diff --git a/Documentation/ABI/testing/sysfs-bus-vdpa b/Documentation/ABI/testing/sysfs-bus-vdpa new file mode 100644 index 0000000000000000000000000000000000000000..4e55761a39df967d31b31059bd0c38486b8a01d8 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-vdpa @@ -0,0 +1,37 @@ +What: /sys/bus/vdpa/driver_autoprobe +Date: March 2020 +Contact: virtualization@lists.linux-foundation.org +Description: + This file determines whether new devices are immediately bound + to a driver after the creation. It initially contains 1, which + means the kernel automatically binds devices to a compatible + driver immediately after they are created. + + Writing "0" to this file disable this feature, any other string + enable it. + +What: /sys/bus/vdpa/driver_probe +Date: March 2020 +Contact: virtualization@lists.linux-foundation.org +Description: + Writing a device name to this file will cause the kernel binds + devices to a compatible driver. + + This can be useful when /sys/bus/vdpa/driver_autoprobe is + disabled. + +What: /sys/bus/vdpa/drivers/.../bind +Date: March 2020 +Contact: virtualization@lists.linux-foundation.org +Description: + Writing a device name to this file will cause the driver to + attempt to bind to the device. This is useful for overriding + default bindings. + +What: /sys/bus/vdpa/drivers/.../unbind +Date: March 2020 +Contact: virtualization@lists.linux-foundation.org +Description: + Writing a device name to this file will cause the driver to + attempt to unbind from the device. This may be useful when + overriding default bindings. diff --git a/MAINTAINERS b/MAINTAINERS index 5cbf5706da9211ecec78d54098f34ead5172608b..898bb8f2fd0ce7790f6c3eda528f9d7d5d2d174b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18651,6 +18651,7 @@ M: "Michael S. Tsirkin" M: Jason Wang L: virtualization@lists.linux-foundation.org S: Maintained +F: Documentation/ABI/testing/sysfs-bus-vdpa F: Documentation/devicetree/bindings/virtio/ F: drivers/block/virtio_blk.c F: drivers/crypto/virtio/ diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 9b54eec9b17eb077dec68777e78c1226ccaef38a..e121a620d201af6547bf660fb9e7ebd8eac5fb1c 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -933,7 +933,7 @@ static void virtblk_remove(struct virtio_device *vdev) mutex_lock(&vblk->vdev_mutex); /* Stop all the virtqueues. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ vblk->vdev = NULL; @@ -953,7 +953,7 @@ static int virtblk_freeze(struct virtio_device *vdev) struct virtio_blk *vblk = vdev->priv; /* Ensure we don't receive any more interrupts */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index a90001e02bf7a098f13906e3d589a733ca96ea8a..95980489514bf55e29405a2a1f93b26ae73a89cf 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -134,7 +134,7 @@ static void remove_common(struct virtio_device *vdev) vi->hwrng_removed = true; vi->data_avail = 0; complete(&vi->have_data); - vdev->config->reset(vdev); + virtio_reset_device(vdev); vi->busy = false; if (vi->hwrng_register_done) hwrng_unregister(&vi->hwrng); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 6d361420ffe827f615b3b06ebc68335758b7e292..309ffac7c97d872c1557d32b6f6fbcbb2036ac17 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1967,7 +1967,7 @@ static void virtcons_remove(struct virtio_device *vdev) flush_work(&portdev->config_work); /* Disable interrupts for vqs */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); /* Finish up work that's lined up */ if (use_multiport(portdev)) cancel_work_sync(&portdev->control_work); @@ -2149,7 +2149,7 @@ static int virtcons_freeze(struct virtio_device *vdev) portdev = vdev->priv; - vdev->config->reset(vdev); + virtio_reset_device(vdev); if (use_multiport(portdev)) virtqueue_disable_cb(portdev->c_ivq); diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index 080955a1dd9c0a5471d0bbcc0490e6af09edfc7a..6dffaaad419f622628b7dcf17968fe46a29eb8c8 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -404,7 +404,7 @@ static int virtcrypto_probe(struct virtio_device *vdev) free_engines: virtcrypto_clear_crypto_engines(vcrypto); free_vqs: - vcrypto->vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_del_vqs(vcrypto); free_dev: virtcrypto_devmgr_rm_dev(vcrypto); @@ -436,7 +436,7 @@ static void virtcrypto_remove(struct virtio_device *vdev) if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); virtcrypto_clear_crypto_engines(vcrypto); virtcrypto_del_vqs(vcrypto); @@ -456,7 +456,7 @@ static int virtcrypto_freeze(struct virtio_device *vdev) { struct virtio_crypto *vcrypto = vdev->priv; - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); @@ -492,7 +492,7 @@ static int virtcrypto_restore(struct virtio_device *vdev) free_engines: virtcrypto_clear_crypto_engines(vcrypto); free_vqs: - vcrypto->vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_del_vqs(vcrypto); return err; } diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index a28b01f9279335829b7d2efbe7f9ad0c3782fbc8..8422ca069a721fe84237e1b813e83eb79eb547d3 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -232,7 +232,7 @@ void virtio_gpu_deinit(struct drm_device *dev) flush_work(&vgdev->ctrlq.dequeue_work); flush_work(&vgdev->cursorq.dequeue_work); flush_work(&vgdev->config_changed_work); - vgdev->vdev->config->reset(vgdev->vdev); + virtio_reset_device(vgdev->vdev); vgdev->vdev->config->del_vqs(vgdev->vdev); } diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 81dea4caf561fff26ed922dbae3eb4c5c3ab9678..3c64cb9fb27df3fc923d01b30a209726add60baf 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -1115,7 +1115,7 @@ static void viommu_remove(struct virtio_device *vdev) iommu_device_unregister(&viommu->iommu); /* Stop all virtqueues */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); dev_info(&vdev->dev, "device removed\n"); diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c index 47a6d62b7511196b7d657e5222f787c841306801..02e61b41c9b11a57a155bd93250b09138b38c233 100644 --- a/drivers/net/caif/caif_virtio.c +++ b/drivers/net/caif/caif_virtio.c @@ -756,7 +756,7 @@ static void cfv_remove(struct virtio_device *vdev) debugfs_remove_recursive(cfv->debugfs); vringh_kiov_cleanup(&cfv->ctx.riov); - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->vringh_config->del_vrhs(cfv->vdev); cfv->vr_rx = NULL; vdev->config->del_vqs(cfv->vdev); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 362cb347d520e0092295e52fb5473498a5ca149f..9618cce6889f530aaf3abe876ef149d36d6ab445 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3228,7 +3228,7 @@ static int virtnet_probe(struct virtio_device *vdev) return 0; free_unregister_netdev: - vi->vdev->config->reset(vdev); + virtio_reset_device(vdev); unregister_netdev(dev); free_failover: @@ -3244,7 +3244,7 @@ static int virtnet_probe(struct virtio_device *vdev) static void remove_vq_common(struct virtnet_info *vi) { - vi->vdev->config->reset(vi->vdev); + virtio_reset_device(vi->vdev); /* Free unused buffers in both send and recv, if any. */ free_unused_bufs(vi); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index afd2d5add04b1b042aa894f3898cf5f6e58e0d79..f89bf43223a1f706924358fe91786c3e6502a745 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -4316,7 +4316,7 @@ static void remove_vqs(struct virtio_device *vdev) { int i; - vdev->config->reset(vdev); + virtio_reset_device(vdev); for (i = 0; i < ARRAY_SIZE(hwsim_vqs); i++) { struct virtqueue *vq = hwsim_vqs[i]; diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c index 726c7354d465984adb4bc35259af54a5ec8d6534..995b6cdc67ede881a3e94eb81472ba52e0945f36 100644 --- a/drivers/nvdimm/virtio_pmem.c +++ b/drivers/nvdimm/virtio_pmem.c @@ -105,7 +105,7 @@ static void virtio_pmem_remove(struct virtio_device *vdev) nvdimm_bus_unregister(nvdimm_bus); vdev->config->del_vqs(vdev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); } static struct virtio_driver virtio_pmem_driver = { diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 7d7ed4e5cce7b3d0cb281414f40e4d4694111b6c..4ef2fe3e65ace006d1a0b6065c9586a1e1b3ddc8 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -1012,7 +1012,7 @@ static void rpmsg_remove(struct virtio_device *vdev) size_t total_buf_space = vrp->num_bufs * vrp->buf_size; int ret; - vdev->config->reset(vdev); + virtio_reset_device(vdev); ret = device_for_each_child(&vdev->dev, NULL, rpmsg_remove_device); if (ret) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index fabbad5cda602d1fe10d1aa7642fbb93c7953df7..d0a770dfa77fa4158b136ed96c81e5df71ee1918 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -780,7 +780,7 @@ static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq, static void virtscsi_remove_vqs(struct virtio_device *vdev) { /* Stop all the virtqueues. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); } diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index 32e6502193763ba2dca3f9971d0f4b409a6574f2..862f4591fff2a2b4c77fecc912fb15b0c99ed970 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -167,7 +167,7 @@ static struct ifcvf_hw *vdpa_to_vf(struct vdpa_device *vdpa_dev) return &adapter->vf; } -static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev) +static u64 ifcvf_vdpa_get_device_features(struct vdpa_device *vdpa_dev) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); u64 features; @@ -177,7 +177,7 @@ static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev) return features; } -static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features) +static int ifcvf_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 features) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); @@ -186,6 +186,13 @@ static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features) return 0; } +static u64 ifcvf_vdpa_get_driver_features(struct vdpa_device *vdpa_dev) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + return vf->req_features; +} + static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); @@ -391,8 +398,9 @@ static int ifcvf_vdpa_get_vq_irq(struct vdpa_device *vdpa_dev, * implemented set_map()/dma_map()/dma_unmap() */ static const struct vdpa_config_ops ifc_vdpa_ops = { - .get_features = ifcvf_vdpa_get_features, - .set_features = ifcvf_vdpa_set_features, + .get_device_features = ifcvf_vdpa_get_device_features, + .set_driver_features = ifcvf_vdpa_set_driver_features, + .get_driver_features = ifcvf_vdpa_get_driver_features, .get_status = ifcvf_vdpa_get_status, .set_status = ifcvf_vdpa_set_status, .reset = ifcvf_vdpa_reset, @@ -457,7 +465,7 @@ 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, NULL); + dev, &ifc_vdpa_ops, 1, 1, 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 da4844ced1247336db9cbfe4c5bfd2e0cbd18cf9..76e7b4bab9d3b28f31df7396b75c0b8fd4fd8e0c 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1467,7 +1467,7 @@ static u64 mlx_to_vritio_features(u16 dev_features) return result; } -static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev) +static u64 mlx5_vdpa_get_device_features(struct vdpa_device *vdev) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); @@ -1550,7 +1550,7 @@ static __virtio16 cpu_to_mlx5vdpa16(struct mlx5_vdpa_dev *mvdev, u16 val) return __cpu_to_virtio16(mlx5_vdpa_is_little_endian(mvdev), val); } -static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features) +static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); @@ -1843,7 +1843,8 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev) return mvdev->generation; } -static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb) +static int mlx5_vdpa_set_map(struct vdpa_device *vdev, unsigned int asid, + struct vhost_iotlb *iotlb) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); @@ -1891,6 +1892,13 @@ static int mlx5_get_vq_irq(struct vdpa_device *vdv, u16 idx) return -EOPNOTSUPP; } +static u64 mlx5_vdpa_get_driver_features(struct vdpa_device *vdev) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + + return mvdev->actual_features; +} + static const struct vdpa_config_ops mlx5_vdpa_ops = { .set_vq_address = mlx5_vdpa_set_vq_address, .set_vq_num = mlx5_vdpa_set_vq_num, @@ -1903,8 +1911,9 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = { .get_vq_notification = mlx5_get_vq_notification, .get_vq_irq = mlx5_get_vq_irq, .get_vq_align = mlx5_vdpa_get_vq_align, - .get_features = mlx5_vdpa_get_features, - .set_features = mlx5_vdpa_set_features, + .get_device_features = mlx5_vdpa_get_device_features, + .set_driver_features = mlx5_vdpa_set_driver_features, + .get_driver_features = mlx5_vdpa_get_driver_features, .set_config_cb = mlx5_vdpa_set_config_cb, .get_vq_num_max = mlx5_vdpa_get_vq_num_max, .get_device_id = mlx5_vdpa_get_device_id, @@ -2006,7 +2015,7 @@ void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev) 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, - NULL); + 1, 1, NULL, false); if (IS_ERR(ndev)) return ndev; diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index fe7842f08d0d632e6bd8ef54b4f83d0088b8f1f0..5c9e37061fce49547c102cc66bb7d6afbc3675e5 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -14,20 +14,37 @@ #include #include #include +#include static LIST_HEAD(mdev_head); /* A global mutex that protects vdpa management device and device level operations. */ -static DEFINE_MUTEX(vdpa_dev_mutex); +static DECLARE_RWSEM(vdpa_dev_lock); static DEFINE_IDA(vdpa_index_ida); +void vdpa_set_status(struct vdpa_device *vdev, u8 status) +{ + down_write(&vdev->cf_lock); + vdev->config->set_status(vdev, status); + up_write(&vdev->cf_lock); +} +EXPORT_SYMBOL(vdpa_set_status); + static struct genl_family vdpa_nl_family; static int vdpa_dev_probe(struct device *d) { struct vdpa_device *vdev = dev_to_vdpa(d); struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver); + const struct vdpa_config_ops *ops = vdev->config; + u32 max_num, min_num = 1; int ret = 0; + max_num = ops->get_vq_num_max(vdev); + if (ops->get_vq_num_min) + min_num = ops->get_vq_num_min(vdev); + if (max_num < min_num) + return -EINVAL; + if (drv && drv->probe) ret = drv->probe(vdev); @@ -47,14 +64,14 @@ static int vdpa_dev_remove(struct device *d) static int vdpa_dev_match(struct device *dev, struct device_driver *drv) { - struct vdpa_device *vdev = dev_to_vdpa(dev); + struct vdpa_device *vdev = dev_to_vdpa(dev); - /* Check override first, and if set, only use the named driver */ - if (vdev->driver_override) - return strcmp(vdev->driver_override, drv->name) == 0; + /* Check override first, and if set, only use the named driver */ + if (vdev->driver_override) + return