kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Xie Yongji <xieyongji@bytedance.com>
To: mst@redhat.com, jasowang@redhat.com, stefanha@redhat.com,
	sgarzare@redhat.com, parav@nvidia.com, bob.liu@oracle.com,
	hch@infradead.org, rdunlap@infradead.org, willy@infradead.org,
	viro@zeniv.linux.org.uk, axboe@kernel.dk, bcrl@kvack.org,
	corbet@lwn.net
Cc: virtualization@lists.linux-foundation.org,
	netdev@vger.kernel.org, kvm@vger.kernel.org, linux-aio@kvack.org,
	linux-fsdevel@vger.kernel.org
Subject: [RFC v3 05/11] vdpa: shared virtual addressing support
Date: Tue, 19 Jan 2021 12:59:14 +0800	[thread overview]
Message-ID: <20210119045920.447-6-xieyongji@bytedance.com> (raw)
In-Reply-To: <20210119045920.447-1-xieyongji@bytedance.com>

This patches introduces SVA (Shared Virtual Addressing)
support for vDPA device. During vDPA device allocation,
vDPA device driver needs to indicate whether SVA is
supported by the device. Then vhost-vdpa bus driver
will not pin user page and transfer userspace virtual
address instead of physical address during DMA mapping.

Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Xie Yongji <xieyongji@bytedance.com>
---
 drivers/vdpa/ifcvf/ifcvf_main.c   |  2 +-
 drivers/vdpa/mlx5/net/mlx5_vnet.c |  2 +-
 drivers/vdpa/vdpa.c               |  5 ++++-
 drivers/vdpa/vdpa_sim/vdpa_sim.c  |  3 ++-
 drivers/vhost/vdpa.c              | 35 +++++++++++++++++++++++------------
 include/linux/vdpa.h              | 10 +++++++---
 6 files changed, 38 insertions(+), 19 deletions(-)

diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 23474af7da40..95c4601f82f5 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -439,7 +439,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
 				    dev, &ifc_vdpa_ops,
-				    IFCVF_MAX_QUEUE_PAIRS * 2, NULL);
+				    IFCVF_MAX_QUEUE_PAIRS * 2, NULL, false);
 	if (adapter == NULL) {
 		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
 		return -ENOMEM;
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 77595c81488d..05988d6907f2 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1959,7 +1959,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
 
 	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
-				 2 * mlx5_vdpa_max_qps(max_vqs), NULL);
+				 2 * mlx5_vdpa_max_qps(max_vqs), NULL, false);
 	if (IS_ERR(ndev))
 		return PTR_ERR(ndev);
 
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 32bd48baffab..50cab930b2e5 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -72,6 +72,7 @@ static void vdpa_release_dev(struct device *d)
  * @nvqs: number of virtqueues supported by this device
  * @size: size of the parent structure that contains private data
  * @name: name of the vdpa device; optional.
+ * @sva: indicate whether SVA (Shared Virtual Addressing) is supported
  *
  * Driver should use vdpa_alloc_device() wrapper macro instead of
  * using this directly.
@@ -81,7 +82,8 @@ static void vdpa_release_dev(struct device *d)
  */
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					int nvqs, size_t size, const char *name)
+					int nvqs, size_t size, const char *name,
+					bool sva)
 {
 	struct vdpa_device *vdev;
 	int err = -EINVAL;
@@ -108,6 +110,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	vdev->config = config;
 	vdev->features_valid = false;
 	vdev->nvqs = nvqs;
+	vdev->sva = sva;
 
 	if (name)
 		err = dev_set_name(&vdev->dev, "%s", name);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 85776e4e6749..03c796873a6b 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -367,7 +367,8 @@ static struct vdpasim *vdpasim_create(const char *name)
 	else
 		ops = &vdpasim_net_config_ops;
 
-	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM, name);
+	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
+				VDPASIM_VQ_NUM, name, false);
 	if (!vdpasim)
 		goto err_alloc;
 
