Control VQ support in vDPA
Subsystems (7)
cover Control VQ support in vDPA
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accesing it directly.
To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address space
Device needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groups
The mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.
vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commands
This will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking in vhost_vdpa_unmap()
Thanks
Jason Wang (20):
vhost: move the backend feature bits to vhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: add the missing comment for nvqs in struct vdpa_device
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertise VIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue support
Stefano Garzarella (1):
vdpa_sim: split vdpasim_virtqueue's iov field in out_iov and in_iov
drivers/vdpa/ifcvf/ifcvf_main.c | 9 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 8 +- drivers/vdpa/vdpa_sim/vdpa_sim.c | 292 ++++++++++++++++++++++++------ drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 246 ++++++++++++++++++++----- drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 42 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 10 +- 13 files changed, 561 insertions(+), 136 deletions(-)
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 1/21 vhost: move the backend feature bits to vhost_types.h
We should store feature bits in vhost_types.h as what has been done for e.g VHOST_F_LOG_ALL.
--- include/uapi/linux/vhost.h | 5 ----- include/uapi/linux/vhost_types.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-)
include/uapi/linux/vhost.h +0 -5
@@ -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)
include/uapi/linux/vhost_types.h +5 -0
@@ -153,4 +153,9 @@ 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 +#endif
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 2/21 virtio-vdpa: don't set callback if virtio doesn't need it
In reply to Jason WangThere's no need for setting callbacks for the driver that doesn't care about that.
--- drivers/virtio/virtio_vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/virtio/virtio_vdpa.c +1 -1
@@ -175,7 +175,7 @@ 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));
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 3/21 vhost-vdpa: passing iotlb to IOMMU mapping helpers
In reply to Jason WangTo prepare for the ASID support for vhost-vdpa, try to pass IOTLB object to dma helpers. No functional changes, it's just a preparation for support multiple IOTLBs.
--- drivers/vhost/vdpa.c | 41 +++++++++++++++++++++++------------------ 1 file changed, 23 insertions(+), 18 deletions(-)
drivers/vhost/vdpa.c +23 -18
@@ -501,10 +501,11 @@ 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_iotlb_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;
@@ -526,8 +527,9 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) {struct vhost_dev *dev = &v->vdev; +struct vhost_iotlb *iotlb = dev->iotlb; -vhost_vdpa_iotlb_unmap (v,0ULL ,0ULL -1 ); +vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 );kfree (dev->iotlb); dev->iotlb =NULL ; }
@@ -554,7 +556,7 @@ static int perm_to_iommu_flags(u32 perm)return flags |IOMMU_CACHE ; } -static int vhost_vdpa_map (struct vhost_vdpa *v, +static int vhost_vdpa_map (struct vhost_vdpa *v,struct vhost_iotlb *iotlb,u64 iova,u64 size,u64 pa,u32 perm) {struct vhost_dev *dev = &v->vdev;
@@ -562,7 +564,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v,const struct vdpa_config_ops *ops = vdpa->config;int r =0 ; - r =vhost_iotlb_add_range (dev->iotlb, iova, iova + size -1 , + r =vhost_iotlb_add_range (iotlb, iova, iova + size -1 , pa, perm);if (r)return r;
@@ -571,43 +573,44 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, r = ops->dma_map (vdpa, iova, size, pa, perm); }else if (ops->set_map) {if (!v->in_batch) - r = ops->set_map (vdpa, dev->iotlb); + r = ops->set_map (vdpa, iotlb); }else { r =iommu_map (v->domain, iova, pa, size,perm_to_iommu_flags (perm)); }if (r) -vhost_iotlb_del_range (dev->iotlb, iova, iova + size -1 ); +vhost_iotlb_del_range (iotlb, iova, iova + size -1 );else atomic64_add (size >>PAGE_SHIFT , &dev->mm->pinned_vm);return r; } -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; -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); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa, dev->iotlb); + ops->set_map (vdpa, iotlb); }else {iommu_unmap (v->domain, iova, size); } }static int vhost_vdpa_process_iotlb_update (struct vhost_vdpa *v, +struct vhost_iotlb *iotlb,struct vhost_iotlb_msg *msg) {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 ;
@@ -676,7 +679,7 @@ 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, + ret =vhost_vdpa_map (v, iotlb, iova, csize, map_pfn <<PAGE_SHIFT , msg->perm);if (ret) {
@@ -706,7 +709,8 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, }/* Pin the rest chunk */ - ret =vhost_vdpa_map (v, iova, (last_pfn - map_pfn +1 ) <<PAGE_SHIFT , + ret =vhost_vdpa_map (v, iotlb, iova, + (last_pfn - map_pfn +1 ) <<PAGE_SHIFT , map_pfn <<PAGE_SHIFT , msg->perm); out:if (ret) {
@@ -726,7 +730,7 @@ 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, msg->iova, msg->size); } unlock:mmap_read_unlock (dev->mm);
@@ -741,6 +745,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, 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 = dev->iotlb;int r =0 ; r =vhost_dev_check_owner (dev);
@@ -749,17 +754,17 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,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->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, iotlb); v->in_batch = false;break ;default :
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 4/21 vhost-vdpa: switch to use vhost-vdpa specific IOTLB
In reply to Jason WangTo ease the implementation of per group ASID support for vDPA device. This patch switches to use a vhost-vdpa specific IOTLB to avoid the unnecessary refactoring of the vhost core.
--- drivers/vhost/vdpa.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)
drivers/vhost/vdpa.c +10 -8
@@ -39,6 +39,7 @@ struct vhost_vdpa {struct vhost_virtqueue *vqs;struct completion completion;struct vdpa_device *vdpa; +struct vhost_iotlb *iotlb;struct device dev;struct cdev cdev;atomic_t opened;
@@ -526,12 +527,11 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) { -struct vhost_dev *dev = &v->vdev; -struct vhost_iotlb *iotlb = dev->iotlb; +struct vhost_iotlb *iotlb = v->iotlb;vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 ); -kfree (dev->iotlb); - dev->iotlb =NULL ; +kfree (v->iotlb); + v->iotlb =NULL ; }static int perm_to_iommu_flags (u32 perm)
@@ -745,7 +745,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, 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 = dev->iotlb; +struct vhost_iotlb *iotlb = v->iotlb;int r =0 ; r =vhost_dev_check_owner (dev);
@@ -883,15 +883,15 @@ 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) { + v->iotlb =vhost_iotlb_alloc (0 ,0 ); +if (!v->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);
@@ -899,6 +899,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; +err_alloc_domain: +vhost_vdpa_iotlb_free (v); err_init_iotlb:vhost_dev_cleanup (&v->vdev);kfree (vqs);
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 5/21 vdpa: add the missing comment for nvqs in struct vdpa_device
In reply to Jason Wang--- include/linux/vdpa.h | 1 + 1 file changed, 1 insertion(+)
include/linux/vdpa.h +1 -0
@@ -42,6 +42,7 @@ struct vdpa_vq_state {* @config: the configuration ops for this device. * @index: device index * @features_valid: were features initialized? for legacy guests +* @nvqs: the number of virtqueues */ struct vdpa_device {struct device dev;
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 6/21 vdpa: introduce virtqueue groups
In reply to Jason WangThis patch introduces virtqueue groups to vDPA device. The virtqueue group is the minimal set of virtqueues that must share an address space. And the adddress space identifier could only be attached to a specific virtqueue group.