strcmp(vdev->driver_override, drv->name) == 0; - /* Currently devices must be supported by all vDPA bus drivers */ - return 1; + /* Currently devices must be supported by all vDPA bus drivers */ + return 1; } static ssize_t driver_override_store(struct device *dev, @@ -95,30 +112,30 @@ static ssize_t driver_override_store(struct device *dev, static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct vdpa_device *vdev = dev_to_vdpa(dev); - ssize_t len; + struct vdpa_device *vdev = dev_to_vdpa(dev); + ssize_t len; - device_lock(dev); - len = snprintf(buf, PAGE_SIZE, "%s\n", vdev->driver_override); - device_unlock(dev); + device_lock(dev); + len = snprintf(buf, PAGE_SIZE, "%s\n", vdev->driver_override); + device_unlock(dev); - return len; + return len; } static DEVICE_ATTR_RW(driver_override); static struct attribute *vdpa_dev_attrs[] = { - &dev_attr_driver_override.attr, - NULL, + &dev_attr_driver_override.attr, + NULL, }; static const struct attribute_group vdpa_dev_group = { - .attrs = vdpa_dev_attrs, + .attrs = vdpa_dev_attrs, }; __ATTRIBUTE_GROUPS(vdpa_dev); static struct bus_type vdpa_bus = { - .name = "vdpa", + .name = "vdpa", .dev_groups = vdpa_dev_groups, .match = vdpa_dev_match, .probe = vdpa_dev_probe, @@ -144,18 +161,23 @@ static void vdpa_release_dev(struct device *d) * initialized but before registered. * @parent: the parent device * @config: the bus operations that is supported by this device + * @ngroups: number of groups supported by this device + * @nas: number of address spaces supported by this device * @size: size of the parent structure that contains private data * @name: name of the vdpa device; optional. + * @use_va: indicate whether virtual address must be used by this device * * Driver should use vdpa_alloc_device() wrapper macro instead of * using this directly. * - * Returns an error when parent/config/dma_dev is not set or fail to get - * ida. + * Return: Returns an error when parent/config/dma_dev is not set or fail to get + * ida. */ struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - size_t size, const char *name) + unsigned int ngroups, unsigned int nas, + size_t size, const char *name, + bool use_va) { struct vdpa_device *vdev; int err = -EINVAL; @@ -166,12 +188,16 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, if (!!config->dma_map != !!config->dma_unmap) goto err; + /* It should only work for the device that use on-chip IOMMU */ + if (use_va && !(config->dma_map || config->set_map)) + goto err; + err = -ENOMEM; vdev = kzalloc(size, GFP_KERNEL); if (!vdev) goto err; - err = ida_simple_get(&vdpa_index_ida, 0, 0, GFP_KERNEL); + err = ida_alloc(&vdpa_index_ida, GFP_KERNEL); if (err < 0) goto err_ida; @@ -181,6 +207,9 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->index = err; vdev->config = config; vdev->features_valid = false; + vdev->use_va = use_va; + vdev->ngroups = ngroups; + vdev->nas = nas; if (name) err = dev_set_name(&vdev->dev, "%s", name); @@ -189,6 +218,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, if (err) goto err_name; + init_rwsem(&vdev->cf_lock); device_initialize(&vdev->dev); return vdev; @@ -209,13 +239,13 @@ static int vdpa_name_match(struct device *dev, const void *data) return (strcmp(dev_name(&vdev->dev), data) == 0); } -static int __vdpa_register_device(struct vdpa_device *vdev, int nvqs) +static int __vdpa_register_device(struct vdpa_device *vdev, u32 nvqs) { struct device *dev; vdev->nvqs = nvqs; - lockdep_assert_held(&vdpa_dev_mutex); + lockdep_assert_held(&vdpa_dev_lock); dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match); if (dev) { put_device(dev); @@ -232,9 +262,9 @@ static int __vdpa_register_device(struct vdpa_device *vdev, int nvqs) * @vdev: the vdpa device to be registered to vDPA bus * @nvqs: number of virtqueues supported by this device * - * Returns an error when fail to add device to vDPA bus + * Return: Returns an error when fail to add device to vDPA bus */ -int _vdpa_register_device(struct vdpa_device *vdev, int nvqs) +int _vdpa_register_device(struct vdpa_device *vdev, u32 nvqs) { if (!vdev->mdev) return -EINVAL; @@ -249,15 +279,15 @@ EXPORT_SYMBOL_GPL(_vdpa_register_device); * @vdev: the vdpa device to be registered to vDPA bus * @nvqs: number of virtqueues supported by this device * - * Returns an error when fail to add to vDPA bus + * Return: Returns an error when fail to add to vDPA bus */ -int vdpa_register_device(struct vdpa_device *vdev, int nvqs) +int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs) { int err; - mutex_lock(&vdpa_dev_mutex); + down_write(&vdpa_dev_lock); err = __vdpa_register_device(vdev, nvqs); - mutex_unlock(&vdpa_dev_mutex); + up_write(&vdpa_dev_lock); return err; } EXPORT_SYMBOL_GPL(vdpa_register_device); @@ -270,7 +300,7 @@ EXPORT_SYMBOL_GPL(vdpa_register_device); */ void _vdpa_unregister_device(struct vdpa_device *vdev) { - lockdep_assert_held(&vdpa_dev_mutex); + lockdep_assert_held(&vdpa_dev_lock); WARN_ON(!vdev->mdev); device_unregister(&vdev->dev); } @@ -282,9 +312,9 @@ EXPORT_SYMBOL_GPL(_vdpa_unregister_device); */ void vdpa_unregister_device(struct vdpa_device *vdev) { - mutex_lock(&vdpa_dev_mutex); + down_write(&vdpa_dev_lock); device_unregister(&vdev->dev); - mutex_unlock(&vdpa_dev_mutex); + up_write(&vdpa_dev_lock); } EXPORT_SYMBOL_GPL(vdpa_unregister_device); @@ -293,7 +323,7 @@ EXPORT_SYMBOL_GPL(vdpa_unregister_device); * @drv: the vdpa device driver to be registered * @owner: module owner of the driver * - * Returns an err when fail to do the registration + * Return: Returns an err when fail to do the registration */ int __vdpa_register_driver(struct vdpa_driver *drv, struct module *owner) { @@ -320,6 +350,8 @@ EXPORT_SYMBOL_GPL(vdpa_unregister_driver); * @mdev: Pointer to vdpa management device * vdpa_mgmtdev_register() register a vdpa management device which supports * vdpa device management. + * Return: Returns 0 on success or failure when required callback ops are not + * initialized. */ int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev) { @@ -327,9 +359,9 @@ int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev) return -EINVAL; INIT_LIST_HEAD(&mdev->list); - mutex_lock(&vdpa_dev_mutex); + down_write(&vdpa_dev_lock); list_add_tail(&mdev->list, &mdev_head); - mutex_unlock(&vdpa_dev_mutex); + up_write(&vdpa_dev_lock); return 0; } EXPORT_SYMBOL_GPL(vdpa_mgmtdev_register); @@ -346,17 +378,64 @@ static int vdpa_match_remove(struct device *dev, void *data) void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev) { - mutex_lock(&vdpa_dev_mutex); + down_write(&vdpa_dev_lock); list_del(&mdev->list); /* Filter out all the entries belong to this management device and delete it. */ bus_for_each_dev(&vdpa_bus, NULL, mdev, vdpa_match_remove); - mutex_unlock(&vdpa_dev_mutex); + up_write(&vdpa_dev_lock); } EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister); +static void vdpa_get_config_unlocked(struct vdpa_device *vdev, + unsigned int offset, + void *buf, unsigned int len) +{ + const struct vdpa_config_ops *ops = vdev->config; + + /* + * Config accesses aren't supposed to trigger before features are set. + * If it does happen we assume a legacy guest. + */ + if (!vdev->features_valid) + vdpa_set_features_unlocked(vdev, 0); + ops->get_config(vdev, offset, buf, len); +} + +/** + * vdpa_get_config - Get one or more device configuration fields. + * @vdev: vdpa device to operate on + * @offset: starting byte offset of the field + * @buf: buffer pointer to read to + * @len: length of the configuration fields in bytes + */ +void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, + void *buf, unsigned int len) +{ + down_read(&vdev->cf_lock); + vdpa_get_config_unlocked(vdev, offset, buf, len); + up_read(&vdev->cf_lock); +} +EXPORT_SYMBOL_GPL(vdpa_get_config); + +/** + * vdpa_set_config - Set one or more device configuration fields. + * @vdev: vdpa device to operate on + * @offset: starting byte offset of the field + * @buf: buffer pointer to read from + * @length: length of the configuration fields in bytes + */ +void vdpa_set_config(struct vdpa_device *vdev, unsigned int offset, + const void *buf, unsigned int length) +{ + down_write(&vdev->cf_lock); + vdev->config->set_config(vdev, offset, buf, length); + up_write(&vdev->cf_lock); +} +EXPORT_SYMBOL_GPL(vdpa_set_config); + static bool mgmtdev_handle_match(const struct vdpa_mgmt_dev *mdev, const char *busname, const char *devname) { @@ -431,6 +510,16 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m err = -EMSGSIZE; goto msg_err; } + if (nla_put_u32(msg, VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, + mdev->max_supported_vqs)) { + err = -EMSGSIZE; + goto msg_err; + } + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_SUPPORTED_FEATURES, + mdev->supported_features, VDPA_ATTR_PAD)) { + err = -EMSGSIZE; + goto msg_err; + } genlmsg_end(msg, hdr); return 0; @@ -450,17 +539,17 @@ static int vdpa_nl_cmd_mgmtdev_get_doit(struct sk_buff *skb, struct genl_info *i if (!msg) return -ENOMEM; - mutex_lock(&vdpa_dev_mutex); + down_read(&vdpa_dev_lock); mdev = vdpa_mgmtdev_get_from_attr(info->attrs); if (IS_ERR(mdev)) { - mutex_unlock(&vdpa_dev_mutex); + up_read(&vdpa_dev_lock); NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified mgmt device"); err = PTR_ERR(mdev); goto out; } err = vdpa_mgmtdev_fill(mdev, msg, info->snd_portid, info->snd_seq, 0); - mutex_unlock(&vdpa_dev_mutex); + up_read(&vdpa_dev_lock); if (err) goto out; err = genlmsg_reply(msg, info); @@ -479,7 +568,7 @@ vdpa_nl_cmd_mgmtdev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) int idx = 0; int err; - mutex_lock(&vdpa_dev_mutex); + down_read(&vdpa_dev_lock); list_for_each_entry(mdev, &mdev_head, list) { if (idx < start) { idx++; @@ -492,14 +581,21 @@ vdpa_nl_cmd_mgmtdev_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) idx++; } out: - mutex_unlock(&vdpa_dev_mutex); + up_read(&vdpa_dev_lock); cb->args[0] = idx; return msg->len; } +#define VDPA_DEV_NET_ATTRS_MASK (BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR) | \ + BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU) | \ + BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP)) + static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info) { + struct vdpa_dev_set_config config = {}; + struct nlattr **nl_attrs = info->attrs; struct vdpa_mgmt_dev *mdev; + const u8 *macaddr; const char *name; int err = 0; @@ -508,17 +604,53 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); - mutex_lock(&vdpa_dev_mutex); + if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]) { + macaddr = nla_data(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]); + memcpy(config.net.mac, macaddr, sizeof(config.net.mac)); + config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR); + } + if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]) { + config.net.mtu = + nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]); + config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MTU); + } + if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]) { + config.net.max_vq_pairs = + nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]); + if (!config.net.max_vq_pairs) { + NL_SET_ERR_MSG_MOD(info->extack, + "At least one pair of VQs is required"); + return -EINVAL; + } + config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP); + } + + /* Skip checking capability if user didn't prefer to configure any + * device networking attributes. It is likely that user might have used + * a device specific method to configure such attributes or using device + * default attributes. + */ + if ((config.mask & VDPA_DEV_NET_ATTRS_MASK) && + !netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + down_write(&vdpa_dev_lock); mdev = vdpa_mgmtdev_get_from_attr(info->attrs); if (IS_ERR(mdev)) { NL_SET_ERR_MSG_MOD(info->extack, "Fail to find the specified management device"); err = PTR_ERR(mdev); goto err; } + if ((config.mask & mdev->config_attr_mask) != config.mask) { + NL_SET_ERR_MSG_MOD(info->extack, + "All provided attributes are not supported"); + err = -EOPNOTSUPP; + goto err; + } - err = mdev->ops->dev_add(mdev, name); + err = mdev->ops->dev_add(mdev, name, &config); err: - mutex_unlock(&vdpa_dev_mutex); + up_write(&vdpa_dev_lock); return err; } @@ -534,7 +666,7 @@ static int vdpa_nl_cmd_dev_del_set_doit(struct sk_buff *skb, struct genl_info *i return -EINVAL; name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); - mutex_lock(&vdpa_dev_mutex); + down_write(&vdpa_dev_lock); dev = bus_find_device(&vdpa_bus, NULL, name, vdpa_name_match); if (!dev) { NL_SET_ERR_MSG_MOD(info->extack, "device not found"); @@ -552,7 +684,7 @@ static int vdpa_nl_cmd_dev_del_set_doit(struct sk_buff *skb, struct genl_info *i mdev_err: put_device(dev); dev_err: - mutex_unlock(&vdpa_dev_mutex); + up_write(&vdpa_dev_lock); return err; } @@ -561,6 +693,7 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq int flags, struct netlink_ext_ack *extack) { u16 max_vq_size; + u16 min_vq_size = 1; u32 device_id; u32 vendor_id; void *hdr; @@ -577,6 +710,8 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq device_id = vdev->config->get_device_id(vdev); vendor_id = vdev->config->get_vendor_id(vdev); max_vq_size = vdev->config->get_vq_num_max(vdev); + if (vdev->config->get_vq_num_min) + min_vq_size = vdev->config->get_vq_num_min(vdev); err = -EMSGSIZE; if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) @@ -589,6 +724,8 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq goto msg_err; if (nla_put_u16(msg, VDPA_ATTR_DEV_MAX_VQ_SIZE, max_vq_size)) goto msg_err; + if (nla_put_u16(msg, VDPA_ATTR_DEV_MIN_VQ_SIZE, min_vq_size)) + goto msg_err; genlmsg_end(msg, hdr); return 0; @@ -613,7 +750,7 @@ static int vdpa_nl_cmd_dev_get_doit(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - mutex_lock(&vdpa_dev_mutex); + down_read(&vdpa_dev_lock); dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match); if (!dev) { NL_SET_ERR_MSG_MOD(info->extack, "device not found"); @@ -626,14 +763,19 @@ static int vdpa_nl_cmd_dev_get_doit(struct sk_buff *skb, struct genl_info *info) goto mdev_err; } err = vdpa_dev_fill(vdev, msg, info->snd_portid, info->snd_seq, 0, info->extack); - if (!err) - err = genlmsg_reply(msg, info); + if (err) + goto mdev_err; + + err = genlmsg_reply(msg, info); + put_device(dev); + up_read(&vdpa_dev_lock); + return err; + mdev_err: put_device(dev); err: - mutex_unlock(&vdpa_dev_mutex); - if (err) - nlmsg_free(msg); + up_read(&vdpa_dev_lock); + nlmsg_free(msg); return