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 4a241d380c40..36b6950ba37f 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -486,21 +486,25 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
 {
 	struct vhost_dev *dev = &v->vdev;
+	struct vdpa_device *vdpa = v->vdpa;
 	struct vhost_iotlb *iotlb = dev->iotlb;
 	struct vhost_iotlb_map *map;
 	struct page *page;
 	unsigned long pfn, pinned;
 
 	while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) {
-		pinned = map->size >> PAGE_SHIFT;
-		for (pfn = map->addr >> PAGE_SHIFT;
-		     pinned > 0; pfn++, pinned--) {
-			page = pfn_to_page(pfn);
-			if (map->perm & VHOST_ACCESS_WO)
-				set_page_dirty_lock(page);
-			unpin_user_page(page);
+		if (!vdpa->sva) {
+			pinned = map->size >> PAGE_SHIFT;
+			for (pfn = map->addr >> PAGE_SHIFT;
+			     pinned > 0; pfn++, pinned--) {
+				page = pfn_to_page(pfn);
+				if (map->perm & VHOST_ACCESS_WO)
+					set_page_dirty_lock(page);
+				unpin_user_page(page);
+			}
+			atomic64_sub(map->size >> PAGE_SHIFT,
+					&dev->mm->pinned_vm);
 		}
-		atomic64_sub(map->size >> PAGE_SHIFT, &dev->mm->pinned_vm);
 		vhost_iotlb_map_free(iotlb, map);
 	}
 }
@@ -558,13 +562,15 @@ static int vhost_vdpa_map(struct vhost_vdpa *v,
 		r = iommu_map(v->domain, iova, pa, size,
 			      perm_to_iommu_flags(perm));
 	}
-
-	if (r)
+	if (r) {
 		vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1);
-	else
+		return r;
+	}
+
+	if (!vdpa->sva)
 		atomic64_add(size >> PAGE_SHIFT, &dev->mm->pinned_vm);
 
-	return r;
+	return 0;
 }
 
 static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
@@ -589,6 +595,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
 					   struct vhost_iotlb_msg *msg)
 {
 	struct vhost_dev *dev = &v->vdev;
+	struct vdpa_device *vdpa = v->vdpa;
 	struct vhost_iotlb *iotlb = dev->iotlb;
 	struct page **page_list;
 	unsigned long list_size = PAGE_SIZE / sizeof(struct page *);
@@ -607,6 +614,10 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
 				    msg->iova + msg->size - 1))
 		return -EEXIST;
 
+	if (vdpa->sva)
+		return vhost_vdpa_map(v, msg->iova, msg->size,
+				      msg->uaddr, msg->perm);
+
 	/* Limit the use of memory for bookkeeping */
 	page_list = (struct page **) __get_free_page(GFP_KERNEL);
 	if (!page_list)
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index cb5a3d847af3..f86869651614 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -44,6 +44,7 @@ struct vdpa_parent_dev;
  * @config: the configuration ops for this device.
  * @index: device index
  * @features_valid: were features initialized? for legacy guests
+ * @sva: indicate whether SVA (Shared Virtual Addressing) is supported
  * @nvqs: maximum number of supported virtqueues
  * @pdev: parent device pointer; caller must setup when registering device as part
  *	  of dev_add() parentdev ops callback before invoking _vdpa_register_device().
@@ -54,6 +55,7 @@ struct vdpa_device {
 	const struct vdpa_config_ops *config;
 	unsigned int index;
 	bool features_valid;
+	bool sva;
 	int nvqs;
 	struct vdpa_parent_dev *pdev;
 };
@@ -250,14 +252,16 @@ struct vdpa_config_ops {
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					int nvqs, size_t size, const char *name);
+					int nvqs, size_t size,
+					const char *name, bool sva);
 
-#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs, name)   \
+#define vdpa_alloc_device(dev_struct, member, parent, config, \
+			  nvqs, name, sva) \
 			  container_of(__vdpa_alloc_device( \
 				       parent, config, nvqs, \
 				       sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
-				       dev_struct, member)), name), \
+				       dev_struct, member)), name, sva), \
 				       dev_struct, member)
 
