linux-mm.kvack.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, akpm@linux-foundation.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, linux-mm@kvack.org
Subject: [RFC v2 09/13] vduse: Add support for processing vhost iotlb message
Date: Tue, 22 Dec 2020 22:52:17 +0800	[thread overview]
Message-ID: <20201222145221.711-10-xieyongji@bytedance.com> (raw)
In-Reply-To: <20201222145221.711-1-xieyongji@bytedance.com>

To support vhost-vdpa bus driver, we need a way to share the
vhost-vdpa backend process's memory with the userspace VDUSE process.

This patch tries to make use of the vhost iotlb message to achieve
that. We will get the shm file from the iotlb message and pass it
to the userspace VDUSE process.

Signed-off-by: Xie Yongji <xieyongji@bytedance.com>
---
 Documentation/driver-api/vduse.rst |  15 +++-
 drivers/vdpa/vdpa_user/vduse_dev.c | 147 ++++++++++++++++++++++++++++++++++++-
 include/uapi/linux/vduse.h         |  11 +++
 3 files changed, 171 insertions(+), 2 deletions(-)

diff --git a/Documentation/driver-api/vduse.rst b/Documentation/driver-api/vduse.rst
index 623f7b040ccf..48e4b1ba353f 100644
--- a/Documentation/driver-api/vduse.rst
+++ b/Documentation/driver-api/vduse.rst
@@ -46,13 +46,26 @@ The following types of messages are provided by the VDUSE framework now:
 
 - VDUSE_GET_CONFIG: Read from device specific configuration space
 
+- VDUSE_UPDATE_IOTLB: Update the memory mapping in device IOTLB
+
+- VDUSE_INVALIDATE_IOTLB: Invalidate the memory mapping in device IOTLB
+
 Please see include/linux/vdpa.h for details.
 
-In the data path, VDUSE framework implements a MMU-based on-chip IOMMU
+The data path of userspace vDPA device is implemented in different ways
+depending on the vdpa bus to which it is attached.
+
+In virtio-vdpa case, VDUSE framework implements a MMU-based on-chip IOMMU
 driver which supports mapping the kernel dma buffer to a userspace iova
 region dynamically. The userspace iova region can be created by passing
 the userspace vDPA device fd to mmap(2).
 
+In vhost-vdpa case, the dma buffer is reside in a userspace memory region
+which will be shared to the VDUSE userspace processs via the file
+descriptor in VDUSE_UPDATE_IOTLB message. And the corresponding address
+mapping (IOVA of dma buffer <-> VA of the memory region) is also included
+in this message.
+
 Besides, the eventfd mechanism is used to trigger interrupt callbacks and
 receive virtqueue kicks in userspace. The following ioctls on the userspace
 vDPA device fd are provided to support that:
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index b974333ed4e9..d24aaacb6008 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -34,6 +34,7 @@
 
 struct vduse_dev_msg {
 	struct vduse_dev_request req;
+	struct file *iotlb_file;
 	struct vduse_dev_response resp;
 	struct list_head list;
 	wait_queue_head_t waitq;
@@ -325,12 +326,80 @@ static int vduse_dev_set_vq_state(struct vduse_dev *dev,
 	return ret;
 }
 
+static int vduse_dev_update_iotlb(struct vduse_dev *dev, struct file *file,
+				u64 offset, u64 iova, u64 size, u8 perm)
+{
+	struct vduse_dev_msg *msg;
+	int ret;
+
+	if (!size)
+		return -EINVAL;
+
+	msg = vduse_dev_new_msg(dev, VDUSE_UPDATE_IOTLB);
+	msg->req.size = sizeof(struct vduse_iotlb);
+	msg->req.iotlb.offset = offset;
+	msg->req.iotlb.iova = iova;
+	msg->req.iotlb.size = size;
+	msg->req.iotlb.perm = perm;
+	msg->req.iotlb.fd = -1;
+	msg->iotlb_file = get_file(file);
+
+	ret = vduse_dev_msg_sync(dev, msg);
+	vduse_dev_msg_put(msg);
+	fput(file);
+
+	return ret;
+}
+
+static int vduse_dev_invalidate_iotlb(struct vduse_dev *dev,
+					u64 iova, u64 size)
+{
+	struct vduse_dev_msg *msg;
+	int ret;
+
+	if (!size)
+		return -EINVAL;
+
+	msg = vduse_dev_new_msg(dev, VDUSE_INVALIDATE_IOTLB);
+	msg->req.size = sizeof(struct vduse_iotlb);
+	msg->req.iotlb.iova = iova;
+	msg->req.iotlb.size = size;
+
+	ret = vduse_dev_msg_sync(dev, msg);
+	vduse_dev_msg_put(msg);
+
+	return ret;
+}
+
+static unsigned int perm_to_file_flags(u8 perm)
+{
+	unsigned int flags = 0;
+
+	switch (perm) {
+	case VHOST_ACCESS_WO:
+		flags |= O_WRONLY;
+		break;
+	case VHOST_ACCESS_RO:
+		flags |= O_RDONLY;
+		break;
+	case VHOST_ACCESS_RW:
+		flags |= O_RDWR;
+		break;
+	default:
+		WARN(1, "invalidate vhost IOTLB permission\n");
+		break;
+	}
+
+	return flags;
+}
+
 static ssize_t vduse_dev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	struct vduse_dev *dev = file->private_data;
 	struct vduse_dev_msg *msg;
-	int size = sizeof(struct vduse_dev_request);
+	unsigned int flags;
+	int fd, size = sizeof(struct vduse_dev_request);
 	ssize_t ret = 0;
 