err; } @@ -674,17 +816,347 @@ static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callba info.start_idx = cb->args[0]; info.idx = 0; - mutex_lock(&vdpa_dev_mutex); + down_read(&vdpa_dev_lock); bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_dump); - mutex_unlock(&vdpa_dev_mutex); + up_read(&vdpa_dev_lock); cb->args[0] = info.idx; return msg->len; } +static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev, + struct sk_buff *msg, u64 features, + const struct virtio_net_config *config) +{ + u16 val_u16; + + if ((features & BIT_ULL(VIRTIO_NET_F_MQ)) == 0) + return 0; + + val_u16 = le16_to_cpu(config->max_virtqueue_pairs); + return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, val_u16); +} + +static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) +{ + struct virtio_net_config config = {}; + u64 features; + u16 val_u16; + + vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config)); + + if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac), + config.mac)) + return -EMSGSIZE; + + val_u16 = __virtio16_to_cpu(true, config.status); + if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_STATUS, val_u16)) + return -EMSGSIZE; + + val_u16 = __virtio16_to_cpu(true, config.mtu); + if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16)) + return -EMSGSIZE; + + features = vdev->config->get_driver_features(vdev); + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features, + VDPA_ATTR_PAD)) + return -EMSGSIZE; + + return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config); +} + +static int +vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) +{ + u32 device_id; + void *hdr; + int err; + + down_read(&vdev->cf_lock); + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, + VDPA_CMD_DEV_CONFIG_GET); + if (!hdr) { + err = -EMSGSIZE; + goto out; + } + + if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) { + err = -EMSGSIZE; + goto msg_err; + } + + device_id = vdev->config->get_device_id(vdev); + if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) { + err = -EMSGSIZE; + goto msg_err; + } + + switch (device_id) { + case VIRTIO_ID_NET: + err = vdpa_dev_net_config_fill(vdev, msg); + break; + default: + err = -EOPNOTSUPP; + break; + } + if (err) + goto msg_err; + + up_read(&vdev->cf_lock); + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); +out: + up_read(&vdev->cf_lock); + return err; +} + +static int vdpa_fill_stats_rec(struct vdpa_device *vdev, struct sk_buff *msg, + struct genl_info *info, u32 index) +{ + struct virtio_net_config config = {}; + u64 features; + u16 max_vqp; + u8 status; + int err; + + status = vdev->config->get_status(vdev); + if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) { + NL_SET_ERR_MSG_MOD(info->extack, "feature negotiation not complete"); + return -EAGAIN; + } + vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config)); + + max_vqp = __virtio16_to_cpu(true, config.max_virtqueue_pairs); + if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, max_vqp)) + return -EMSGSIZE; + + features = vdev->config->get_driver_features(vdev); + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, + features, VDPA_ATTR_PAD)) + return -EMSGSIZE; + + if (nla_put_u32(msg, VDPA_ATTR_DEV_QUEUE_INDEX, index)) + return -EMSGSIZE; + + err = vdev->config->get_vendor_vq_stats(vdev, index, msg, info->extack); + if (err) + return err; + + return 0; +} + +static int vendor_stats_fill(struct vdpa_device *vdev, struct sk_buff *msg, + struct genl_info *info, u32 index) +{ + int err; + + down_read(&vdev->cf_lock); + if (!vdev->config->get_vendor_vq_stats) { + err = -EOPNOTSUPP; + goto out; + } + + err = vdpa_fill_stats_rec(vdev, msg, info, index); +out: + up_read(&vdev->cf_lock); + return err; +} + +static int vdpa_dev_vendor_stats_fill(struct vdpa_device *vdev, + struct sk_buff *msg, + struct genl_info *info, u32 index) +{ + u32 device_id; + void *hdr; + int err; + u32 portid = info->snd_portid; + u32 seq = info->snd_seq; + u32 flags = 0; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, + VDPA_CMD_DEV_VSTATS_GET); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) { + err = -EMSGSIZE; + goto undo_msg; + } + + device_id = vdev->config->get_device_id(vdev); + if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) { + err = -EMSGSIZE; + goto undo_msg; + } + + switch (device_id) { + case VIRTIO_ID_NET: + if (index > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX) { + NL_SET_ERR_MSG_MOD(info->extack, "queue index excceeds max value"); + err = -ERANGE; + break; + } + + err = vendor_stats_fill(vdev, msg, info, index); + break; + default: + err = -EOPNOTSUPP; + break; + } + genlmsg_end(msg, hdr); + + return err; + +undo_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_dev_config_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_device *vdev; + struct sk_buff *msg; + const char *devname; + struct device *dev; + int err; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + down_read(&vdpa_dev_lock); + dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto dev_err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device"); + err = -EINVAL; + goto mdev_err; + } + err = vdpa_dev_config_fill(vdev, msg, info->snd_portid, info->snd_seq, + 0, info->extack); + if (!err) + err = genlmsg_reply(msg, info); + +mdev_err: + put_device(dev); +dev_err: + up_read(&vdpa_dev_lock); + if (err) + nlmsg_free(msg); + return err; +} + +static int vdpa_dev_config_dump(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_dev_dump_info *info = data; + int err; + + if (!vdev->mdev) + return 0; + if (info->idx < info->start_idx) { + info->idx++; + return 0; + } + err = vdpa_dev_config_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid, + info->cb->nlh->nlmsg_seq, NLM_F_MULTI, + info->cb->extack); + if (err) + return err; + + info->idx++; + return 0; +} + +static int +vdpa_nl_cmd_dev_config_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_dev_dump_info info; + + info.msg = msg; + info.cb = cb; + info.start_idx = cb->args[0]; + info.idx = 0; + + down_read(&vdpa_dev_lock); + bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_config_dump); + up_read(&vdpa_dev_lock); + cb->args[0] = info.idx; + return msg->len; +} + +static int vdpa_nl_cmd_dev_stats_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct vdpa_device *vdev; + struct sk_buff *msg; + const char *devname; + struct device *dev; + u32 index; + int err; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + + if (!info->attrs[VDPA_ATTR_DEV_QUEUE_INDEX]) + return -EINVAL; + + devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + index = nla_get_u32(info->attrs[VDPA_ATTR_DEV_QUEUE_INDEX]); + down_read(&vdpa_dev_lock); + dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto dev_err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device"); + err = -EINVAL; + goto mdev_err; + } + err = vdpa_dev_vendor_stats_fill(vdev, msg, info, index); + if (err) + goto mdev_err; + + err = genlmsg_reply(msg, info); + + put_device(dev); + up_read(&vdpa_dev_lock); + + return err; + +mdev_err: + put_device(dev); +dev_err: + nlmsg_free(msg); + up_read(&vdpa_dev_lock); + return err; +} + static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, [VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING }, + [VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR, + /* virtio spec 1.1 section 5.1.4.1 for valid MTU range */ + [VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68), }; static const struct genl_ops vdpa_nl_ops[] = { @@ -712,6 +1184,18 @@ static const struct genl_ops vdpa_nl_ops[] = { .doit = vdpa_nl_cmd_dev_get_doit, .dumpit = vdpa_nl_cmd_dev_get_dumpit, }, + { + .cmd = VDPA_CMD_DEV_CONFIG_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_config_get_doit, + .dumpit = vdpa_nl_cmd_dev_config_get_dumpit, + }, + { + .cmd = VDPA_CMD_DEV_VSTATS_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_stats_get_doit, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_family vdpa_nl_family __ro_after_init = { diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index e856562db9d072907a6e9c3a57f28932df0bb4c0..c141f08b82740b3dc562d0e72b9d050dbb7ad6fb 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -52,6 +52,17 @@ static struct vdpasim *dev_to_sim(struct device *dev) return vdpa_to_sim(vdpa); } +static void vdpasim_vq_notify(struct vringh *vring) +{ + struct vdpasim_virtqueue *vq = + container_of(vring, struct vdpasim_virtqueue, vring); + + if (!vq->cb) + return; + + vq->cb(vq->private); +} + static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) { struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; @@ -63,6 +74,8 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) (uintptr_t)vq->driver_addr, (struct vring_used *) (uintptr_t)vq->device_addr); + + vq->vring.notify = vdpasim_vq_notify; } static void vdpasim_vq_reset(struct vdpasim *vdpasim, @@ -76,6 +89,8 @@ static void vdpasim_vq_reset(struct vdpasim *vdpasim, vq->private = NULL; vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features, VDPASIM_QUEUE_MAX, false, NULL, NULL, NULL); + + vq->vring.notify = NULL; } static void vdpasim_do_reset(struct vdpasim *vdpasim) @@ -221,8 +236,8 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) else ops = &vdpasim_net_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, - dev_attr->name); + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, + 1, dev_attr->name, false); if (!vdpasim) goto err_alloc; @@ -363,14 +378,19 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa) return VDPASIM_QUEUE_ALIGN; } -static u64 vdpasim_get_features(struct vdpa_device *vdpa) +static u32 vdpasim_get_vq_group(struct vdpa_device *vdpa, u16 idx) +{ + return 0; +} + +static u64 vdpasim_get_device_features(struct vdpa_device *vdpa) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); return vdpasim->dev_attr.supported_features; } -static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) +static int vdpasim_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); @@ -383,6 +403,13 @@ static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 vdpasim_get_driver_features(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vdpasim->features; +} + static void vdpasim_set_config_cb(struct vdpa_device *vdpa, struct vdpa_callback *cb) { @@ -491,7 +518,7 @@ static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa) return range; } -static int vdpasim_set_map(struct vdpa_device *vdpa, +static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid, struct vhost_iotlb *iotlb) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); @@ -518,21 +545,23 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, return ret; } -static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size, - u64 pa, u32 perm) +static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid, + u64 iova, u64 size, + u64 pa, u32 perm, void *opaque) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); int ret; spin_lock(&vdpasim->iommu_lock); - ret = vhost_iotlb_add_range(vdpasim->iommu, iova, iova + size - 1, pa, - perm); + ret = vhost_iotlb_add_range_ctx(vdpasim->iommu, iova, iova + size - 1, + pa, perm, opaque); spin_unlock(&vdpasim->iommu_lock); return ret; } -static int vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size) +static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid, + u64 iova, u64 size) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); @@ -565,8 +594,10 @@ static const struct vdpa_config_ops vdpasim_net_config_ops = { .set_vq_state = vdpasim_set_vq_state, .get_vq_state = vdpasim_get_vq_state, .get_vq_align = vdpasim_get_vq_align, - .get_features = vdpasim_get_features, - .set_features = vdpasim_set_features, + .get_vq_group = vdpasim_get_vq_group, + .get_device_features = vdpasim_get_device_features, + .set_driver_features = vdpasim_set_driver_features, + .get_driver_features = vdpasim_get_driver_features, .set_config_cb = vdpasim_set_config_cb, .get_vq_num_max = vdpasim_get_vq_num_max, .get_device_id = vdpasim_get_device_id, @@ -594,8 +625,10 @@ static const struct vdpa_config_ops vdpasim_net_batch_config_ops = { .set_vq_state = vdpasim_set_vq_state, .get_vq_state = vdpasim_get_vq_state, .get_vq_align = vdpasim_get_vq_align, - .get_features = vdpasim_get_features, - .set_features = vdpasim_set_features, + .get_vq_group = vdpasim_get_vq_group, + .get_device_features = vdpasim_get_device_features, + .set_driver_features = vdpasim_set_driver_features, + .get_driver_features = vdpasim_get_driver_features, .set_config_cb = vdpasim_set_config_cb, .get_vq_num_max = vdpasim_get_vq_num_max, .get_device_id = vdpasim_get_device_id, diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h index 6d75444f994825f88e8ad191e339f93e195d4f09..b4bb4f2905f0f29762bfb5b43fc37544947a1932 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.h +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h @@ -61,6 +61,7 @@ struct vdpasim { u32 status; u32 generation; u64 features; + u32 groups; /* spinlock to synchronize iommu table */ spinlock_t iommu_lock; }; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index 0650328c7475017a0b312b457f85a1d014d0cd7b..eddc2475559518a5023b61142813842d1cc4b501 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -105,7 +105,8 @@ static struct device vdpasim_blk_mgmtdev = { .release = vdpasim_blk_mgmtdev_release, }; -static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) +static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config) { struct vdpasim_dev_attr dev_attr = {}; struct vdpasim *simdev; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index bf766bfd694a1d7a75cf91d23474a8317d1fd242..7360e678f62f199b20841a6b60713177f1c3b995 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -127,7 +127,8 @@ static struct device vdpasim_net_mgmtdev = { .release = vdpasim_net_mgmtdev_release, }; -static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) +static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config) { struct vdpasim_dev_attr dev_attr = {}; struct vdpasim *simdev; diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index 1b0ced8a48ba005c7c870e502de567a83d1054e0..f4e375b1d903c3d34b11126a3f73561945c59ae4 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -32,7 +32,7 @@ struct vp_vring { struct vp_vdpa { struct vdpa_device vdpa; - struct virtio_pci_modern_device mdev; + struct virtio_pci_modern_device *mdev; struct vp_vring *vring; struct vdpa_callback config_cb; char