A new mandated bus operation is introduced to get the virtqueue group ID for a specific virtqueue.
All the vDPA device drivers were converted to simply support a single virtqueue group.
--- drivers/vdpa/ifcvf/ifcvf_main.c | 9 ++++++++- drivers/vdpa/mlx5/net/mlx5_vnet.c | 8 +++++++- drivers/vdpa/vdpa.c | 4 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 11 ++++++++++- include/linux/vdpa.h | 12 +++++++++--- 5 files changed, 37 insertions(+), 7 deletions(-)
drivers/vdpa/ifcvf/ifcvf_main.c +8 -1
@@ -332,6 +332,11 @@ static u32 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev)return IFCVF_QUEUE_ALIGNMENT ; } +static u32 ifcvf_vdpa_get_vq_group (struct vdpa_device *vdpa,u16 idx) +{ +return 0 ; +} +static void ifcvf_vdpa_get_config (struct vdpa_device *vdpa_dev,unsigned int offset,void *buf,unsigned int len)
@@ -392,6 +397,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = { .get_device_id = ifcvf_vdpa_get_device_id, .get_vendor_id = ifcvf_vdpa_get_vendor_id, .get_vq_align = ifcvf_vdpa_get_vq_align, + .get_vq_group = ifcvf_vdpa_get_vq_group, .get_config = ifcvf_vdpa_get_config, .set_config = ifcvf_vdpa_set_config, .set_config_cb = ifcvf_vdpa_set_config_cb,
@@ -439,7 +445,8 @@ 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, -IFCVF_MAX_QUEUE_PAIRS *2 ); +IFCVF_MAX_QUEUE_PAIRS *2 ,1 ); +if (adapter ==NULL ) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" );return -ENOMEM ;
drivers/vdpa/mlx5/net/mlx5_vnet.c +7 -1
@@ -1436,6 +1436,11 @@ static u32 mlx5_vdpa_get_vq_align(struct vdpa_device *vdev)return PAGE_SIZE ; } +static u32 mlx5_vdpa_get_vq_group (struct vdpa_device *vdpa,u16 idx) +{ +return 0 ; +} +enum {MLX5_VIRTIO_NET_F_GUEST_CSUM =1 <<9 ,MLX5_VIRTIO_NET_F_CSUM =1 <<10 ,MLX5_VIRTIO_NET_F_HOST_TSO6 =1 <<11 ,
@@ -1854,6 +1859,7 @@ 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_vq_group = mlx5_vdpa_get_vq_group, .get_features = mlx5_vdpa_get_features, .set_features = mlx5_vdpa_set_features, .set_config_cb = mlx5_vdpa_set_config_cb,
@@ -1941,7 +1947,7 @@ 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, -2 *mlx5_vdpa_max_qps (max_vqs)); +2 *mlx5_vdpa_max_qps (max_vqs),1 );if (IS_ERR (ndev))return ndev;
drivers/vdpa/vdpa.c +3 -1
@@ -62,6 +62,7 @@ static void vdpa_release_dev(struct device *d)* @parent: the parent device * @config: the bus operations that is supported by this device * @nvqs: number of virtqueues supported by this device +* @ngroups: number of groups supported by this device * @size: size of the parent structure that contains private data * * Driver should use vdpa_alloc_device() wrapper macro instead of
@@ -72,7 +73,7 @@ static void vdpa_release_dev(struct device *d)*/ struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, -int nvqs, +int nvqs,unsigned int ngroups,size_t size) {struct vdpa_device *vdev;
@@ -100,6 +101,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->config = config; vdev->features_valid = false; vdev->nvqs = nvqs; + vdev->ngroups = ngroups; err =dev_set_name (&vdev->dev,"vdpa%u" , vdev->index);if (err)
drivers/vdpa/vdpa_sim/vdpa_sim.c +10 -1
@@ -80,6 +80,7 @@ struct vdpasim {u32 status;u32 generation;u64 features; +u32 groups;/* spinlock to synchronize iommu table */ spinlock_t iommu_lock; };
@@ -357,7 +358,8 @@ static struct vdpasim *vdpasim_create(void)else ops = &vdpasim_net_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM); + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, +VDPASIM_VQ_NUM ,1 );if (!vdpasim) goto err_alloc;
@@ -496,6 +498,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)return VDPASIM_QUEUE_ALIGN ; } +static u32 vdpasim_get_vq_group (struct vdpa_device *vdpa,u16 idx) +{ +return 0 ; +} +static u64 vdpasim_get_features (struct vdpa_device *vdpa) {return vdpasim_features;
@@ -671,6 +678,7 @@ 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_vq_group = vdpasim_get_vq_group, .get_features = vdpasim_get_features, .set_features = vdpasim_set_features, .set_config_cb = vdpasim_set_config_cb,
@@ -698,6 +706,7 @@ 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_vq_group = vdpasim_get_vq_group, .get_features = vdpasim_get_features, .set_features = vdpasim_set_features, .set_config_cb = vdpasim_set_config_cb,
include/linux/vdpa.h +9 -3
@@ -51,6 +51,7 @@ struct vdpa_device {unsigned int index;bool features_valid;int nvqs; +unsigned int ngroups; };/**
@@ -119,6 +120,10 @@ struct vdpa_iova_range {* for the device * @vdev: vdpa device * Returns virtqueue algin requirement +* @get_vq_group: Get the group id for a specific virtqueue +* @vdev: vdpa device +* @idx: virtqueue index +* Returns u32: group id for this virtqueue * @get_features: Get virtio features supported by the device * @vdev: vdpa device * Returns the virtio features support by the
@@ -217,6 +222,7 @@ struct vdpa_config_ops {/* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); +u32 (*get_vq_group)(struct vdpa_device *vdev,u16 idx);u64 (*get_features)(struct vdpa_device *vdev);int (*set_features)(struct vdpa_device *vdev,u64 features); void (*set_config_cb)(struct vdpa_device *vdev,
@@ -245,12 +251,12 @@ struct vdpa_config_ops {struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, -int nvqs, +int nvqs,unsigned int ngroups,size_t size); -#define vdpa_alloc_device (dev_struct, member, parent, config, nvqs) \ +#define vdpa_alloc_device (dev_struct, member, parent, config, nvqs, ngroups) \ container_of(__vdpa_alloc_device( \ - parent, config, nvqs, \ + parent, config, nvqs, ngroups, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ dev_struct, member))), \
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 06/21] vdpa: introduce virtqueue groups
Quoted 11 lines · Jason Wang
This patch introduces virtqueue groups to vDPA device. The virtqueue group is the minimal set of virtqueues that must share an address space. And the adddress space identifier could only be attached to a specific virtqueue group.
A new mandated bus operation is introduced to get the virtqueue group ID for a specific virtqueue.
All the vDPA device drivers were converted to simply support a single virtqueue group.
