From 1ab5d1385af40272ca44a5cd38af7e13da6ed847 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 24 May 2019 04:12:13 -0400
Subject: vhost: generalize adding used elem

Use one generic vhost_copy_to_user() instead of two dedicated
accessor. This will simplify the conversion to fine grain
accessors. About 2% improvement of PPS were seen during vitio-user
txonly test.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vhost.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

(limited to 'drivers/vhost')

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 3f3eac4bcc58..3fb58015f8b3 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2273,16 +2273,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 
 	start = vq->last_used_idx & (vq->num - 1);
 	used = vq->used->ring + start;
-	if (count == 1) {
-		if (vhost_put_user(vq, heads[0].id, &used->id)) {
-			vq_err(vq, "Failed to write used id");
-			return -EFAULT;
-		}
-		if (vhost_put_user(vq, heads[0].len, &used->len)) {
-			vq_err(vq, "Failed to write used len");
-			return -EFAULT;
-		}
-	} else if (vhost_copy_to_user(vq, used, heads, count * sizeof *used)) {
+	if (vhost_copy_to_user(vq, used, heads, count * sizeof *used)) {
 		vq_err(vq, "Failed to write used");
 		return -EFAULT;
 	}
-- 
cgit v1.2.3-59-g8ed1b


From 7b5d753ebc22c5b6935a70ce9a857dc6220784f8 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 24 May 2019 04:12:14 -0400
Subject: vhost: fine grain userspace memory accessors

This is used to hide the metadata address from virtqueue helpers. This
will allow to implement a vmap based fast accessing to metadata.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vhost.c | 94 +++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 77 insertions(+), 17 deletions(-)

(limited to 'drivers/vhost')

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 3fb58015f8b3..b89faedbb9bd 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -887,6 +887,34 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
 	ret; \
 })
 
+static inline int vhost_put_avail_event(struct vhost_virtqueue *vq)
+{
+	return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
+			      vhost_avail_event(vq));
+}
+
+static inline int vhost_put_used(struct vhost_virtqueue *vq,
+				 struct vring_used_elem *head, int idx,
+				 int count)
+{
+	return vhost_copy_to_user(vq, vq->used->ring + idx, head,
+				  count * sizeof(*head));
+}
+
+static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
+
+{
+	return vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
+			      &vq->used->flags);
+}
+
+static inline int vhost_put_used_idx(struct vhost_virtqueue *vq)
+
+{
+	return vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
+			      &vq->used->idx);
+}
+
 #define vhost_get_user(vq, x, ptr, type)		\
 ({ \
 	int ret; \
@@ -925,6 +953,43 @@ static void vhost_dev_unlock_vqs(struct vhost_dev *d)
 		mutex_unlock(&d->vqs[i]->mutex);
 }
 
+static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq,
+				      __virtio16 *idx)
+{
+	return vhost_get_avail(vq, *idx, &vq->avail->idx);
+}
+
+static inline int vhost_get_avail_head(struct vhost_virtqueue *vq,
+				       __virtio16 *head, int idx)
+{
+	return vhost_get_avail(vq, *head,
+			       &vq->avail->ring[idx & (vq->num - 1)]);
+}
+
+static inline int vhost_get_avail_flags(struct vhost_virtqueue *vq,
+					__virtio16 *flags)
+{
+	return vhost_get_avail(vq, *flags, &vq->avail->flags);
+}
+
+static inline int vhost_get_used_event(struct vhost_virtqueue *vq,
+				       __virtio16 *event)
+{
+	return vhost_get_avail(vq, *event, vhost_used_event(vq));
+}
+
+static inline int vhost_get_used_idx(struct vhost_virtqueue *vq,
+				     __virtio16 *idx)
+{
+	return vhost_get_used(vq, *idx, &vq->used->idx);
+}
+
+static inline int vhost_get_desc(struct vhost_virtqueue *vq,
+				 struct vring_desc *desc, int idx)
+{
+	return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc));
+}
+
 static int vhost_new_umem_range(struct vhost_umem *umem,
 				u64 start, u64 size, u64 end,
 				u64 userspace_addr, int perm)
@@ -1862,8 +1927,7 @@ EXPORT_SYMBOL_GPL(vhost_log_write);
 static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 {
 	void __user *used;
-	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
-			   &vq->used->flags) < 0)
+	if (vhost_put_used_flags(vq))
 		return -EFAULT;
 	if (unlikely(vq->log_used)) {
 		/* Make sure the flag is seen before log. */
@@ -1880,8 +1944,7 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 
 static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
 {
-	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
-			   vhost_avail_event(vq)))
+	if (vhost_put_avail_event(vq))
 		return -EFAULT;
 	if (unlikely(vq->log_used)) {
 		void __user *used;
@@ -1917,7 +1980,7 @@ int vhost_vq_init_access(struct vhost_virtqueue *vq)
 		r = -EFAULT;
 		goto err;
 	}
-	r = vhost_get_used(vq, last_used_idx, &vq->used->idx);
+	r = vhost_get_used_idx(vq, &last_used_idx);
 	if (r) {
 		vq_err(vq, "Can't access used idx at %p\n",
 		       &vq->used->idx);
@@ -2116,7 +2179,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 	last_avail_idx = vq->last_avail_idx;
 
