" kthread
  virtio/s390: size of SET_IND payload
  virtio/s390: use dev_to_virtio
  vhost: rename vhost_init_used()
  vhost: rename cross-endian helpers
  virtio_blk: VIRTIO_BLK_F_WCE->VIRTIO_BLK_F_FLUSH
  vring: Use the DMA API on Xen
  virtio_pci: Use the DMA API if enabled
  virtio_mmio: Use the DMA API if enabled
  virtio: Add improved queue allocation API
  virtio_ring: Support DMA APIs
  vring: Introduce vring_use_dma_api()
  s390/dma: Allow per device dma ops
  alpha/dma: use common noop dma ops
  dma: Provide simple noop dma ops

arch/alpha/kernel/pci-noop.c

@@ -123,44 +123,6 @@ static void *alpha_noop_alloc_coherent(struct device *dev, size_t size,
 	return ret;
 }
 
-static void alpha_noop_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_addr,
-				     struct dma_attrs *attrs)
-{
-	free_pages((unsigned long)cpu_addr, get_order(size));
-}
-
-static dma_addr_t alpha_noop_map_page(struct device *dev, struct page *page,
-				      unsigned long offset, size_t size,
-				      enum dma_data_direction dir,
-				      struct dma_attrs *attrs)
-{
-	return page_to_pa(page) + offset;
-}
-
-static int alpha_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
-			     enum dma_data_direction dir, struct dma_attrs *attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sgl, sg, nents, i) {
-		void *va;
-
-		BUG_ON(!sg_page(sg));
-		va = sg_virt(sg);
-		sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va);
-		sg_dma_len(sg) = sg->length;
-	}
-
-	return nents;
-}
-
-static int alpha_noop_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
 static int alpha_noop_supported(struct device *dev, u64 mask)
 {
 	return mask < 0x00ffffffUL ? 0 : 1;
@@ -168,10 +130,10 @@ static int alpha_noop_supported(struct device *dev, u64 mask)
 
 struct dma_map_ops alpha_noop_ops = {
 	.alloc			= alpha_noop_alloc_coherent,
-	.free			= alpha_noop_free_coherent,
-	.map_page		= alpha_noop_map_page,
-	.map_sg			= alpha_noop_map_sg,
-	.mapping_error		= alpha_noop_mapping_error,
+	.free			= dma_noop_free_coherent,
+	.map_page		= dma_noop_map_page,
+	.map_sg			= dma_noop_map_sg,
+	.mapping_error		= dma_noop_mapping_error,
 	.dma_supported		= alpha_noop_supported,
 };
 

arch/s390/Kconfig

@@ -124,6 +124,7 @@ config S390
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DMA_API_DEBUG
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_FTRACE_MCOUNT_RECORD
@@ -617,10 +618,6 @@ config HAS_IOMEM
 config IOMMU_HELPER
 	def_bool PCI
 
-config HAS_DMA
-	def_bool PCI
-	select HAVE_DMA_API_DEBUG
-
 config NEED_SG_DMA_LENGTH
 	def_bool PCI
 

arch/s390/include/asm/device.h

@@ -3,5 +3,9 @@
  *
  * This file is released under the GPLv2
  */
-#include <asm-generic/device.h>
+struct dev_archdata {
+	struct dma_map_ops *dma_ops;
+};
 
+struct pdev_archdata {
+};

arch/s390/include/asm/dma-mapping.h

@@ -11,11 +11,13 @@
 
 #define DMA_ERROR_CODE		(~(dma_addr_t) 0x0)
 
-extern struct dma_map_ops s390_dma_ops;
+extern struct dma_map_ops s390_pci_dma_ops;
 
 static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	return &s390_dma_ops;
+	if (dev && dev->archdata.dma_ops)
+		return dev->archdata.dma_ops;
+	return &dma_noop_ops;
 }
 
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,

arch/s390/pci/pci.c

@@ -641,6 +641,7 @@ int pcibios_add_device(struct pci_dev *pdev)
 	int i;
 
 	pdev->dev.groups = zpci_attr_groups;
+	pdev->dev.archdata.dma_ops = &s390_pci_dma_ops;
 	zpci_map_resources(pdev);
 
 	for (i = 0; i < PCI_BAR_COUNT; i++) {

arch/s390/pci/pci_dma.c

@@ -547,7 +547,7 @@ static int __init dma_debug_do_init(void)
 }
 fs_initcall(dma_debug_do_init);
 
-struct dma_map_ops s390_dma_ops = {
+struct dma_map_ops s390_pci_dma_ops = {
 	.alloc		= s390_dma_alloc,
 	.free		= s390_dma_free,
 	.map_sg		= s390_dma_map_sg,
@@ -558,7 +558,7 @@ struct dma_map_ops s390_dma_ops = {
 	.is_phys	= 0,
 	/* dma_supported is unconditionally true without a callback */
 };
-EXPORT_SYMBOL_GPL(s390_dma_ops);
+EXPORT_SYMBOL_GPL(s390_pci_dma_ops);
 
 static int __init s390_iommu_setup(char *str)
 {

drivers/block/virtio_blk.c

@@ -477,8 +477,13 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev)
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE,
 				   struct virtio_blk_config, wce,
 				   &writeback);
+
+	/*
+	 * If WCE is not configurable and flush is not available,
+	 * assume no writeback cache is in use.
+	 */
 	if (err)
-		writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE);
+		writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH);
 
 	return writeback;
 }
@@ -833,14 +838,14 @@ static const struct virtio_device_id id_table[] = {
 static unsigned int features_legacy[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
 	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
-	VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
+	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
 	VIRTIO_BLK_F_MQ,
 }
 ;
 static unsigned int features[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
 	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
-	VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
+	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
 	VIRTIO_BLK_F_MQ,
 };
 

drivers/net/virtio_net.c

@@ -260,7 +260,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	p = page_address(page) + offset;
 
 	/* copy small packet so we can reuse these pages for small data */
-	skb = netdev_alloc_skb_ip_align(vi->dev, GOOD_COPY_LEN);
+	skb = napi_alloc_skb(&rq->napi, GOOD_COPY_LEN);
 	if (unlikely(!skb))
 		return NULL;
 

drivers/s390/virtio/virtio_ccw.c

@@ -342,13 +342,14 @@ static void virtio_ccw_drop_indicator(struct virtio_ccw_device *vcdev,
 		ccw->count = sizeof(*thinint_area);
 		ccw->cda = (__u32)(unsigned long) thinint_area;
 	} else {
+		/* payload is the address of the indicators */
 		indicatorp = kmalloc(sizeof(&vcdev->indicators),
 				     GFP_DMA | GFP_KERNEL);
 		if (!indicatorp)
 			return;
 		*indicatorp = 0;
 		ccw->cmd_code = CCW_CMD_SET_IND;
-		ccw->count = sizeof(vcdev->indicators);
+		ccw->count = sizeof(&vcdev->indicators);
 		ccw->cda = (__u32)(unsigned long) indicatorp;
 	}
 	/* Deregister indicators from host. */
@@ -656,7 +657,10 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		}
 	}
 	ret = -ENOMEM;
-	/* We need a data area under 2G to communicate. */
+	/*
+	 * We need a data area under 2G to communicate. Our payload is
+	 * the address of the indicators.
+	*/
 	indicatorp = kmalloc(sizeof(&vcdev->indicators), GFP_DMA | GFP_KERNEL);
 	if (!indicatorp)
 		goto out;
@@ -672,7 +676,7 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		vcdev->indicators = 0;
 		ccw->cmd_code = CCW_CMD_SET_IND;
 		ccw->flags = 0;
-		ccw->count = sizeof(vcdev->indicators);
+		ccw->count = sizeof(&vcdev->indicators);
 		ccw->cda = (__u32)(unsigned long) indicatorp;
 		ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND);
 		if (ret)
@@ -683,7 +687,7 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	vcdev->indicators2 = 0;
 	ccw->cmd_code = CCW_CMD_SET_CONF_IND;
 	ccw->flags = 0;
-	ccw->count = sizeof(vcdev->indicators2);
+	ccw->count = sizeof(&vcdev->indicators2);
 	ccw->cda = (__u32)(unsigned long) indicatorp;
 	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_CONF_IND);
 	if (ret)
@@ -945,8 +949,7 @@ static struct virtio_config_ops virtio_ccw_config_ops = {
 
 static void virtio_ccw_release_dev(struct device *_d)
 {
-	struct virtio_device *dev = container_of(_d, struct virtio_device,
-						 dev);
+	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_ccw_device *vcdev = to_vc_device(dev);
 
 	kfree(vcdev->status);

drivers/vhost/net.c

@@ -287,6 +287,43 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
 	rcu_read_unlock_bh();
 }
 