Quoted 8 lines
Signed-off-by Jason Wang <[email protected]>--- drivers/vdpa/ifcvf/ifcvf_main.c | 9 ++++++++- drivers/vdpa/mlx5/net/mlx5_vnet.c | 8 +++++++- drivers/vdpa/vdpa.c | 4 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 11 ++++++++++- include/linux/vdpa.h | 12 +++++++++--- 5 files changed, 37 insertions(+), 7 deletions(-)
Maybe consider calling it iotlb_group or iommu_group so the purpose of the group is clear?
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 06/21] vdpa: introduce virtqueue groups
Quoted 20 lines · Stefan Hajnoczi
Quoted 11 lines · Jason Wang
This patch introduces virtqueue groups to vDPA device. The virtqueue group is the minimal set of virtqueues that must share an address space. And the adddress space identifier could only be attached to a specific virtqueue group.
A new mandated bus operation is introduced to get the virtqueue group ID for a specific virtqueue.
All the vDPA device drivers were converted to simply support a single virtqueue group.
Quoted 8 lines
Signed-off-by Jason Wang <[email protected]>--- drivers/vdpa/ifcvf/ifcvf_main.c | 9 ++++++++- drivers/vdpa/mlx5/net/mlx5_vnet.c | 8 +++++++- drivers/vdpa/vdpa.c | 4 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 11 ++++++++++- include/linux/vdpa.h | 12 +++++++++--- 5 files changed, 37 insertions(+), 7 deletions(-)
Quoted 2 lines
Maybe consider calling it
iotlb_grouporiommu_groupso the purpose of the group is clear?
I'm not sure. The reason that I choose virtqueue group is because:
1) Virtqueue is the only entity that tries to issues DMA
2) For IOMMU group, it may cause confusion to the existing IOMMU group who group devices
3) IOTLB is the concept in vhost, we don't have such definition in the virtio spec
Thanks
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 7/21 vdpa: multiple address spaces support
In reply to Jason WangThis patches introduces the multiple address spaces support for vDPA device. This idea is to identify a specific address space via an dedicated identifier - ASID.
During vDPA device allocation, vDPA device driver needs to report the number of address spaces supported by the device then the DMA mapping ops of the vDPA device needs to be extended to support ASID.
This helps to isolate the environments for the virtqueue that will not be assigned directly. E.g in the case of virtio-net, the control virtqueue will not be assigned directly to guest.
As a start, simply claim 1 virtqueue groups and 1 address spaces for all vDPA devices. And vhost-vDPA will simply reject the device with more than 1 virtqueue groups or address spaces.
--- drivers/vdpa/ifcvf/ifcvf_main.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 +++-- drivers/vdpa/vdpa.c | 4 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 10 ++++++---- drivers/vhost/vdpa.c | 14 +++++++++----- include/linux/vdpa.h | 23 ++++++++++++++++------- 6 files changed, 38 insertions(+), 20 deletions(-)
drivers/vdpa/ifcvf/ifcvf_main.c +1 -1
@@ -445,7 +445,7 @@ 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, -IFCVF_MAX_QUEUE_PAIRS *2 ,1 ); +IFCVF_MAX_QUEUE_PAIRS *2 ,1 ,1 );if (adapter ==NULL ) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" );
drivers/vdpa/mlx5/net/mlx5_vnet.c +3 -2
@@ -1804,7 +1804,8 @@ 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);
@@ -1947,7 +1948,7 @@ 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, -2 *mlx5_vdpa_max_qps (max_vqs),1 ); +2 *mlx5_vdpa_max_qps (max_vqs),1 ,1 );if (IS_ERR (ndev))return ndev;
drivers/vdpa/vdpa.c +3 -1
@@ -63,6 +63,7 @@ static void vdpa_release_dev(struct device *d)* @config: the bus operations that is supported by this device * @nvqs: number of virtqueues 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 * * Driver should use vdpa_alloc_device() wrapper macro instead of
@@ -74,7 +75,7 @@ static void vdpa_release_dev(struct device *d)struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config,int nvqs,unsigned int ngroups, -size_t size) +unsigned int nas,size_t size) {struct vdpa_device *vdev;int err = -EINVAL ;
@@ -102,6 +103,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->features_valid = false; vdev->nvqs = nvqs; vdev->ngroups = ngroups; + vdev->nas = nas; err =dev_set_name (&vdev->dev,"vdpa%u" , vdev->index);if (err)
drivers/vdpa/vdpa_sim/vdpa_sim.c +6 -4
@@ -359,7 +359,7 @@ static struct vdpasim *vdpasim_create(void) ops = &vdpasim_net_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, -VDPASIM_VQ_NUM ,1 ); +VDPASIM_VQ_NUM ,1 ,1 );if (!vdpasim) goto err_alloc;
@@ -606,7 +606,7 @@ 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);
@@ -633,7 +633,8 @@ static int vdpasim_set_map(struct vdpa_device *vdpa,return ret; } -static int vdpasim_dma_map (struct vdpa_device *vdpa,u64 iova,u64 size, +static int vdpasim_dma_map (struct vdpa_device *vdpa,unsigned int asid, +u64 iova,u64 size,u64 pa,u32 perm) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);
@@ -647,7 +648,8 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,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);
drivers/vhost/vdpa.c +9 -5
@@ -570,10 +570,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r;if (ops->dma_map) { - r = ops->dma_map (vdpa, iova, size, pa, perm); + r = ops->dma_map (vdpa,0 , iova, size, pa, perm); }else if (ops->set_map) {if (!v->in_batch) - r = ops->set_map (vdpa, iotlb); + r = ops->set_map (vdpa,0 , iotlb); }else { r =iommu_map (v->domain, iova, pa, size,perm_to_iommu_flags (perm));
@@ -597,10 +597,10 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v,vhost_vdpa_iotlb_unmap (v, iotlb, iova, iova + size -1 );if (ops->dma_map) { - ops->dma_unmap (vdpa, iova, size); + ops->dma_unmap (vdpa,0 , iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); }else {iommu_unmap (v->domain, iova, size); }
@@ -764,7 +764,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,break ;case VHOST_IOTLB_BATCH_END :if (v->in_batch && ops->set_map) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); v->in_batch = false;break ;default :
@@ -1032,6 +1032,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int r; +/* Only support 1 address space and 1 groups */ +if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +return -ENOTSUPP ; +/* Currently, we only accept the network devices. */ if (ops->get_device_id (vdpa) !=VIRTIO_ID_NET )return -ENOTSUPP ;
include/linux/vdpa.h +16 -7
@@ -43,6 +43,8 @@ struct vdpa_vq_state {* @index: device index * @features_valid: were features initialized? for legacy guests * @nvqs: the number of virtqueues +* @ngroups: the number of virtqueue groups +* @nas: the number of address spaces */ struct vdpa_device {struct device dev;
@@ -52,6 +54,7 @@ struct vdpa_device {bool features_valid;int nvqs;unsigned int ngroups; +unsigned int nas; };/**
@@ -175,6 +178,7 @@ struct vdpa_iova_range {* 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)
@@ -183,6 +187,7 @@ 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
@@ -194,6 +199,7 @@ 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)
@@ -240,10 +246,12 @@ 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); +int (*dma_unmap)(struct vdpa_device *vdev,unsigned int asid, +u64 iova,u64 size);/* Free device resources */ void (*free)(struct vdpa_device *vdev);
@@ -252,11 +260,12 @@ struct vdpa_config_ops {struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config,int nvqs,unsigned int ngroups, -size_t size); +unsigned int nas,size_t size); -#define vdpa_alloc_device (dev_struct, member, parent, config, nvqs, ngroups) \ +#define vdpa_alloc_device (dev_struct, member, parent, config, nvqs, \ + ngroups, nas) \ container_of(__vdpa_alloc_device( \ - parent, config, nvqs, ngroups, \ + parent, config, nvqs, ngroups, nas, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ dev_struct, member))), \
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 07/21] vdpa: multiple address spaces support
Quoted 188 lines · Jason Wang
This patches introduces the multiple address spaces support for vDPA device. This idea is to identify a specific address space via an dedicated identifier - ASID.