msix_name[VP_VDPA_NAME_SIZE]; @@ -41,6 +41,12 @@ struct vp_vdpa { int vectors; }; +struct vp_vdpa_mgmtdev { + struct vdpa_mgmt_dev mgtdev; + struct virtio_pci_modern_device *mdev; + struct vp_vdpa *vp_vdpa; +}; + static struct vp_vdpa *vdpa_to_vp(struct vdpa_device *vdpa) { return container_of(vdpa, struct vp_vdpa, vdpa); @@ -50,17 +56,22 @@ static struct virtio_pci_modern_device *vdpa_to_mdev(struct vdpa_device *vdpa) { struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa); - return &vp_vdpa->mdev; + return vp_vdpa->mdev; +} + +static struct virtio_pci_modern_device *vp_vdpa_to_mdev(struct vp_vdpa *vp_vdpa) +{ + return vp_vdpa->mdev; } -static u64 vp_vdpa_get_features(struct vdpa_device *vdpa) +static u64 vp_vdpa_get_device_features(struct vdpa_device *vdpa) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); return vp_modern_get_features(mdev); } -static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features) +static int vp_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); @@ -69,6 +80,13 @@ static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 vp_vdpa_get_driver_features(struct vdpa_device *vdpa) +{ + struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); + + return vp_modern_get_driver_features(mdev); +} + static u8 vp_vdpa_get_status(struct vdpa_device *vdpa) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); @@ -89,7 +107,7 @@ static int vp_vdpa_get_vq_irq(struct vdpa_device *vdpa, u16 idx) static void vp_vdpa_free_irq(struct vp_vdpa *vp_vdpa) { - struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev; + struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa); struct pci_dev *pdev = mdev->pci_dev; int i; @@ -136,7 +154,7 @@ static irqreturn_t vp_vdpa_config_handler(int irq, void *arg) static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa) { - struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev; + struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa); struct pci_dev *pdev = mdev->pci_dev; int i, ret, irq; int queues = vp_vdpa->queues; @@ -191,7 +209,7 @@ static int vp_vdpa_request_irq(struct vp_vdpa *vp_vdpa) static void vp_vdpa_set_status(struct vdpa_device *vdpa, u8 status) { struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa); - struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev; + struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa); u8 s = vp_vdpa_get_status(vdpa); if (status & VIRTIO_CONFIG_S_DRIVER_OK && @@ -205,7 +223,7 @@ static void vp_vdpa_set_status(struct vdpa_device *vdpa, u8 status) static int vp_vdpa_reset(struct vdpa_device *vdpa) { struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa); - struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev; + struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa); u8 s = vp_vdpa_get_status(vdpa); vp_modern_set_status(mdev, 0); @@ -365,7 +383,7 @@ static void vp_vdpa_get_config(struct vdpa_device *vdpa, void *buf, unsigned int len) { struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa); - struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev; + struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa); u8 old, new; u8 *p; int i; @@ -385,7 +403,7 @@ static void vp_vdpa_set_config(struct vdpa_device *vdpa, unsigned int len) { struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa); - struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev; + struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa); const u8 *p = buf; int i; @@ -405,7 +423,7 @@ static struct vdpa_notification_area vp_vdpa_get_vq_notification(struct vdpa_device *vdpa, u16 qid) { struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa); - struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev; + struct virtio_pci_modern_device *mdev = vp_vdpa_to_mdev(vp_vdpa); struct vdpa_notification_area notify; notify.addr = vp_vdpa->vring[qid].notify_pa; @@ -415,8 +433,9 @@ vp_vdpa_get_vq_notification(struct vdpa_device *vdpa, u16 qid) } static const struct vdpa_config_ops vp_vdpa_ops = { - .get_features = vp_vdpa_get_features, - .set_features = vp_vdpa_set_features, + .get_device_features = vp_vdpa_get_device_features, + .set_driver_features = vp_vdpa_set_driver_features, + .get_driver_features = vp_vdpa_get_driver_features, .get_status = vp_vdpa_get_status, .set_status = vp_vdpa_set_status, .reset = vp_vdpa_reset, @@ -446,38 +465,31 @@ static void vp_vdpa_free_irq_vectors(void *data) pci_free_irq_vectors(data); } -static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) +static int vp_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, + const struct vdpa_dev_set_config *add_config) { - struct virtio_pci_modern_device *mdev; + struct vp_vdpa_mgmtdev *vp_vdpa_mgtdev = + container_of(v_mdev, struct vp_vdpa_mgmtdev, mgtdev); + + struct virtio_pci_modern_device *mdev = vp_vdpa_mgtdev->mdev; + struct pci_dev *pdev = mdev->pci_dev; struct device *dev = &pdev->dev; - struct vp_vdpa *vp_vdpa; + struct vp_vdpa *vp_vdpa = NULL; int ret, i; - ret = pcim_enable_device(pdev); - if (ret) - return ret; - vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa, - dev, &vp_vdpa_ops, NULL); + dev, &vp_vdpa_ops, 1, 1, name, false); + if (IS_ERR(vp_vdpa)) { dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n"); return PTR_ERR(vp_vdpa); } - mdev = &vp_vdpa->mdev; - mdev->pci_dev = pdev; - - ret = vp_modern_probe(mdev); - if (ret) { - dev_err(&pdev->dev, "Failed to probe modern PCI device\n"); - goto err; - } - - pci_set_master(pdev); - pci_set_drvdata(pdev, vp_vdpa); + vp_vdpa_mgtdev->vp_vdpa = vp_vdpa; vp_vdpa->vdpa.dma_dev = &pdev->dev; vp_vdpa->queues = vp_modern_get_num_queues(mdev); + vp_vdpa->mdev = mdev; ret = devm_add_action_or_reset(dev, vp_vdpa_free_irq_vectors, pdev); if (ret) { @@ -501,13 +513,15 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) vp_modern_map_vq_notify(mdev, i, &vp_vdpa->vring[i].notify_pa); if (!vp_vdpa->vring[i].notify) { + ret = -EINVAL; dev_warn(&pdev->dev, "Fail to map vq notify %d\n", i); goto err; } } vp_vdpa->config_irq = VIRTIO_MSI_NO_VECTOR; - ret = vdpa_register_device(&vp_vdpa->vdpa, vp_vdpa->queues); + vp_vdpa->vdpa.mdev = &vp_vdpa_mgtdev->mgtdev; + ret = _vdpa_register_device(&vp_vdpa->vdpa, vp_vdpa->queues); if (ret) { dev_err(&pdev->dev, "Failed to register to vdpa bus\n"); goto err; @@ -520,12 +534,104 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) return ret; } +static void vp_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, + struct vdpa_device *dev) +{ + struct vp_vdpa_mgmtdev *vp_vdpa_mgtdev = + container_of(v_mdev, struct vp_vdpa_mgmtdev, mgtdev); + + struct vp_vdpa *vp_vdpa = vp_vdpa_mgtdev->vp_vdpa; + + _vdpa_unregister_device(&vp_vdpa->vdpa); + vp_vdpa_mgtdev->vp_vdpa = NULL; +} + +static const struct vdpa_mgmtdev_ops vp_vdpa_mdev_ops = { + .dev_add = vp_vdpa_dev_add, + .dev_del = vp_vdpa_dev_del, +}; + +static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct vp_vdpa_mgmtdev *vp_vdpa_mgtdev = NULL; + struct vdpa_mgmt_dev *mgtdev; + struct device *dev = &pdev->dev; + struct virtio_pci_modern_device *mdev = NULL; + struct virtio_device_id *mdev_id = NULL; + int err; + + vp_vdpa_mgtdev = kzalloc(sizeof(*vp_vdpa_mgtdev), GFP_KERNEL); + if (!vp_vdpa_mgtdev) + return -ENOMEM; + + mgtdev = &vp_vdpa_mgtdev->mgtdev; + mgtdev->ops = &vp_vdpa_mdev_ops; + mgtdev->device = dev; + + mdev = kzalloc(sizeof(struct virtio_pci_modern_device), GFP_KERNEL); + if (!mdev) { + err = -ENOMEM; + goto mdev_err; + } + + mdev_id = kzalloc(sizeof(struct virtio_device_id), GFP_KERNEL); + if (!mdev_id) { + err = -ENOMEM; + goto mdev_id_err; + } + + vp_vdpa_mgtdev->mdev = mdev; + mdev->pci_dev = pdev; + + err = pcim_enable_device(pdev); + if (err) { + goto probe_err; + } + + err = vp_modern_probe(mdev); + if (err) { + dev_err(&pdev->dev, "Failed to probe modern PCI device\n"); + goto probe_err; + } + + mdev_id->device = mdev->id.device; + mdev_id->vendor = mdev->id.vendor; + mgtdev->id_table = mdev_id; + mgtdev->max_supported_vqs = vp_modern_get_num_queues(mdev); + mgtdev->supported_features = vp_modern_get_features(mdev); + pci_set_master(pdev); + pci_set_drvdata(pdev, vp_vdpa_mgtdev); + + err = vdpa_mgmtdev_register(mgtdev); + if (err) { + dev_err(&pdev->dev, "Failed to register vdpa mgmtdev device\n"); + goto register_err; + } + + return 0; + +register_err: + vp_modern_remove(vp_vdpa_mgtdev->mdev); +probe_err: + kfree(mdev_id); +mdev_id_err: + kfree(mdev); +mdev_err: + kfree(vp_vdpa_mgtdev); + return err; +} + static void vp_vdpa_remove(struct pci_dev *pdev) { - struct vp_vdpa *vp_vdpa = pci_get_drvdata(pdev); + struct vp_vdpa_mgmtdev *vp_vdpa_mgtdev = pci_get_drvdata(pdev); + struct virtio_pci_modern_device *mdev = NULL; - vp_modern_remove(&vp_vdpa->mdev); - vdpa_unregister_device(&vp_vdpa->vdpa); + mdev = vp_vdpa_mgtdev->mdev; + vp_modern_remove(mdev); + vdpa_mgmtdev_unregister(&vp_vdpa_mgtdev->mgtdev); + kfree(vp_vdpa_mgtdev->mgtdev.id_table); + kfree(mdev); + kfree(vp_vdpa_mgtdev); } static struct pci_driver vp_vdpa_driver = { diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c index 0fd3f87e913c7f70e8d670729632f2bff33779cc..dc936bb65627a00da29b9999235883d841eb7fcc 100644 --- a/drivers/vhost/iotlb.c +++ b/drivers/vhost/iotlb.c @@ -36,25 +36,42 @@ void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, EXPORT_SYMBOL_GPL(vhost_iotlb_map_free); /** - * vhost_iotlb_add_range - add a new range to vhost IOTLB + * vhost_iotlb_add_range_ctx - add a new range to vhost IOTLB * @iotlb: the IOTLB * @start: start of the IOVA range * @last: last of IOVA range * @addr: the address that is mapped to @start * @perm: access permission of this range + * @opaque: the opaque pointer for the new mapping * * Returns an error last is smaller than start or memory allocation * fails */ -int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, - u64 start, u64 last, - u64 addr, unsigned int perm) +int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, + u64 start, u64 last, + u64 addr, unsigned int perm, + void *opaque) { struct vhost_iotlb_map *map; if (last < start) return -EFAULT; + /* If the range being mapped is [0, ULONG_MAX], split it into two entries + * otherwise its size would overflow u64. + */ + if (start == 0 && last == ULONG_MAX) { + u64 mid = last / 2; + int err = vhost_iotlb_add_range_ctx(iotlb, start, mid, addr, + perm, opaque); + + if (err) + return err; + + addr += mid + 1; + start = mid + 1; + } + if (iotlb->limit && iotlb->nmaps == iotlb->limit && iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) { @@ -71,6 +88,7 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, map->last = last; map->addr = addr; map->perm = perm; + map->opaque = opaque; iotlb->nmaps++; vhost_iotlb_itree_insert(map, &iotlb->root); @@ -80,6 +98,15 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, return 0; } +EXPORT_SYMBOL_GPL(vhost_iotlb_add_range_ctx); + +int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, + u64 start, u64 last, + u64 addr, unsigned int perm) +{ + return vhost_iotlb_add_range_ctx(iotlb, start, last, + addr, perm, NULL); +} EXPORT_SYMBOL_GPL(vhost_iotlb_add_range); /** @@ -98,6 +125,23 @@ void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last) } EXPORT_SYMBOL_GPL(vhost_iotlb_del_range); +/** + * vhost_iotlb_init - initialize a vhost IOTLB + * @iotlb: the IOTLB that needs to be initialized + * @limit: maximum number of IOTLB entries + * @flags: VHOST_IOTLB_FLAG_XXX + */ +void vhost_iotlb_init(struct vhost_iotlb *iotlb, unsigned int limit, + unsigned int flags) +{ + iotlb->root = RB_ROOT_CACHED; + iotlb->limit = limit; + iotlb->nmaps = 0; + iotlb->flags = flags; + INIT_LIST_HEAD(&iotlb->list); +} +EXPORT_SYMBOL_GPL(vhost_iotlb_init); + /** * vhost_iotlb_alloc - add a new vhost IOTLB * @limit: maximum number of IOTLB entries @@ -112,11 +156,7 @@ struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags) if (!iotlb) return NULL; - iotlb->root = RB_ROOT_CACHED; - iotlb->limit = limit; - iotlb->nmaps = 0; - iotlb->flags = flags; - INIT_LIST_HEAD(&iotlb->list); + vhost_iotlb_init(iotlb, limit, flags); return iotlb; } diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 02ae9c4a571c5a79282cde23fad44e5858bf1f36..ebafc05d2b74f1d14b52b0d9dc8b379c2cbe03e4 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -16,44 +16,131 @@ #include #include #include +#include #include #include #include #include #include -#include #include "vhost.h" enum { VHOST_VDPA_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) | - (1ULL << VHOST_BACKEND_F_IOTLB_BATCH), + (1ULL << VHOST_BACKEND_F_IOTLB_BATCH) | + (1ULL << VHOST_BACKEND_F_IOTLB_ASID), }; #define VHOST_VDPA_DEV_MAX (1U << MINORBITS) +#define VHOST_VDPA_IOTLB_BUCKETS 16 + +struct vhost_vdpa_as { + struct hlist_node hash_link; + struct vhost_iotlb iotlb; + u32 id; +}; + struct vhost_vdpa { struct vhost_dev vdev; struct iommu_domain *domain; struct vhost_virtqueue *vqs; struct completion completion; struct vdpa_device *vdpa; + struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS]; struct device dev; struct cdev cdev; atomic_t opened; - int nvqs; + u32 nvqs; int virtio_id; int minor; struct eventfd_ctx *config_ctx; int in_batch; struct vdpa_iova_range range; + u32 batch_asid; }; static DEFINE_IDA(vhost_vdpa_ida); static dev_t vhost_vdpa_major; +static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb) +{ + struct vhost_vdpa_as *as = container_of(iotlb, struct + vhost_vdpa_as, iotlb); + return as->id; +} + +static struct vhost_vdpa_as *asid_to_as(struct vhost_vdpa *v, u32 asid) +{ + struct hlist_head *head = &v->as[asid % VHOST_VDPA_IOTLB_BUCKETS]; + struct vhost_vdpa_as *as; + + hlist_for_each_entry(as, head, hash_link) + if (as->id == asid) + return as; + + return NULL; +} + +static struct vhost_iotlb *asid_to_iotlb(struct vhost_vdpa *v, u32 asid) +{ + struct vhost_vdpa_as *as = asid_to_as(v, asid); + + if (!as) + return NULL; + + return &as->iotlb; +} + +static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid) +{ + struct hlist_head *head = &v->as[asid % VHOST_VDPA_IOTLB_BUCKETS]; + struct vhost_vdpa_as *as; + + if (asid_to_as(v, asid)) + return NULL; + + if (asid >= v->vdpa->nas) + return NULL; + + as = kmalloc(sizeof(*as), GFP_KERNEL); + if (!as) + return NULL; + + vhost_iotlb_init(&as->iotlb, 0, 0); + as->id = asid; + hlist_add_head(&as->hash_link, head); + + return as; +} + +static struct vhost_vdpa_as *vhost_vdpa_find_alloc_as(struct vhost_vdpa *v, + u32 asid) +{ + struct vhost_vdpa_as *as = asid_to_as(v, asid); + + if (as) + return as; + + return vhost_vdpa_alloc_as(v, asid); +} + +static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid) +{ + struct vhost_vdpa_as *as = asid_to_as(v, asid); + + if (!as) + return -EINVAL; + + hlist_del(&as->hash_link); + vhost_iotlb_reset(&as->iotlb); + kfree(as); + + return 0; +} + static void handle_vq_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, @@ -119,12 +206,13 @@ static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid) irq_bypass_unregister_producer(&vq->call_ctx.producer); } -static void vhost_vdpa_reset(struct vhost_vdpa *v) +static int vhost_vdpa_reset(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; - vdpa_reset(vdpa); v->in_batch = 0; + + return vdpa_reset(vdpa); } static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp) @@ -160,7 +248,8 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; u8 status, status_old; - int ret, nvqs = v->nvqs; + u32 nvqs = v->nvqs; + int ret; u16 i; if (copy_from_user(&status, statusp, sizeof(status))) @@ -172,24 +261,24 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) * Userspace shouldn't remove status bits unless reset the * status to 0. */ - if (status != 0 && (ops->get_status(vdpa) & ~status) != 0) + if (status != 0 && (status_old & ~status) != 0) return -EINVAL; + if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) && !