 	if (vq->avail_idx == vq->last_avail_idx) {
-		if (unlikely(vhost_get_avail(vq, avail_idx, &vq->avail->idx))) {
+		if (unlikely(vhost_get_avail_idx(vq, &avail_idx))) {
 			vq_err(vq, "Failed to access avail idx at %p\n",
 				&vq->avail->idx);
 			return -EFAULT;
@@ -2143,8 +2206,7 @@ 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(vhost_get_avail(vq, ring_head,
-		     &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
+	if (unlikely(vhost_get_avail_head(vq, &ring_head, last_avail_idx))) {
 		vq_err(vq, "Failed to read head: idx %d address %p\n",
 		       last_avail_idx,
 		       &vq->avail->ring[last_avail_idx % vq->num]);
@@ -2179,8 +2241,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 			       i, vq->num, head);
 			return -EINVAL;
 		}
-		ret = vhost_copy_from_user(vq, &desc, vq->desc + i,
-					   sizeof desc);
+		ret = vhost_get_desc(vq, &desc, i);
 		if (unlikely(ret)) {
 			vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
 			       i, vq->desc + i);
@@ -2273,7 +2334,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 
 	start = vq->last_used_idx & (vq->num - 1);
 	used = vq->used->ring + start;
-	if (vhost_copy_to_user(vq, used, heads, count * sizeof *used)) {
+	if (vhost_put_used(vq, heads, start, count)) {
 		vq_err(vq, "Failed to write used");
 		return -EFAULT;
 	}
@@ -2315,8 +2376,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 
 	/* Make sure buffer is written before we update index. */
 	smp_wmb();
-	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
-			   &vq->used->idx)) {
+	if (vhost_put_used_idx(vq)) {
 		vq_err(vq, "Failed to increment used idx");
 		return -EFAULT;
 	}
@@ -2349,7 +2409,7 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 
 	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
 		__virtio16 flags;
-		if (vhost_get_avail(vq, flags, &vq->avail->flags)) {
+		if (vhost_get_avail_flags(vq, &flags)) {
 			vq_err(vq, "Failed to get flags");
 			return true;
 		}
@@ -2363,7 +2423,7 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	if (unlikely(!v))
 		return true;
 
-	if (vhost_get_avail(vq, event, vhost_used_event(vq))) {
+	if (vhost_get_used_event(vq, &event)) {
 		vq_err(vq, "Failed to get used event idx");
 		return true;
 	}
@@ -2408,7 +2468,7 @@ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	if (vq->avail_idx != vq->last_avail_idx)
 		return false;
 
-	r = vhost_get_avail(vq, avail_idx, &vq->avail->idx);
+	r = vhost_get_avail_idx(vq, &avail_idx);
 	if (unlikely(r))
 		return false;
 	vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
@@ -2444,7 +2504,7 @@ bool vhost_enable_notify(struct vhost_dev *dev, 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 = vhost_get_avail(vq, avail_idx, &vq->avail->idx);
+	r = vhost_get_avail_idx(vq, &avail_idx);
 	if (r) {
 		vq_err(vq, "Failed to check avail idx at %p: %d\n",
 		       &vq->avail->idx, r);
-- 
cgit v1.2.3-59-g8ed1b


From 9b5e830b7120847da6c636af2d101f8380e73fa0 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 24 May 2019 04:12:15 -0400
Subject: vhost: rename vq_iotlb_prefetch() to vq_meta_prefetch()

Rename the function to be more accurate since it actually tries to
prefetch vq metadata address in IOTLB. And this will be used by
following patch to prefetch metadata virtual addresses.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/net.c   | 4 ++--
 drivers/vhost/vhost.c | 4 ++--
 drivers/vhost/vhost.h | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'drivers/vhost')

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 2d9df786a9d3..3beb401235c0 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -957,7 +957,7 @@ static void handle_tx(struct vhost_net *net)
 	if (!sock)
 		goto out;
 
-	if (!vq_iotlb_prefetch(vq))
+	if (!vq_meta_prefetch(vq))
 		goto out;
 
 	vhost_disable_notify(&net->dev, vq);
@@ -1126,7 +1126,7 @@ static void handle_rx(struct vhost_net *net)
 	if (!sock)
 		goto out;
 
-	if (!vq_iotlb_prefetch(vq))
+	if (!vq_meta_prefetch(vq))
 		goto out;
 
 	vhost_disable_notify(&net->dev, vq);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index b89faedbb9bd..a0f2fbf35a27 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1331,7 +1331,7 @@ static bool iotlb_access_ok(struct vhost_virtqueue *vq,
 	return true;
 }
 
-int vq_iotlb_prefetch(struct vhost_virtqueue *vq)
+int vq_meta_prefetch(struct vhost_virtqueue *vq)
 {
 	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 	unsigned int num = vq->num;
@@ -1350,7 +1350,7 @@ int vq_iotlb_prefetch(struct vhost_virtqueue *vq)
 			       num * sizeof(*vq->used->ring) + s,
 			       VHOST_ADDR_USED);
 }
-EXPORT_SYMBOL_GPL(vq_iotlb_prefetch);
+EXPORT_SYMBOL_GPL(vq_meta_prefetch);
 
 /* Can we log writes? */
 /* Caller should have device mutex but not vq mutex */
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 27a78a9b8cc7..e9ed2722b633 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -212,7 +212,7 @@ bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 		    unsigned int log_num, u64 len,
 		    struct iovec *iov, int count);
-int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
+int vq_meta_prefetch(struct vhost_virtqueue *vq);
 
 struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);
 void vhost_enqueue_msg(struct vhost_dev *dev,
-- 
cgit v1.2.3-59-g8ed1b


From 4942e8254d93b31ea14cf63a9dfd10a8112caafa Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 24 May 2019 04:12:16 -0400
Subject: vhost: introduce helpers to get the size of metadata area

To avoid code duplication since it will be used by kernel VA prefetching.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vhost.c | 51 +++++++++++++++++++++++++++++++++------------------
 1 file changed, 33 insertions(+), 18 deletions(-)

(limited to 'drivers/vhost')

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a0f2fbf35a27..30afc79d551e 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -428,6 +428,32 @@ bool vhost_exceeds_weight(struct vhost_virtqueue *vq,
 }
 EXPORT_SYMBOL_GPL(vhost_exceeds_weight);
 