During vDPA device allocation, vDPA device driver needs to report the number of address spaces supported by the device then the DMA mapping ops of the vDPA device needs to be extended to support ASID.
This helps to isolate the environments for the virtqueue that will not be assigned directly. E.g in the case of virtio-net, the control virtqueue will not be assigned directly to guest.
As a start, simply claim 1 virtqueue groups and 1 address spaces for all vDPA devices. And vhost-vDPA will simply reject the device with more than 1 virtqueue groups or address spaces.
Signed-off-by Jason Wang <[email protected]>--- drivers/vdpa/ifcvf/ifcvf_main.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 +++-- drivers/vdpa/vdpa.c | 4 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 10 ++++++---- drivers/vhost/vdpa.c | 14 +++++++++----- include/linux/vdpa.h | 23 ++++++++++++++++------- 6 files changed, 38 insertions(+), 20 deletions(-)drivers/vdpa/ifcvf/ifcvf_main.c +1
-1@@ -445,7 +445,7 @@ 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, -IFCVF_MAX_QUEUE_PAIRS *2 ,1 ); +IFCVF_MAX_QUEUE_PAIRS *2 ,1 ,1 );if (adapter ==NULL ) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" );drivers/vdpa/mlx5/net/mlx5_vnet.c +3
-2@@ -1804,7 +1804,8 @@ 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);@@ -1947,7 +1948,7 @@ 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, -2 *mlx5_vdpa_max_qps (max_vqs),1 ); +2 *mlx5_vdpa_max_qps (max_vqs),1 ,1 );if (IS_ERR (ndev))return ndev;drivers/vdpa/vdpa.c +3
-1@@ -63,6 +63,7 @@ static void vdpa_release_dev(struct device *d)* @config: the bus operations that is supported by this device * @nvqs: number of virtqueues 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 * * Driver should use vdpa_alloc_device() wrapper macro instead of @@ -74,7 +75,7 @@ static void vdpa_release_dev(struct device *d)struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config,int nvqs,unsigned int ngroups, -size_t size) +unsigned int nas,size_t size) {struct vdpa_device *vdev;int err = -EINVAL ;@@ -102,6 +103,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->features_valid = false; vdev->nvqs = nvqs; vdev->ngroups = ngroups; + vdev->nas = nas; err =dev_set_name (&vdev->dev,"vdpa%u" , vdev->index);if (err)drivers/vdpa/vdpa_sim/vdpa_sim.c +6
-4@@ -359,7 +359,7 @@ static struct vdpasim *vdpasim_create(void) ops = &vdpasim_net_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, -VDPASIM_VQ_NUM ,1 ); +VDPASIM_VQ_NUM ,1 ,1 );if (!vdpasim) goto err_alloc;@@ -606,7 +606,7 @@ 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);@@ -633,7 +633,8 @@ static int vdpasim_set_map(struct vdpa_device *vdpa,return ret; } -static int vdpasim_dma_map (struct vdpa_device *vdpa,u64 iova,u64 size, +static int vdpasim_dma_map (struct vdpa_device *vdpa,unsigned int asid, +u64 iova,u64 size,u64 pa,u32 perm) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);@@ -647,7 +648,8 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,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);drivers/vhost/vdpa.c +9
-5@@ -570,10 +570,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r;if (ops->dma_map) { - r = ops->dma_map (vdpa, iova, size, pa, perm); + r = ops->dma_map (vdpa,0 , iova, size, pa, perm); }else if (ops->set_map) {if (!v->in_batch) - r = ops->set_map (vdpa, iotlb); + r = ops->set_map (vdpa,0 , iotlb); }else { r =iommu_map (v->domain, iova, pa, size,perm_to_iommu_flags (perm));@@ -597,10 +597,10 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v,vhost_vdpa_iotlb_unmap (v, iotlb, iova, iova + size -1 );if (ops->dma_map) { - ops->dma_unmap (vdpa, iova, size); + ops->dma_unmap (vdpa,0 , iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); }else {iommu_unmap (v->domain, iova, size); }@@ -764,7 +764,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,break ;case VHOST_IOTLB_BATCH_END :if (v->in_batch && ops->set_map) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); v->in_batch = false;break ;default :@@ -1032,6 +1032,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int r; +/* Only support 1 address space and 1 groups */ +if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +return -ENOTSUPP ; +/* Currently, we only accept the network devices. */ if (ops->get_device_id (vdpa) !=VIRTIO_ID_NET )return -ENOTSUPP ;include/linux/vdpa.h +0
-0
include/linux/vdpa.h struct vdpa_vq_state { · line 47
Quoted 5 lines
include/linux/vdpa.h +2
-0@@ -43,6 +43,8 @@ struct vdpa_vq_state {* @index: device index * @features_valid: were features initialized? for legacy guests * @nvqs: the number of virtqueues +* @ngroups: the number of virtqueue groups +* @nas: the number of address spaces
I am not sure these can be categorised as part of the state of the VQ. It's more of a property so maybe we can have a callback to get the properties of the VQ?
Moreover, I think they should be handled in the hardware drivers to return 1 for both ngroups and nas.
Quoted 71 lines
include/linux/vdpa.h +14
-7*/ struct vdpa_device {struct device dev;@@ -52,6 +54,7 @@ struct vdpa_device {bool features_valid;int nvqs;unsigned int ngroups; +unsigned int nas; };/** @@ -175,6 +178,7 @@ struct vdpa_iova_range {* 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) @@ -183,6 +187,7 @@ 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 @@ -194,6 +199,7 @@ 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) @@ -240,10 +246,12 @@ 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); +int (*dma_unmap)(struct vdpa_device *vdev,unsigned int asid, +u64 iova,u64 size);/* Free device resources */ void (*free)(struct vdpa_device *vdev);@@ -252,11 +260,12 @@ struct vdpa_config_ops {struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config,int nvqs,unsigned int ngroups, -size_t size); +unsigned int nas,size_t size); -#define vdpa_alloc_device (dev_struct, member, parent, config, nvqs, ngroups) \ +#define vdpa_alloc_device (dev_struct, member, parent, config, nvqs, \ + ngroups, nas) \ container_of(__vdpa_alloc_device( \ - parent, config, nvqs, ngroups, \ + parent, config, nvqs, ngroups, nas, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ dev_struct, member))), \Signature · 1 line
2.25.1
Re: [PATCH 07/21] vdpa: multiple address spaces support
Quoted 10 lines · Eli Cohen
include/linux/vdpa.h struct vdpa_vq_state { · line 47
Quoted 6 lines
include/linux/vdpa.h +2
-0@@ -43,6 +43,8 @@ struct vdpa_vq_state {* @index: device index * @features_valid: were features initialized? for legacy guests * @nvqs: the number of virtqueues +* @ngroups: the number of virtqueue groups +* @nas: the number of address spaces I am not sure these can be categorised as part of the state of the VQ. It's more of a property so maybe we can have a callback to get the properties of the VQ?