+static inline unsigned long busy_clock(void)
+{
+	return local_clock() >> 10;
+}
+
+static bool vhost_can_busy_poll(struct vhost_dev *dev,
+				unsigned long endtime)
+{
+	return likely(!need_resched()) &&
+	       likely(!time_after(busy_clock(), endtime)) &&
+	       likely(!signal_pending(current)) &&
+	       !vhost_has_work(dev);
+}
+
+static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
+				    struct vhost_virtqueue *vq,
+				    struct iovec iov[], unsigned int iov_size,
+				    unsigned int *out_num, unsigned int *in_num)
+{
+	unsigned long uninitialized_var(endtime);
+	int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
+				    out_num, in_num, NULL, NULL);
+
+	if (r == vq->num && vq->busyloop_timeout) {
+		preempt_disable();
+		endtime = busy_clock() + vq->busyloop_timeout;
+		while (vhost_can_busy_poll(vq->dev, endtime) &&
+		       vhost_vq_avail_empty(vq->dev, vq))
+			cpu_relax_lowlatency();
+		preempt_enable();
+		r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
+					out_num, in_num, NULL, NULL);
+	}
+
+	return r;
+}
+
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
@@ -331,10 +368,9 @@ static void handle_tx(struct vhost_net *net)
 			      % UIO_MAXIOV == nvq->done_idx))
 			break;
 
-		head = vhost_get_vq_desc(vq, vq->iov,
-					 ARRAY_SIZE(vq->iov),
-					 &out, &in,
-					 NULL, NULL);
+		head = vhost_net_tx_get_vq_desc(net, vq, vq->iov,
+						ARRAY_SIZE(vq->iov),
+						&out, &in);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(head < 0))
 			break;
@@ -435,6 +471,38 @@ static int peek_head_len(struct sock *sk)
 	return len;
 }
 
+static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
+{
+	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *vq = &nvq->vq;
+	unsigned long uninitialized_var(endtime);
+	int len = peek_head_len(sk);
+
+	if (!len && vq->busyloop_timeout) {
+		/* Both tx vq and rx socket were polled here */
+		mutex_lock(&vq->mutex);
+		vhost_disable_notify(&net->dev, vq);
+
+		preempt_disable();
+		endtime = busy_clock() + vq->busyloop_timeout;
+
+		while (vhost_can_busy_poll(&net->dev, endtime) &&
+		       skb_queue_empty(&sk->sk_receive_queue) &&
+		       vhost_vq_avail_empty(&net->dev, vq))
+			cpu_relax_lowlatency();
+
+		preempt_enable();
+
+		if (vhost_enable_notify(&net->dev, vq))
+			vhost_poll_queue(&vq->poll);
+		mutex_unlock(&vq->mutex);
+
+		len = peek_head_len(sk);
+	}
+
+	return len;
+}
+
 /* This is a multi-buffer version of vhost_get_desc, that works if
  *	vq has read descriptors only.
  * @vq		- the relevant virtqueue
@@ -553,7 +621,7 @@ static void handle_rx(struct vhost_net *net)
 		vq->log : NULL;
 	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
 
-	while ((sock_len = peek_head_len(sock->sk))) {
+	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
 		headcount = get_rx_bufs(vq, vq->heads, vhost_len,
@@ -917,7 +985,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 
 		vhost_net_disable_vq(n, vq);
 		vq->private_data = sock;
-		r = vhost_init_used(vq);
+		r = vhost_vq_init_access(vq);
 		if (r)
 			goto err_used;
 		r = vhost_net_enable_vq(n, vq);

drivers/vhost/scsi.c

@@ -1274,7 +1274,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 			vq = &vs->vqs[i].vq;
 			mutex_lock(&vq->mutex);
 			vq->private_data = vs_tpg;
-			vhost_init_used(vq);
+			vhost_vq_init_access(vq);
 			mutex_unlock(&vq->mutex);
 		}
 		ret = 0;

drivers/vhost/test.c

@@ -196,7 +196,7 @@ static long vhost_test_run(struct vhost_test *n, int test)
 		oldpriv = vq->private_data;
 		vq->private_data = priv;
 
-		r = vhost_init_used(&n->vqs[index]);
+		r = vhost_vq_init_access(&n->vqs[index]);
 
 		mutex_unlock(&vq->mutex);
 

drivers/vhost/vhost.c

@@ -43,11 +43,21 @@ enum {
 #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])
 
 #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
-static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq)
+static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
 {
 	vq->user_be = !virtio_legacy_is_little_endian();
 }
 
+static void vhost_enable_cross_endian_big(struct vhost_virtqueue *vq)
+{
+	vq->user_be = true;
+}
+
+static void vhost_enable_cross_endian_little(struct vhost_virtqueue *vq)
+{
+	vq->user_be = false;
+}
+
 static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
 {
 	struct vhost_vring_state s;
@@ -62,7 +72,10 @@ static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
 	    s.num != VHOST_VRING_BIG_ENDIAN)
 		return -EINVAL;
 
-	vq->user_be = s.num;
+	if (s.num == VHOST_VRING_BIG_ENDIAN)
+		vhost_enable_cross_endian_big(vq);
+	else
+		vhost_enable_cross_endian_little(vq);
 
 	return 0;
 }
@@ -91,7 +104,7 @@ static void vhost_init_is_le(struct vhost_virtqueue *vq)
 	vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || !vq->user_be;
 }
 #else
-static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq)
+static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
 {
 }
 
@@ -113,6 +126,11 @@ static void vhost_init_is_le(struct vhost_virtqueue *vq)
 }
 #endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */
 
+static void vhost_reset_is_le(struct vhost_virtqueue *vq)
+{
+	vq->is_le = virtio_legacy_is_little_endian();
+}
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
@@ -245,6 +263,13 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work)
 }
 EXPORT_SYMBOL_GPL(vhost_work_queue);
 
+/* A lockless hint for busy polling code to exit the loop */
+bool vhost_has_work(struct vhost_dev *dev)
+{
+	return !list_empty(&dev->work_list);
+}
+EXPORT_SYMBOL_GPL(vhost_has_work);
+
 void vhost_poll_queue(struct vhost_poll *poll)
 {
 	vhost_work_queue(poll->dev, &poll->work);
@@ -276,8 +301,9 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->call = NULL;
 	vq->log_ctx = NULL;
 	vq->memory = NULL;
-	vq->is_le = virtio_legacy_is_little_endian();
-	vhost_vq_reset_user_be(vq);
+	vhost_reset_is_le(vq);
+	vhost_disable_cross_endian(vq);
+	vq->busyloop_timeout = 0;
 }
 
 static int vhost_worker(void *data)
@@ -912,6 +938,19 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp)
 	case VHOST_GET_VRING_ENDIAN:
 		r = vhost_get_vring_endian(vq, idx, argp);
 		break;
+	case VHOST_SET_VRING_BUSYLOOP_TIMEOUT:
+		if (copy_from_user(&s, argp, sizeof(s))) {
+			r = -EFAULT;
+			break;
+		}
+		vq->busyloop_timeout = s.num;
+		break;
+	case VHOST_GET_VRING_BUSYLOOP_TIMEOUT:
+		s.index = idx;
+		s.num = vq->busyloop_timeout;
+		if (copy_to_user(argp, &s, sizeof(s)))
+			r = -EFAULT;
+		break;
 	default:
 		r = -ENOIOCTLCMD;
 	}
@@ -1152,14 +1191,14 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
 	return 0;
 }
 
-int vhost_init_used(struct vhost_virtqueue *vq)
+int vhost_vq_init_access(struct vhost_virtqueue *vq)
 {
 	__virtio16 last_used_idx;
 	int r;
 	bool is_le = vq->is_le;
 
 	if (!vq->private_data) {
-		vq->is_le = virtio_legacy_is_little_endian();
+		vhost_reset_is_le(vq);
 		return 0;
 	}
 