+static size_t vhost_get_avail_size(struct vhost_virtqueue *vq,
+				   unsigned int num)
+{
+	size_t event __maybe_unused =
+	       vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
+
+	return sizeof(*vq->avail) +
+	       sizeof(*vq->avail->ring) * num + event;
+}
+
+static size_t vhost_get_used_size(struct vhost_virtqueue *vq,
+				  unsigned int num)
+{
+	size_t event __maybe_unused =
+	       vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
+
+	return sizeof(*vq->used) +
+	       sizeof(*vq->used->ring) * num + event;
+}
+
+static size_t vhost_get_desc_size(struct vhost_virtqueue *vq,
+				  unsigned int num)
+{
+	return sizeof(*vq->desc) * num;
+}
+
 void vhost_dev_init(struct vhost_dev *dev,
 		    struct vhost_virtqueue **vqs, int nvqs,
 		    int iov_limit, int weight, int byte_weight)
@@ -1275,13 +1301,9 @@ static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
 			 struct vring_used __user *used)
 
 {
-	size_t s __maybe_unused = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
-
-	return access_ok(desc, num * sizeof *desc) &&
-	       access_ok(avail,
-			 sizeof *avail + num * sizeof *avail->ring + s) &&
-	       access_ok(used,
-			sizeof *used + num * sizeof *used->ring + s);
+	return access_ok(desc, vhost_get_desc_size(vq, num)) &&
+	       access_ok(avail, vhost_get_avail_size(vq, num)) &&
+	       access_ok(used, vhost_get_used_size(vq, num));
 }
 
 static void vhost_vq_meta_update(struct vhost_virtqueue *vq,
@@ -1333,22 +1355,18 @@ static bool iotlb_access_ok(struct vhost_virtqueue *vq,
 
 int vq_meta_prefetch(struct vhost_virtqueue *vq)
 {
-	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 	unsigned int num = vq->num;
 
 	if (!vq->iotlb)
 		return 1;
 
 	return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
-			       num * sizeof(*vq->desc), VHOST_ADDR_DESC) &&
+			       vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) &&
 	       iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail,
-			       sizeof *vq->avail +
-			       num * sizeof(*vq->avail->ring) + s,
+			       vhost_get_avail_size(vq, num),
 			       VHOST_ADDR_AVAIL) &&
 	       iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used,
-			       sizeof *vq->used +
-			       num * sizeof(*vq->used->ring) + s,
-			       VHOST_ADDR_USED);
+			       vhost_get_used_size(vq, num), VHOST_ADDR_USED);
 }
 EXPORT_SYMBOL_GPL(vq_meta_prefetch);
 
@@ -1365,13 +1383,10 @@ EXPORT_SYMBOL_GPL(vhost_log_access_ok);
 static bool vq_log_access_ok(struct vhost_virtqueue *vq,
 			     void __user *log_base)
 {
-	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
-
 	return vq_memory_access_ok(log_base, vq->umem,
 				   vhost_has_feature(vq, VHOST_F_LOG_ALL)) &&
 		(!vq->log_used || log_access_ok(log_base, vq->log_addr,
-					sizeof *vq->used +
-					vq->num * sizeof *vq->used->ring + s));
+				  vhost_get_used_size(vq, vq->num)));
 }
 
 /* Can we start vq? */
-- 
cgit v1.2.3-59-g8ed1b


From feebcaeac79ad86fb289ef55fa92f4a97ab8314e Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 24 May 2019 04:12:17 -0400
Subject: vhost: factor out setting vring addr and num

Factoring vring address and num setting which needs special care for
accelerating vq metadata accessing.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vhost.c | 177 +++++++++++++++++++++++++++++---------------------
 1 file changed, 103 insertions(+), 74 deletions(-)

(limited to 'drivers/vhost')

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 30afc79d551e..e27d1da5f979 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1486,6 +1486,104 @@ err:
 	return -EFAULT;
 }
 
+static long vhost_vring_set_num(struct vhost_dev *d,
+				struct vhost_virtqueue *vq,
+				void __user *argp)
+{
+	struct vhost_vring_state s;
+
+	/* Resizing ring with an active backend?
+	 * You don't want to do that. */
+	if (vq->private_data)
+		return -EBUSY;
+
+	if (copy_from_user(&s, argp, sizeof s))
+		return -EFAULT;
+
+	if (!s.num || s.num > 0xffff || (s.num & (s.num - 1)))
+		return -EINVAL;
+	vq->num = s.num;
+
+	return 0;
+}
+
+static long vhost_vring_set_addr(struct vhost_dev *d,
+				 struct vhost_virtqueue *vq,
+				 void __user *argp)
+{
+	struct vhost_vring_addr a;
+
+	if (copy_from_user(&a, argp, sizeof a))
+		return -EFAULT;
+	if (a.flags & ~(0x1 << VHOST_VRING_F_LOG))
+		return -EOPNOTSUPP;
+
+	/* For 32bit, verify that the top 32bits of the user
+	   data are set to zero. */
+	if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
+	    (u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
+	    (u64)(unsigned long)a.avail_user_addr != a.avail_user_addr)
+		return -EFAULT;
+
+	/* Make sure it's safe to cast pointers to vring types. */
+	BUILD_BUG_ON(__alignof__ *vq->avail > VRING_AVAIL_ALIGN_SIZE);
+	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 & (VRING_USED_ALIGN_SIZE - 1)))
+		return -EINVAL;
+
+	/* We only verify access here if backend is configured.
+	 * If it is not, we don't as size might not have been setup.
+	 * We will verify when backend is configured. */
+	if (vq->private_data) {
+		if (!vq_access_ok(vq, vq->num,
+			(void __user *)(unsigned long)a.desc_user_addr,
+			(void __user *)(unsigned long)a.avail_user_addr,
+			(void __user *)(unsigned long)a.used_user_addr))
+			return -EINVAL;
+
+		/* Also validate log access for used ring if enabled. */
+		if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
+			!log_access_ok(vq->log_base, a.log_guest_addr,
+				sizeof *vq->used +
+				vq->num * sizeof *vq->used->ring))
+			return -EINVAL;
+	}
+
+	vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
+	vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
+	vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
+	vq->log_addr = a.log_guest_addr;
+	vq->used = (void __user *)(unsigned long)a.used_user_addr;
+
+	return 0;
+}
+
+static long vhost_vring_set_num_addr(struct vhost_dev *d,
+				     struct vhost_virtqueue *vq,
+				     unsigned int ioctl,
+				     void __user *argp)
+{
+	long r;
+
+	mutex_lock(&vq->mutex);
+
+	switch (ioctl) {
+	case VHOST_SET_VRING_NUM:
+		r = vhost_vring_set_num(d, vq, argp);
+		break;
+	case VHOST_SET_VRING_ADDR:
+		r = vhost_vring_set_addr(d, vq, argp);
+		break;
+	default:
+		BUG();
+	}
+
+	mutex_unlock(&vq->mutex);
+
+	return r;
+}
 long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
 {
 	struct file *eventfp, *filep = NULL;
@@ -1495,7 +1593,6 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
 	struct vhost_virtqueue *vq;
 	struct vhost_vring_state s;
 	struct vhost_vring_file f;
-	struct vhost_vring_addr a;
 	u32 idx;
 	long r;
 