Quoted 2 lines
Moreover, I think they should be handled in the hardware drivers to return 1 for both ngroups and nas.
We can, but those are static attributes that is not expected to be changed by the driver.
Introduce callbacks for those static stuffs does not give us any advantage.
For group id and notification area, since we don't have a abstract of vdpa_virtqueue. The only choice is to introduce callbacks for them.
Maybe it's time to introduce vdpa_virtqueue.
Thanks
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 07/21] vdpa: multiple address spaces support
In reply to Eli CohenQuoted 9 lines · Eli Cohen
include/linux/vdpa.h struct vdpa_vq_state { · line 47
Quoted 6 lines
include/linux/vdpa.h +2
-0@@ -43,6 +43,8 @@ struct vdpa_vq_state {* @index: device index * @features_valid: were features initialized? for legacy guests * @nvqs: the number of virtqueues +* @ngroups: the number of virtqueue groups +* @nas: the number of address spaces I am not sure these can be categorised as part of the state of the VQ. It's more of a property so maybe we can have a callback to get the properties of the VQ?
Or maybe there's a misunderstanding of the patch.
Those two attributes belongs to vdpa_device instead of vdpa_vq_state actually.
Thanks
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 07/21] vdpa: multiple address spaces support
Quoted 13 lines · Jason Wang
Quoted 9 lines · Eli Cohen
include/linux/vdpa.h struct vdpa_vq_state { · line 47
Quoted 6 lines
include/linux/vdpa.h +2
-0@@ -43,6 +43,8 @@ struct vdpa_vq_state {* @index: device index * @features_valid: were features initialized? for legacy guests * @nvqs: the number of virtqueues +* @ngroups: the number of virtqueue groups +* @nas: the number of address spaces I am not sure these can be categorised as part of the state of the VQ. It's more of a property so maybe we can have a callback to get the properties of the VQ?
Quoted 2 lines
Or maybe there's a misunderstanding of the patch.
Yes, I misinterpreted the hunk. No issue here.
Quoted 5 lines
Those two attributes belongs to
vdpa_deviceinstead ofvdpa_vq_stateactually.Thanks
PATCH 8/21 vdpa: introduce config operations for associating ASID to a virtqueue group
In reply to Jason WangThis patch introduces a new bus operation to allow the vDPA bus driver to associate an ASID to a virtqueue group.
--- include/linux/vdpa.h | 10 ++++++++++ 1 file changed, 10 insertions(+)
include/linux/vdpa.h +10 -0
@@ -174,6 +174,12 @@ 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 +* @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)
@@ -252,6 +258,10 @@ struct vdpa_config_ops { u64 iova, u64 size, u64 pa, u32 perm);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);
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 9/21 vhost_iotlb: split out IOTLB initialization
In reply to Jason WangThis patch splits out IOTLB initialization to make sure it could be reused by external modules.
--- drivers/vhost/iotlb.c | 23 ++++++++++++++++++----- include/linux/vhost_iotlb.h | 2 ++ 2 files changed, 20 insertions(+), 5 deletions(-)
drivers/vhost/iotlb.c +18 -5
@@ -98,6 +98,23 @@ 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 +129,7 @@ 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; }
include/linux/vhost_iotlb.h +2 -0
@@ -33,6 +33,8 @@ 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);
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 10/21 vhost: support ASID in IOTLB API
In reply to Jason WangThis patches allows userspace to send ASID based IOTLB message to vhost. This idea is to use the reserved u32 field in the existing V2 IOTLB message. Vhost device should advertise this capability via VHOST_BACKEND_F_IOTLB_ASID backend feature.
--- drivers/vhost/vdpa.c | 5 ++++- drivers/vhost/vhost.c | 23 ++++++++++++++++++----- drivers/vhost/vhost.h | 4 ++-- include/uapi/linux/vhost_types.h | 5 ++++- 4 files changed, 28 insertions(+), 9 deletions(-)
drivers/vhost/vdpa.c +4 -1
@@ -739,7 +739,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,return ret; } -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);
@@ -748,6 +748,9 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,struct vhost_iotlb *iotlb = v->iotlb;int r =0 ; +if (asid !=0 ) +return -EINVAL ; + r =vhost_dev_check_owner (dev);if (r)return r;
drivers/vhost/vhost.c +18 -5
@@ -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;
@@ -1084,11 +1084,14 @@ 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,u16 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) {
@@ -1135,6 +1138,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,struct vhost_iotlb_msg msg;size_t offset;int type, ret; +u16 asid =0 ; ret =copy_from_iter (&type,sizeof (type), from);if (ret !=sizeof (type)) {
@@ -1150,7 +1154,16 @@ 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 =sizeof (__u16); + }else + offset =sizeof (__u32);break ;default : ret = -EINVAL ;
@@ -1165,9 +1178,9 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, }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;
drivers/vhost/vhost.h +2 -2
@@ -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);
include/uapi/linux/vhost_types.h +4 -1
@@ -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 ];
@@ -157,5 +157,8 @@ struct vhost_vdpa_iova_range {#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#endif
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 10/21] vhost: support ASID in IOTLB API
Quoted 66 lines · Jason Wang
This patches allows userspace to send ASID based IOTLB message to vhost. This idea is to use the reserved u32 field in the existing V2 IOTLB message. Vhost device should advertise this capability via
VHOST_BACKEND_F_IOTLB_ASIDbackend feature.Signed-off-by Jason Wang <[email protected]>--- drivers/vhost/vdpa.c | 5 ++++- drivers/vhost/vhost.c | 23 ++++++++++++++++++----- drivers/vhost/vhost.h | 4 ++-- include/uapi/linux/vhost_types.h | 5 ++++- 4 files changed, 28 insertions(+), 9 deletions(-)drivers/vhost/vdpa.c +4
-1@@ -739,7 +739,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,return ret; } -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);@@ -748,6 +748,9 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,struct vhost_iotlb *iotlb = v->iotlb;int r =0 ; +if (asid !=0 ) +return -EINVAL ; + r =vhost_dev_check_owner (dev);if (r)return r;drivers/vhost/vhost.c +5
-2@@ -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;@@ -1084,11 +1084,14 @@ 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,u16 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) {
drivers/vhost/vhost.c ssize_t vhost_chr_write_iter(struct vhost_dev *dev, · line 1141
Quoted 4 lines
drivers/vhost/vhost.c +1
-0@@ -1135,6 +1138,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,struct vhost_iotlb_msg msg;size_t offset;int type, ret; +u16 asid =0 ;
You assume asid occupies just 16 bits. So maybe you should reserve the other 16 bits for future extension:
struct vhost_msg_v2 {
__u32 type;
- __u32 reserved;
+ __u16 asid;
+ __u16 reserved;
union {Moreover, maybe this should be reflected in previous patches that use the asid:
-static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb) +static int mlx5_vdpa_set_map(struct vdpa_device *vdev, u16 asid,
+ struct vhost_iotlb *iotlb)
-static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, +static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u16 asid,
struct vhost_iotlb_msg *msg)
etc.