@@ -1182,7 +1221,7 @@ int vhost_init_used(struct vhost_virtqueue *vq)
 	vq->is_le = is_le;
 	return r;
 }
-EXPORT_SYMBOL_GPL(vhost_init_used);
+EXPORT_SYMBOL_GPL(vhost_vq_init_access);
 
 static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
 			  struct iovec iov[], int iov_size)
@@ -1633,6 +1672,20 @@ void vhost_add_used_and_signal_n(struct vhost_dev *dev,
 }
 EXPORT_SYMBOL_GPL(vhost_add_used_and_signal_n);
 
+/* return true if we're sure that avaiable ring is empty */
+bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
+	__virtio16 avail_idx;
+	int r;
+
+	r = __get_user(avail_idx, &vq->avail->idx);
+	if (r)
+		return false;
+
+	return vhost16_to_cpu(vq, avail_idx) == vq->avail_idx;
+}
+EXPORT_SYMBOL_GPL(vhost_vq_avail_empty);
+
 /* OK, now we need to know about added descriptors. */
 bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {

drivers/vhost/vhost.h

@@ -37,6 +37,7 @@ struct vhost_poll {
 
 void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
 void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work);
+bool vhost_has_work(struct vhost_dev *dev);
 
 void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
 		     unsigned long mask, struct vhost_dev *dev);
@@ -114,6 +115,7 @@ struct vhost_virtqueue {
 	/* Ring endianness requested by userspace for cross-endian support. */
 	bool user_be;
 #endif
+	u32 busyloop_timeout;
 };
 
 struct vhost_dev {
@@ -148,7 +150,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *,
 		      struct vhost_log *log, unsigned int *log_num);
 void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);
 
-int vhost_init_used(struct vhost_virtqueue *);
+int vhost_vq_init_access(struct vhost_virtqueue *);
 int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
 int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads,
 		     unsigned count);
@@ -158,6 +160,7 @@ void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
 			       struct vring_used_elem *heads, unsigned count);
 void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
 void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
+bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *);
 bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,

drivers/virtio/Kconfig

@@ -60,7 +60,7 @@ config VIRTIO_INPUT
 
  config VIRTIO_MMIO
 	tristate "Platform bus driver for memory mapped virtio devices"
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && HAS_DMA
  	select VIRTIO
  	---help---
  	 This drivers provides support for memory mapped virtio

drivers/virtio/virtio_balloon.c

@@ -22,8 +22,7 @@
 #include <linux/virtio.h>
 #include <linux/virtio_balloon.h>
 #include <linux/swap.h>
-#include <linux/kthread.h>
-#include <linux/freezer.h>
+#include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -50,11 +49,13 @@ struct virtio_balloon {
 	struct virtio_device *vdev;
 	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
 
-	/* Where the ballooning thread waits for config to change. */
-	wait_queue_head_t config_change;
+	/* The balloon servicing is delegated to a freezable workqueue. */
+	struct work_struct update_balloon_stats_work;
+	struct work_struct update_balloon_size_work;
 
-	/* The thread servicing the balloon. */
-	struct task_struct *thread;
+	/* Prevent updating balloon when it is being canceled. */
+	spinlock_t stop_update_lock;
+	bool stop_update;
 
 	/* Waiting for host to ack the pages we released. */
 	wait_queue_head_t acked;
@@ -77,7 +78,6 @@ struct virtio_balloon {
 	u32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
 
 	/* Memory statistics */
-	int need_stats_update;
 	struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
 
 	/* To register callback in oom notifier call chain */
@@ -124,6 +124,7 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
 
 	/* When host has read buffer, this completes via balloon_ack */
 	wait_event(vb->acked, virtqueue_get_buf(vq, &len));
+
 }
 
 static void set_page_pfns(u32 pfns[], struct page *page)
@@ -136,9 +137,10 @@ static void set_page_pfns(u32 pfns[], struct page *page)
 		pfns[i] = page_to_balloon_pfn(page) + i;
 }
 
-static void fill_balloon(struct virtio_balloon *vb, size_t num)
+static unsigned fill_balloon(struct virtio_balloon *vb, size_t num)
 {
 	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
+	unsigned num_allocated_pages;
 
 	/* We can only do one array worth at a time. */
 	num = min(num, ARRAY_SIZE(vb->pfns));
@@ -163,10 +165,13 @@ static void fill_balloon(struct virtio_balloon *vb, size_t num)
 			adjust_managed_page_count(page, -1);
 	}
 
+	num_allocated_pages = vb->num_pfns;
 	/* Did we get any? */
 	if (vb->num_pfns != 0)
 		tell_host(vb, vb->inflate_vq);
 	mutex_unlock(&vb->balloon_lock);
+
+	return num_allocated_pages;
 }
 
 static void release_pages_balloon(struct virtio_balloon *vb)
@@ -257,14 +262,17 @@ static void update_balloon_stats(struct virtio_balloon *vb)
  * with a single buffer.  From that point forward, all conversations consist of
  * a hypervisor request (a call to this function) which directs us to refill
  * the virtqueue with a fresh stats buffer.  Since stats collection can sleep,
- * we notify our kthread which does the actual work via stats_handle_request().
+ * we delegate the job to a freezable workqueue that will do the actual work via
+ * stats_handle_request().
  */
 static void stats_request(struct virtqueue *vq)
 {
 	struct virtio_balloon *vb = vq->vdev->priv;
 
-	vb->need_stats_update = 1;
-	wake_up(&vb->config_change);
+	spin_lock(&vb->stop_update_lock);
+	if (!vb->stop_update)
+		queue_work(system_freezable_wq, &vb->update_balloon_stats_work);
+	spin_unlock(&vb->stop_update_lock);
 }
 
 static void stats_handle_request(struct virtio_balloon *vb)
@@ -273,7 +281,6 @@ static void stats_handle_request(struct virtio_balloon *vb)
 	struct scatterlist sg;
 	unsigned int len;
 
-	vb->need_stats_update = 0;
 	update_balloon_stats(vb);
 
 	vq = vb->stats_vq;
@@ -287,8 +294,12 @@ static void stats_handle_request(struct virtio_balloon *vb)
 static void virtballoon_changed(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
+	unsigned long flags;
 
-	wake_up(&vb->config_change);
+	spin_lock_irqsave(&vb->stop_update_lock, flags);
+	if (!vb->stop_update)
+		queue_work(system_freezable_wq, &vb->update_balloon_size_work);
+	spin_unlock_irqrestore(&vb->stop_update_lock, flags);
 }
 
 static inline s64 towards_target(struct virtio_balloon *vb)
@@ -351,43 +362,32 @@ static int virtballoon_oom_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static int balloon(void *_vballoon)
+static void update_balloon_stats_func(struct work_struct *work)
 {
-	struct virtio_balloon *vb = _vballoon;
-	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-
-	set_freezable();
-	while (!kthread_should_stop()) {
-		s64 diff;
-
-		try_to_freeze();
-
-		add_wait_queue(&vb->config_change, &wait);
-		for (;;) {
-			if ((diff = towards_target(vb)) != 0 ||
-			    vb->need_stats_update ||
-			    kthread_should_stop() ||
-			    freezing(current))
-				break;
-			wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-		}
-		remove_wait_queue(&vb->config_change, &wait);
+	struct virtio_balloon *vb;
 
-		if (vb->need_stats_update)
-			stats_handle_request(vb);
-		if (diff > 0)
-			fill_balloon(vb, diff);
-		else if (diff < 0)
-			leak_balloon(vb, -diff);
-		update_balloon_size(vb);
+	vb = container_of(work, struct virtio_balloon,
+			  update_balloon_stats_work);
+	stats_handle_request(vb);
+}
 
-		/*
-		 * For large balloon changes, we could spend a lot of time
-		 * and always have work to do.  Be nice if preempt disabled.
-		 */
-		cond_resched();
-	}
-	return 0;
+static void update_balloon_size_func(struct work_struct *work)
+{
+	struct virtio_balloon *vb;
+	s64 diff;
+
+	vb = container_of(work, struct virtio_balloon,
+			  update_balloon_size_work);
+	diff = towards_target(vb);
+
+	if (diff > 0)
+		diff -= fill_balloon(vb, diff);
+	else if (diff < 0)
+		diff += leak_balloon(vb, -diff);
+	update_balloon_size(vb);
+
+	if (diff)
+		queue_work(system_freezable_wq, work);
 }
 
 static int init_vqs(struct virtio_balloon *vb)
@@ -505,12 +505,14 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		goto out;
 	}
 
