diff options
Diffstat (limited to 'drivers/vhost/vdpa.c')
| -rw-r--r-- | drivers/vhost/vdpa.c | 313 |
1 files changed, 262 insertions, 51 deletions
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ec32f785dfde..05a481e4c385 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -59,6 +59,7 @@ struct vhost_vdpa { int in_batch; struct vdpa_iova_range range; u32 batch_asid; + bool suspended; }; static DEFINE_IDA(vhost_vdpa_ida); @@ -131,6 +132,15 @@ static struct vhost_vdpa_as *vhost_vdpa_find_alloc_as(struct vhost_vdpa *v, return vhost_vdpa_alloc_as(v, asid); } +static void vhost_vdpa_reset_map(struct vhost_vdpa *v, u32 asid) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (ops->reset_map) + ops->reset_map(vdpa, asid); +} + static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid) { struct vhost_vdpa_as *as = asid_to_as(v, asid); @@ -140,6 +150,14 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid) hlist_del(&as->hash_link); vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1, asid); + /* + * Devices with vendor specific IOMMU may need to restore + * iotlb to the initial or default state, which cannot be + * cleaned up in the all range unmap call above. Give them + * a chance to clean up or reset the map to the desired + * state. + */ + vhost_vdpa_reset_map(v, asid); kfree(as); return 0; @@ -161,7 +179,7 @@ static irqreturn_t vhost_vdpa_virtqueue_cb(void *private) struct eventfd_ctx *call_ctx = vq->call_ctx.ctx; if (call_ctx) - eventfd_signal(call_ctx, 1); + eventfd_signal(call_ctx); return IRQ_HANDLED; } @@ -172,7 +190,7 @@ static irqreturn_t vhost_vdpa_config_cb(void *private) struct eventfd_ctx *config_ctx = v->config_ctx; if (config_ctx) - eventfd_signal(config_ctx, 1); + eventfd_signal(config_ctx); return IRQ_HANDLED; } @@ -191,16 +209,14 @@ static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid) if (irq < 0) return; - irq_bypass_unregister_producer(&vq->call_ctx.producer); if (!vq->call_ctx.ctx) return; - vq->call_ctx.producer.token = vq->call_ctx.ctx; - vq->call_ctx.producer.irq = irq; - ret = irq_bypass_register_producer(&vq->call_ctx.producer); + ret = irq_bypass_register_producer(&vq->call_ctx.producer, + vq->call_ctx.ctx, irq); if (unlikely(ret)) - dev_info(&v->dev, "vq %u, irq bypass producer (token %p) registration fails, ret = %d\n", - qid, vq->call_ctx.producer.token, ret); + dev_info(&v->dev, "vq %u, irq bypass producer (eventfd %p) registration fails, ret = %d\n", + qid, vq->call_ctx.ctx, ret); } static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid) @@ -210,13 +226,48 @@ static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid) irq_bypass_unregister_producer(&vq->call_ctx.producer); } -static int vhost_vdpa_reset(struct vhost_vdpa *v) +static int _compat_vdpa_reset(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; + u32 flags = 0; + + v->suspended = false; + + if (v->vdev.vqs) { + flags |= !vhost_backend_has_feature(v->vdev.vqs[0], + VHOST_BACKEND_F_IOTLB_PERSIST) ? + VDPA_RESET_F_CLEAN_MAP : 0; + } + + return vdpa_reset(vdpa, flags); +} +static int vhost_vdpa_reset(struct vhost_vdpa *v) +{ v->in_batch = 0; + return _compat_vdpa_reset(v); +} + +static long vhost_vdpa_bind_mm(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!vdpa->use_va || !ops->bind_mm) + return 0; + + return ops->bind_mm(vdpa, v->vdev.mm); +} + +static void vhost_vdpa_unbind_mm(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!vdpa->use_va || !ops->unbind_mm) + return; - return vdpa_reset(vdpa); + ops->unbind_mm(vdpa); } static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp) @@ -273,7 +324,7 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) vhost_vdpa_unsetup_vq_irq(v, i); if (status == 0) { - ret = vdpa_reset(vdpa); + ret = _compat_vdpa_reset(v); if (ret) return ret; } else @@ -359,6 +410,22 @@ static bool vhost_vdpa_can_suspend(const struct vhost_vdpa *v) return ops->suspend; } +static bool vhost_vdpa_can_resume(const struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->resume; +} + +static bool vhost_vdpa_has_desc_group(const struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->get_vq_desc_group; +} + static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) { struct vdpa_device *vdpa = v->vdpa; @@ -373,11 +440,34 @@ static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) return 0; } +static u64 vhost_vdpa_get_backend_features(const struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!ops->get_backend_features) + return 0; + else + return ops->get_backend_features(vdpa); +} + +static bool vhost_vdpa_has_persistent_map(const struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + return (!ops->set_map && !ops->dma_map) || ops->reset_map || + vhost_vdpa_get_backend_features(v) & BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST); +} + static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep) { struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; + struct vhost_dev *d = &v->vdev; + u64 actual_features; u64 features; + int i; /* * It's not allowed to change the features after they have @@ -392,6 +482,16 @@ static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep) if (vdpa_set_features(vdpa, features)) return -EINVAL; + /* let the vqs know what has been configured */ + actual_features = ops->get_driver_features(vdpa); + for (i = 0; i < d->nvqs; ++i) { + struct vhost_virtqueue *vq = d->vqs[i]; + + mutex_lock(&vq->mutex); + vq->acked_features = actual_features; + mutex_unlock(&vq->mutex); + } + return 0; } @@ -491,11 +591,42 @@ static long vhost_vdpa_suspend(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; + int ret; + + if (!(ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK)) + return 0; if (!ops->suspend) return -EOPNOTSUPP; - return ops->suspend(vdpa); + ret = ops->suspend(vdpa); + if (!ret) + v->suspended = true; + + return ret; +} + +/* After a successful return of this ioctl the device resumes processing + * virtqueue descriptors. The device becomes fully operational the same way it + * was before it was suspended. + */ +static long vhost_vdpa_resume(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + int ret; + + if (!(ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK)) + return 0; + + if (!ops->resume) + return -EOPNOTSUPP; + + ret = ops->resume(vdpa); + if (!ret) + v->suspended = false; + + return ret; } static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, @@ -536,6 +667,16 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, else if (copy_to_user(argp, &s, sizeof(s))) return -EFAULT; return 0; + case VHOST_VDPA_GET_VRING_DESC_GROUP: + if (!vhost_vdpa_has_desc_group(v)) + return -EOPNOTSUPP; + s.index = idx; + s.num = ops->get_vq_desc_group(vdpa, idx); + if (s.num >= vdpa->ngroups) + return -EIO; + else if (copy_to_user(argp, &s, sizeof(s))) + return -EFAULT; + return 0; case VHOST_VDPA_SET_GROUP_ASID: if (copy_from_user(&s, argp, sizeof(s))) return -EFAULT; @@ -544,12 +685,34 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, if (!ops->set_group_asid) return -EOPNOTSUPP; return ops->set_group_asid(vdpa, idx, s.num); + case VHOST_VDPA_GET_VRING_SIZE: + if (!ops->get_vq_size) + return -EOPNOTSUPP; + s.index = idx; + s.num = ops->get_vq_size(vdpa, idx); + if (copy_to_user(argp, &s, sizeof(s))) + return -EFAULT; + return 0; case VHOST_GET_VRING_BASE: r = ops->get_vq_state(v->vdpa, idx, &vq_state); if (r) return r; - vq->last_avail_idx = vq_state.split.avail_index; + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { + vq->last_avail_idx = vq_state.packed.last_avail_idx | + (vq_state.packed.last_avail_counter << 15); + vq->last_used_idx = vq_state.packed.last_used_idx | + (vq_state.packed.last_used_counter << 15); + } else { + vq->last_avail_idx = vq_state.split.avail_index; + } + break; + case VHOST_SET_VRING_CALL: + if (vq->call_ctx.ctx) { + if (ops->get_status(vdpa) & + VIRTIO_CONFIG_S_DRIVER_OK) + vhost_vdpa_unsetup_vq_irq(v, idx); + } break; } @@ -559,6 +722,9 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, switch (cmd) { case VHOST_SET_VRING_ADDR: + if ((ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) && !v->suspended) + return -EINVAL; + if (ops->set_vq_address(vdpa, idx, (u64)(uintptr_t)vq->desc, (u64)(uintptr_t)vq->avail, @@ -567,21 +733,34 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, break; case VHOST_SET_VRING_BASE: - vq_state.split.avail_index = vq->last_avail_idx; - if (ops->set_vq_state(vdpa, idx, &vq_state)) - r = -EINVAL; + if ((ops->get_status(vdpa) & VIRTIO_CONFIG_S_DRIVER_OK) && !v->suspended) + return -EINVAL; + + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { + vq_state.packed.last_avail_idx = vq->last_avail_idx & 0x7fff; + vq_state.packed.last_avail_counter = !!