Quoted 80 lines
drivers/vhost/vhost.c +12
-3ret =copy_from_iter (&type,sizeof (type), from);if (ret !=sizeof (type)) {@@ -1150,7 +1154,16 @@ 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 =sizeof (__u16); + }else + offset =sizeof (__u32);break ;default : ret = -EINVAL ;@@ -1165,9 +1178,9 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, }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;drivers/vhost/vhost.h +2
-2@@ -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);include/uapi/linux/vhost_types.h +4
-1@@ -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 ];@@ -157,5 +157,8 @@ struct vhost_vdpa_iova_range {#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#endif Signature · 1 line
2.25.1
Re: [PATCH 10/21] vhost: support ASID in IOTLB API
Quoted 38 lines · Eli Cohen
Quoted 13 lines
drivers/vhost/vhost.c +4
-1-static int vhost_process_iotlb_msg (struct vhost_dev *dev, +static int vhost_process_iotlb_msg (struct vhost_dev *dev,u16 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) {drivers/vhost/vhost.c ssize_t vhost_chr_write_iter(struct vhost_dev *dev, · line 1141
Quoted 4 lines
drivers/vhost/vhost.c +1
-0@@ -1135,6 +1138,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,struct vhost_iotlb_msg msg;size_t offset;int type, ret; +u16 asid =0 ;You assume asid occupies just 16 bits. So maybe you should reserve the other 16 bits for future extension:
struct vhost_msg_v2 { __u32 type;include/uapi/linux/vhost_types.h +2
-1-__u32 reserved; +__u16 asid; +__u16 reserved;union {Moreover, maybe this should be reflected in previous patches that use the asid:
(quoted diff) +3
-2-static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb) +static int mlx5_vdpa_set_map(struct vdpa_device *vdev, u16 asid, + struct vhost_iotlb *iotlb) -static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, +static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u16 asid, struct vhost_iotlb_msg *msg)
Quoted 1 line
etc.
Good catch.
This is a bug of the code actually. Since I want to stick to 32bit to be large enough for e.g PASID.
Will fix.
Thanks
Quoted 1 line
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 11/21 vhost-vdpa: introduce asid based IOTLB
In reply to Jason WangThis patch converts the vhost-vDPA device to support multiple IOTLBs tagged via ASID via hlist. This will be used for supporting multiple address spaces in the following patches.
--- drivers/vhost/vdpa.c | 106 ++++++++++++++++++++++++++++++++----------- 1 file changed, 80 insertions(+), 26 deletions(-)
drivers/vhost/vdpa.c +80 -26
@@ -33,13 +33,21 @@ enum {#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 vhost_iotlb *iotlb; +struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS ];struct device dev;struct cdev cdev;atomic_t opened;
@@ -49,12 +57,64 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; +int used_as; };static DEFINE_IDA (vhost_vdpa_ida);static dev_t vhost_vdpa_major; +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_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 ; + + 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); + ++v->used_as; + +return as; +} + +static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) +{ +struct vhost_vdpa_as *as =asid_to_as (v, asid); + +/* Remove default address space is not allowed */ +if (asid ==0 ) +return -EINVAL ; + +if (!as) +return -EINVAL ; + +hlist_del (&as->hash_link); +vhost_iotlb_reset (&as->iotlb); +kfree (as); + --v->used_as; + +return 0 ; +} +static void handle_vq_kick (struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
@@ -525,15 +585,6 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, } } -static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) -{ -struct vhost_iotlb *iotlb = v->iotlb; - -vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 ); -kfree (v->iotlb); - v->iotlb =NULL ; -} -static int perm_to_iommu_flags (u32 perm) {int flags =0 ;
@@ -745,7 +796,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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 = v->iotlb; +struct vhost_vdpa_as *as =asid_to_as (v,0 ); +struct vhost_iotlb *iotlb = &as->iotlb;int r =0 ;if (asid !=0 )
@@ -856,6 +908,13 @@ static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v) } } +static void vhost_vdpa_cleanup (struct vhost_vdpa *v) +{ +vhost_dev_cleanup (&v->vdev); +kfree (v->vdev.vqs); +vhost_vdpa_remove_as (v,0 ); +} +static int vhost_vdpa_open (struct inode *inode,struct file *filep) {struct vhost_vdpa *v;
@@ -886,15 +945,12 @@ 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); - v->iotlb =vhost_iotlb_alloc (0 ,0 ); -if (!v->iotlb) { - r = -ENOMEM ; - goto err_init_iotlb; - } +if (!vhost_vdpa_alloc_as (v,0 )) + goto err_alloc_as; r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_domain; + goto err_alloc_as;vhost_vdpa_set_iova_range (v);
@@ -902,11 +958,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_domain: -vhost_vdpa_iotlb_free (v); -err_init_iotlb: -vhost_dev_cleanup (&v->vdev); -kfree (vqs); +err_alloc_as: +vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);return r;
@@ -933,12 +986,10 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) filep->private_data =NULL ;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);
@@ -1033,7 +1084,7 @@ 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;/* Only support 1 address space and 1 groups */ if (vdpa->ngroups !=1 || vdpa->nas !=1 )
@@ -1085,6 +1136,9 @@ 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:
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 11/21] vhost-vdpa: introduce asid based IOTLB
Quoted 37 lines · Jason Wang
This patch converts the vhost-vDPA device to support multiple IOTLBs tagged via ASID via hlist. This will be used for supporting multiple address spaces in the following patches.
Signed-off-by Jason Wang <[email protected]>--- drivers/vhost/vdpa.c | 106 ++++++++++++++++++++++++++++++++----------- 1 file changed, 80 insertions(+), 26 deletions(-)drivers/vhost/vdpa.c +9
-1@@ -33,13 +33,21 @@ enum {#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 vhost_iotlb *iotlb; +struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS ];struct device dev;struct cdev cdev;atomic_t opened;
drivers/vhost/vdpa.c struct vhost_vdpa { · line 60
Quoted 4 lines
drivers/vhost/vdpa.c +1
-0@@ -49,12 +57,64 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; +int used_as;
This is not really used. Not in this patch and later removed.
