lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20190423055420.26408-7-jasowang@redhat.com>
Date:   Tue, 23 Apr 2019 01:54:20 -0400
From:   Jason Wang <jasowang@...hat.com>
To:     mst@...hat.com, jasowang@...hat.com, kvm@...r.kernel.org,
        virtualization@...ts.linux-foundation.org, netdev@...r.kernel.org,
        linux-kernel@...r.kernel.org
Cc:     peterx@...hat.com, aarcange@...hat.com,
        James.Bottomley@...senpartnership.com, hch@...radead.org,
        davem@...emloft.net, jglisse@...hat.com, linux-mm@...ck.org,
        linux-arm-kernel@...ts.infradead.org, linux-parisc@...r.kernel.org,
        christophe.de.dinechin@...il.com, jrdr.linux@...il.com
Subject: [RFC PATCH V3 6/6] 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@...hat.com>
Cc: James Bottomley <James.Bottomley@...senpartnership.com>
Cc: Christoph Hellwig <hch@...radead.org>
Cc: David Miller <davem@...emloft.net>
Cc: Jerome Glisse <jglisse@...hat.com>
Cc: linux-mm@...ck.org
Cc: linux-arm-kernel@...ts.infradead.org
Cc: linux-parisc@...r.kernel.org
Signed-off-by: Jason Wang <jasowang@...hat.com>
---
 drivers/vhost/vhost.c | 517 +++++++++++++++++++++++++++++++++++++++++-
 drivers/vhost/vhost.h |  32 +++
 2 files changed, 546 insertions(+), 3 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c2362ed5839e..a9fe04f0016a 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -299,6 +299,49 @@ static void vhost_vq_meta_reset(struct vhost_dev *d)
 		__vhost_vq_meta_reset(d->vqs[i]);
 }
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+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]);
+
+}
+#endif
+
+static void vhost_reset_vq_maps(struct vhost_virtqueue *vq)
+{
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	int i;
+
+	vhost_uninit_vq_maps(vq);
+	for (i = 0; i < VHOST_NUM_ADDRS; i++)
+		vq->uaddrs[i].size = 0;
+#endif
+}
+
 static void vhost_vq_reset(struct vhost_dev *dev,
 			   struct vhost_virtqueue *vq)
 {
@@ -327,7 +370,9 @@ 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);
+	vhost_reset_vq_maps(vq);
 }
 
 static int vhost_worker(void *data)
@@ -439,6 +484,123 @@ static size_t vhost_get_desc_size(struct vhost_virtqueue *vq,
 	return sizeof(*vq->desc) * num;
 }
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 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 (!range->blockable)
+		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,
+};
+#endif
+
+static void vhost_init_maps(struct vhost_dev *dev)
+{
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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
+}
+
 void vhost_dev_init(struct vhost_dev *dev,
 		    struct vhost_virtqueue **vqs, int nvqs, int iov_limit)
 {
@@ -459,7 +621,7 @@ 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);
-
+	vhost_init_maps(dev);
 
 	for (i = 0; i < dev->nvqs; ++i) {
 		vq = dev->vqs[i];
@@ -468,6 +630,7 @@ 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,
@@ -547,7 +710,18 @@ long vhost_dev_set_owner(struct vhost_dev *dev)
 	if (err)
 		goto err_cgroup;
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	err = mmu_notifier_register(&dev->mmu_notifier, dev->mm);
+	if (err)
+		goto err_mmu_notifier;
+#endif
+
 	return 0;
+
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+err_mmu_notifier:
+	vhost_dev_free_iovecs(dev);
+#endif
 err_cgroup:
 	kthread_stop(worker);
 	dev->worker = NULL;
@@ -638,6 +812,107 @@ static void vhost_clear_msg(struct vhost_dev *dev)
 	spin_unlock(&dev->iotlb_lock);
 }
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+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;
@@ -667,8 +942,16 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 		kthread_stop(dev->worker);
 		dev->worker = NULL;
 	}
-	if (dev->mm)
+	if (dev->mm) {
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+		mmu_notifier_unregister(&dev->mmu_notifier, dev->mm);
+#endif
 		mmput(dev->mm);
+	}
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	for (i = 0; i < dev->nvqs; i++)
+		vhost_uninit_vq_maps(dev->vqs[i]);
+#endif
 	dev->mm = NULL;
 }
 EXPORT_SYMBOL_GPL(vhost_dev_cleanup);
@@ -897,6 +1180,26 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
 
 static inline int vhost_put_avail_event(struct vhost_virtqueue *vq)
 {
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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));
 }
@@ -905,6 +1208,27 @@ static inline int vhost_put_used(struct vhost_virtqueue *vq,
 				 struct vring_used_elem *head, int idx,
 				 int count)
 {
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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));
 }
@@ -912,6 +1236,25 @@ static inline int vhost_put_used(struct vhost_virtqueue *vq,
 static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
 
 {
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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);
 }
@@ -919,6 +1262,25 @@ static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
 static inline int vhost_put_used_idx(struct vhost_virtqueue *vq)
 
 {
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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);
 }
@@ -964,12 +1326,50 @@ static void vhost_dev_unlock_vqs(struct vhost_dev *d)
 static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq,
 				      __virtio16 *idx)
 {
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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 ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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)]);
 }
@@ -977,24 +1377,98 @@ 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 ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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 ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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 ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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 ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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));
 }
 
@@ -1335,12 +1809,32 @@ static bool iotlb_access_ok(struct vhost_virtqueue *vq,
 	return true;
 }
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+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 ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+		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) &&
@@ -1551,6 +2045,16 @@ static long vhost_vring_set_num_addr(struct vhost_dev *d,
 
 	mutex_lock(&vq->mutex);
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	/* 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);
@@ -1562,6 +2066,13 @@ static long vhost_vring_set_num_addr(struct vhost_dev *d,
 		BUG();
 	}
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	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 7a7fc001265f..f33208b55875 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 +83,18 @@ 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;
+};
+
 /* The virtqueue structure describes a queue attached to a device. */
 struct vhost_virtqueue {
 	struct vhost_dev *dev;
@@ -90,7 +105,21 @@ struct vhost_virtqueue {
 	struct vring_desc __user *desc;
 	struct vring_avail __user *avail;
 	struct vring_used __user *used;
+
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
+	/* 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, write by vring ioctl(), synchronized
+	 * through register/unregister MMU notifier.
+	 */
+	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 +174,8 @@ struct vhost_virtqueue {
 	bool user_be;
 #endif
 	u32 busyloop_timeout;
+	spinlock_t mmu_lock;
+	int invalidate_count;
 };
 
 struct vhost_msg_node {
@@ -158,6 +189,7 @@ struct vhost_msg_node {
 
 struct vhost_dev {
 	struct mm_struct *mm;
+	struct mmu_notifier mmu_notifier;
 	struct mutex mutex;
 	struct vhost_virtqueue **vqs;
 	int nvqs;
-- 
2.18.1

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