@@ -1508,26 +1605,14 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
 	idx = array_index_nospec(idx, d->nvqs);
 	vq = d->vqs[idx];
 
+	if (ioctl == VHOST_SET_VRING_NUM ||
+	    ioctl == VHOST_SET_VRING_ADDR) {
+		return vhost_vring_set_num_addr(d, vq, ioctl, argp);
+	}
+
 	mutex_lock(&vq->mutex);
 
 	switch (ioctl) {
-	case VHOST_SET_VRING_NUM:
-		/* Resizing ring with an active backend?
-		 * You don't want to do that. */
-		if (vq->private_data) {
-			r = -EBUSY;
-			break;
-		}
-		if (copy_from_user(&s, argp, sizeof s)) {
-			r = -EFAULT;
-			break;
-		}
-		if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) {
-			r = -EINVAL;
-			break;
-		}
-		vq->num = s.num;
-		break;
 	case VHOST_SET_VRING_BASE:
 		/* Moving base with an active backend?
 		 * You don't want to do that. */
@@ -1553,62 +1638,6 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
 		if (copy_to_user(argp, &s, sizeof s))
 			r = -EFAULT;
 		break;
-	case VHOST_SET_VRING_ADDR:
-		if (copy_from_user(&a, argp, sizeof a)) {
-			r = -EFAULT;
-			break;
-		}
-		if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) {
-			r = -EOPNOTSUPP;
-			break;
-		}
-		/* For 32bit, verify that the top 32bits of the user
-		   data are set to zero. */
-		if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
-		    (u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
-		    (u64)(unsigned long)a.avail_user_addr != a.avail_user_addr) {
-			r = -EFAULT;
-			break;
-		}
-
-		/* Make sure it's safe to cast pointers to vring types. */
-		BUILD_BUG_ON(__alignof__ *vq->avail > VRING_AVAIL_ALIGN_SIZE);
-		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 & (VRING_USED_ALIGN_SIZE - 1))) {
-			r = -EINVAL;
-			break;
-		}
-
-		/* We only verify access here if backend is configured.
-		 * If it is not, we don't as size might not have been setup.
-		 * We will verify when backend is configured. */
-		if (vq->private_data) {
-			if (!vq_access_ok(vq, vq->num,
-				(void __user *)(unsigned long)a.desc_user_addr,
-				(void __user *)(unsigned long)a.avail_user_addr,
-				(void __user *)(unsigned long)a.used_user_addr)) {
-				r = -EINVAL;
-				break;
-			}
-
-			/* Also validate log access for used ring if enabled. */
-			if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
-			    !log_access_ok(vq->log_base, a.log_guest_addr,
-					   sizeof *vq->used +
-					   vq->num * sizeof *vq->used->ring)) {
-				r = -EINVAL;
-				break;
-			}
-		}
-
-		vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
-		vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
-		vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
-		vq->log_addr = a.log_guest_addr;
-		vq->used = (void __user *)(unsigned long)a.used_user_addr;
-		break;
 	case VHOST_SET_VRING_KICK:
 		if (copy_from_user(&f, argp, sizeof f)) {
 			r = -EFAULT;
-- 
cgit v1.2.3-59-g8ed1b


From 7f466032dc9e5a61217f22ea34b2df932786bbfc Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 24 May 2019 04:12:18 -0400
Subject: vhost: access vq metadata through kernel virtual address

It was noticed that the copy_to/from_user() friends that was used to
access virtqueue metdata tends to be very expensive for dataplane
implementation like vhost since it involves lots of software checks,
speculation barriers, hardware feature toggling (e.g SMAP). The
extra cost will be more obvious when transferring small packets since
the time spent on metadata accessing become more significant.

This patch tries to eliminate those overheads by accessing them
through direct mapping of those pages. Invalidation callbacks is
implemented for co-operation with general VM management (swap, KSM,
THP or NUMA balancing). We will try to get the direct mapping of vq
metadata before each round of packet processing if it doesn't
exist. If we fail, we will simplely fallback to copy_to/from_user()
friends.

This invalidation and direct mapping access are synchronized through
spinlock and RCU. All matedata accessing through direct map is
protected by RCU, and the setup or invalidation are done under
spinlock.

