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

Pull virtio fixes from Michael Tsirkin:
 "This includes some fixes and cleanups in virtio and vhost code.

  Most notably, shadowing the index fixes the excessive cacheline
  bouncing observed on AMD platforms"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_ring: shadow available ring flags & index
  virtio: Do not drop __GFP_HIGH in alloc_indirect
  vhost: replace % with & on data path
  tools/virtio: fix byteswap logic
  tools/virtio: move list macro stubs
  virtio: fix memory leak of virtio ida cache layers
  vhost: relax log address alignment
  virtio-net: Stop doing DMA from the stack

drivers/net/virtio_net.c

@@ -140,6 +140,12 @@ struct virtnet_info {
 
 	/* CPU hot plug notifier */
 	struct notifier_block nb;
+
+	/* Control VQ buffers: protected by the rtnl lock */
+	struct virtio_net_ctrl_hdr ctrl_hdr;
+	virtio_net_ctrl_ack ctrl_status;
+	u8 ctrl_promisc;
+	u8 ctrl_allmulti;
 };
 
 struct padded_vnet_hdr {
@@ -976,31 +982,30 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 				 struct scatterlist *out)
 {
 	struct scatterlist *sgs[4], hdr, stat;
-	struct virtio_net_ctrl_hdr ctrl;
-	virtio_net_ctrl_ack status = ~0;
 	unsigned out_num = 0, tmp;
 
 	/* Caller should know better */
 	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
 
-	ctrl.class = class;
-	ctrl.cmd = cmd;
+	vi->ctrl_status = ~0;
+	vi->ctrl_hdr.class = class;
+	vi->ctrl_hdr.cmd = cmd;
 	/* Add header */
-	sg_init_one(&hdr, &ctrl, sizeof(ctrl));
+	sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
 	sgs[out_num++] = &hdr;
 
 	if (out)
 		sgs[out_num++] = out;
 
 	/* Add return status. */
-	sg_init_one(&stat, &status, sizeof(status));
+	sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
 	sgs[out_num] = &stat;
 
 	BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
 	virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
 
 	if (unlikely(!virtqueue_kick(vi->cvq)))
-		return status == VIRTIO_NET_OK;
+		return vi->ctrl_status == VIRTIO_NET_OK;
 
 	/* Spin for a response, the kick causes an ioport write, trapping
 	 * into the hypervisor, so the request should be handled immediately.
@@ -1009,7 +1014,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 	       !virtqueue_is_broken(vi->cvq))
 		cpu_relax();
 
-	return status == VIRTIO_NET_OK;
+	return vi->ctrl_status == VIRTIO_NET_OK;
 }
 
 static int virtnet_set_mac_address(struct net_device *dev, void *p)
@@ -1151,7 +1156,6 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg[2];
-	u8 promisc, allmulti;
 	struct virtio_net_ctrl_mac *mac_data;
 	struct netdev_hw_addr *ha;
 	int uc_count;
@@ -1163,22 +1167,22 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
 		return;
 
-	promisc = ((dev->flags & IFF_PROMISC) != 0);
-	allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
+	vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
+	vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
 
-	sg_init_one(sg, &promisc, sizeof(promisc));
+	sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_PROMISC, sg))
 		dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
-			 promisc ? "en" : "dis");
+			 vi->ctrl_promisc ? "en" : "dis");
 
-	sg_init_one(sg, &allmulti, sizeof(allmulti));
+	sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
 		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
-			 allmulti ? "en" : "dis");
+			 vi->ctrl_allmulti ? "en" : "dis");
 
 	uc_count = netdev_uc_count(dev);
 	mc_count = netdev_mc_count(dev);

drivers/vhost/vhost.c

@@ -819,7 +819,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp)
 		BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE);
 		if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) ||
 		    (a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) ||
-		    (a.log_guest_addr & (sizeof(u64) - 1))) {
+		    (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1))) {
 			r = -EINVAL;
 			break;
 		}
@@ -1369,7 +1369,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 	/* Grab the next descriptor number they're advertising, and increment
 	 * the index we've seen. */
 	if (unlikely(__get_user(ring_head,
-				&vq->avail->ring[last_avail_idx % vq->num]))) {
+				&vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
 		vq_err(vq, "Failed to read head: idx %d address %p\n",
 		       last_avail_idx,
 		       &vq->avail->ring[last_avail_idx % vq->num]);
@@ -1489,7 +1489,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 	u16 old, new;
 	int start;
 
-	start = vq->last_used_idx % vq->num;
+	start = vq->last_used_idx & (vq->num - 1);
 	used = vq->used->ring + start;
 	if (count == 1) {
 		if (__put_user(heads[0].id, &used->id)) {
@@ -1531,7 +1531,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 {
 	int start, n, r;
 
-	start = vq->last_used_idx % vq->num;
+	start = vq->last_used_idx & (vq->num - 1);
 	n = vq->num - start;
 	if (n < count) {
 		r = __vhost_add_used_n(vq, heads, n);

drivers/virtio/virtio.c

@@ -412,6 +412,7 @@ static int virtio_init(void)
 static void __exit virtio_exit(void)
 {
 	bus_unregister(&virtio_bus);
+	ida_destroy(&virtio_index_ida);
 }
 core_initcall(virtio_init);
 module_exit(virtio_exit);

drivers/virtio/virtio_ring.c

@@ -80,6 +80,12 @@ struct vring_virtqueue {
 	/* Last used index we've seen. */
 	u16 last_used_idx;
 