 	if (iov_iter_count(to) < size)
@@ -349,6 +418,18 @@ static ssize_t vduse_dev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		if (ret)
 			return ret;
 	}
+
+	if (msg->req.type == VDUSE_UPDATE_IOTLB && msg->req.iotlb.fd == -1) {
+		flags = perm_to_file_flags(msg->req.iotlb.perm);
+		fd = get_unused_fd_flags(flags);
+		if (fd < 0) {
+			vduse_dev_enqueue_msg(dev, msg, &dev->send_list);
+			return fd;
+		}
+		fd_install(fd, get_file(msg->iotlb_file));
+		msg->req.iotlb.fd = fd;
+	}
+
 	ret = copy_to_iter(&msg->req, size, to);
 	if (ret != size) {
 		vduse_dev_enqueue_msg(dev, msg, &dev->send_list);
@@ -565,6 +646,69 @@ static void vduse_vdpa_set_config(struct vdpa_device *vdpa, unsigned int offset,
 	vduse_dev_set_config(dev, offset, buf, len);
 }
 
+static void vduse_vdpa_invalidate_iotlb(struct vduse_dev *dev,
+					struct vhost_iotlb_msg *msg)
+{
+	vduse_dev_invalidate_iotlb(dev, msg->iova, msg->size);
+}
+
+static int vduse_vdpa_update_iotlb(struct vduse_dev *dev,
+					struct vhost_iotlb_msg *msg)
+{
+	u64 uaddr = msg->uaddr;
+	u64 iova = msg->iova;
+	u64 size = msg->size;
+	u64 offset;
+	struct vm_area_struct *vma;
+	int ret;
+
+	while (uaddr < msg->uaddr + msg->size) {
+		vma = find_vma(current->mm, uaddr);
+		ret = -EINVAL;
+		if (!vma)
+			goto err;
+
+		size = min(msg->size, vma->vm_end - uaddr);
+		offset = (vma->vm_pgoff << PAGE_SHIFT) + uaddr - vma->vm_start;
+		if (vma->vm_file && (vma->vm_flags & VM_SHARED)) {
+			ret = vduse_dev_update_iotlb(dev, vma->vm_file, offset,
+							iova, size, msg->perm);
+			if (ret)
+				goto err;
+		}
+		iova += size;
+		uaddr += size;
+	}
+	return 0;
+err:
+	vduse_dev_invalidate_iotlb(dev, msg->iova, iova - msg->iova);
+	return ret;
+}
+
+static int vduse_vdpa_process_iotlb_msg(struct vdpa_device *vdpa,
+					struct vhost_iotlb_msg *msg)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	int ret = 0;
+
+	switch (msg->type) {
+	case VHOST_IOTLB_UPDATE:
+		ret = vduse_vdpa_update_iotlb(dev, msg);
+		break;
+	case VHOST_IOTLB_INVALIDATE:
+		vduse_vdpa_invalidate_iotlb(dev, msg);
+		break;
+	case VHOST_IOTLB_BATCH_BEGIN:
+	case VHOST_IOTLB_BATCH_END:
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
 static void vduse_vdpa_free(struct vdpa_device *vdpa)
 {
 	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
@@ -597,6 +741,7 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = {
 	.set_status		= vduse_vdpa_set_status,
 	.get_config		= vduse_vdpa_get_config,
 	.set_config		= vduse_vdpa_set_config,
+	.process_iotlb_msg	= vduse_vdpa_process_iotlb_msg,
 	.free			= vduse_vdpa_free,
 };
 
diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h
index 873305dfd93f..c5080851f140 100644
--- a/include/uapi/linux/vduse.h
+++ b/include/uapi/linux/vduse.h
@@ -21,6 +21,8 @@ enum vduse_req_type {
 	VDUSE_GET_STATUS,
 	VDUSE_SET_CONFIG,
 	VDUSE_GET_CONFIG,
+	VDUSE_UPDATE_IOTLB,
+	VDUSE_INVALIDATE_IOTLB,
 };
 
 struct vduse_vq_num {
@@ -51,6 +53,14 @@ struct vduse_dev_config_data {
 	__u8 data[VDUSE_CONFIG_DATA_LEN];
 };
 