+	INIT_WORK(&vb->update_balloon_stats_work, update_balloon_stats_func);
+	INIT_WORK(&vb->update_balloon_size_work, update_balloon_size_func);
+	spin_lock_init(&vb->stop_update_lock);
+	vb->stop_update = false;
 	vb->num_pages = 0;
 	mutex_init(&vb->balloon_lock);
-	init_waitqueue_head(&vb->config_change);
 	init_waitqueue_head(&vb->acked);
 	vb->vdev = vdev;
-	vb->need_stats_update = 0;
 
 	balloon_devinfo_init(&vb->vb_dev_info);
 #ifdef CONFIG_BALLOON_COMPACTION
@@ -529,16 +531,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	vb->thread = kthread_run(balloon, vb, "vballoon");
-	if (IS_ERR(vb->thread)) {
-		err = PTR_ERR(vb->thread);
-		goto out_del_vqs;
-	}
-
 	return 0;
 
-out_del_vqs:
-	unregister_oom_notifier(&vb->nb);
 out_oom_notify:
 	vdev->config->del_vqs(vdev);
 out_free_vb:
@@ -565,7 +559,13 @@ static void virtballoon_remove(struct virtio_device *vdev)
 	struct virtio_balloon *vb = vdev->priv;
 
 	unregister_oom_notifier(&vb->nb);
-	kthread_stop(vb->thread);
+
+	spin_lock_irq(&vb->stop_update_lock);
+	vb->stop_update = true;
+	spin_unlock_irq(&vb->stop_update_lock);
+	cancel_work_sync(&vb->update_balloon_size_work);
+	cancel_work_sync(&vb->update_balloon_stats_work);
+
 	remove_common(vb);
 	kfree(vb);
 }
@@ -576,10 +576,9 @@ static int virtballoon_freeze(struct virtio_device *vdev)
 	struct virtio_balloon *vb = vdev->priv;
 
 	/*
-	 * The kthread is already frozen by the PM core before this
+	 * The workqueue is already frozen by the PM core before this
 	 * function is called.
 	 */
-
 	remove_common(vb);
 	return 0;
 }
@@ -595,7 +594,8 @@ static int virtballoon_restore(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	fill_balloon(vb, towards_target(vb));
+	if (towards_target(vb))
+		virtballoon_changed(vdev);
 	update_balloon_size(vb);
 	return 0;
 }

drivers/virtio/virtio_mmio.c

@@ -99,12 +99,6 @@ struct virtio_mmio_vq_info {
 	/* the actual virtqueue */
 	struct virtqueue *vq;
 
-	/* the number of entries in the queue */
-	unsigned int num;
-
-	/* the virtual address of the ring queue */
-	void *queue;
-
 	/* the list node for the virtqueues list */
 	struct list_head node;
 };
@@ -322,15 +316,13 @@ static void vm_del_vq(struct virtqueue *vq)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
 	struct virtio_mmio_vq_info *info = vq->priv;
-	unsigned long flags, size;
+	unsigned long flags;
 	unsigned int index = vq->index;
 
 	spin_lock_irqsave(&vm_dev->lock, flags);
 	list_del(&info->node);
 	spin_unlock_irqrestore(&vm_dev->lock, flags);
 
-	vring_del_virtqueue(vq);
-
 	/* Select and deactivate the queue */
 	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
 	if (vm_dev->version == 1) {
@@ -340,8 +332,8 @@ static void vm_del_vq(struct virtqueue *vq)
 		WARN_ON(readl(vm_dev->base + VIRTIO_MMIO_QUEUE_READY));
 	}
 
-	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_MMIO_VRING_ALIGN));
-	free_pages_exact(info->queue, size);
+	vring_del_virtqueue(vq);
+
 	kfree(info);
 }
 
@@ -356,8 +348,6 @@ static void vm_del_vqs(struct virtio_device *vdev)
 	free_irq(platform_get_irq(vm_dev->pdev, 0), vm_dev);
 }
 
-
-
 static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name)
@@ -365,7 +355,8 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	struct virtio_mmio_vq_info *info;
 	struct virtqueue *vq;
-	unsigned long flags, size;
+	unsigned long flags;
+	unsigned int num;
 	int err;
 
 	if (!name)
@@ -388,66 +379,40 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 		goto error_kmalloc;
 	}
 
-	/* Allocate pages for the queue - start with a queue as big as
-	 * possible (limited by maximum size allowed by device), drop down
-	 * to a minimal size, just big enough to fit descriptor table
-	 * and two rings (which makes it "alignment_size * 2")
-	 */
-	info->num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX);
-
-	/* If the device reports a 0 entry queue, we won't be able to
-	 * use it to perform I/O, and vring_new_virtqueue() can't create
-	 * empty queues anyway, so don't bother to set up the device.
-	 */
-	if (info->num == 0) {
+	num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX);
+	if (num == 0) {
 		err = -ENOENT;
-		goto error_alloc_pages;
-	}
-
-	while (1) {
-		size = PAGE_ALIGN(vring_size(info->num,
-				VIRTIO_MMIO_VRING_ALIGN));
-		/* Did the last iter shrink the queue below minimum size? */
-		if (size < VIRTIO_MMIO_VRING_ALIGN * 2) {
-			err = -ENOMEM;
-			goto error_alloc_pages;
-		}
-
-		info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
-		if (info->queue)
-			break;
-
-		info->num /= 2;
+		goto error_new_virtqueue;
 	}
 
 	/* Create the vring */
-	vq = vring_new_virtqueue(index, info->num, VIRTIO_MMIO_VRING_ALIGN, vdev,
-				 true, info->queue, vm_notify, callback, name);
+	vq = vring_create_virtqueue(index, num, VIRTIO_MMIO_VRING_ALIGN, vdev,
+				 true, true, vm_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
 		goto error_new_virtqueue;
 	}
 
 	/* Activate the queue */
-	writel(info->num, vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
+	writel(virtqueue_get_vring_size(vq), vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
 	if (vm_dev->version == 1) {
 		writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
-		writel(virt_to_phys(info->queue) >> PAGE_SHIFT,
+		writel(virtqueue_get_desc_addr(vq) >> PAGE_SHIFT,
 				vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
 	} else {
 		u64 addr;
 
-		addr = virt_to_phys(info->queue);
+		addr = virtqueue_get_desc_addr(vq);
 		writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_DESC_LOW);
 		writel((u32)(addr >> 32),
 				vm_dev->base + VIRTIO_MMIO_QUEUE_DESC_HIGH);
 
-		addr = virt_to_phys(virtqueue_get_avail(vq));
+		addr = virtqueue_get_avail_addr(vq);
 		writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_AVAIL_LOW);
 		writel((u32)(addr >> 32),
 				vm_dev->base + VIRTIO_MMIO_QUEUE_AVAIL_HIGH);
 
-		addr = virt_to_phys(virtqueue_get_used(vq));
+		addr = virtqueue_get_used_addr(vq);
 		writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_USED_LOW);
 		writel((u32)(addr >> 32),
 				vm_dev->base + VIRTIO_MMIO_QUEUE_USED_HIGH);
@@ -471,8 +436,6 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 		writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_READY);
 		WARN_ON(readl(vm_dev->base + VIRTIO_MMIO_QUEUE_READY));
 	}
-	free_pages_exact(info->queue, size);
-error_alloc_pages:
 	kfree(info);
 error_kmalloc:
 error_available:

drivers/virtio/virtio_pci_common.h

@@ -35,12 +35,6 @@ struct virtio_pci_vq_info {
 	/* the actual virtqueue */
 	struct virtqueue *vq;
 
-	/* the number of entries in the queue */
-	int num;
-
-	/* the virtual address of the ring queue */
-	void *queue;
-
 	/* the list node for the virtqueues list */
 	struct list_head node;
 

drivers/virtio/virtio_pci_legacy.c

@@ -119,7 +119,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  u16 msix_vec)
 {
 	struct virtqueue *vq;
-	unsigned long size;
 	u16 num;
 	int err;
 