This method might does not work for high mem page which requires
temporary mapping so we just fallback to normal
copy_to/from_user() and may not for arch that has virtual tagged cache
since extra cache flushing is needed to eliminate the alias. This will
result complex logic and bad performance. For those archs, this patch
simply go for copy_to/from_user() friends. This is done by ruling out
kernel mapping codes through ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE.

Note that this is only done when device IOTLB is not enabled. We
could use similar method to optimize IOTLB in the future.

Tests shows at most about 23% improvement on TX PPS when using
virtio-user + vhost_net + xdp1 + TAP on 2.6GHz Broadwell:

        SMAP on | SMAP off
Before: 5.2Mpps | 7.1Mpps
After:  6.4Mpps | 8.2Mpps

Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: James Bottomley <James.Bottomley@hansenpartnership.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David Miller <davem@davemloft.net>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: linux-mm@kvack.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-parisc@vger.kernel.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vhost.c | 515 +++++++++++++++++++++++++++++++++++++++++++++++++-
 drivers/vhost/vhost.h |  38 ++++
 2 files changed, 550 insertions(+), 3 deletions(-)

(limited to 'drivers/vhost')

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index e27d1da5f979..dc9301d31f12 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -299,6 +299,160 @@ static void vhost_vq_meta_reset(struct vhost_dev *d)
 		__vhost_vq_meta_reset(d->vqs[i]);
 }
 
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+static void vhost_map_unprefetch(struct vhost_map *map)
+{
+	kfree(map->pages);
+	map->pages = NULL;
+	map->npages = 0;
+	map->addr = NULL;
+}
+
+static void vhost_uninit_vq_maps(struct vhost_virtqueue *vq)
+{
+	struct vhost_map *map[VHOST_NUM_ADDRS];
+	int i;
+
+	spin_lock(&vq->mmu_lock);
+	for (i = 0; i < VHOST_NUM_ADDRS; i++) {
+		map[i] = rcu_dereference_protected(vq->maps[i],
+				  lockdep_is_held(&vq->mmu_lock));
+		if (map[i])
+			rcu_assign_pointer(vq->maps[i], NULL);
+	}
+	spin_unlock(&vq->mmu_lock);
+
+	synchronize_rcu();
+
+	for (i = 0; i < VHOST_NUM_ADDRS; i++)
+		if (map[i])
+			vhost_map_unprefetch(map[i]);
+
+}
+
+static void vhost_reset_vq_maps(struct vhost_virtqueue *vq)
+{
+	int i;
+
+	vhost_uninit_vq_maps(vq);
+	for (i = 0; i < VHOST_NUM_ADDRS; i++)
+		vq->uaddrs[i].size = 0;
+}
+
+static bool vhost_map_range_overlap(struct vhost_uaddr *uaddr,
+				     unsigned long start,
+				     unsigned long end)
+{
+	if (unlikely(!uaddr->size))
+		return false;
+
+	return !(end < uaddr->uaddr || start > uaddr->uaddr - 1 + uaddr->size);
+}
+
+static void vhost_invalidate_vq_start(struct vhost_virtqueue *vq,
+				      int index,
+				      unsigned long start,
+				      unsigned long end)
+{
+	struct vhost_uaddr *uaddr = &vq->uaddrs[index];
+	struct vhost_map *map;
+	int i;
+
+	if (!vhost_map_range_overlap(uaddr, start, end))
+		return;
+
+	spin_lock(&vq->mmu_lock);
+	++vq->invalidate_count;
+
+	map = rcu_dereference_protected(vq->maps[index],
+					lockdep_is_held(&vq->mmu_lock));
+	if (map) {
+		if (uaddr->write) {
+			for (i = 0; i < map->npages; i++)
+				set_page_dirty(map->pages[i]);
+		}
+		rcu_assign_pointer(vq->maps[index], NULL);
+	}
+	spin_unlock(&vq->mmu_lock);
+
+	if (map) {
+		synchronize_rcu();
+		vhost_map_unprefetch(map);
+	}
+}
+
+static void vhost_invalidate_vq_end(struct vhost_virtqueue *vq,
+				    int index,
+				    unsigned long start,
+				    unsigned long end)
+{
+	if (!vhost_map_range_overlap(&vq->uaddrs[index], start, end))
+		return;
+
+	spin_lock(&vq->mmu_lock);
+	--vq->invalidate_count;
+	spin_unlock(&vq->mmu_lock);
+}
+
+static int vhost_invalidate_range_start(struct mmu_notifier *mn,
+					const struct mmu_notifier_range *range)
+{
+	struct vhost_dev *dev = container_of(mn, struct vhost_dev,
+					     mmu_notifier);
+	int i, j;
+
+	if (!mmu_notifier_range_blockable(range))
+		return -EAGAIN;
+
+	for (i = 0; i < dev->nvqs; i++) {
+		struct vhost_virtqueue *vq = dev->vqs[i];
+
+		for (j = 0; j < VHOST_NUM_ADDRS; j++)
+			vhost_invalidate_vq_start(vq, j,
+						  range->start,
+						  range->end);
+	}
+
+	return 0;
+}
+
+static void vhost_invalidate_range_end(struct mmu_notifier *mn,
+				       const struct mmu_notifier_range *range)
+{
+	struct vhost_dev *dev = container_of(mn, struct vhost_dev,
+					     mmu_notifier);
+	int i, j;
+
+	for (i = 0; i < dev->nvqs; i++) {
+		struct vhost_virtqueue *vq = dev->vqs[i];
+
+		for (j = 0; j < VHOST_NUM_ADDRS; j++)
+			vhost_invalidate_vq_end(vq, j,
+						range->start,
+						range->end);
+	}
+}
+
+static const struct mmu_notifier_ops vhost_mmu_notifier_ops = {
+	.invalidate_range_start = vhost_invalidate_range_start,
+	.invalidate_range_end = vhost_invalidate_range_end,
+};
+
+static void vhost_init_maps(struct vhost_dev *dev)
+{
+	struct vhost_virtqueue *vq;
+	int i, j;
+
+	dev->mmu_notifier.ops = &vhost_mmu_notifier_ops;
+
+	for (i = 0; i < dev->nvqs; ++i) {
+		vq = dev->vqs[i];
+		for (j = 0; j < VHOST_NUM_ADDRS; j++)
+			RCU_INIT_POINTER(vq->maps[j], NULL);
+	}
+}
+#endif
+
 static void vhost_vq_reset(struct vhost_dev *dev,
 			   struct vhost_virtqueue *vq)
 {
@@ -327,7 +481,11 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->busyloop_timeout = 0;
 	vq->umem = NULL;
 	vq->iotlb = NULL;
+	vq->invalidate_count = 0;
 	__vhost_vq_meta_reset(vq);
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	vhost_reset_vq_maps(vq);
+#endif
 }
 