+struct vduse_iotlb {
+	__u32 fd;
+	__u64 offset;
+	__u64 iova;
+	__u64 size;
+	__u8 perm;
+};
+
 struct vduse_dev_request {
 	__u32 type; /* request type */
 	__u32 unique; /* request id */
@@ -62,6 +72,7 @@ struct vduse_dev_request {
 		struct vduse_vq_ready vq_ready; /* virtqueue ready status */
 		struct vduse_vq_state vq_state; /* virtqueue state */
 		struct vduse_dev_config_data config; /* virtio device config space */
+		struct vduse_iotlb iotlb; /* iotlb message */
 		__u64 features; /* virtio features */
 		__u8 status; /* device status */
 	};
-- 
2.11.0



  parent reply	other threads:[~2020-12-22 14:54 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-22 14:52 [RFC v2 00/13] Introduce VDUSE - vDPA Device in Userspace Xie Yongji
2020-12-22 14:52 ` [RFC v2 01/13] mm: export zap_page_range() for driver use Xie Yongji
2020-12-22 15:44   ` Christoph Hellwig
2020-12-22 14:52 ` [RFC v2 02/13] eventfd: track eventfd_signal() recursion depth separately in different cases Xie Yongji
2020-12-22 14:52 ` [RFC v2 03/13] eventfd: Increase the recursion depth of eventfd_signal() Xie Yongji
2020-12-22 14:52 ` [RFC v2 04/13] vdpa: Remove the restriction that only supports virtio-net devices Xie Yongji
2020-12-22 14:52 ` [RFC v2 05/13] vdpa: Pass the netlink attributes to ops.dev_add() Xie Yongji
2020-12-22 14:52 ` [RFC v2 06/13] vduse: Introduce VDUSE - vDPA Device in Userspace Xie Yongji
2020-12-23  8:08   ` Jason Wang
2020-12-23 14:17     ` Yongji Xie
2020-12-24  3:01       ` Jason Wang
2020-12-24  8:34         ` Yongji Xie
2020-12-25  6:59           ` Jason Wang
2021-01-08 13:32   ` Bob Liu
2021-01-10 10:03     ` Yongji Xie
2020-12-22 14:52 ` [RFC v2 07/13] vduse: support get/set virtqueue state Xie Yongji
2020-12-22 14:52 ` [RFC v2 08/13] vdpa: Introduce process_iotlb_msg() in vdpa_config_ops Xie Yongji
2020-12-23  8:36   ` Jason Wang
2020-12-23 11:06     ` Yongji Xie
2020-12-24  2:36       ` Jason Wang
2020-12-24  7:24         ` Yongji Xie
2020-12-22 14:52 ` Xie Yongji [this message]
2020-12-23  9:05   ` [RFC v2 09/13] vduse: Add support for processing vhost iotlb message Jason Wang
2020-12-23 12:14     ` [External] " Yongji Xie
2020-12-24  2:41       ` Jason Wang
2020-12-24  7:37         ` Yongji Xie
2020-12-25  2:37           ` Yongji Xie
2020-12-25  7:02             ` Jason Wang
2020-12-25 11:36               ` Yongji Xie
2020-12-25  6:57           ` Jason Wang
2020-12-25 10:31             ` Yongji Xie
2020-12-28  7:43               ` Jason Wang
2020-12-28  8:14                 ` Yongji Xie
2020-12-28  8:43                   ` Jason Wang
2020-12-28  9:12                     ` Yongji Xie
2020-12-29  9:11                       ` Jason Wang
2020-12-29 10:26                         ` Yongji Xie
2020-12-30  6:10                           ` Jason Wang
2020-12-30  7:09                             ` Yongji Xie
2020-12-30  8:41                               ` Jason Wang
2020-12-30 10:12                                 ` Yongji Xie
2020-12-31  2:49                                   ` Jason Wang
2020-12-31  5:15                                     ` Yongji Xie
2020-12-31  5:49                                       ` Jason Wang
2020-12-31  6:52                                         ` Yongji Xie
2020-12-31  7:11                                           ` Jason Wang
2020-12-31  8:00                                             ` Yongji Xie
2020-12-22 14:52 ` [RFC v2 10/13] vduse: grab the module's references until there is no vduse device Xie Yongji
2020-12-22 14:52 ` [RFC v2 11/13] vduse/iova_domain: Support reclaiming bounce pages Xie Yongji
2020-12-22 14:52 ` [RFC v2 12/13] vduse: Add memory shrinker to reclaim " Xie Yongji
2020-12-22 14:52 ` [RFC v2 13/13] vduse: Introduce a workqueue for irq injection Xie Yongji
2020-12-23  6:38 ` [RFC v2 00/13] Introduce VDUSE - vDPA Device in Userspace Jason Wang
2020-12-23  8:14   ` Jason Wang
2020-12-23 10:59   ` Yongji Xie
2020-12-24  2:24     ` Jason Wang

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=20201222145221.711-10-xieyongji@bytedance.com \
    --to=xieyongji@bytedance.com \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=bcrl@kvack.org \
    --cc=corbet@lwn.net \
    --cc=jasowang@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-aio@kvack.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.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).