@@ -131,27 +130,19 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
 		return ERR_PTR(-ENOENT);
 
-	info->num = num;
 	info->msix_vector = msix_vec;
 
-	size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
-	info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
-	if (info->queue == NULL)
+	/* create the vring */
+	vq = vring_create_virtqueue(index, num,
+				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
+				    true, false, vp_notify, callback, name);
+	if (!vq)
 		return ERR_PTR(-ENOMEM);
 
 	/* activate the queue */
-	iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
+	iowrite32(virtqueue_get_desc_addr(vq) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
 		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
 
-	/* create the vring */
-	vq = vring_new_virtqueue(index, info->num,
-				 VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
-				 true, info->queue, vp_notify, callback, name);
-	if (!vq) {
-		err = -ENOMEM;
-		goto out_activate_queue;
-	}
-
 	vq->priv = (void __force *)vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
 
 	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
@@ -159,17 +150,15 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
 		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
 			err = -EBUSY;
-			goto out_assign;
+			goto out_deactivate;
 		}
 	}
 
 	return vq;
 
-out_assign:
-	vring_del_virtqueue(vq);
-out_activate_queue:
+out_deactivate:
 	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
-	free_pages_exact(info->queue, size);
+	vring_del_virtqueue(vq);
 	return ERR_PTR(err);
 }
 
@@ -177,7 +166,6 @@ static void del_vq(struct virtio_pci_vq_info *info)
 {
 	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
-	unsigned long size;
 
 	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 
@@ -188,13 +176,10 @@ static void del_vq(struct virtio_pci_vq_info *info)
 		ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
 	}
 
-	vring_del_virtqueue(vq);
-
 	/* Select and deactivate the queue */
 	iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
 
-	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
-	free_pages_exact(info->queue, size);
+	vring_del_virtqueue(vq);
 }
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -227,6 +212,13 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
 		return -ENODEV;
 	}
 
+	rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
+	if (rc)
+		rc = dma_set_mask_and_coherent(&pci_dev->dev,
+						DMA_BIT_MASK(32));
+	if (rc)
+		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
+
 	rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy");
 	if (rc)
 		return rc;

drivers/virtio/virtio_pci_modern.c

@@ -287,31 +287,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 	return vp_ioread16(&vp_dev->common->msix_config);
 }
 
-static size_t vring_pci_size(u16 num)
-{
-	/* We only need a cacheline separation. */
-	return PAGE_ALIGN(vring_size(num, SMP_CACHE_BYTES));
-}
-
-static void *alloc_virtqueue_pages(int *num)
-{
-	void *pages;
-
-	/* TODO: allocate each queue chunk individually */
-	for (; *num && vring_pci_size(*num) > PAGE_SIZE; *num /= 2) {
-		pages = alloc_pages_exact(vring_pci_size(*num),
-					  GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
-		if (pages)
-			return pages;
-	}
-
-	if (!*num)
-		return NULL;
-
-	/* Try to get a single page. You are my only hope! */
-	return alloc_pages_exact(vring_pci_size(*num), GFP_KERNEL|__GFP_ZERO);
-}
-
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  struct virtio_pci_vq_info *info,
 				  unsigned index,
@@ -343,29 +318,22 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	/* get offset of notification word for this vq */
 	off = vp_ioread16(&cfg->queue_notify_off);
 
-	info->num = num;
 	info->msix_vector = msix_vec;
 
-	info->queue = alloc_virtqueue_pages(&info->num);
-	if (info->queue == NULL)
-		return ERR_PTR(-ENOMEM);
-
 	/* create the vring */
-	vq = vring_new_virtqueue(index, info->num,
-				 SMP_CACHE_BYTES, &vp_dev->vdev,
-				 true, info->queue, vp_notify, callback, name);
-	if (!vq) {
-		err = -ENOMEM;
-		goto err_new_queue;
-	}
+	vq = vring_create_virtqueue(index, num,
+				    SMP_CACHE_BYTES, &vp_dev->vdev,
+				    true, true, vp_notify, callback, name);
+	if (!vq)
+		return ERR_PTR(-ENOMEM);
 
 	/* activate the queue */
-	vp_iowrite16(num, &cfg->queue_size);
-	vp_iowrite64_twopart(virt_to_phys(info->queue),
+	vp_iowrite16(virtqueue_get_vring_size(vq), &cfg->queue_size);
+	vp_iowrite64_twopart(virtqueue_get_desc_addr(vq),
 			     &cfg->queue_desc_lo, &cfg->queue_desc_hi);
-	vp_iowrite64_twopart(virt_to_phys(virtqueue_get_avail(vq)),
+	vp_iowrite64_twopart(virtqueue_get_avail_addr(vq),
 			     &cfg->queue_avail_lo, &cfg->queue_avail_hi);
-	vp_iowrite64_twopart(virt_to_phys(virtqueue_get_used(vq)),
+	vp_iowrite64_twopart(virtqueue_get_used_addr(vq),
 			     &cfg->queue_used_lo, &cfg->queue_used_hi);
 
 	if (vp_dev->notify_base) {
@@ -410,8 +378,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		pci_iounmap(vp_dev->pci_dev, (void __iomem __force *)vq->priv);
 err_map_notify:
 	vring_del_virtqueue(vq);
-err_new_queue:
-	free_pages_exact(info->queue, vring_pci_size(info->num));
 	return ERR_PTR(err);
 }
 
@@ -456,8 +422,6 @@ static void del_vq(struct virtio_pci_vq_info *info)
 		pci_iounmap(vp_dev->pci_dev, (void __force __iomem *)vq->priv);
 
 	vring_del_virtqueue(vq);
-
-	free_pages_exact(info->queue, vring_pci_size(info->num));
 }
 
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
@@ -641,6 +605,13 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 		return -EINVAL;
 	}
 
+	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
+	if (err)
+		err = dma_set_mask_and_coherent(&pci_dev->dev,
+						DMA_BIT_MASK(32));
+	if (err)
+		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
+
 	/* Device capability is only mandatory for devices that have
 	 * device-specific configuration.
 	 */

drivers/virtio/virtio_ring.c

@@ -24,6 +24,8 @@
 #include <linux/module.h>
 #include <linux/hrtimer.h>
 #include <linux/kmemleak.h>
+#include <linux/dma-mapping.h>
+#include <xen/xen.h>
 
 #ifdef DEBUG
 /* For development, we want to crash whenever the ring is screwed. */
@@ -54,6 +56,11 @@
 #define END_USE(vq)
 #endif
 
+struct vring_desc_state {
+	void *data;			/* Data for callback. */
+	struct vring_desc *indir_desc;	/* Indirect descriptor, if any. */
+};
+
 struct vring_virtqueue {
 	struct virtqueue vq;
 
@@ -89,6 +96,11 @@ struct vring_virtqueue {
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	bool (*notify)(struct virtqueue *vq);
 
+	/* DMA, allocation, and size information */
+	bool we_own_ring;
+	size_t queue_size_in_bytes;
+	dma_addr_t queue_dma_addr;
+
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
 	unsigned int in_use;
@@ -98,12 +110,120 @@ struct vring_virtqueue {
 	ktime_t last_add_time;
 #endif
 
-	/* Tokens for callbacks. */
-	void *data[];
+	/* Per-descriptor state. */
+	struct vring_desc_state desc_state[];
 };
 