 static int vhost_worker(void *data)
@@ -477,7 +635,9 @@ void vhost_dev_init(struct vhost_dev *dev,
 	INIT_LIST_HEAD(&dev->read_list);
 	INIT_LIST_HEAD(&dev->pending_list);
 	spin_lock_init(&dev->iotlb_lock);
-
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	vhost_init_maps(dev);
+#endif
 
 	for (i = 0; i < dev->nvqs; ++i) {
 		vq = dev->vqs[i];
@@ -486,6 +646,7 @@ void vhost_dev_init(struct vhost_dev *dev,
 		vq->heads = NULL;
 		vq->dev = dev;
 		mutex_init(&vq->mutex);
+		spin_lock_init(&vq->mmu_lock);
 		vhost_vq_reset(dev, vq);
 		if (vq->handle_kick)
 			vhost_poll_init(&vq->poll, vq->handle_kick,
@@ -565,7 +726,18 @@ long vhost_dev_set_owner(struct vhost_dev *dev)
 	if (err)
 		goto err_cgroup;
 
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	err = mmu_notifier_register(&dev->mmu_notifier, dev->mm);
+	if (err)
+		goto err_mmu_notifier;
+#endif
+
 	return 0;
+
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+err_mmu_notifier:
+	vhost_dev_free_iovecs(dev);
+#endif
 err_cgroup:
 	kthread_stop(worker);
 	dev->worker = NULL;
@@ -656,6 +828,107 @@ static void vhost_clear_msg(struct vhost_dev *dev)
 	spin_unlock(&dev->iotlb_lock);
 }
 
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+static void vhost_setup_uaddr(struct vhost_virtqueue *vq,
+			      int index, unsigned long uaddr,
+			      size_t size, bool write)
+{
+	struct vhost_uaddr *addr = &vq->uaddrs[index];
+
+	addr->uaddr = uaddr;
+	addr->size = size;
+	addr->write = write;
+}
+
+static void vhost_setup_vq_uaddr(struct vhost_virtqueue *vq)
+{
+	vhost_setup_uaddr(vq, VHOST_ADDR_DESC,
+			  (unsigned long)vq->desc,
+			  vhost_get_desc_size(vq, vq->num),
+			  false);
+	vhost_setup_uaddr(vq, VHOST_ADDR_AVAIL,
+			  (unsigned long)vq->avail,
+			  vhost_get_avail_size(vq, vq->num),
+			  false);
+	vhost_setup_uaddr(vq, VHOST_ADDR_USED,
+			  (unsigned long)vq->used,
+			  vhost_get_used_size(vq, vq->num),
+			  true);
+}
+
+static int vhost_map_prefetch(struct vhost_virtqueue *vq,
+			       int index)
+{
+	struct vhost_map *map;
+	struct vhost_uaddr *uaddr = &vq->uaddrs[index];
+	struct page **pages;
+	int npages = DIV_ROUND_UP(uaddr->size, PAGE_SIZE);
+	int npinned;
+	void *vaddr, *v;
+	int err;
+	int i;
+
+	spin_lock(&vq->mmu_lock);
+
+	err = -EFAULT;
+	if (vq->invalidate_count)
+		goto err;
+
+	err = -ENOMEM;
+	map = kmalloc(sizeof(*map), GFP_ATOMIC);
+	if (!map)
+		goto err;
+
+	pages = kmalloc_array(npages, sizeof(struct page *), GFP_ATOMIC);
+	if (!pages)
+		goto err_pages;
+
+	err = EFAULT;
+	npinned = __get_user_pages_fast(uaddr->uaddr, npages,
+					uaddr->write, pages);
+	if (npinned > 0)
+		release_pages(pages, npinned);
+	if (npinned != npages)
+		goto err_gup;
+
+	for (i = 0; i < npinned; i++)
+		if (PageHighMem(pages[i]))
+			goto err_gup;
+
+	vaddr = v = page_address(pages[0]);
+
+	/* For simplicity, fallback to userspace address if VA is not
+	 * contigious.
+	 */
+	for (i = 1; i < npinned; i++) {
+		v += PAGE_SIZE;
+		if (v != page_address(pages[i]))
+			goto err_gup;
+	}
+
+	map->addr = vaddr + (uaddr->uaddr & (PAGE_SIZE - 1));
+	map->npages = npages;
+	map->pages = pages;
+
+	rcu_assign_pointer(vq->maps[index], map);
+	/* No need for a synchronize_rcu(). This function should be
+	 * called by dev->worker so we are serialized with all
+	 * readers.
+	 */
+	spin_unlock(&vq->mmu_lock);
+
+	return 0;
+
+err_gup:
+	kfree(pages);
+err_pages:
+	kfree(map);
+err:
+	spin_unlock(&vq->mmu_lock);
+	return err;
+}
+#endif
+
 void vhost_dev_cleanup(struct vhost_dev *dev)
 {
 	int i;
@@ -685,8 +958,16 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 		kthread_stop(dev->worker);
 		dev->worker = NULL;
 	}
-	if (dev->mm)
+	if (dev->mm) {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+		mmu_notifier_unregister(&dev->mmu_notifier, dev->mm);
+#endif
 		mmput(dev->mm);
+	}
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	for (i = 0; i < dev->nvqs; i++)
+		vhost_uninit_vq_maps(dev->vqs[i]);
+#endif
 	dev->mm = NULL;
 }
 EXPORT_SYMBOL_GPL(vhost_dev_cleanup);
@@ -915,6 +1196,26 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
 
