search for: desc_user_addr

...ivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -322,6 +322,8 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) 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) { @@ -334,7 +336,8 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) r = -EINVAL; break; } - r = i...

...ivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -322,6 +322,8 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) 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) { @@ -334,7 +336,8 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) r = -EINVAL; break; } - r = i...

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. This is done through setup kernel address through direct mapping and co-opreate VM management with MMU notifiers. Test shows about 23% improvement on TX PPS. TCP_STREAM doesn't see obvious

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling like SMAP. This is done through setup kernel address through direct mapping and co-opreate VM management with MMU notifiers. Test shows about 23% improvement on TX PPS. TCP_STREAM

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling like SMAP. This is done through setup kernel address through direct mapping and co-opreate VM management with MMU notifiers. Test shows about 23% improvement on TX PPS. TCP_STREAM

...ost_dev *d, int ioctl, void __user *argp) * 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->num, + if (!vq_access_ok(d, 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)) { @@ -473,6 +474,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG)); vq->desc =...

...ost_dev *d, int ioctl, void __user *argp) * 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->num, + if (!vq_access_ok(d, 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)) { @@ -473,6 +474,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG)); vq->desc =...

...; + int r; + vq->used = used; + r = vhost_update_used_flags(vq); if (r) return r; return get_user(vq->last_used_idx, &used->idx); @@ -700,7 +702,6 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) 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)) { @@ -1375,6 +1376,23 @@ void vhost_add_u...

...; + int r; + vq->used = used; + r = vhost_update_used_flags(vq); if (r) return r; return get_user(vq->last_used_idx, &used->idx); @@ -700,7 +702,6 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) 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)) { @@ -1375,6 +1376,23 @@ void vhost_add_u...

...ost_dev *d, int ioctl, void __user *argp) * 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->num, + if (!vq_access_ok(d, 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)) { @@ -473,6 +474,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG)); vq->desc =...

...ost_dev *d, int ioctl, void __user *argp) * 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->num, + if (!vq_access_ok(d, 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)) { @@ -473,6 +474,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp) vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG)); vq->desc =...

...vhost. > > There's one problem here, and that is that VQs still do not undergo > > translation. In theory VQ could be mapped in such a way > > that it's not contigious in userspace memory. > > I'm not sure I get the issue, current vhost API support setting > desc_user_addr, used_user_addr and avail_user_addr independently. So > looks ok? If not, looks not a problem to device IOTLB API itself. The problem is that addresses are all HVA. Without an iommu, we ask for them to be contigious and since bus address == GPA, this means contigious GPA => contigious HVA....

...vhost. > > There's one problem here, and that is that VQs still do not undergo > > translation. In theory VQ could be mapped in such a way > > that it's not contigious in userspace memory. > > I'm not sure I get the issue, current vhost API support setting > desc_user_addr, used_user_addr and avail_user_addr independently. So > looks ok? If not, looks not a problem to device IOTLB API itself. The problem is that addresses are all HVA. Without an iommu, we ask for them to be contigious and since bus address == GPA, this means contigious GPA => contigious HVA....

...+ return 0; + } + return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc)); } @@ -1551,6 +1722,13 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg } } + if (!vq->iotlb && vhost_setup_vmaps(vq, a.avail_user_addr, + a.desc_user_addr, + a.used_user_addr)) { + 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; diff --git a/drivers/vhost/vh...

...{ > - if (!vq_access_ok(vq, vq->num, > + /* If an IOTLB device is present, the vring addresses are > + * GIOVAs. Access will be validated during IOTLB prefetch. */ > + if (!vq->iotlb && > + !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)) >

...{ > - if (!vq_access_ok(vq, vq->num, > + /* If an IOTLB device is present, the vring addresses are > + * GIOVAs. Access will be validated during IOTLB prefetch. */ > + if (!vq->iotlb && > + !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)) OK I think you are right here. Jason, can you ack pls? However, I think a cleaner way to check this is by moving the following check from vhost_vq_access_ok to vq_access_ok:...

...t_vring_addr { /* Flag values: */ /* Whether log address is valid. If set enables logging. */ #define VHOST_VRING_F_LOG 0 + /* Whether we have a big-endian legacy virtio device. */ +#define VHOST_VRING_F_LEGACY_BIG_ENDIAN 1 /* Start of array of descriptors (virtually contiguous) */ __u64 desc_user_addr;

...t_vring_addr { /* Flag values: */ /* Whether log address is valid. If set enables logging. */ #define VHOST_VRING_F_LOG 0 + /* Whether we have a big-endian legacy virtio device. */ +#define VHOST_VRING_F_LEGACY_BIG_ENDIAN 1 /* Start of array of descriptors (virtually contiguous) */ __u64 desc_user_addr;

...mdev_get_drvdata(mdev); > + if (!vdpa) > + return -ENODEV; > + > + if (qid >= vdpa->max_vrings) > + return -EINVAL; > + > + if (qid >= vdpa->nr_vring) > + vdpa->nr_vring = qid + 1; > + > + vring = &vdpa->vring_info[qid]; > + > + vring->desc_user_addr = addr->desc_user_addr; > + vring->used_user_addr = addr->used_user_addr; > + vring->avail_user_addr = addr->avail_user_addr; > + vring->log_guest_addr = addr->log_guest_addr; > + > + return 0; > +} > + > +static int vhost_set_vring_num(struct mdev_devic...

...addr->index; + struct vdpa_vring_info *vring; + + vdpa = mdev_get_drvdata(mdev); + if (!vdpa) + return -ENODEV; + + if (qid >= vdpa->max_vrings) + return -EINVAL; + + if (qid >= vdpa->nr_vring) + vdpa->nr_vring = qid + 1; + + vring = &vdpa->vring_info[qid]; + + vring->desc_user_addr = addr->desc_user_addr; + vring->used_user_addr = addr->used_user_addr; + vring->avail_user_addr = addr->avail_user_addr; + vring->log_guest_addr = addr->log_guest_addr; + + return 0; +} + +static int vhost_set_vring_num(struct mdev_device *mdev, + struct vhost_vring_state *nu...