Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/gi…

…t/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

@@ -123,55 +123,17 @@ 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;
 }
 
 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);