[RFC V1 03/13] vhost-vdpa: VHOST_NEW_OWNER

From: Steve Sistare
Date: Wed Jan 10 2024 - 15:43:07 EST


Add an ioctl to transfer file descriptor ownership and pinned memory
accounting from one process to another.

Signed-off-by: Steve Sistare <steven.sistare@xxxxxxxxxx>
---
drivers/vhost/vdpa.c | 37 +++++++++++++++++++++++++++++++++++++
drivers/vhost/vhost.c | 15 +++++++++++++++
drivers/vhost/vhost.h | 1 +
include/uapi/linux/vhost.h | 10 ++++++++++
4 files changed, 63 insertions(+)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 2269988d6d33..eb3a95e703b0 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -613,6 +613,40 @@ static long vhost_vdpa_resume(struct vhost_vdpa *v)
return ops->resume(vdpa);
}

+static long vhost_vdpa_new_owner(struct vhost_vdpa *v)
+{
+ int r;
+ struct vhost_dev *vdev = &v->vdev;
+ struct mm_struct *mm_old = vdev->mm;
+ struct mm_struct *mm_new = current->mm;
+ long pinned_vm = v->pinned_vm;
+ unsigned long lock_limit = PFN_DOWN(rlimit(RLIMIT_MEMLOCK));
+
+ if (!mm_old)
+ return -EINVAL;
+
+ if (!v->vdpa->use_va &&
+ pinned_vm + atomic64_read(&mm_new->pinned_vm) > lock_limit)
+ return -ENOMEM;
+
+ r = vhost_vdpa_bind_mm(v, mm_new);
+ if (r)
+ return r;
+
+ r = vhost_dev_new_owner(vdev);
+ if (r) {
+ vhost_vdpa_bind_mm(v, mm_old);
+ return r;
+ }
+
+ if (!v->vdpa->use_va) {
+ atomic64_sub(pinned_vm, &mm_old->pinned_vm);
+ atomic64_add(pinned_vm, &mm_new->pinned_vm);
+ }
+
+ return r;
+}
+
static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
void __user *argp)
{
@@ -843,6 +877,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
case VHOST_VDPA_RESUME:
r = vhost_vdpa_resume(v);
break;
+ case VHOST_NEW_OWNER:
+ r = vhost_vdpa_new_owner(v);
+ break;
default:
r = vhost_dev_ioctl(&v->vdev, cmd, argp);
if (r == -ENOIOCTLCMD)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index e0c181ad17e3..0ce7ee9834f4 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -907,6 +907,21 @@ long vhost_dev_set_owner(struct vhost_dev *dev)
}
EXPORT_SYMBOL_GPL(vhost_dev_set_owner);

+/* Caller should have device mutex */
+long vhost_dev_new_owner(struct vhost_dev *dev)
+{
+ if (dev->mm == current->mm)
+ return -EBUSY;
+
+ if (!vhost_dev_has_owner(dev))
+ return -EINVAL;
+
+ vhost_detach_mm(dev);
+ vhost_attach_mm(dev);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(vhost_dev_new_owner);
+
static struct vhost_iotlb *iotlb_alloc(void)
{
return vhost_iotlb_alloc(max_iotlb_entries,
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index f60d5f7bef94..cd0dab21d99e 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -185,6 +185,7 @@ void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
int (*msg_handler)(struct vhost_dev *dev, u32 asid,
struct vhost_iotlb_msg *msg));
long vhost_dev_set_owner(struct vhost_dev *dev);
+long vhost_dev_new_owner(struct vhost_dev *dev);
bool vhost_dev_has_owner(struct vhost_dev *dev);
long vhost_dev_check_owner(struct vhost_dev *);
struct vhost_iotlb *vhost_dev_reset_owner_prepare(void);
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index 649560c685f1..5e3cdce4c0cf 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -123,6 +123,16 @@
#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)

+/* Set current process as the new owner of this file descriptor. The fd must
+ * already be owned, via a prior call to VHOST_SET_OWNER. The pinned memory
+ * count is transferred from the previous to the new owner.
+ * Errors:
+ * EINVAL: not owned
+ * EBUSY: caller is already the owner
+ * ENOMEM: RLIMIT_MEMLOCK exceeded
+ */
+#define VHOST_NEW_OWNER _IO(VHOST_VIRTIO, 0x27)
+
/* VHOST_NET specific defines */

/* Attach virtio net ring to a raw socket, or tap device.
--
2.39.3