 int vdpa_register_device(struct vdpa_device *vdev);
-- 
2.11.0


  parent reply	other threads:[~2021-01-19  5:23 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-19  4:59 [RFC v3 00/11] Introduce VDUSE - vDPA Device in Userspace Xie Yongji
2021-01-19  4:59 ` [RFC v3 01/11] eventfd: track eventfd_signal() recursion depth separately in different cases Xie Yongji
2021-01-20  4:24   ` Jason Wang
2021-01-20  6:52     ` Yongji Xie
2021-01-27  3:37       ` Jason Wang
2021-01-27  9:11         ` Yongji Xie
2021-01-28  3:04           ` Jason Wang
2021-01-28  3:08             ` Jens Axboe
2021-01-28  5:12               ` Yongji Xie
2021-01-28  3:52             ` Yongji Xie
2021-01-28  4:31               ` Jason Wang
2021-01-28  6:08                 ` Yongji Xie
2021-01-19  4:59 ` [RFC v3 02/11] eventfd: Increase the recursion depth of eventfd_signal() Xie Yongji
2021-01-19  4:59 ` [RFC v3 03/11] vdpa: Remove the restriction that only supports virtio-net devices Xie Yongji
2021-01-20  3:46   ` Jason Wang
2021-01-20  6:46     ` Yongji Xie
2021-01-20 11:08     ` Stefano Garzarella
2021-01-27  3:33       ` Jason Wang
2021-01-27  8:57         ` Stefano Garzarella
2021-01-28  3:11           ` Jason Wang
     [not found]             ` <20210129150359.caitcskrfhqed73z@steredhat>
2021-01-30 11:33               ` Yongji Xie
2021-02-01 11:05                 ` Stefano Garzarella
2021-01-27  8:59   ` Stefano Garzarella
2021-01-27  9:05     ` Yongji Xie
2021-01-19  4:59 ` [RFC v3 04/11] vhost-vdpa: protect concurrent access to vhost device iotlb Xie Yongji
2021-01-20  3:44   ` Jason Wang
2021-01-20  6:44     ` Yongji Xie
2021-01-19  4:59 ` Xie Yongji [this message]
2021-01-20  5:55   ` [RFC v3 05/11] vdpa: shared virtual addressing support Jason Wang
2021-01-20  7:10     ` Yongji Xie
2021-01-27  3:43       ` Jason Wang
2021-01-19  4:59 ` [RFC v3 06/11] vhost-vdpa: Add an opaque pointer for vhost IOTLB Xie Yongji
2021-01-20  6:24   ` Jason Wang
2021-01-20  7:52     ` Yongji Xie
2021-01-27  3:51       ` Jason Wang
2021-01-27  9:27         ` Yongji Xie
2021-01-19  5:07 ` [RFC v3 07/11] vdpa: Pass the netlink attributes to ops.dev_add() Xie Yongji
2021-01-19  5:07   ` [RFC v3 08/11] vduse: Introduce VDUSE - vDPA Device in Userspace Xie Yongji
2021-01-19 14:53     ` Jonathan Corbet
2021-01-20  2:25       ` Yongji Xie
2021-01-19 17:53     ` Randy Dunlap
2021-01-20  2:42       ` Yongji Xie
2021-01-26  8:08     ` Jason Wang
2021-01-27  8:50       ` Yongji Xie
2021-01-28  4:27         ` Jason Wang
2021-01-28  6:03           ` Yongji Xie
2021-01-28  6:14             ` Jason Wang
2021-01-28  6:43               ` Yongji Xie
2021-01-26  8:19     ` Jason Wang
2021-01-27  8:59       ` Yongji Xie
2021-01-19  5:07   ` [RFC v3 09/11] vduse: Add VDUSE_GET_DEV ioctl Xie Yongji
2021-01-19  5:07   ` [RFC v3 10/11] vduse: grab the module's references until there is no vduse device Xie Yongji
2021-01-26  8:09     ` Jason Wang
2021-01-27  8:51       ` Yongji Xie
2021-01-19  5:07   ` [RFC v3 11/11] vduse: Introduce a workqueue for irq injection Xie Yongji
2021-01-26  8:17     ` Jason Wang
2021-01-27  9:00       ` Yongji Xie

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210119045920.447-6-xieyongji@bytedance.com \
    --to=xieyongji@bytedance.com \
    --cc=axboe@kernel.dk \
    --cc=bcrl@kvack.org \
    --cc=bob.liu@oracle.com \
    --cc=corbet@lwn.net \
    --cc=hch@infradead.org \
    --cc=jasowang@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-aio@kvack.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=parav@nvidia.com \
    --cc=rdunlap@infradead.org \
    --cc=sgarzare@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).