 #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
 
+/*
+ * The interaction between virtio and a possible IOMMU is a mess.
+ *
+ * On most systems with virtio, physical addresses match bus addresses,
+ * and it doesn't particularly matter whether we use the DMA API.
+ *
+ * On some systems, including Xen and any system with a physical device
+ * that speaks virtio behind a physical IOMMU, we must use the DMA API
+ * for virtio DMA to work at all.
+ *
+ * On other systems, including SPARC and PPC64, virtio-pci devices are
+ * enumerated as though they are behind an IOMMU, but the virtio host
+ * ignores the IOMMU, so we must either pretend that the IOMMU isn't
+ * there or somehow map everything as the identity.
+ *
+ * For the time being, we preserve historic behavior and bypass the DMA
+ * API.
+ */
+
+static bool vring_use_dma_api(struct virtio_device *vdev)
+{
+	/*
+	 * In theory, it's possible to have a buggy QEMU-supposed
+	 * emulated Q35 IOMMU and Xen enabled at the same time.  On
+	 * such a configuration, virtio has never worked and will
+	 * not work without an even larger kludge.  Instead, enable
+	 * the DMA API if we're a Xen guest, which at least allows
+	 * all of the sensible Xen configurations to work correctly.
+	 */
+	if (xen_domain())
+		return true;
+
+	return false;
+}
+
+/*
+ * The DMA ops on various arches are rather gnarly right now, and
+ * making all of the arch DMA ops work on the vring device itself
+ * is a mess.  For now, we use the parent device for DMA ops.
+ */
+struct device *vring_dma_dev(const struct vring_virtqueue *vq)
+{
+	return vq->vq.vdev->dev.parent;
+}
+
+/* Map one sg entry. */
+static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq,
+				   struct scatterlist *sg,
+				   enum dma_data_direction direction)
+{
+	if (!vring_use_dma_api(vq->vq.vdev))
+		return (dma_addr_t)sg_phys(sg);
+
+	/*
+	 * We can't use dma_map_sg, because we don't use scatterlists in
+	 * the way it expects (we don't guarantee that the scatterlist
+	 * will exist for the lifetime of the mapping).
+	 */
+	return dma_map_page(vring_dma_dev(vq),
+			    sg_page(sg), sg->offset, sg->length,
+			    direction);
+}
+
+static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
+				   void *cpu_addr, size_t size,
+				   enum dma_data_direction direction)
+{
+	if (!vring_use_dma_api(vq->vq.vdev))
+		return (dma_addr_t)virt_to_phys(cpu_addr);
+
+	return dma_map_single(vring_dma_dev(vq),
+			      cpu_addr, size, direction);
+}
+
+static void vring_unmap_one(const struct vring_virtqueue *vq,
+			    struct vring_desc *desc)
+{
+	u16 flags;
+
+	if (!vring_use_dma_api(vq->vq.vdev))
+		return;
+
+	flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);
+
+	if (flags & VRING_DESC_F_INDIRECT) {
+		dma_unmap_single(vring_dma_dev(vq),
+				 virtio64_to_cpu(vq->vq.vdev, desc->addr),
+				 virtio32_to_cpu(vq->vq.vdev, desc->len),
+				 (flags & VRING_DESC_F_WRITE) ?
+				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	} else {
+		dma_unmap_page(vring_dma_dev(vq),
+			       virtio64_to_cpu(vq->vq.vdev, desc->addr),
+			       virtio32_to_cpu(vq->vq.vdev, desc->len),
+			       (flags & VRING_DESC_F_WRITE) ?
+			       DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+}
+
+static int vring_mapping_error(const struct vring_virtqueue *vq,
+			       dma_addr_t addr)
+{
+	if (!vring_use_dma_api(vq->vq.vdev))
+		return 0;
+
+	return dma_mapping_error(vring_dma_dev(vq), addr);
+}
+
 static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
 					 unsigned int total_sg, gfp_t gfp)
 {
@@ -137,7 +257,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	struct scatterlist *sg;
 	struct vring_desc *desc;
-	unsigned int i, n, avail, descs_used, uninitialized_var(prev);
+	unsigned int i, n, avail, descs_used, uninitialized_var(prev), err_idx;
 	int head;
 	bool indirect;
 
@@ -177,21 +297,15 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 
 	if (desc) {
 		/* Use a single buffer which doesn't continue */
-		vq->vring.desc[head].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT);
-		vq->vring.desc[head].addr = cpu_to_virtio64(_vq->vdev, virt_to_phys(desc));
-		/* avoid kmemleak false positive (hidden by virt_to_phys) */
-		kmemleak_ignore(desc);
-		vq->vring.desc[head].len = cpu_to_virtio32(_vq->vdev, total_sg * sizeof(struct vring_desc));
-
+		indirect = true;
 		/* Set up rest to use this indirect table. */
 		i = 0;
 		descs_used = 1;
-		indirect = true;
 	} else {
+		indirect = false;
 		desc = vq->vring.desc;
 		i = head;
 		descs_used = total_sg;
-		indirect = false;
 	}
 
 	if (vq->vq.num_free < descs_used) {
@@ -206,13 +320,14 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 		return -ENOSPC;
 	}
 
-	/* We're about to use some buffers from the free list. */
-	vq->vq.num_free -= descs_used;
-
 	for (n = 0; n < out_sgs; n++) {
 		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			dma_addr_t addr = vring_map_one_sg(vq, sg, DMA_TO_DEVICE);
+			if (vring_mapping_error(vq, addr))
+				goto unmap_release;
+
 			desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT);
-			desc[i].addr = cpu_to_virtio64(_vq->vdev, sg_phys(sg));
+			desc[i].addr = cpu_to_virtio64(_vq->vdev, addr);
 			desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
 			prev = i;
 			i = virtio16_to_cpu(_vq->vdev, desc[i].next);
@@ -220,8 +335,12 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	}
 	for (; n < (out_sgs + in_sgs); n++) {
 		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			dma_addr_t addr = vring_map_one_sg(vq, sg, DMA_FROM_DEVICE);
+			if (vring_mapping_error(vq, addr))
+				goto unmap_release;
+
 			desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE);
-			desc[i].addr = cpu_to_virtio64(_vq->vdev, sg_phys(sg));
+			desc[i].addr = cpu_to_virtio64(_vq->vdev, addr);
 			desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
 			prev = i;
 			i = virtio16_to_cpu(_vq->vdev, desc[i].next);
@@ -230,14 +349,33 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	/* Last one doesn't continue. */
 	desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);
 
+	if (indirect) {
+		/* Now that the indirect table is filled in, map it. */
+		dma_addr_t addr = vring_map_single(
+			vq, desc, total_sg * sizeof(struct vring_desc),
+			DMA_TO_DEVICE);
+		if (vring_mapping_error(vq, addr))
+			goto unmap_release;
+
+		vq->vring.desc[head].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT);
+		vq->vring.desc[head].addr = cpu_to_virtio64(_vq->vdev, addr);
+
+		vq->vring.desc[head].len = cpu_to_virtio32(_vq->vdev, total_sg * sizeof(struct vring_desc));
+	}
+
+	/* We're using some buffers from the free list. */
+	vq->vq.num_free -= descs_used;
+
 	/* Update free pointer */
 	if (indirect)
 		vq->free_head = virtio16_to_cpu(_vq->vdev, vq->vring.desc[head].next);
 	else
 		vq->free_head = i;
 
-	/* Set token. */
-	vq->data[head] = data;
+	/* Store token and indirect buffer state. */
+	vq->desc_state[head].data = data;
+	if (indirect)
+		vq->desc_state[head].indir_desc = desc;
 
 	/* Put entry in available array (but don't update avail->idx until they
 	 * do sync). */
@@ -260,6 +398,24 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 		virtqueue_kick(_vq);
 
 	return 0;
+
+unmap_release:
+	err_idx = i;
+	i = head;
+
+	for (n = 0; n < total_sg; n++) {
+		if (i == err_idx)
+			break;
+		vring_unmap_one(vq, &desc[i]);
+		i = vq->vring.desc[i].next;
+	}
+
+	vq->vq.num_free += total_sg;
+
+	if (indirect)
+		kfree(desc);
+
+	return -EIO;
 }
 
 /**
@@ -430,27 +586,43 @@ EXPORT_SYMBOL_GPL(virtqueue_kick);
 
 static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
 {
-	unsigned int i;
+	unsigned int i, j;
+	u16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
 
 	/* Clear data ptr. */
-	vq->data[head] = NULL;
+	vq->desc_state[head].data = NULL;
 
-	/* Put back on free list: find end */
+	/* Put back on free list: unmap first-level descriptors and find end */
 	i = head;
 
-	/* Free the indirect table */
-	if (vq->vring.desc[i].flags & cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT))
-		kfree(phys_to_virt(virtio64_to_cpu(vq->vq.vdev, vq->vring.desc[i].addr)));
-
-	while (vq->vring.desc[i].flags & cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT)) {
+	while (vq->vring.desc[i].flags & nextflag) {
+		vring_unmap_one(vq, &vq->vring.desc[i]);
 		i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
 		vq->vq.num_free++;
 	}
 