Quoted 169 lines
drivers/vhost/vdpa.c +70
-25};static DEFINE_IDA (vhost_vdpa_ida);static dev_t vhost_vdpa_major; +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_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 ; + + 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); + ++v->used_as; + +return as; +} + +static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) +{ +struct vhost_vdpa_as *as =asid_to_as (v, asid); + +/* Remove default address space is not allowed */ +if (asid ==0 ) +return -EINVAL ; + +if (!as) +return -EINVAL ; + +hlist_del (&as->hash_link); +vhost_iotlb_reset (&as->iotlb); +kfree (as); + --v->used_as; + +return 0 ; +} +static void handle_vq_kick (struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,@@ -525,15 +585,6 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, } } -static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) -{ -struct vhost_iotlb *iotlb = v->iotlb; - -vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 ); -kfree (v->iotlb); - v->iotlb =NULL ; -} -static int perm_to_iommu_flags (u32 perm) {int flags =0 ;@@ -745,7 +796,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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 = v->iotlb; +struct vhost_vdpa_as *as =asid_to_as (v,0 ); +struct vhost_iotlb *iotlb = &as->iotlb;int r =0 ;if (asid !=0 )@@ -856,6 +908,13 @@ static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v) } } +static void vhost_vdpa_cleanup (struct vhost_vdpa *v) +{ +vhost_dev_cleanup (&v->vdev); +kfree (v->vdev.vqs); +vhost_vdpa_remove_as (v,0 ); +} +static int vhost_vdpa_open (struct inode *inode,struct file *filep) {struct vhost_vdpa *v;@@ -886,15 +945,12 @@ 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); - v->iotlb =vhost_iotlb_alloc (0 ,0 ); -if (!v->iotlb) { - r = -ENOMEM ; - goto err_init_iotlb; - } +if (!vhost_vdpa_alloc_as (v,0 )) + goto err_alloc_as; r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_domain; + goto err_alloc_as;vhost_vdpa_set_iova_range (v);@@ -902,11 +958,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_domain: -vhost_vdpa_iotlb_free (v); -err_init_iotlb: -vhost_dev_cleanup (&v->vdev); -kfree (vqs); +err_alloc_as: +vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);return r;@@ -933,12 +986,10 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) filep->private_data =NULL ;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);@@ -1033,7 +1084,7 @@ 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;/* Only support 1 address space and 1 groups */ if (vdpa->ngroups !=1 || vdpa->nas !=1 )@@ -1085,6 +1136,9 @@ 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:Signature · 1 line
2.25.1
Re: [PATCH 11/21] vhost-vdpa: introduce asid based IOTLB
Quoted 35 lines · Eli Cohen
Quoted 34 lines · Jason Wang
This patch converts the vhost-vDPA device to support multiple IOTLBs tagged via ASID via hlist. This will be used for supporting multiple address spaces in the following patches.
Signed-off-by Jason Wang <[email protected]>--- drivers/vhost/vdpa.c | 106 ++++++++++++++++++++++++++++++++----------- 1 file changed, 80 insertions(+), 26 deletions(-)drivers/vhost/vdpa.c +9
-1@@ -33,13 +33,21 @@ enum {#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 vhost_iotlb *iotlb; +struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS ];struct device dev;
Quoted 8 lines
drivers/vhost/vdpa.c struct vhost_vdpa { · line 60
Quoted 7 lines
drivers/vhost/vdpa.c +1
-0struct cdev cdev;atomic_t opened;@@ -49,12 +57,64 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; +int used_as;This is not really used. Not in this patch and later removed.
Right, will remove this.
Thanks
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 11/21] vhost-vdpa: introduce asid based IOTLB
In reply to Jason WangQuoted 58 lines · Jason Wang
This patch converts the vhost-vDPA device to support multiple IOTLBs tagged via ASID via hlist. This will be used for supporting multiple address spaces in the following patches.
Signed-off-by Jason Wang <[email protected]>--- drivers/vhost/vdpa.c | 106 ++++++++++++++++++++++++++++++++----------- 1 file changed, 80 insertions(+), 26 deletions(-)drivers/vhost/vdpa.c +21
-1@@ -33,13 +33,21 @@ enum {#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 vhost_iotlb *iotlb; +struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS ];struct device dev;struct cdev cdev;atomic_t opened;@@ -49,12 +57,64 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; +int used_as; };static DEFINE_IDA (vhost_vdpa_ida);static dev_t vhost_vdpa_major; +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 ; +}
drivers/vhost/vdpa.c struct vhost_vdpa { · line 87
Quoted 10 lines
drivers/vhost/vdpa.c +10
-0+ +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 ; + + as =kmalloc (sizeof (*as),GFP_KERNEL );
kzalloc()? See comment below.
drivers/vhost/vdpa.c struct vhost_vdpa { · line 94
Quoted 7 lines
drivers/vhost/vdpa.c +7
-0+if (!as) +return NULL ; + +vhost_iotlb_init (&as->iotlb,0 ,0 ); + as->id = asid; +hlist_add_head (&as->hash_link, head); + ++v->used_as;
Although you eventually ended up removing used_as, this is a bug since you're incrementing a random value. Maybe it's better to be on the safe side and use kzalloc() for as above.
Quoted 135 lines
drivers/vhost/vdpa.c +42
-25+ +return as; +} + +static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) +{ +struct vhost_vdpa_as *as =asid_to_as (v, asid); + +/* Remove default address space is not allowed */ +if (asid ==0 ) +return -EINVAL ; + +if (!as) +return -EINVAL ; + +hlist_del (&as->hash_link); +vhost_iotlb_reset (&as->iotlb); +kfree (as); + --v->used_as; + +return 0 ; +} +static void handle_vq_kick (struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,@@ -525,15 +585,6 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, } } -static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) -{ -struct vhost_iotlb *iotlb = v->iotlb; - -vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 ); -kfree (v->iotlb); - v->iotlb =NULL ; -} -static int perm_to_iommu_flags (u32 perm) {int flags =0 ;@@ -745,7 +796,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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 = v->iotlb; +struct vhost_vdpa_as *as =asid_to_as (v,0 ); +struct vhost_iotlb *iotlb = &as->iotlb;int r =0 ;if (asid !=0 )@@ -856,6 +908,13 @@ static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v) } } +static void vhost_vdpa_cleanup (struct vhost_vdpa *v) +{ +vhost_dev_cleanup (&v->vdev); +kfree (v->vdev.vqs); +vhost_vdpa_remove_as (v,0 ); +} +static int vhost_vdpa_open (struct inode *inode,struct file *filep) {struct vhost_vdpa *v;@@ -886,15 +945,12 @@ 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); - v->iotlb =vhost_iotlb_alloc (0 ,0 ); -if (!v->iotlb) { - r = -ENOMEM ; - goto err_init_iotlb; - } +if (!vhost_vdpa_alloc_as (v,0 )) + goto err_alloc_as; r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_domain; + goto err_alloc_as;vhost_vdpa_set_iova_range (v);@@ -902,11 +958,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_domain: -vhost_vdpa_iotlb_free (v); -err_init_iotlb: -vhost_dev_cleanup (&v->vdev); -kfree (vqs); +err_alloc_as: +vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);return r;@@ -933,12 +986,10 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) filep->private_data =NULL ;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);@@ -1033,7 +1084,7 @@ 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;/* Only support 1 address space and 1 groups */ if (vdpa->ngroups !=1 || vdpa->nas !=1 )@@ -1085,6 +1136,9 @@ 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:Signature · 1 line
2.25.1
Re: [PATCH 11/21] vhost-vdpa: introduce asid based IOTLB
Quoted 12 lines · Eli Cohen
drivers/vhost/vdpa.c struct vhost_vdpa { · line 87
Quoted 10 lines
drivers/vhost/vdpa.c +10
-0+ +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 ; + + as =kmalloc (sizeof (*as),GFP_KERNEL );
kzalloc()? See comment below.