+	/* Last written value to avail->flags */
+	u16 avail_flags_shadow;
+
+	/* Last written value to avail->idx in guest byte order */
+	u16 avail_idx_shadow;
+
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	bool (*notify)(struct virtqueue *vq);
 
@@ -109,7 +115,7 @@ static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
 	 * otherwise virt_to_phys will give us bogus addresses in the
 	 * virtqueue.
 	 */
-	gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH);
+	gfp &= ~__GFP_HIGHMEM;
 
 	desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
 	if (!desc)
@@ -235,13 +241,14 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 
 	/* Put entry in available array (but don't update avail->idx until they
 	 * do sync). */
-	avail = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) & (vq->vring.num - 1);
+	avail = vq->avail_idx_shadow & (vq->vring.num - 1);
 	vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
 
 	/* Descriptors and available array need to be set before we expose the
 	 * new available array entries. */
 	virtio_wmb(vq->weak_barriers);
-	vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) + 1);
+	vq->avail_idx_shadow++;
+	vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
 	vq->num_added++;
 
 	pr_debug("Added buffer head %i to %p\n", head, vq);
@@ -354,8 +361,8 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq)
 	 * event. */
 	virtio_mb(vq->weak_barriers);
 
-	old = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->num_added;
-	new = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx);
+	old = vq->avail_idx_shadow - vq->num_added;
+	new = vq->avail_idx_shadow;
 	vq->num_added = 0;
 
 #ifdef DEBUG
@@ -510,7 +517,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	/* If we expect an interrupt for the next entry, tell host
 	 * by writing event index and flush out the write before
 	 * the read in the next get_buf call. */
-	if (!(vq->vring.avail->flags & cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT))) {
+	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
 		vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx);
 		virtio_mb(vq->weak_barriers);
 	}
@@ -537,7 +544,11 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
-	vq->vring.avail->flags |= cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT);
+	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
+		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+		vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+	}
+
 }
 EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
 
@@ -565,7 +576,10 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
 	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
 	 * either clear the flags bit or point the event index at the next
 	 * entry. Always do both to keep code simple. */
-	vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT);
+	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+		vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+	}
 	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
 	END_USE(vq);
 	return last_used_idx;
@@ -633,9 +647,12 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
 	 * either clear the flags bit or point the event index at the next
 	 * entry. Always do both to keep code simple. */
-	vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT);
+	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+		vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+	}
 	/* TODO: tune this threshold */
-	bufs = (u16)(virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->last_used_idx) * 3 / 4;
+	bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
 	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs);
 	virtio_mb(vq->weak_barriers);
 	if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
@@ -670,7 +687,8 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 		/* detach_buf clears data, so grab it now. */
 		buf = vq->data[i];
 		detach_buf(vq, i);
-		vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - 1);
+		vq->avail_idx_shadow--;
+		vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
 		END_USE(vq);
 		return buf;
 	}
@@ -735,6 +753,8 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
 	vq->last_used_idx = 0;
+	vq->avail_flags_shadow = 0;
+	vq->avail_idx_shadow = 0;
 	vq->num_added = 0;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
@@ -746,8 +766,10 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
 	/* No callback?  Tell other side not to bother us. */
-	if (!callback)
-		vq->vring.avail->flags |= cpu_to_virtio16(vdev, VRING_AVAIL_F_NO_INTERRUPT);
+	if (!callback) {
+		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+		vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+	}
 
 	/* Put everything in free lists. */
 	vq->free_head = 0;

tools/virtio/linux/kernel.h

@@ -110,4 +110,10 @@ static inline void free_page(unsigned long addr)
 	(void) (&_min1 == &_min2);		\
 	_min1 < _min2 ? _min1 : _min2; })
 
+/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
+#define list_add_tail(a, b) do {} while (0)
+#define list_del(a) do {} while (0)
+#define list_for_each_entry(a, b, c) while (0)
+/* end of stubs */
+
 #endif /* KERNEL_H */

tools/virtio/linux/virtio.h

@@ -3,12 +3,6 @@
 #include <linux/scatterlist.h>
 #include <linux/kernel.h>
 
-/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
-#define list_add_tail(a, b) do {} while (0)
-#define list_del(a) do {} while (0)
-#define list_for_each_entry(a, b, c) while (0)
-/* end of stubs */
-
 struct virtio_device {
 	void *dev;
 	u64 features;

tools/virtio/linux/virtio_config.h

@@ -40,33 +40,39 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev,
 #define virtio_has_feature(dev, feature) \
 	(__virtio_test_bit((dev), feature))
 
+static inline bool virtio_is_little_endian(struct virtio_device *vdev)
+{
+	return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
+		virtio_legacy_is_little_endian();
+}
+
+/* Memory accessors */
 static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
 {
-	return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __virtio16_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
 {
-	return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio16(virtio_is_little_endian(vdev), val);
 }
 
 static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
 {
-	return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __virtio32_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
 {
-	return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio32(virtio_is_little_endian(vdev), val);
 }
 
 static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
 {
-	return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __virtio64_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 {
-	return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
 }
-