 static inline int vhost_put_avail_event(struct vhost_virtqueue *vq)
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_used *used;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+
+		map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
+		if (likely(map)) {
+			used = map->addr;
+			*((__virtio16 *)&used->ring[vq->num]) =
+				cpu_to_vhost16(vq, vq->avail_idx);
+			rcu_read_unlock();
+			return 0;
+		}
+
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
 			      vhost_avail_event(vq));
 }
@@ -923,6 +1224,27 @@ static inline int vhost_put_used(struct vhost_virtqueue *vq,
 				 struct vring_used_elem *head, int idx,
 				 int count)
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_used *used;
+	size_t size;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+
+		map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
+		if (likely(map)) {
+			used = map->addr;
+			size = count * sizeof(*head);
+			memcpy(used->ring + idx, head, size);
+			rcu_read_unlock();
+			return 0;
+		}
+
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_copy_to_user(vq, vq->used->ring + idx, head,
 				  count * sizeof(*head));
 }
@@ -930,6 +1252,25 @@ static inline int vhost_put_used(struct vhost_virtqueue *vq,
 static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
 
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_used *used;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+
+		map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
+		if (likely(map)) {
+			used = map->addr;
+			used->flags = cpu_to_vhost16(vq, vq->used_flags);
+			rcu_read_unlock();
+			return 0;
+		}
+
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
 			      &vq->used->flags);
 }
@@ -937,6 +1278,25 @@ static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
 static inline int vhost_put_used_idx(struct vhost_virtqueue *vq)
 
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_used *used;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+
+		map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
+		if (likely(map)) {
+			used = map->addr;
+			used->idx = cpu_to_vhost16(vq, vq->last_used_idx);
+			rcu_read_unlock();
+			return 0;
+		}
+
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
 			      &vq->used->idx);
 }
@@ -982,12 +1342,50 @@ static void vhost_dev_unlock_vqs(struct vhost_dev *d)
 static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq,
 				      __virtio16 *idx)
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_avail *avail;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+
+		map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]);
+		if (likely(map)) {
+			avail = map->addr;
+			*idx = avail->idx;
+			rcu_read_unlock();
+			return 0;
+		}
+
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_get_avail(vq, *idx, &vq->avail->idx);
 }
 
 static inline int vhost_get_avail_head(struct vhost_virtqueue *vq,
 				       __virtio16 *head, int idx)
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_avail *avail;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+
+		map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]);
+		if (likely(map)) {
+			avail = map->addr;
+			*head = avail->ring[idx & (vq->num - 1)];
+			rcu_read_unlock();
+			return 0;
+		}
+
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_get_avail(vq, *head,
 			       &vq->avail->ring[idx & (vq->num - 1)]);
 }
@@ -995,24 +1393,98 @@ static inline int vhost_get_avail_head(struct vhost_virtqueue *vq,
 static inline int vhost_get_avail_flags(struct vhost_virtqueue *vq,
 					__virtio16 *flags)
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_avail *avail;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+
+		map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]);
+		if (likely(map)) {
+			avail = map->addr;
+			*flags = avail->flags;
+			rcu_read_unlock();
+			return 0;
+		}
+
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_get_avail(vq, *flags, &vq->avail->flags);
 }
 
 static inline int vhost_get_used_event(struct vhost_virtqueue *vq,
 				       __virtio16 *event)
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_avail *avail;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+		map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]);
+		if (likely(map)) {
+			avail = map->addr;
+			*event = (__virtio16)avail->ring[vq->num];
+			rcu_read_unlock();
+			return 0;
+		}
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_get_avail(vq, *event, vhost_used_event(vq));
 }
 
 static inline int vhost_get_used_idx(struct vhost_virtqueue *vq,
 				     __virtio16 *idx)
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_used *used;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+
+		map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
+		if (likely(map)) {
+			used = map->addr;
+			*idx = used->idx;
+			rcu_read_unlock();
+			return 0;
+		}
+
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_get_used(vq, *idx, &vq->used->idx);
 }
 
 static inline int vhost_get_desc(struct vhost_virtqueue *vq,
 				 struct vring_desc *desc, int idx)
 {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	struct vhost_map *map;
+	struct vring_desc *d;
+
+	if (!vq->iotlb) {
+		rcu_read_lock();
+
+		map = rcu_dereference(vq->maps[VHOST_ADDR_DESC]);
+		if (likely(map)) {
+			d = map->addr;
+			*desc = *(d + idx);
+			rcu_read_unlock();
+			return 0;
+		}
+
+		rcu_read_unlock();
+	}
+#endif
+
 	return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc));
 }
 
@@ -1353,12 +1825,32 @@ static bool iotlb_access_ok(struct vhost_virtqueue *vq,
 	return true;
 }
 
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+static void vhost_vq_map_prefetch(struct vhost_virtqueue *vq)
+{
+	struct vhost_map __rcu *map;
+	int i;
+
+	for (i = 0; i < VHOST_NUM_ADDRS; i++) {
+		rcu_read_lock();
+		map = rcu_dereference(vq->maps[i]);
+		rcu_read_unlock();
+		if (unlikely(!map))
+			vhost_map_prefetch(vq, i);
+	}
+}
+#endif
+
 int vq_meta_prefetch(struct vhost_virtqueue *vq)
 {
 	unsigned int num = vq->num;
 