(vq->last_avail_idx & 0x8000); + vq_state.packed.last_used_idx = vq->last_used_idx & 0x7fff; + vq_state.packed.last_used_counter = !!(vq->last_used_idx & 0x8000); + } else { + vq_state.split.avail_index = vq->last_avail_idx; + } + r = ops->set_vq_state(vdpa, idx, &vq_state); break; case VHOST_SET_VRING_CALL: if (vq->call_ctx.ctx) { cb.callback = vhost_vdpa_virtqueue_cb; cb.private = vq; + cb.trigger = vq->call_ctx.ctx; + if (ops->get_status(vdpa) & + VIRTIO_CONFIG_S_DRIVER_OK) + vhost_vdpa_setup_vq_irq(v, idx); } else { cb.callback = NULL; cb.private = NULL; + cb.trigger = NULL; } ops->set_vq_cb(vdpa, idx, &cb); - vhost_vdpa_setup_vq_irq(v, idx); break; case VHOST_SET_VRING_NUM: @@ -606,11 +785,27 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; if (features & ~(VHOST_VDPA_BACKEND_FEATURES | - BIT_ULL(VHOST_BACKEND_F_SUSPEND))) + BIT_ULL(VHOST_BACKEND_F_DESC_ASID) | + BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST) | + BIT_ULL(VHOST_BACKEND_F_SUSPEND) | + BIT_ULL(VHOST_BACKEND_F_RESUME) | + BIT_ULL(VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK))) return -EOPNOTSUPP; if ((features & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) && !vhost_vdpa_can_suspend(v)) return -EOPNOTSUPP; + if ((features & BIT_ULL(VHOST_BACKEND_F_RESUME)) && + !vhost_vdpa_can_resume(v)) + return -EOPNOTSUPP; + if ((features & BIT_ULL(VHOST_BACKEND_F_DESC_ASID)) && + !(features & BIT_ULL(VHOST_BACKEND_F_IOTLB_ASID))) + return -EINVAL; + if ((features & BIT_ULL(VHOST_BACKEND_F_DESC_ASID)) && + !vhost_vdpa_has_desc_group(v)) + return -EOPNOTSUPP; + if ((features & BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST)) && + !vhost_vdpa_has_persistent_map(v)) + return -EOPNOTSUPP; vhost_set_backend_features(&v->vdev, features); return 0; } @@ -662,6 +857,13 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, features = VHOST_VDPA_BACKEND_FEATURES; if (vhost_vdpa_can_suspend(v)) features |= BIT_ULL(VHOST_BACKEND_F_SUSPEND); + if (vhost_vdpa_can_resume(v)) + features |= BIT_ULL(VHOST_BACKEND_F_RESUME); + if (vhost_vdpa_has_desc_group(v)) + features |= BIT_ULL(VHOST_BACKEND_F_DESC_ASID); + if (vhost_vdpa_has_persistent_map(v)) + features |= BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST); + features |= vhost_vdpa_get_backend_features(v); if (copy_to_user(featurep, &features, sizeof(features))) r = -EFAULT; break; @@ -677,6 +879,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, case VHOST_VDPA_SUSPEND: r = vhost_vdpa_suspend(v); break; + case VHOST_VDPA_RESUME: + r = vhost_vdpa_resume(v); + break; default: r = vhost_dev_ioctl(&v->vdev, cmd, argp); if (r == -ENOIOCTLCMD) @@ -684,6 +889,17 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, break; } + if (r) + goto out; + + switch (cmd) { + case VHOST_SET_OWNER: + r = vhost_vdpa_bind_mm(v); + if (r) + vhost_dev_reset_owner(d, NULL); + break; + } +out: mutex_unlock(&d->mutex); return r; } @@ -792,7 +1008,8 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, r = ops->set_map(vdpa, asid, iotlb); } else { r = iommu_map(v->domain, iova, pa, size, - perm_to_iommu_flags(perm)); + perm_to_iommu_flags(perm), + GFP_KERNEL_ACCOUNT); } if (r) { vhost_iotlb_del_range(iotlb, iova, iova + size - 1); @@ -819,11 +1036,7 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, if (!v->in_batch) ops->set_map(vdpa, asid, iotlb); } - /* If we are in the middle of batch processing, delay the free - * of AS until BATCH_END. - */ - if (!v->in_batch && !iotlb->nmaps) - vhost_vdpa_remove_as(v, asid); + } static int vhost_vdpa_va_map(struct vhost_vdpa *v, @@ -920,7 +1133,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v, while (npages) { sz2pin = min_t(unsigned long, npages, list_size); pinned = pin_user_pages(cur_base, sz2pin, - gup_flags, page_list, NULL); + gup_flags, page_list); if (sz2pin != pinned) { if (pinned < 0) { ret = pinned; @@ -1080,8 +1293,6 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, if (v->in_batch && ops->set_map) ops->set_map(vdpa, asid, iotlb); v->in_batch = false; - if (!iotlb->nmaps) - vhost_vdpa_remove_as(v, asid); break; default: r = -EINVAL; @@ -1107,24 +1318,26 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; - struct device *dma_dev = vdpa_get_dma_dev(vdpa); - struct bus_type *bus; + union virtio_map map = vdpa_get_map(vdpa); + struct device *dma_dev = map.dma_dev; int ret; /* Device want to do DMA by itself */ if (ops->set_map || ops->dma_map) return 0; - bus = dma_dev->bus; - if (!bus) - return -EFAULT; - - if (!device_iommu_capable(dma_dev, IOMMU_CAP_CACHE_COHERENCY)) + if (!device_iommu_capable(dma_dev, IOMMU_CAP_CACHE_COHERENCY)) { + dev_warn_once(&v->dev, + "Failed to allocate domain, device is not IOMMU cache coherent capable\n"); return -ENOTSUPP; + } - v->domain = iommu_domain_alloc(bus); - if (!v->domain) - return -EIO; + v->domain = iommu_paging_domain_alloc(dma_dev); + if (IS_ERR(v->domain)) { + ret = PTR_ERR(v->domain); + v->domain = NULL; + return ret; + } ret = iommu_attach_device(v->domain, dma_dev); if (ret) @@ -1134,13 +1347,15 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) err_attach: iommu_domain_free(v->domain); + v->domain = NULL; return ret; } static void vhost_vdpa_free_domain(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; - struct device *dma_dev = vdpa_get_dma_dev(vdpa); + union virtio_map map = vdpa_get_map(vdpa); + struct device *dma_dev = map.dma_dev; if (v->domain) { iommu_detach_device(v->domain, dma_dev); @@ -1178,8 +1393,10 @@ static void vhost_vdpa_cleanup(struct vhost_vdpa *v) vhost_vdpa_remove_as(v, asid); } + vhost_vdpa_free_domain(v); vhost_dev_cleanup(&v->vdev); kfree(v->vdev.vqs); + v->vdev.vqs = NULL; } static int vhost_vdpa_open(struct inode *inode, struct file *filep) @@ -1211,6 +1428,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) for (i = 0; i < nvqs; i++) { vqs[i] = &v->vqs[i]; vqs[i]->handle_kick = handle_vq_kick; + vqs[i]->call_ctx.ctx = NULL; } vhost_dev_init(dev, vqs, nvqs, 0, 0, 0, false, vhost_vdpa_process_iotlb_msg); @@ -1250,7 +1468,7 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) vhost_vdpa_clean_irq(v); vhost_vdpa_reset(v); vhost_dev_stop(&v->vdev); - vhost_vdpa_free_domain(v); + vhost_vdpa_unbind_mm(v); vhost_vdpa_config_put(v); vhost_vdpa_cleanup(v); mutex_unlock(&d->mutex); @@ -1273,13 +1491,7 @@ static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf) notify = ops->get_vq_notification(vdpa, index); - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - if (remap_pfn_range(vma, vmf->address & PAGE_MASK, - PFN_DOWN(notify.addr), PAGE_SIZE, - vma->vm_page_prot)) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; + return vmf_insert_pfn(vma, vmf->address & PAGE_MASK, PFN_DOWN(notify.addr)); } static const struct vm_operations_struct vhost_vdpa_vm_ops = { @@ -1315,7 +1527,7 @@ static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma) if (vma->vm_end - vma->vm_start != notify.size) return -ENOTSUPP; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &vhost_vdpa_vm_ops; return 0; } @@ -1338,7 +1550,7 @@ static void vhost_vdpa_release_dev(struct device *device) struct vhost_vdpa *v = container_of(device, struct vhost_vdpa, dev); - ida_simple_remove(&vhost_vdpa_ida, v->minor); + ida_free(&vhost_vdpa_ida, v->minor); kfree(v->vqs); kfree(v); } @@ -1361,8 +1573,8 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) if (!v) return -ENOMEM; - minor = ida_simple_get(&vhost_vdpa_ida, 0, - VHOST_VDPA_DEV_MAX, GFP_KERNEL); + minor = ida_alloc_max(&vhost_vdpa_ida, VHOST_VDPA_DEV_MAX - 1, + GFP_KERNEL); if (minor < 0) { kfree(v); return minor; @@ -1406,7 +1618,6 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) err: put_device(&v->dev); - ida_simple_remove(&vhost_vdpa_ida, v->minor); return r; } |