+	vring_unmap_one(vq, &vq->vring.desc[i]);
 	vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
 	vq->free_head = head;
+
 	/* Plus final descriptor */
 	vq->vq.num_free++;
+
+	/* Free the indirect table, if any, now that it's unmapped. */
+	if (vq->desc_state[head].indir_desc) {
+		struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
+		u32 len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
+
+		BUG_ON(!(vq->vring.desc[head].flags &
+			 cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
+		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
+
+		for (j = 0; j < len / sizeof(struct vring_desc); j++)
+			vring_unmap_one(vq, &indir_desc[j]);
+
+		kfree(vq->desc_state[head].indir_desc);
+		vq->desc_state[head].indir_desc = NULL;
+	}
 }
 
 static inline bool more_used(const struct vring_virtqueue *vq)
@@ -505,13 +677,13 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 		BAD_RING(vq, "id %u out of range\n", i);
 		return NULL;
 	}
-	if (unlikely(!vq->data[i])) {
+	if (unlikely(!vq->desc_state[i].data)) {
 		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];
+	ret = vq->desc_state[i].data;
 	detach_buf(vq, i);
 	vq->last_used_idx++;
 	/* If we expect an interrupt for the next entry, tell host
@@ -685,10 +857,10 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 	START_USE(vq);
 
 	for (i = 0; i < vq->vring.num; i++) {
-		if (!vq->data[i])
+		if (!vq->desc_state[i].data)
 			continue;
 		/* detach_buf clears data, so grab it now. */
-		buf = vq->data[i];
+		buf = vq->desc_state[i].data;
 		detach_buf(vq, i);
 		vq->avail_idx_shadow--;
 		vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
@@ -723,35 +895,31 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 }
 EXPORT_SYMBOL_GPL(vring_interrupt);
 
-struct virtqueue *vring_new_virtqueue(unsigned int index,
-				      unsigned int num,
-				      unsigned int vring_align,
-				      struct virtio_device *vdev,
-				      bool weak_barriers,
-				      void *pages,
-				      bool (*notify)(struct virtqueue *),
-				      void (*callback)(struct virtqueue *),
-				      const char *name)
+struct virtqueue *__vring_new_virtqueue(unsigned int index,
+					struct vring vring,
+					struct virtio_device *vdev,
+					bool weak_barriers,
+					bool (*notify)(struct virtqueue *),
+					void (*callback)(struct virtqueue *),
+					const char *name)
 {
-	struct vring_virtqueue *vq;
 	unsigned int i;
+	struct vring_virtqueue *vq;
 
-	/* We assume num is a power of 2. */
-	if (num & (num - 1)) {
-		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
-		return NULL;
-	}
-
-	vq = kmalloc(sizeof(*vq) + sizeof(void *)*num, GFP_KERNEL);
+	vq = kmalloc(sizeof(*vq) + vring.num * sizeof(struct vring_desc_state),
+		     GFP_KERNEL);
 	if (!vq)
 		return NULL;
 
-	vring_init(&vq->vring, num, pages, vring_align);
+	vq->vring = vring;
 	vq->vq.callback = callback;
 	vq->vq.vdev = vdev;
 	vq->vq.name = name;
-	vq->vq.num_free = num;
+	vq->vq.num_free = vring.num;
 	vq->vq.index = index;
+	vq->we_own_ring = false;
+	vq->queue_dma_addr = 0;
+	vq->queue_size_in_bytes = 0;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
@@ -776,20 +944,145 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 
 	/* Put everything in free lists. */
 	vq->free_head = 0;
-	for (i = 0; i < num-1; i++) {
+	for (i = 0; i < vring.num-1; i++)
 		vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
-		vq->data[i] = NULL;
-	}
-	vq->data[i] = NULL;
+	memset(vq->desc_state, 0, vring.num * sizeof(struct vring_desc_state));
 
 	return &vq->vq;
 }
+EXPORT_SYMBOL_GPL(__vring_new_virtqueue);
+
+static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
+			      dma_addr_t *dma_handle, gfp_t flag)
+{
+	if (vring_use_dma_api(vdev)) {
+		return dma_alloc_coherent(vdev->dev.parent, size,
+					  dma_handle, flag);
+	} else {
+		void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
+		if (queue) {
+			phys_addr_t phys_addr = virt_to_phys(queue);
+			*dma_handle = (dma_addr_t)phys_addr;
+
+			/*
+			 * Sanity check: make sure we dind't truncate
+			 * the address.  The only arches I can find that
+			 * have 64-bit phys_addr_t but 32-bit dma_addr_t
+			 * are certain non-highmem MIPS and x86
+			 * configurations, but these configurations
+			 * should never allocate physical pages above 32
+			 * bits, so this is fine.  Just in case, throw a
+			 * warning and abort if we end up with an
+			 * unrepresentable address.
+			 */
+			if (WARN_ON_ONCE(*dma_handle != phys_addr)) {
+				free_pages_exact(queue, PAGE_ALIGN(size));
+				return NULL;
+			}
+		}
+		return queue;
+	}
+}
+
+static void vring_free_queue(struct virtio_device *vdev, size_t size,
+			     void *queue, dma_addr_t dma_handle)
+{
+	if (vring_use_dma_api(vdev)) {
+		dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
+	} else {
+		free_pages_exact(queue, PAGE_ALIGN(size));
+	}
+}
+
+struct virtqueue *vring_create_virtqueue(
+	unsigned int index,
+	unsigned int num,
+	unsigned int vring_align,
+	struct virtio_device *vdev,
+	bool weak_barriers,
+	bool may_reduce_num,
+	bool (*notify)(struct virtqueue *),
+	void (*callback)(struct virtqueue *),
+	const char *name)
+{
+	struct virtqueue *vq;
+	void *queue;
+	dma_addr_t dma_addr;
+	size_t queue_size_in_bytes;
+	struct vring vring;
+
+	/* We assume num is a power of 2. */
+	if (num & (num - 1)) {
+		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
+		return NULL;
+	}
+
+	/* TODO: allocate each queue chunk individually */
+	for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
+		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+					  &dma_addr,
+					  GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+		if (queue)
+			break;
+	}
+
+	if (!num)
+		return NULL;
+
+	if (!queue) {
+		/* Try to get a single page. You are my only hope! */
+		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+					  &dma_addr, GFP_KERNEL|__GFP_ZERO);
+	}
+	if (!queue)
+		return NULL;
+
+	queue_size_in_bytes = vring_size(num, vring_align);
+	vring_init(&vring, num, queue, vring_align);
+
+	vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers,
+				   notify, callback, name);
+	if (!vq) {
+		vring_free_queue(vdev, queue_size_in_bytes, queue,
+				 dma_addr);
+		return NULL;
+	}
+
+	to_vvq(vq)->queue_dma_addr = dma_addr;
+	to_vvq(vq)->queue_size_in_bytes = queue_size_in_bytes;
+	to_vvq(vq)->we_own_ring = true;
+
+	return vq;
+}
+EXPORT_SYMBOL_GPL(vring_create_virtqueue);
+
+struct virtqueue *vring_new_virtqueue(unsigned int index,
+				      unsigned int num,
+				      unsigned int vring_align,
+				      struct virtio_device *vdev,
+				      bool weak_barriers,
+				      void *pages,
+				      bool (*notify)(struct virtqueue *vq),
+				      void (*callback)(struct virtqueue *vq),
+				      const char *name)
+{
+	struct vring vring;
+	vring_init(&vring, num, pages, vring_align);
+	return __vring_new_virtqueue(index, vring, vdev, weak_barriers,
+				     notify, callback, name);
+}
 EXPORT_SYMBOL_GPL(vring_new_virtqueue);
 
-void vring_del_virtqueue(struct virtqueue *vq)
+void vring_del_virtqueue(struct virtqueue *_vq)
 {
-	list_del(&vq->list);
-	kfree(to_vvq(vq));
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (vq->we_own_ring) {
+		vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes,
+				 vq->vring.desc, vq->queue_dma_addr);
+	}
+	list_del(&_vq->list);
+	kfree(vq);
 }
 EXPORT_SYMBOL_GPL(vring_del_virtqueue);
 
@@ -853,20 +1146,42 @@ void virtio_break_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(virtio_break_device);
 