-	if (!vq->iotlb)
+	if (!vq->iotlb) {
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+		vhost_vq_map_prefetch(vq);
+#endif
 		return 1;
+	}
 
 	return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
 			       vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) &&
@@ -1569,6 +2061,16 @@ static long vhost_vring_set_num_addr(struct vhost_dev *d,
 
 	mutex_lock(&vq->mutex);
 
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	/* Unregister MMU notifer to allow invalidation callback
+	 * can access vq->uaddrs[] without holding a lock.
+	 */
+	if (d->mm)
+		mmu_notifier_unregister(&d->mmu_notifier, d->mm);
+
+	vhost_uninit_vq_maps(vq);
+#endif
+
 	switch (ioctl) {
 	case VHOST_SET_VRING_NUM:
 		r = vhost_vring_set_num(d, vq, argp);
@@ -1580,6 +2082,13 @@ static long vhost_vring_set_num_addr(struct vhost_dev *d,
 		BUG();
 	}
 
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	vhost_setup_vq_uaddr(vq);
+
+	if (d->mm)
+		mmu_notifier_register(&d->mmu_notifier, d->mm);
+#endif
+
 	mutex_unlock(&vq->mutex);
 
 	return r;
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index e9ed2722b633..c5d950cf7627 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -12,6 +12,9 @@
 #include <linux/virtio_config.h>
 #include <linux/virtio_ring.h>
 #include <linux/atomic.h>
+#include <linux/pagemap.h>
+#include <linux/mmu_notifier.h>
+#include <asm/cacheflush.h>
 
 struct vhost_work;
 typedef void (*vhost_work_fn_t)(struct vhost_work *work);
@@ -80,6 +83,21 @@ enum vhost_uaddr_type {
 	VHOST_NUM_ADDRS = 3,
 };
 
+struct vhost_map {
+	int npages;
+	void *addr;
+	struct page **pages;
+};
+
+struct vhost_uaddr {
+	unsigned long uaddr;
+	size_t size;
+	bool write;
+};
+
+#define VHOST_ARCH_CAN_ACCEL_UACCESS defined(CONFIG_MMU_NOTIFIER) && \
+	ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+
 /* The virtqueue structure describes a queue attached to a device. */
 struct vhost_virtqueue {
 	struct vhost_dev *dev;
@@ -90,7 +108,22 @@ struct vhost_virtqueue {
 	struct vring_desc __user *desc;
 	struct vring_avail __user *avail;
 	struct vring_used __user *used;
+
+#if VHOST_ARCH_CAN_ACCEL_UACCESS
+	/* Read by memory accessors, modified by meta data
+	 * prefetching, MMU notifier and vring ioctl().
+	 * Synchonrized through mmu_lock (writers) and RCU (writers
+	 * and readers).
+	 */
+	struct vhost_map __rcu *maps[VHOST_NUM_ADDRS];
+	/* Read by MMU notifier, modified by vring ioctl(),
+	 * synchronized through MMU notifier
+	 * registering/unregistering.
+	 */
+	struct vhost_uaddr uaddrs[VHOST_NUM_ADDRS];
+#endif
 	const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
+
 	struct file *kick;
 	struct eventfd_ctx *call_ctx;
 	struct eventfd_ctx *error_ctx;
@@ -145,6 +178,8 @@ struct vhost_virtqueue {
 	bool user_be;
 #endif
 	u32 busyloop_timeout;
+	spinlock_t mmu_lock;
+	int invalidate_count;
 };
 
 struct vhost_msg_node {
@@ -158,6 +193,9 @@ struct vhost_msg_node {
 
 struct vhost_dev {
 	struct mm_struct *mm;
+#ifdef CONFIG_MMU_NOTIFIER
+	struct mmu_notifier mmu_notifier;
+#endif
 	struct mutex mutex;
 	struct vhost_virtqueue **vqs;
 	int nvqs;
-- 
cgit v1.2.3-59-g8ed1b


From 0b4a7092ffe568a55bf8f3cefdf79ff666586d91 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 6 Jun 2019 17:17:36 -0400
Subject: vhost: fix clang build warning

Clang warns:

  drivers/vhost/vhost.c:2085:5: warning: macro expansion producing
  'defined' has undefined behavior [-Wexpansion-to-defined]
  #if VHOST_ARCH_CAN_ACCEL_UACCESS
      ^
  drivers/vhost/vhost.h:98:38: note: expanded from macro
  'VHOST_ARCH_CAN_ACCEL_UACCESS'
  #define VHOST_ARCH_CAN_ACCEL_UACCESS defined(CONFIG_MMU_NOTIFIER) && \
                                       ^

It's being pedantic for the sake of portability, but the fix is easy
enough.

Rework the definition of VHOST_ARCH_CAN_ACCEL_UACCESS to expand to a constant.

Fixes: 7f466032dc9e ("vhost: access vq metadata through kernel virtual address")
Link: https://github.com/ClangBuiltLinux/linux/issues/508
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
---
 drivers/vhost/vhost.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'drivers/vhost')

diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index c5d950cf7627..819296332913 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -95,8 +95,11 @@ struct vhost_uaddr {
 	bool write;
 };
 
-#define VHOST_ARCH_CAN_ACCEL_UACCESS defined(CONFIG_MMU_NOTIFIER) && \
-	ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+#if defined(CONFIG_MMU_NOTIFIER) && ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+#define VHOST_ARCH_CAN_ACCEL_UACCESS 1
+#else
+#define VHOST_ARCH_CAN_ACCEL_UACCESS 0
+#endif
 
 /* The virtqueue structure describes a queue attached to a device. */
 struct vhost_virtqueue {
-- 
cgit v1.2.3-59-g8ed1b