(status & VIRTIO_CONFIG_S_DRIVER_OK)) + for (i = 0; i < nvqs; i++) + vhost_vdpa_unsetup_vq_irq(v, i); + if (status == 0) { - ret = ops->reset(vdpa); + ret = vdpa_reset(vdpa); if (ret) return ret; } else - ops->set_status(vdpa, status); + vdpa_set_status(vdpa, status); if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) for (i = 0; i < nvqs; i++) vhost_vdpa_setup_vq_irq(v, i); - if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) && !(status & VIRTIO_CONFIG_S_DRIVER_OK)) - for (i = 0; i < nvqs; i++) - vhost_vdpa_unsetup_vq_irq(v, i); - return 0; } @@ -239,7 +328,6 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v, struct vhost_vdpa_config __user *c) { struct vdpa_device *vdpa = v->vdpa; - const struct vdpa_config_ops *ops = vdpa->config; struct vhost_vdpa_config config; unsigned long size = offsetof(struct vhost_vdpa_config, buf); u8 *buf; @@ -248,28 +336,32 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v, return -EFAULT; if (vhost_vdpa_config_validate(v, &config)) return -EINVAL; - buf = kvzalloc(config.len, GFP_KERNEL); - if (!buf) - return -ENOMEM; - if (copy_from_user(buf, c->buf, config.len)) { - kvfree(buf); - return -EFAULT; - } + buf = vmemdup_user(c->buf, config.len); + if (IS_ERR(buf)) + return PTR_ERR(buf); - ops->set_config(vdpa, config.off, buf, config.len); + vdpa_set_config(vdpa, config.off, buf, config.len); kvfree(buf); return 0; } +static bool vhost_vdpa_can_suspend(const struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + return ops->suspend; +} + static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) { struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; u64 features; - features = ops->get_features(vdpa); + features = ops->get_device_features(vdpa); if (copy_to_user(featurep, &features, sizeof(features))) return -EFAULT; @@ -386,6 +478,22 @@ static long vhost_vdpa_get_vqs_count(struct vhost_vdpa *v, u32 __user *argp) return 0; } +/* After a successful return of ioctl the device must not process more + * virtqueue descriptors. The device can answer to read or writes of config + * fields as if it were not suspended. In particular, writing to "queue_enable" + * with a value of 1 will not make the device start processing buffers. + */ +static long vhost_vdpa_suspend(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!ops->suspend) + return -EOPNOTSUPP; + + return ops->suspend(vdpa); +} + static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, void __user *argp) { @@ -414,6 +522,24 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, return -EFAULT; ops->set_vq_ready(vdpa, idx, s.num); return 0; + case VHOST_VDPA_GET_VRING_GROUP: + if (!ops->get_vq_group) + return -EOPNOTSUPP; + s.index = idx; + s.num = ops->get_vq_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; + if (s.num >= vdpa->nas) + return -EINVAL; + if (!ops->set_group_asid) + return -EOPNOTSUPP; + return ops->set_group_asid(vdpa, idx, s.num); case VHOST_GET_VRING_BASE: r = ops->get_vq_state(v->vdpa, idx, &vq_state); if (r) @@ -475,7 +601,11 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, if (cmd == VHOST_SET_BACKEND_FEATURES) { if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; - if (features & ~VHOST_VDPA_BACKEND_FEATURES) + if (features & ~(VHOST_VDPA_BACKEND_FEATURES | + BIT_ULL(VHOST_BACKEND_F_SUSPEND))) + return -EOPNOTSUPP; + if ((features & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) && + !vhost_vdpa_can_suspend(v)) return -EOPNOTSUPP; vhost_set_backend_features(&v->vdev, features); return 0; @@ -508,6 +638,15 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, case VHOST_VDPA_GET_VRING_NUM: r = vhost_vdpa_get_vring_num(v, argp); break; + case VHOST_VDPA_GET_GROUP_NUM: + if (copy_to_user(argp, &v->vdpa->ngroups, + sizeof(v->vdpa->ngroups))) + r = -EFAULT; + break; + case VHOST_VDPA_GET_AS_NUM: + if (copy_to_user(argp, &v->vdpa->nas, sizeof(v->vdpa->nas))) + r = -EFAULT; + break; case VHOST_SET_LOG_BASE: case VHOST_SET_LOG_FD: r = -ENOIOCTLCMD; @@ -517,6 +656,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, break; case VHOST_GET_BACKEND_FEATURES: features = VHOST_VDPA_BACKEND_FEATURES; + if (vhost_vdpa_can_suspend(v)) + features |= BIT_ULL(VHOST_BACKEND_F_SUSPEND); if (copy_to_user(featurep, &features, sizeof(features))) r = -EFAULT; break; @@ -529,6 +670,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, case VHOST_VDPA_GET_VQS_COUNT: r = vhost_vdpa_get_vqs_count(v, argp); break; + case VHOST_VDPA_SUSPEND: + r = vhost_vdpa_suspend(v); + break; default: r = vhost_dev_ioctl(&v->vdev, cmd, argp); if (r == -ENOIOCTLCMD) @@ -540,35 +684,54 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, return r; } -static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last) +static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, + struct vhost_iotlb *iotlb, + u64 start, u64 last) { struct vhost_dev *dev = &v->vdev; - 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 = PFN_DOWN(map->size); + for (pfn = PFN_DOWN(map->addr); 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(PFN_DOWN(map->size), &dev->mm->pinned_vm); vhost_iotlb_map_free(iotlb, map); } } -static void vhost_vdpa_iotlb_free(struct vhost_vdpa *v) +static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, + struct vhost_iotlb *iotlb, + u64 start, u64 last) { - struct vhost_dev *dev = &v->vdev; + struct vhost_iotlb_map *map; + struct vdpa_map_file *map_file; + + while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) { + map_file = (struct vdpa_map_file *)map->opaque; + fput(map_file->file); + kfree(map_file); + vhost_iotlb_map_free(iotlb, map); + } +} + +static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, + struct vhost_iotlb *iotlb, + u64 start, u64 last) +{ + struct vdpa_device *vdpa = v->vdpa; + + if (vdpa->use_va) + return vhost_vdpa_va_unmap(v, iotlb, start, last); - vhost_vdpa_iotlb_unmap(v, 0ULL, 0ULL - 1); - kfree(dev->iotlb); - dev->iotlb = NULL; + return vhost_vdpa_pa_unmap(v, iotlb, start, last); } static int perm_to_iommu_flags(u32 perm) @@ -593,87 +756,140 @@ static int perm_to_iommu_flags(u32 perm) return flags | IOMMU_CACHE; } -static int vhost_vdpa_map(struct vhost_vdpa *v, - u64 iova, u64 size, u64 pa, u32 perm) +static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, + u64 iova, u64 size, u64 pa, u32 perm, void *opaque) { struct vhost_dev *dev = &v->vdev; struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; + u32 asid = iotlb_to_asid(iotlb); int r = 0; - r = vhost_iotlb_add_range(dev->iotlb, iova, iova + size - 1, - pa, perm); + r = vhost_iotlb_add_range_ctx(iotlb, iova, iova + size - 1, + pa, perm, opaque); if (r) return r; if (ops->dma_map) { - r = ops->dma_map(vdpa, iova, size, pa, perm); + r = ops->dma_map(vdpa, asid, iova, size, pa, perm, opaque); } else if (ops->set_map) { if (!v->in_batch) - r = ops->set_map(vdpa, dev->iotlb); + r = ops->set_map(vdpa, asid, iotlb); } else { r = iommu_map(v->domain, iova, pa, size, perm_to_iommu_flags(perm)); } + if (r) { + vhost_iotlb_del_range(iotlb, iova, iova + size - 1); + return r; + } - if (r) - vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1); - else - atomic64_add(size >> PAGE_SHIFT, &dev->mm->pinned_vm); + if (!vdpa->use_va) + atomic64_add(PFN_DOWN(size), &dev->mm->pinned_vm); - return r; + return 0; } -static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size) +static void vhost_vdpa_unmap(struct vhost_vdpa *v, + struct vhost_iotlb *iotlb, + u64 iova, u64 size) { - struct vhost_dev *dev = &v->vdev; struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; + u32 asid = iotlb_to_asid(iotlb); - vhost_vdpa_iotlb_unmap(v, iova, iova + size - 1); + vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1); if (ops->dma_map) { - ops->dma_unmap(vdpa, iova, size); + ops->dma_unmap(vdpa, asid, iova, size); } else if (ops->set_map) { if (!v->in_batch) - ops->set_map(vdpa, dev->iotlb); + ops->set_map(vdpa, asid, iotlb); } else { iommu_unmap(v->domain, iova, size); } + + /* 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_process_iotlb_update(struct vhost_vdpa *v, - struct vhost_iotlb_msg *msg) +static int vhost_vdpa_va_map(struct vhost_vdpa *v, + struct vhost_iotlb *iotlb, + u64 iova, u64 size, u64 uaddr, u32 perm) +{ + struct vhost_dev *dev = &v->vdev; + u64 offset, map_size, map_iova = iova; + struct vdpa_map_file *map_file; + struct vm_area_struct *vma; + int ret = 0; + + mmap_read_lock(dev->mm); + + while (size) { + vma = find_vma(dev->mm, uaddr); + if (!vma) { + ret = -EINVAL; + break; + } + map_size = min(size, vma->vm_end - uaddr); + if (!(vma->vm_file && (vma->vm_flags & VM_SHARED) && + !(vma->vm_flags & (VM_IO | VM_PFNMAP)))) + goto next; + + map_file = kzalloc(sizeof(*map_file), GFP_KERNEL); + if (!map_file) { + ret = -ENOMEM; + break; + } + offset = (vma->vm_pgoff << PAGE_SHIFT) + uaddr - vma->vm_start; + map_file->offset = offset; + map_file->file = get_file(vma->vm_file); + ret = vhost_vdpa_map(v, iotlb, map_iova, map_size, uaddr, + perm, map_file); + if (ret) { + fput(map_file->file); + kfree(map_file); + break; + } +next: + size -= map_size; + uaddr += map_size; + map_iova += map_size; + } + if (ret) + vhost_vdpa_unmap(v, iotlb, iova, map_iova - iova); + + mmap_read_unlock(dev->mm); + + return ret; +} + +static int vhost_vdpa_pa_map(struct vhost_vdpa *v, + struct vhost_iotlb *iotlb, + u64 iova, u64 size, u64 uaddr, u32 perm) { struct vhost_dev *dev = &v->vdev; - struct vhost_iotlb *iotlb = dev->iotlb; struct page **page_list; unsigned long list_size = PAGE_SIZE / sizeof(struct page *); unsigned int gup_flags = FOLL_LONGTERM; unsigned long npages, cur_base, map_pfn, last_pfn = 0; unsigned long lock_limit, sz2pin, nchunks, i; - u64 iova = msg->iova; + u64 start = iova; long pinned; int ret = 0; - if (msg->iova < v->range.first || !msg->size || - msg->iova > U64_MAX - msg->size + 1 || - msg->iova + msg->size - 1 > v->range.last) - return -EINVAL; - - if (vhost_iotlb_itree_first(iotlb, msg->iova, - msg->iova + msg->size - 1)) - return -EEXIST; - /* Limit the use of memory for bookkeeping */ page_list = (struct page **) __get_free_page(GFP_KERNEL); if (!page_list) return -ENOMEM; - if (msg->perm & VHOST_ACCESS_WO) + if (perm & VHOST_ACCESS_WO) gup_flags |= FOLL_WRITE; - npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT; + npages = PFN_UP(size + (iova & ~PAGE_MASK)); if (!npages) { ret = -EINVAL; goto free; @@ -681,13 +897,13 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, mmap_read_lock(dev->mm); - lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + lock_limit = PFN_DOWN(rlimit(RLIMIT_MEMLOCK)); if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) { ret = -ENOMEM; goto unlock; } - cur_base = msg->uaddr & PAGE_MASK; + cur_base = uaddr & PAGE_MASK; iova &= PAGE_MASK; nchunks = 0; @@ -715,10 +931,10 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, if (last_pfn && (this_pfn != last_pfn + 1)) { /* Pin a contiguous chunk of memory */ - csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT; - ret = vhost_vdpa_map(v, iova, csize, - map_pfn << PAGE_SHIFT, - msg->perm); + csize = PFN_PHYS(last_pfn - map_pfn + 1); + ret = vhost_vdpa_map(v, iotlb, iova, csize, + PFN_PHYS(map_pfn), + perm, NULL); if (ret) { /* * Unpin the pages that are left unmapped @@ -741,13 +957,13 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, last_pfn = this_pfn; } - cur_base += pinned << PAGE_SHIFT; + cur_base += PFN_PHYS(pinned); npages -= pinned; } /* Pin the rest chunk */ - ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT, - map_pfn << PAGE_SHIFT, msg->perm); + ret = vhost_vdpa_map(v, iotlb, iova, PFN_PHYS(last_pfn - map_pfn + 1), + PFN_PHYS(map_pfn), perm, NULL); out: if (ret) { if (nchunks) { @@ -766,21 +982,47 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, for (pfn = map_pfn; pfn <= last_pfn; pfn++) unpin_user_page(pfn_to_page(pfn)); } - vhost_vdpa_unmap(v, msg->iova, msg->size); + vhost_vdpa_unmap(v, iotlb, start, size); } unlock: mmap_read_unlock(dev->mm); free: free_page((unsigned long)page_list); return ret; + +} + +static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, + struct vhost_iotlb *iotlb, + struct vhost_iotlb_msg *msg) +{ + struct vdpa_device *vdpa = v->vdpa; + + if (msg->iova < v->range.first || !msg->size || + msg->iova > U64_MAX - msg->size + 1 || + msg->iova + msg->size - 1 > v->range.last) + return -EINVAL; + + if (vhost_iotlb_itree_first(iotlb, msg->iova, + msg->iova + msg->size - 1)) + return -EEXIST; + + if (vdpa->use_va) + return vhost_vdpa_va_map(v, iotlb, msg->iova, msg->size, + msg->uaddr, msg->perm); + + return vhost_vdpa_pa_map(v, iotlb, msg->iova, msg->size, msg->uaddr, + msg->perm); } -static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, +static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, struct vhost_iotlb_msg *msg) { struct vhost_vdpa *v = container_of(dev, struct vhost_vdpa, vdev); struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; + struct vhost_iotlb *iotlb = NULL; + struct vhost_vdpa_as *as = NULL; int r = 0; mutex_lock(&dev->mutex); @@ -789,20 +1031,47 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, if (r) goto unlock; + if (msg->type == VHOST_IOTLB_UPDATE || + msg->type == VHOST_IOTLB_BATCH_BEGIN) { + as = vhost_vdpa_find_alloc_as(v, asid); + if (!as) { + dev_err(&v->dev, "can't find and alloc asid %d\n", + asid); + r = -EINVAL; + goto unlock; + } + iotlb = &as->iotlb; + } else + iotlb = asid_to_iotlb(v, asid); + + if ((v->in_batch && v->batch_asid != asid) || !iotlb) { + if (v->in_batch && v->batch_asid != asid) { + dev_info(&v->dev, "batch id %d asid %d\n", + v->batch_asid, asid); + } + if (!iotlb) + dev_err(&v->dev, "no iotlb for asid %d\n", asid); + r = -EINVAL; + goto unlock; + } + switch (msg->type) { case VHOST_IOTLB_UPDATE: - r = vhost_vdpa_process_iotlb_update(v, msg); + r = vhost_vdpa_process_iotlb_update(v, iotlb, msg); break; case VHOST_IOTLB_INVALIDATE: - vhost_vdpa_unmap(v, msg->iova, msg->size); + vhost_vdpa_unmap(v, iotlb, msg->iova, msg->size); break; case VHOST_IOTLB_BATCH_BEGIN: + v->batch_asid = asid; v->in_batch = true; break; case VHOST_IOTLB_BATCH_END: if (v->in_batch && ops->set_map) - ops->set_map(vdpa, dev->iotlb); + ops->set_map(vdpa, asid, iotlb); v->in_batch = false; + if (!iotlb->nmaps) + vhost_vdpa_remove_as(v, asid); break; default: r = -EINVAL; @@ -892,12 +1161,28 @@ static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v) } } +static void vhost_vdpa_cleanup(struct vhost_vdpa *v) +{ + struct vhost_vdpa_as *as; + u32 asid; + + vhost_dev_cleanup(&v->vdev); + kfree(v->vdev.vqs); + + for (asid = 0; asid < v->vdpa->nas; asid++) { + as = asid_to_as(v, asid); + if (as) + vhost_vdpa_remove_as(v, asid); + } +} + static int vhost_vdpa_open(struct inode *inode, struct file *filep) { struct vhost_vdpa *v; struct vhost_dev *dev; struct vhost_virtqueue **vqs; - int nvqs, i, r, opened; + int r, opened; + u32 i, nvqs; v = container_of(inode->i_cdev, struct vhost_vdpa, cdev); @@ -906,7 +1191,9 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) return -EBUSY; nvqs = v->nvqs; - vhost_vdpa_reset(v); + r = vhost_vdpa_reset(v); + if (r) + goto err; vqs = kmalloc_array(nvqs, sizeof(*vqs), GFP_KERNEL); if (!vqs) { @@ -922,15 +1209,9 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) vhost_dev_init(dev, vqs, nvqs, 0, 0, 0, false, vhost_vdpa_process_iotlb_msg); - dev->iotlb = vhost_iotlb_alloc(0, 0); - if (!dev->iotlb) { - r = -ENOMEM; - goto err_init_iotlb; - } - r = vhost_vdpa_alloc_domain(v); if (r) - goto err_init_iotlb; + goto err_alloc_domain; vhost_vdpa_set_iova_range(v); @@ -938,9 +1219,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) return 0; -err_init_iotlb: - vhost_dev_cleanup(&v->vdev); - kfree(vqs); +err_alloc_domain: + vhost_vdpa_cleanup(v); err: atomic_dec(&v->opened); return r; @@ -948,7 +1228,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) static void vhost_vdpa_clean_irq(struct vhost_vdpa *v) { - int i; + u32 i; for (i = 0; i < v->nvqs; i++) vhost_vdpa_unsetup_vq_irq(v, i); @@ -961,14 +1241,12 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) mutex_lock(&d->mutex); filep->private_data = NULL; + vhost_vdpa_clean_irq(v); vhost_vdpa_reset(v); vhost_dev_stop(&v->vdev); - vhost_vdpa_iotlb_free(v); vhost_vdpa_free_domain(v); vhost_vdpa_config_put(v); - vhost_vdpa_clean_irq(v); - vhost_dev_cleanup(&v->vdev); - kfree(v->vdev.vqs); + vhost_vdpa_cleanup(v); mutex_unlock(&d->mutex); atomic_dec(&v->opened); @@ -991,7 +1269,7 @@ static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf) vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); if (remap_pfn_range(vma, vmf->address & PAGE_MASK, - notify.addr >> PAGE_SHIFT, PAGE_SIZE, + PFN_DOWN(notify.addr), PAGE_SIZE, vma->vm_page_prot)) return VM_FAULT_SIGBUS; @@ -1064,11 +1342,14 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) const struct vdpa_config_ops *ops = vdpa->config; struct vhost_vdpa *v; int minor; - int r; + int i, r; - /* Currently, we only accept the network devices. */ - if (ops->get_device_id(vdpa) != VIRTIO_ID_NET) - return -ENOTSUPP; + /* We can't support platform IOMMU device with more than 1 + * group or as + */ + if (!ops->set_map && !ops->dma_map && + (vdpa->ngroups > 1 || vdpa->nas > 1)) + return -EOPNOTSUPP; v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!v) @@ -1112,10 +1393,14 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) init_completion(&v->completion); vdpa_set_drvdata(vdpa, v); + for (i = 0; i < VHOST_VDPA_IOTLB_BUCKETS; i++) + INIT_HLIST_HEAD(&v->as[i]); + return 0; err: put_device(&v->dev); + ida_simple_remove(&vhost_vdpa_ida, v->minor); return r; } diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index f41463ab4031ddbf8a4041457959c45b20093b61..63e959073d470e6b1790c854ec1a303c557cfccf 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -468,7 +468,7 @@ void vhost_dev_init(struct vhost_dev *dev, struct vhost_virtqueue **vqs, int nvqs, int iov_limit, int weight, int byte_weight, bool use_worker, - int (*msg_handler)(struct vhost_dev *dev, + int (*msg_handler)(struct vhost_dev *dev, u32 asid, struct vhost_iotlb_msg *msg)) { struct vhost_virtqueue *vq; @@ -1090,11 +1090,14 @@ static bool umem_access_ok(u64 uaddr, u64 size, int access) return true; } -static int vhost_process_iotlb_msg(struct vhost_dev *dev, +static int vhost_process_iotlb_msg(struct vhost_dev *dev, u32 asid, struct vhost_iotlb_msg *msg) { int ret = 0; + if (asid != 0) + return -EINVAL; + mutex_lock(&dev->mutex); vhost_dev_lock_vqs(dev); switch (msg->type) { @@ -1141,6 +1144,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, struct vhost_iotlb_msg msg; size_t offset; int type, ret; + u32 asid = 0; ret = copy_from_iter(&type, sizeof(type), from); if (ret != sizeof(type)) { @@ -1156,7 +1160,16 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, offset = offsetof(struct vhost_msg, iotlb) - sizeof(int); break; case VHOST_IOTLB_MSG_V2: - offset = sizeof(__u32); + if (vhost_backend_has_feature(dev->vqs[0], + VHOST_BACKEND_F_IOTLB_ASID)) { + ret = copy_from_iter(&asid, sizeof(asid), from); + if (ret != sizeof(asid)) { + ret = -EINVAL; + goto done; + } + offset = 0; + } else + offset = sizeof(__u32); break; default: ret = -EINVAL; @@ -1170,10 +1183,17 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, goto done; } + if ((msg.type == VHOST_IOTLB_UPDATE || + msg.type == VHOST_IOTLB_INVALIDATE) && + msg.size == 0) { + ret = -EINVAL; + goto done; + } + if (dev->msg_handler) - ret = dev->msg_handler(dev, &msg); + ret = dev->msg_handler(dev, asid, &msg); else - ret = vhost_process_iotlb_msg(dev, &msg); + ret = vhost_process_iotlb_msg(dev, asid, &msg); if (ret) { ret = -EFAULT; goto done; diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index b063324c7669d20bda8b0b45f822ae419c047997..19753a90875c8e602263d15280df87fd2391a7c4 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -162,7 +162,7 @@ struct vhost_dev { int byte_weight; u64 kcov_handle; bool use_worker; - int (*msg_handler)(struct vhost_dev *dev, + int (*msg_handler)(struct vhost_dev *dev, u32 asid, struct vhost_iotlb_msg *msg); }; @@ -170,7 +170,7 @@ bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len); void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs, int iov_limit, int weight, int byte_weight, bool use_worker, - int (*msg_handler)(struct vhost_dev *dev, + int (*msg_handler)(struct vhost_dev *dev, u32 asid, struct vhost_iotlb_msg *msg)); long vhost_dev_set_owner(struct vhost_dev *dev); bool vhost_dev_has_owner(struct vhost_dev *dev); diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 441bc057896f5fd6521791467f2c152385a1a5b0..30460d7332cc250e833edd9fc2d7c260eb0b5af5 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -203,6 +203,28 @@ static int virtio_features_ok(struct virtio_device *dev) return 0; } +/** + * virtio_reset_device - quiesce device for removal + * @dev: the device to reset + * + * Prevents device from sending interrupts and accessing memory. + * + * Generally used for cleanup during driver / device removal. + * + * Once this has been invoked, caller must ensure that + * virtqueue_notify / virtqueue_kick are not in progress. + * + * Note: this guarantees that vq callbacks are not in progress, however caller + * is responsible for preventing access from other contexts, such as a system + * call/workqueue/bh. Invoking virtio_break_device then flushing any such + * contexts is one way to handle that. + * */ +void virtio_reset_device(struct virtio_device *dev) +{ + dev->config->reset(dev); +} +EXPORT_SYMBOL_GPL(virtio_reset_device); + static int virtio_dev_probe(struct device *_d) { int err, i; @@ -362,7 +384,7 @@ int register_virtio_device(struct virtio_device *dev) /* We always start by resetting the device, in case a previous * driver messed it up. This also tests that code path a little. */ - dev->config->reset(dev); + virtio_reset_device(dev); /* Acknowledge that we've seen the device. */ virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); @@ -422,7 +444,7 @@ int virtio_device_restore(struct virtio_device *dev) /* We always start by resetting the device, in case a previous * driver messed it up. */ - dev->config->reset(dev); + virtio_reset_device(dev); /* Acknowledge that we've seen the device. */ virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 481611c09dae1cc3d850214d8806d54434f84bb6..2a44835f76fbc005073c8429a8d5100d05c832b7 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -1039,7 +1039,7 @@ static void remove_common(struct virtio_balloon *vb) return_free_pages_to_mm(vb, ULONG_MAX); /* Now we reset the device so we can clean up the queues. */ - vb->vdev->config->reset(vb->vdev); + virtio_reset_device(vb->vdev); vb->vdev->config->del_vqs(vb->vdev); } diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index f1f6208edcf59278522ceb52d5cc56d9be1889d1..b30dc57184b86be98e971204dc41f9b2cf334368 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -323,7 +323,7 @@ static void virtinput_remove(struct virtio_device *vdev) spin_unlock_irqrestore(&vi->lock, flags); input_unregister_device(vi->idev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL) kfree(buf); vdev->config->del_vqs(vdev); diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 181e2f18beae5b3603c9c239dd9e589767078ae2..d07ada962e24b1b14999140fcd4bb3744648284e 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -1889,7 +1889,7 @@ static void virtio_mem_remove(struct virtio_device *vdev) vfree(vm->sb_bitmap); /* reset the device and cleanup the queues */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); kfree(vm); diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 30654d3a0b41ed6fca1a46f9dac6ac01d925da53..0aef96f9770329b561c671e3c2dd5012419761e8 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -176,6 +176,29 @@ static void vp_reset(struct virtio_device *vdev) vp_synchronize_vectors(vdev); } +static int vp_active_vq(struct virtqueue *vq, u16 msix_vec) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); + struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + unsigned long index; + + index = vq->index; + + /* activate the queue */ + vp_modern_set_queue_size(mdev, index, virtqueue_get_vring_size(vq)); + vp_modern_queue_address(mdev, index, virtqueue_get_desc_addr(vq), + virtqueue_get_avail_addr(vq), + virtqueue_get_used_addr(vq)); + + if (msix_vec != VIRTIO_MSI_NO_VECTOR) { + msix_vec = vp_modern_queue_vector(mdev, index, msix_vec); + if (msix_vec == VIRTIO_MSI_NO_VECTOR) + return -EBUSY; + } + + return 0; +} + static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) { return vp_modern_config_vector(&vp_dev->mdev, vector); @@ -218,32 +241,19 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, if (!vq) return ERR_PTR(-ENOMEM); - /* activate the queue */ - vp_modern_set_queue_size(mdev, index, virtqueue_get_vring_size(vq)); - vp_modern_queue_address(mdev, index, virtqueue_get_desc_addr(vq), - virtqueue_get_avail_addr(vq), - virtqueue_get_used_addr(vq)); + err = vp_active_vq(vq, msix_vec); + if (err) + goto err; vq->priv = (void __force *)vp_modern_map_vq_notify(mdev, index, NULL); if (!vq->priv) { err = -ENOMEM; - goto err_map_notify; - } - - if (msix_vec != VIRTIO_MSI_NO_VECTOR) { - msix_vec = vp_modern_queue_vector(mdev, index, msix_vec); - if (msix_vec == VIRTIO_MSI_NO_VECTOR) { - err = -EBUSY; - goto err_assign_vector; - } + goto err; } return vq; -err_assign_vector: - if (!mdev->notify_base) - pci_iounmap(mdev->pci_dev, (void __iomem __force *)vq->priv); -err_map_notify: +err: vring_del_virtqueue(vq); return ERR_PTR(err); } diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c index ae51a81502ef95ac4dc5b4f3fe73764162872d12..ff63f4dc11f6b4148603467618114cf6e7ffb1d4 100644 --- a/drivers/virtio/virtio_pci_modern_dev.c +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -3,6 +3,7 @@ #include #include #include +#include /* * vp_modern_map_capability - map a part of virtio pci capability @@ -17,11 +18,10 @@ * * Returns the io address of for the part of the capability */ -void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, - size_t minlen, - u32 align, - u32 start, u32 size, - size_t *len, resource_size_t *pa) +static void __iomem* +vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, + size_t minlen, u32 align, u32 start, u32 size, + size_t *len, resource_size_t *pa) { struct pci_dev *dev = mdev->pci_dev; u8 bar; @@ -95,7 +95,6 @@ void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, in return p; } -EXPORT_SYMBOL_GPL(vp_modern_map_capability); /** * virtio_pci_find_capability - walk capabilities to find device info. @@ -466,6 +465,44 @@ void vp_modern_set_status(struct virtio_pci_modern_device *mdev, } EXPORT_SYMBOL_GPL(vp_modern_set_status); +/* + * vp_modern_get_queue_reset - get the queue reset status + * @mdev: the modern virtio-pci device + * @index: queue index + */ +int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index) +{ + struct virtio_pci_modern_common_cfg __iomem *cfg; + + cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common; + + vp_iowrite16(index, &cfg->cfg.queue_select); + return vp_ioread16(&cfg->queue_reset); +} +EXPORT_SYMBOL_GPL(vp_modern_get_queue_reset); + +/* + * vp_modern_set_queue_reset - reset the queue + * @mdev: the modern virtio-pci device + * @index: queue index + */ +void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index) +{ + struct virtio_pci_modern_common_cfg __iomem *cfg; + + cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common; + + vp_iowrite16(index, &cfg->cfg.queue_select); + vp_iowrite16(1, &cfg->queue_reset); + + while (vp_ioread16(&cfg->queue_reset)) + msleep(1); + + while (vp_ioread16(&cfg->cfg.queue_enable)) + msleep(1); +} +EXPORT_SYMBOL_GPL(vp_modern_set_queue_reset); + /* * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue * @mdev: the modern virtio-pci device @@ -612,14 +649,13 @@ EXPORT_SYMBOL_GPL(vp_modern_get_num_queues); * * Returns the notification offset for a virtqueue */ -u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, - u16 index) +static u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, + u16 index) { vp_iowrite16(index, &mdev->common->queue_select); return vp_ioread16(&mdev->common->queue_notify_off); } -EXPORT_SYMBOL_GPL(vp_modern_get_queue_notify_off); /* * vp_modern_map_vq_notify - map notification area for a diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index 3f95dedcccebe475669b94d807becafdb0678b72..46c71653f508ba841e5bdcc7d7b211baba34db44 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -65,9 +65,8 @@ static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset, const void *buf, unsigned len) { struct vdpa_device *vdpa = vd_get_vdpa(vdev); - const struct vdpa_config_ops *ops = vdpa->config; - ops->set_config(vdpa, offset, buf, len); + vdpa_set_config(vdpa, offset, buf, len); } static u32 virtio_vdpa_generation(struct virtio_device *vdev) @@ -92,9 +91,8 @@ static u8 virtio_vdpa_get_status(struct virtio_device *vdev) static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status) { struct vdpa_device *vdpa = vd_get_vdpa(vdev); - const struct vdpa_config_ops *ops = vdpa->config; - return ops->set_status(vdpa, status); + return vdpa_set_status(vdpa, status); } static void virtio_vdpa_reset(struct virtio_device *vdev) @@ -142,8 +140,11 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, struct vdpa_callback cb; struct virtqueue *vq; u64 desc_addr, driver_addr, device_addr; + /* Assume split virtqueue, switch to packed if necessary */ + struct vdpa_vq_state state = {0}; unsigned long flags; - u32 align, num; + u32 align, max_num, min_num = 1; + bool may_reduce_num = true; int err; if (!name) @@ -161,16 +162,21 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, if (!info) return ERR_PTR(-ENOMEM); - num = ops->get_vq_num_max(vdpa); - if (num == 0) { + max_num = ops->get_vq_num_max(vdpa); + if (max_num == 0) { err = -ENOENT; goto error_new_virtqueue; } + if (ops->get_vq_num_min) + min_num = ops->get_vq_num_min(vdpa); + + may_reduce_num = (max_num == min_num) ? false : true; + /* Create the vring */ align = ops->get_vq_align(vdpa); - vq = vring_create_virtqueue(index, num, align, vdev, - true, true, ctx, + vq = vring_create_virtqueue(index, max_num, align, vdev, + true, may_reduce_num, ctx, virtio_vdpa_notify, callback, name); if (!vq) { err = -ENOMEM; @@ -178,7 +184,7 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, } /* Setup virtqueue callback */ - cb.callback = virtio_vdpa_virtqueue_cb; + cb.callback = callback ? virtio_vdpa_virtqueue_cb : NULL; cb.private = info; ops->set_vq_cb(vdpa, index, &cb); ops->set_vq_num(vdpa, index, virtqueue_get_vring_size(vq)); @@ -194,6 +200,19 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, goto err_vq; } + /* reset virtqueue state index */ + if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) { + struct vdpa_vq_state_packed *s = &state.packed; + + s->last_avail_counter = 1; + s->last_avail_idx = 0; + s->last_used_counter = 1; + s->last_used_idx = 0; + } + err = ops->set_vq_state(vdpa, index, &state); + if (err) + goto err_vq; + ops->set_vq_ready(vdpa, index, 1); vq->priv = info; @@ -228,9 +247,8 @@ static void virtio_vdpa_del_vq(struct virtqueue *vq) list_del(&info->node); spin_unlock_irqrestore(&vd_dev->lock, flags); - /* Select and deactivate the queue */ + /* Select and deactivate the queue (best effort) */ ops->set_vq_ready(vdpa, index, 0); - WARN_ON(ops->get_vq_ready(vdpa, index)); vring_del_virtqueue(vq); @@ -289,7 +307,7 @@ static u64 virtio_vdpa_get_features(struct virtio_device *vdev) struct vdpa_device *vdpa = vd_get_vdpa(vdev); const struct vdpa_config_ops *ops = vdpa->config; - return ops->get_features(vdpa); + return ops->get_device_features(vdpa); } static int virtio_vdpa_finalize_features(struct virtio_device *vdev) diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index b9cfb1165ff422c36e22e9c1c2e5e9595c65c02f..77338f139cb27e91ed24c8a30d506a8b1daa339c 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -894,7 +894,7 @@ static int virtio_fs_probe(struct virtio_device *vdev) return 0; out_vqs: - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev, fs); kfree(fs->vqs); @@ -926,7 +926,7 @@ static void virtio_fs_remove(struct virtio_device *vdev) list_del_init(&fs->list); virtio_fs_stop_all_queues(fs); virtio_fs_drain_all_queues_locked(fs); - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev, fs); vdev->priv = NULL; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index d88ae99865df9ffac8ec460028ff8d184a7917d0..3751b672451d9139dca2785dc6f406d4d5686818 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -6,9 +6,11 @@ #include #include #include +#include +#include /** - * vDPA callback definition. + * struct vdpa_calllback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function */ @@ -18,7 +20,7 @@ struct vdpa_callback { }; /** - * vDPA notification area + * struct vdpa_notification_area - vDPA notification area * @addr: base address of the notification area * @size: size of the notification area */ @@ -43,29 +45,33 @@ struct vdpa_vq_state_split { * @last_used_idx: used index */ struct vdpa_vq_state_packed { - u16 last_avail_counter:1; - u16 last_avail_idx:15; - u16 last_used_counter:1; - u16 last_used_idx:15; + u16 last_avail_counter:1; + u16 last_avail_idx:15; + u16 last_used_counter:1; + u16 last_used_idx:15; }; struct vdpa_vq_state { - union { - struct vdpa_vq_state_split split; - struct vdpa_vq_state_packed packed; - }; + union { + struct vdpa_vq_state_split split; + struct vdpa_vq_state_packed packed; + }; }; struct vdpa_mgmt_dev; /** - * vDPA device - representation of a vDPA device + * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA * @driver_override: driver name to force a match * @config: the configuration ops for this device. + * @cf_lock: Protects get and set access to configuration layout. * @index: device index * @features_valid: were features initialized? for legacy guests + * @ngroups: the number of virtqueue groups + * @nas: the number of address spaces + * @use_va: indicate whether virtual address must be used by this device * @nvqs: maximum number of supported virtqueues * @mdev: management device pointer; caller must setup when registering device as part * of dev_add() mgmtdev ops callback before invoking _vdpa_register_device(). @@ -75,14 +81,18 @@ struct vdpa_device { struct device *dma_dev; const char *driver_override; const struct vdpa_config_ops *config; + struct rw_semaphore cf_lock; /* Protects get/set config */ unsigned int index; bool features_valid; - int nvqs; + bool use_va; + u32 nvqs; struct vdpa_mgmt_dev *mdev; + unsigned int ngroups; + unsigned int nas; }; /** - * vDPA IOVA range - the IOVA range support by the device + * struct vdpa_iova_range - the IOVA range support by the device * @first: start of the IOVA range * @last: end of the IOVA range */ @@ -91,8 +101,27 @@ struct vdpa_iova_range { u64 last; }; +struct vdpa_dev_set_config { + struct { + u8 mac[ETH_ALEN]; + u16 mtu; + u16 max_vq_pairs; + } net; + u64 mask; +}; + /** - * vDPA_config_ops - operations for configuring a vDPA device. + * Corresponding file area for device memory mapping + * @file: vma->vm_file for the mapping + * @offset: mapping offset in the vm_file + */ +struct vdpa_map_file { + struct file *file; + u64 offset; +}; + +/** + * struct vdpa_config_ops - operations for configuring a vDPA device. * Note: vDPA device drivers are required to implement all of the * operations unless it is mentioned to be optional in the following * list. @@ -133,7 +162,7 @@ struct vdpa_iova_range { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) - * @get_vq_notification: Get the notification area for a virtqueue + * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index * Returns the notifcation area @@ -147,20 +176,31 @@ struct vdpa_iova_range { * for the device * @vdev: vdpa device * Returns virtqueue algin requirement - * @get_features: Get virtio features supported by the device + * @get_vq_group: Get the group id for a specific + * virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns u32: group id for this virtqueue + * @get_device_features: Get virtio features supported by the device * @vdev: vdpa device * Returns the virtio features support by the * device - * @set_features: Set virtio features supported by the driver + * @set_driver_features: Set virtio features supported by the driver * @vdev: vdpa device * @features: feature support by the driver * Returns integer: success (0) or error (< 0) + * @get_driver_features: Get the virtio driver features in action + * @vdev: vdpa device + * Returns the virtio features accepted * @set_config_cb: Set the config interrupt callback * @vdev: vdpa device * @cb: virtio-vdev interrupt callback structure * @get_vq_num_max: Get the max size of virtqueue * @vdev: vdpa device * Returns u16: max size of virtqueue + * @get_vq_num_min: Get the min size of virtqueue (optional) + * @vdev: vdpa device + * Returns u16: min size of virtqueue * @get_device_id: Get virtio device id * @vdev: vdpa device * Returns u32: virtio device id @@ -176,6 +216,9 @@ struct vdpa_iova_range { * @reset: Reset device * @vdev: vdpa device * Returns integer: success (0) or error (< 0) + * @suspend: Suspend or resume the device (optional) + * @vdev: vdpa device + * Returns integer: success (0) or error (< 0) * @get_config_size: Get the size of the configuration space includes * fields that are conditional on feature bits. * @vdev: vdpa device @@ -201,10 +244,17 @@ struct vdpa_iova_range { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @set_group_asid: Set address space identifier for a + * virtqueue group (optional) + * @vdev: vdpa device + * @group: virtqueue group + * @asid: address space id for this group + * Returns integer: success (0) or error (< 0) * @set_map: Set device memory mapping (optional) * Needed for device that using device * specific DMA translation (on-chip IOMMU) * @vdev: vdpa device + * @asid: address space identifier * @iotlb: vhost memory mapping to be * used by the vDPA * Returns integer: success (0) or error (< 0) @@ -213,6 +263,7 @@ struct vdpa_iova_range { * specific DMA translation (on-chip IOMMU) * and preferring incremental map. * @vdev: vdpa device + * @asid: address space identifier * @iova: iova to be mapped * @size: size of the area * @pa: physical address for the map @@ -224,6 +275,7 @@ struct vdpa_iova_range { * specific DMA translation (on-chip IOMMU) * and preferring incremental unmap. * @vdev: vdpa device + * @asid: address space identifier * @iova: iova to be unmapped * @size: size of the area * Returns integer: success (0) or error (< 0) @@ -245,6 +297,9 @@ struct vdpa_config_ops { const struct vdpa_vq_state *state); int (*get_vq_state)(struct vdpa_device *vdev, u16 idx, struct vdpa_vq_state *state); + int (*get_vendor_vq_stats)(struct vdpa_device *vdev, u16 idx, + struct sk_buff *msg, + struct netlink_ext_ack *extack); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ @@ -252,16 +307,20 @@ struct vdpa_config_ops { /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); - u64 (*get_features)(struct vdpa_device *vdev); - int (*set_features)(struct vdpa_device *vdev, u64 features); + u32 (*get_vq_group)(struct vdpa_device *vdev, u16 idx); + u64 (*get_device_features)(struct vdpa_device *vdev); + int (*set_driver_features)(struct vdpa_device *vdev, u64 features); + u64 (*get_driver_features)(struct vdpa_device *vdev); void (*set_config_cb)(struct vdpa_device *vdev, struct vdpa_callback *cb); u16 (*get_vq_num_max)(struct vdpa_device *vdev); + u16 (*get_vq_num_min)(struct vdpa_device *vdev); u32 (*get_device_id)(struct vdpa_device *vdev); u32 (*get_vendor_id)(struct vdpa_device *vdev); u8 (*get_status)(struct vdpa_device *vdev); void (*set_status)(struct vdpa_device *vdev, u8 status); int (*reset)(struct vdpa_device *vdev); + int (*suspend)(struct vdpa_device *vdev); size_t (*get_config_size)(struct vdpa_device *vdev); void (*get_config)(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); @@ -271,10 +330,14 @@ struct vdpa_config_ops { struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); /* DMA ops */ - int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb); - int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size, - u64 pa, u32 perm); - int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size); + int (*set_map)(struct vdpa_device *vdev, unsigned int asid, + struct vhost_iotlb *iotlb); + int (*dma_map)(struct vdpa_device *vdev, unsigned int asid, + u64 iova, u64 size, u64 pa, u32 perm, void *opaque); + int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid, + u64 iova, u64 size); + int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, + unsigned int asid); /* Free device resources */ void (*free)(struct vdpa_device *vdev); @@ -282,24 +345,41 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - size_t size, const char *name); + unsigned int ngroups, unsigned int nas, + size_t size, const char *name, + bool use_va); -#define vdpa_alloc_device(dev_struct, member, parent, config, name) \ - container_of(__vdpa_alloc_device( \ - parent, config, \ - sizeof(dev_struct) + \ +/** + * vdpa_alloc_device - allocate and initilaize a vDPA device + * + * @dev_struct: the type of the parent structure + * @member: the name of struct vdpa_device within the @dev_struct + * @parent: the parent device + * @config: the bus operations that is supported by this device + * @ngroups: the number of virtqueue groups supported by this device + * @nas: the number of address spaces + * @name: name of the vdpa device + * @use_va: indicate whether virtual address must be used by this device + * + * Return allocated data structure or ERR_PTR upon error + */ +#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, nas, \ + name, use_va) \ + container_of((__vdpa_alloc_device( \ + parent, config, ngroups, nas, \ + (sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name), \ + dev_struct, member))), name, use_va)), \ dev_struct, member) -int vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void vdpa_unregister_device(struct vdpa_device *vdev); -int _vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int _vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void _vdpa_unregister_device(struct vdpa_device *vdev); /** - * vdpa_driver - operations for a vDPA driver + * struct vdpa_driver - operations for a vDPA driver * @driver: underlying device driver * @probe: the function to call when a device is found. Returns 0 or -errno. * @remove: the function to call when a device is removed. @@ -346,59 +426,82 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev) static inline int vdpa_reset(struct vdpa_device *vdev) { - const struct vdpa_config_ops *ops = vdev->config; + const struct vdpa_config_ops *ops = vdev->config; + int ret; + down_write(&vdev->cf_lock); vdev->features_valid = false; - return ops->reset(vdev); + ret = ops->reset(vdev); + up_write(&vdev->cf_lock); + return ret; } -static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +static inline int vdpa_set_features_unlocked(struct vdpa_device *vdev, u64 features) { - const struct vdpa_config_ops *ops = vdev->config; + const struct vdpa_config_ops *ops = vdev->config; + int ret; vdev->features_valid = true; - return ops->set_features(vdev, features); -} + ret = ops->set_driver_features(vdev, features); + return ret; +} -static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, - void *buf, unsigned int len) +static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) { - const struct vdpa_config_ops *ops = vdev->config; - - /* - * Config accesses aren't supposed to trigger before features are set. - * If it does happen we assume a legacy guest. - */ - if (!vdev->features_valid) - vdpa_set_features(vdev, 0); - ops->get_config(vdev, offset, buf, len); + int ret; + + down_write(&vdev->cf_lock); + ret = vdpa_set_features_unlocked(vdev, features); + up_write(&vdev->cf_lock); + + return ret; } +void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, + void *buf, unsigned int len); +void vdpa_set_config(struct vdpa_device *dev, unsigned int offset, + const void *buf, unsigned int length); +void vdpa_set_status(struct vdpa_device *vdev, u8 status); + /** - * vdpa_mgmtdev_ops - vdpa device ops - * @dev_add: Add a vdpa device using alloc and register - * @mdev: parent device to use for device addition - * @name: name of the new vdpa device - * Driver need to add a new device using _vdpa_register_device() - * after fully initializing the vdpa device. Driver must return 0 - * on success or appropriate error code. - * @dev_del: Remove a vdpa device using unregister - * @mdev: parent device to use for device removal - * @dev: vdpa device to remove - * Driver need to remove the specified device by calling - * _vdpa_unregister_device(). + * struct vdpa_mgmtdev_ops - vdpa device ops + * @dev_add: Add a vdpa device using alloc and register + * @mdev: parent device to use for device addition + * @name: name of the new vdpa device + * @config: config attributes to apply to the device under creation + * Driver need to add a new device using _vdpa_register_device() + * after fully initializing the vdpa device. Driver must return 0 + * on success or appropriate error code. + * @dev_del: Remove a vdpa device using unregister + * @mdev: parent device to use for device removal + * @dev: vdpa device to remove + * Driver need to remove the specified device by calling + * _vdpa_unregister_device(). */ struct vdpa_mgmtdev_ops { - int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name); + int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config); void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev); }; +/** + * struct vdpa_mgmt_dev - vdpa management device + * @device: Management parent device + * @ops: operations supported by management device + * @id_table: Pointer to device id table of supported ids + * @config_attr_mask: bit mask of attributes of type enum vdpa_attr that + * management device support during dev_add callback + * @list: list entry + */ struct vdpa_mgmt_dev { struct device *device; const struct vdpa_mgmtdev_ops *ops; - const struct virtio_device_id *id_table; /* supported ids */ + struct virtio_device_id *id_table; + u64 config_attr_mask; struct list_head list; + u64 supported_features; + u32 max_supported_vqs; }; int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); diff --git a/include/linux/vhost_iotlb.h b/include/linux/vhost_iotlb.h index 6b09b786a7623c5c25a6fb70f576d2f97f7fcba0..e79a408389981e8bb0254aa6ba93cc4c265017e7 100644 --- a/include/linux/vhost_iotlb.h +++ b/include/linux/vhost_iotlb.h @@ -17,6 +17,7 @@ struct vhost_iotlb_map { u32 perm; u32 flags_padding; u64 __subtree_last; + void *opaque; }; #define VHOST_IOTLB_FLAG_RETIRE 0x1 @@ -29,10 +30,14 @@ struct vhost_iotlb { unsigned int flags; }; +int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, u64 start, u64 last, + u64 addr, unsigned int perm, void *opaque); int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last, u64 addr, unsigned int perm); void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last); +void vhost_iotlb_init(struct vhost_iotlb *iotlb, unsigned int limit, + unsigned int flags); struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags); void vhost_iotlb_free(struct vhost_iotlb *iotlb); void vhost_iotlb_reset(struct vhost_iotlb *iotlb); diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 90c5ad556809721a37fe6512bc7265fb9e251e18..51b94a439ced6a55af19af3f70d63d63f6310b67 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -139,6 +139,7 @@ void virtio_config_enable(struct virtio_device *dev); int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); #endif +void virtio_reset_device(struct virtio_device *dev); size_t virtio_max_dma_size(struct virtio_device *vdev); diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index e0615f42b0596dff0164f196b8709e36d66616e9..87778a45c78e7151ea461ae02aa7899dec43fe61 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -5,6 +5,13 @@ #include #include +struct virtio_pci_modern_common_cfg { + struct virtio_pci_common_cfg cfg; + + __le16 queue_notify_data; /* read-write */ + __le16 queue_reset; /* read-write */ +}; + struct virtio_pci_modern_device { struct pci_dev *pci_dev; @@ -102,15 +109,10 @@ void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev, u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev, u16 idx); u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev); -u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, - u16 idx); -void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, - size_t minlen, - u32 align, - u32 start, u32 size, - size_t *len, resource_size_t *pa); void __iomem *vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev, u16 index, resource_size_t *pa); int vp_modern_probe(struct virtio_pci_modern_device *mdev); void vp_modern_remove(struct virtio_pci_modern_device *mdev); +int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); +void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); #endif diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 66a41e4ec163aa460b1730f20ef3eca7aeb069ed..25c55cab3d7c7da5dbbc89a94562462cc907cf20 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -17,11 +17,16 @@ enum vdpa_command { VDPA_CMD_DEV_NEW, VDPA_CMD_DEV_DEL, VDPA_CMD_DEV_GET, /* can dump */ + VDPA_CMD_DEV_CONFIG_GET, /* can dump */ + VDPA_CMD_DEV_VSTATS_GET, }; enum vdpa_attr { VDPA_ATTR_UNSPEC, + /* Pad attribute for 64b alignment */ + VDPA_ATTR_PAD = VDPA_ATTR_UNSPEC, + /* bus name (optional) + dev name together make the parent device handle */ VDPA_ATTR_MGMTDEV_BUS_NAME, /* string */ VDPA_ATTR_MGMTDEV_DEV_NAME, /* string */ @@ -32,6 +37,20 @@ enum vdpa_attr { VDPA_ATTR_DEV_VENDOR_ID, /* u32 */ VDPA_ATTR_DEV_MAX_VQS, /* u32 */ VDPA_ATTR_DEV_MAX_VQ_SIZE, /* u16 */ + VDPA_ATTR_DEV_MIN_VQ_SIZE, /* u16 */ + + VDPA_ATTR_DEV_NET_CFG_MACADDR, /* binary */ + VDPA_ATTR_DEV_NET_STATUS, /* u8 */ + VDPA_ATTR_DEV_NET_CFG_MAX_VQP, /* u16 */ + VDPA_ATTR_DEV_NET_CFG_MTU, /* u16 */ + + VDPA_ATTR_DEV_NEGOTIATED_FEATURES, /* u64 */ + VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, /* u32 */ + VDPA_ATTR_DEV_SUPPORTED_FEATURES, /* u64 */ + + VDPA_ATTR_DEV_QUEUE_INDEX, /* u32 */ + VDPA_ATTR_DEV_VENDOR_ATTR_NAME, /* string */ + VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, /* u64 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 5d99e7c242a25e11dc579e059564aec4989b3387..f9f115a7c75b8a3060f0678599e7662d0015b878 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -89,11 +89,6 @@ /* Set or get vhost backend capability */ -/* Use message type V2 */ -#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 -/* IOTLB can accept batching hints */ -#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 - #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) @@ -150,11 +145,39 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) - /* Get the config size */ #define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) /* Get the count of all virtqueues */ #define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) + +/* Get the number of address spaces. */ +#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) + +/* Get the group for a virtqueue: read index, write group in num, + * The virtqueue index is stored in the index field of + * vhost_vring_state. The group for this specific virtqueue is + * returned via num field of vhost_vring_state. + */ +#define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \ + struct vhost_vring_state) +/* Set the ASID for a virtqueue group. The group index is stored in + * the index field of vhost_vring_state, the ASID associated with this + * group is stored at num field of vhost_vring_state. + */ +#define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \ + struct vhost_vring_state) + +/* Suspend a device so it does not process virtqueue requests anymore + * + * After the return of ioctl the device must preserve all the necessary state + * (the virtqueue vring base plus the possible device specific states) that is + * required for restoring in the future. The device must not change its + * configuration after that point. + */ +#define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) + #endif diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index f7f6a3a28977ae15f7391e270fa327cc60e4f101..1bdd6e363f4c9f1557608bf2218363e7024b1489 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -87,7 +87,7 @@ struct vhost_msg { struct vhost_msg_v2 { __u32 type; - __u32 reserved; + __u32 asid; union { struct vhost_iotlb_msg iotlb; __u8 padding[64]; @@ -153,4 +153,15 @@ struct vhost_vdpa_iova_range { /* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ #define VHOST_NET_F_VIRTIO_NET_HDR 27 +/* Use message type V2 */ +#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 +/* IOTLB can accept batching hints */ +#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 +/* IOTLB can accept address space identifier through V2 type of IOTLB + * message + */ +#define VHOST_BACKEND_F_IOTLB_ASID 0x3 +/* Device can be suspended */ +#define VHOST_BACKEND_F_SUSPEND 0x4 + #endif diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 3a86f36d7e3d965633594fa9210c9ab28221b6b3..f703afc7ad31ba0791101585fd95b9a10a48f3ce 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -202,6 +202,8 @@ struct virtio_pci_cfg_cap { #define VIRTIO_PCI_COMMON_Q_AVAILHI 44 #define VIRTIO_PCI_COMMON_Q_USEDLO 48 #define VIRTIO_PCI_COMMON_Q_USEDHI 52 +#define VIRTIO_PCI_COMMON_Q_NDATA 56 +#define VIRTIO_PCI_COMMON_Q_RESET 58 #endif /* VIRTIO_PCI_NO_MODERN */ diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index f582351d84ecbac0cee4d792ef903af9040ba5d5..67ec5ed831dde68f5f2b74facdbe51e9465c6e18 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -716,7 +716,7 @@ static void p9_virtio_remove(struct virtio_device *vdev) mutex_unlock(&virtio_9p_lock); - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index e131121533ad93d718a826f4a634aa12ce2aa476..9a1bdaffc0324a311e97dd3152f4117635d79535 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -641,7 +641,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev) virtio_vsock_reset_sock); /* Stop all work handlers to make sure no one is accessing the device, - * so we can safely call vdev->config->reset(). + * so we can safely call virtio_reset_device(). */ mutex_lock(&vsock->rx_lock); vsock->rx_run = false; @@ -658,7 +658,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev) /* Flush all device writes and interrupts, device will not use any * more buffers. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); mutex_lock(&vsock->rx_lock); while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX]))) diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c998860d7bbc4351c37c702ea69ea88a814b19cf..f9f115a7c75b8a3060f0678599e7662d0015b878 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -89,11 +89,6 @@ /* Set or get vhost backend capability */ -/* Use message type V2 */ -#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 -/* IOTLB can accept batching hints */ -#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 - #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) @@ -150,4 +145,39 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) +/* Get the config size */ +#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) + +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) + +/* Get the number of address spaces. */ +#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) + +/* Get the group for a virtqueue: read index, write group in num, + * The virtqueue index is stored in the index field of + * vhost_vring_state. The group for this specific virtqueue is + * returned via num field of vhost_vring_state. + */ +#define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \ + struct vhost_vring_state) +/* Set the ASID for a virtqueue group. The group index is stored in + * the index field of vhost_vring_state, the ASID associated with this + * group is stored at num field of vhost_vring_state. + */ +#define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \ + struct vhost_vring_state) + +/* Suspend a device so it does not process virtqueue requests anymore + * + * After the return of ioctl the device must preserve all the necessary state + * (the virtqueue vring base plus the possible device specific states) that is + * required for restoring in the future. The device must not change its + * configuration after that point. + */ +#define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) + #endif