-void *virtqueue_get_avail(struct virtqueue *_vq)
+dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
-	return vq->vring.avail;
+	BUG_ON(!vq->we_own_ring);
+
+	return vq->queue_dma_addr;
 }
-EXPORT_SYMBOL_GPL(virtqueue_get_avail);
+EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr);
 
-void *virtqueue_get_used(struct virtqueue *_vq)
+dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
-	return vq->vring.used;
+	BUG_ON(!vq->we_own_ring);
+
+	return vq->queue_dma_addr +
+		((char *)vq->vring.avail - (char *)vq->vring.desc);
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr);
+
+dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	BUG_ON(!vq->we_own_ring);
+
+	return vq->queue_dma_addr +
+		((char *)vq->vring.used - (char *)vq->vring.desc);
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_used_addr);
+
+const struct vring *virtqueue_get_vring(struct virtqueue *vq)
+{
+	return &to_vvq(vq)->vring;
 }
-EXPORT_SYMBOL_GPL(virtqueue_get_used);
+EXPORT_SYMBOL_GPL(virtqueue_get_vring);
 
 MODULE_LICENSE("GPL");

include/linux/dma-mapping.h

@@ -70,6 +70,8 @@ struct dma_map_ops {
 	int is_phys;
 };
 
+extern struct dma_map_ops dma_noop_ops;
+
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
 #define DMA_MASK_NONE	0x0ULL

include/linux/virtio.h

@@ -75,8 +75,27 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *vq);
 
 bool virtqueue_is_broken(struct virtqueue *vq);
 
-void *virtqueue_get_avail(struct virtqueue *vq);
-void *virtqueue_get_used(struct virtqueue *vq);
+const struct vring *virtqueue_get_vring(struct virtqueue *vq);
+dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq);
+dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq);
+dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq);
+
+/*
+ * Legacy accessors -- in almost all cases, these are the wrong functions
+ * to use.
+ */
+static inline void *virtqueue_get_desc(struct virtqueue *vq)
+{
+	return virtqueue_get_vring(vq)->desc;
+}
+static inline void *virtqueue_get_avail(struct virtqueue *vq)
+{
+	return virtqueue_get_vring(vq)->avail;
+}
+static inline void *virtqueue_get_used(struct virtqueue *vq)
+{
+	return virtqueue_get_vring(vq)->used;
+}
 
 /**
  * virtio_device - representation of a device using virtio

include/linux/virtio_ring.h

@@ -59,6 +59,35 @@ static inline void virtio_store_mb(bool weak_barriers,
 struct virtio_device;
 struct virtqueue;
 
+/*
+ * Creates a virtqueue and allocates the descriptor ring.  If
+ * may_reduce_num is set, then this may allocate a smaller ring than
+ * expected.  The caller should query virtqueue_get_ring_size to learn
+ * the actual size of the ring.
+ */
+struct virtqueue *vring_create_virtqueue(unsigned int index,
+					 unsigned int num,
+					 unsigned int vring_align,
+					 struct virtio_device *vdev,
+					 bool weak_barriers,
+					 bool may_reduce_num,
+					 bool (*notify)(struct virtqueue *vq),
+					 void (*callback)(struct virtqueue *vq),
+					 const char *name);
+
+/* Creates a virtqueue with a custom layout. */
+struct virtqueue *__vring_new_virtqueue(unsigned int index,
+					struct vring vring,
+					struct virtio_device *vdev,
+					bool weak_barriers,
+					bool (*notify)(struct virtqueue *),
+					void (*callback)(struct virtqueue *),
+					const char *name);
+
+/*
+ * Creates a virtqueue with a standard layout but a caller-allocated
+ * ring.
+ */
 struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      unsigned int num,
 				      unsigned int vring_align,
@@ -68,7 +97,13 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      bool (*notify)(struct virtqueue *vq),
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name);
+
+/*
+ * Destroys a virtqueue.  If created with vring_create_virtqueue, this
+ * also frees the ring.
+ */
 void vring_del_virtqueue(struct virtqueue *vq);
+
 /* Filter out transport-specific feature bits. */
 void vring_transport_features(struct virtio_device *vdev);
 

include/uapi/linux/vhost.h

@@ -126,6 +126,12 @@ struct vhost_memory {
 #define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
 /* Set eventfd to signal an error */
 #define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
+/* Set busy loop timeout (in us) */
+#define VHOST_SET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x23,	\
+					 struct vhost_vring_state)
+/* Get busy loop timeout (in us) */
+#define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24,	\
+					 struct vhost_vring_state)
 
 /* VHOST_NET specific defines */
 

include/uapi/linux/virtio_blk.h

@@ -43,11 +43,11 @@
 #ifndef VIRTIO_BLK_NO_LEGACY
 #define VIRTIO_BLK_F_BARRIER	0	/* Does host support barriers? */
 #define VIRTIO_BLK_F_SCSI	7	/* Supports scsi command passthru */
-#define VIRTIO_BLK_F_WCE	9	/* Writeback mode enabled after reset */
+#define VIRTIO_BLK_F_FLUSH	9	/* Flush command supported */
 #define VIRTIO_BLK_F_CONFIG_WCE	11	/* Writeback mode available in config */
 #ifndef __KERNEL__
-/* Old (deprecated) name for VIRTIO_BLK_F_WCE. */
-#define VIRTIO_BLK_F_FLUSH VIRTIO_BLK_F_WCE
+/* Old (deprecated) name for VIRTIO_BLK_F_FLUSH. */
+#define VIRTIO_BLK_F_WCE VIRTIO_BLK_F_FLUSH
 #endif
 #endif /* !VIRTIO_BLK_NO_LEGACY */
 

lib/Makefile

@@ -18,6 +18,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
+lib-$(CONFIG_HAS_DMA) += dma-noop.o
 
 lib-y	+= kobject.o klist.o
 obj-y	+= lockref.o

lib/dma-noop.c

+/*
+ *	lib/dma-noop.c
+ *
+ * Simple DMA noop-ops that map 1:1 with memory
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+
+static void *dma_noop_alloc(struct device *dev, size_t size,
+			    dma_addr_t *dma_handle, gfp_t gfp,
+			    struct dma_attrs *attrs)
+{
+	void *ret;
+
+	ret = (void *)__get_free_pages(gfp, get_order(size));
+	if (ret)
+		*dma_handle = virt_to_phys(ret);
+	return ret;
+}
+
+static void dma_noop_free(struct device *dev, size_t size,
+			  void *cpu_addr, dma_addr_t dma_addr,
+			  struct dma_attrs *attrs)
+{
+	free_pages((unsigned long)cpu_addr, get_order(size));
+}
+
+static dma_addr_t dma_noop_map_page(struct device *dev, struct page *page,
+				      unsigned long offset, size_t size,
+				      enum dma_data_direction dir,
+				      struct dma_attrs *attrs)
+{
+	return page_to_phys(page) + offset;
+}
+
+static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+			     enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, nents, i) {
+		void *va;
+
+		BUG_ON(!sg_page(sg));
+		va = sg_virt(sg);
+		sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va);
+		sg_dma_len(sg) = sg->length;
+	}
+
+	return nents;
+}
+
+static int dma_noop_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return 0;
+}
+
+static int dma_noop_supported(struct device *dev, u64 mask)
+{
+	return 1;
+}
+
+struct dma_map_ops dma_noop_ops = {
+	.alloc			= dma_noop_alloc,
+	.free			= dma_noop_free,
+	.map_page		= dma_noop_map_page,
+	.map_sg			= dma_noop_map_sg,
+	.mapping_error		= dma_noop_mapping_error,
+	.dma_supported		= dma_noop_supported,
+};
+
+EXPORT_SYMBOL(dma_noop_ops);

tools/virtio/linux/dma-mapping.h

+#ifndef _LINUX_DMA_MAPPING_H
+#define _LINUX_DMA_MAPPING_H
+
+#ifdef CONFIG_HAS_DMA
+# error Virtio userspace code does not support CONFIG_HAS_DMA
+#endif
+
+#define PCI_DMA_BUS_IS_PHYS 1
+
+enum dma_data_direction {
+	DMA_BIDIRECTIONAL = 0,
+	DMA_TO_DEVICE = 1,
+	DMA_FROM_DEVICE = 2,
+	DMA_NONE = 3,
+};
+
+#endif