Quoted 10 lines
drivers/vhost/vdpa.c struct vhost_vdpa { · line 94
Quoted 7 lines
drivers/vhost/vdpa.c +7
-0+if (!as) +return NULL ; + +vhost_iotlb_init (&as->iotlb,0 ,0 ); + as->id = asid; +hlist_add_head (&as->hash_link, head); + ++v->used_as;Although you eventually ended up removing
used_as, this is a bug since you're incrementing a random value. Maybe it's better to be on the safe side and usekzalloc()for as above.
Yes and used_as needs to be removed.
Thanks
Quoted 1 line
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 11/21] vhost-vdpa: introduce asid based IOTLB
In reply to Jason WangQuoted 70 lines · Jason Wang
This patch converts the vhost-vDPA device to support multiple IOTLBs tagged via ASID via hlist. This will be used for supporting multiple address spaces in the following patches.
Signed-off-by Jason Wang <[email protected]>--- drivers/vhost/vdpa.c | 106 ++++++++++++++++++++++++++++++++----------- 1 file changed, 80 insertions(+), 26 deletions(-)drivers/vhost/vdpa.c +33
-1@@ -33,13 +33,21 @@ enum {#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 vhost_iotlb *iotlb; +struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS ];struct device dev;struct cdev cdev;atomic_t opened;@@ -49,12 +57,64 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; +int used_as; };static DEFINE_IDA (vhost_vdpa_ida);static dev_t vhost_vdpa_major; +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_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 ; + + as =kmalloc (sizeof (*as),GFP_KERNEL ); +if (!as) +return NULL ;
drivers/vhost/vdpa.c struct vhost_vdpa { · line 99
Quoted 10 lines
drivers/vhost/vdpa.c +10
-0+ +vhost_iotlb_init (&as->iotlb,0 ,0 ); + as->id = asid; +hlist_add_head (&as->hash_link, head); + ++v->used_as; + +return as; +} + +static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid)
The return value is never interpreted. I think it should either be made void or return values checked.
drivers/vhost/vdpa.c struct vhost_vdpa { · line 105
Quoted 6 lines
drivers/vhost/vdpa.c +6
-0+{ +struct vhost_vdpa_as *as =asid_to_as (v, asid); + +/* Remove default address space is not allowed */ +if (asid ==0 ) +return -EINVAL ;
Can you explain why? I think you have a memory leak due to this as no one will ever free as with id 0.
Quoted 124 lines
drivers/vhost/vdpa.c +31
-25+ +if (!as) +return -EINVAL ; + +hlist_del (&as->hash_link); +vhost_iotlb_reset (&as->iotlb); +kfree (as); + --v->used_as; + +return 0 ; +} +static void handle_vq_kick (struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,@@ -525,15 +585,6 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, } } -static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) -{ -struct vhost_iotlb *iotlb = v->iotlb; - -vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 ); -kfree (v->iotlb); - v->iotlb =NULL ; -} -static int perm_to_iommu_flags (u32 perm) {int flags =0 ;@@ -745,7 +796,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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 = v->iotlb; +struct vhost_vdpa_as *as =asid_to_as (v,0 ); +struct vhost_iotlb *iotlb = &as->iotlb;int r =0 ;if (asid !=0 )@@ -856,6 +908,13 @@ static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v) } } +static void vhost_vdpa_cleanup (struct vhost_vdpa *v) +{ +vhost_dev_cleanup (&v->vdev); +kfree (v->vdev.vqs); +vhost_vdpa_remove_as (v,0 ); +} +static int vhost_vdpa_open (struct inode *inode,struct file *filep) {struct vhost_vdpa *v;@@ -886,15 +945,12 @@ 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); - v->iotlb =vhost_iotlb_alloc (0 ,0 ); -if (!v->iotlb) { - r = -ENOMEM ; - goto err_init_iotlb; - } +if (!vhost_vdpa_alloc_as (v,0 )) + goto err_alloc_as; r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_domain; + goto err_alloc_as;vhost_vdpa_set_iova_range (v);@@ -902,11 +958,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_domain: -vhost_vdpa_iotlb_free (v); -err_init_iotlb: -vhost_dev_cleanup (&v->vdev); -kfree (vqs); +err_alloc_as: +vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);return r;@@ -933,12 +986,10 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) filep->private_data =NULL ;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);@@ -1033,7 +1084,7 @@ 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;/* Only support 1 address space and 1 groups */ if (vdpa->ngroups !=1 || vdpa->nas !=1 )@@ -1085,6 +1136,9 @@ 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:Signature · 1 line
2.25.1
Re: [PATCH 11/21] vhost-vdpa: introduce asid based IOTLB
Quoted 4 lines · Eli Cohen
Review
Quoted 2 lines
(quoted diff) +2
-0+ +static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)The return value is never interpreted. I think it should either be made void or return values checked.
Right, will make it void.
Quoted 10 lines
drivers/vhost/vdpa.c struct vhost_vdpa { · line 105
Quoted 7 lines
drivers/vhost/vdpa.c +6
-0+{ +struct vhost_vdpa_as *as =asid_to_as (v, asid); + +/* Remove default address space is not allowed */ +if (asid ==0 ) +return -EINVAL ;Can you explain why? I think you have a memory leak due to this as no one will ever free as with id 0.
Looks like a bug. Will remove this.
Thanks
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 12/21 vhost-vdpa: introduce uAPI to get the number of virtqueue groups
In reply to Jason WangFollows the vDPA support for multiple address spaces, this patch introduce uAPI for the userspace to know the number of virtqueue groups supported by the vDPA device.
--- drivers/vhost/vdpa.c | 4 ++++ include/uapi/linux/vhost.h | 3 +++ 2 files changed, 7 insertions(+)
drivers/vhost/vdpa.c +4 -0
@@ -536,6 +536,10 @@ 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 : + r =copy_to_user (argp, &v->vdpa->ngroups, +sizeof (v->vdpa->ngroups)); +break ;case VHOST_SET_LOG_BASE :case VHOST_SET_LOG_FD : r = -ENOIOCTLCMD ;
include/uapi/linux/vhost.h +3 -0
@@ -145,4 +145,7 @@/* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x79, unsigned int) +#endif
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 12/21] vhost-vdpa: introduce uAPI to get the number of virtqueue groups
Quoted 3 lines · Jason Wang
Follows the vDPA support for multiple address spaces, this patch introduce uAPI for the userspace to know the number of virtqueue groups supported by the vDPA device.
Can you explain what exactly you mean be userspace? Is it just qemu or is it destined to the virtio_net driver run by the qemu process? Also can you say for what purpose?
Quoted 37 lines
Signed-off-by Jason Wang <[email protected]>--- drivers/vhost/vdpa.c | 4 ++++ include/uapi/linux/vhost.h | 3 +++ 2 files changed, 7 insertions(+)drivers/vhost/vdpa.c +4
-0@@ -536,6 +536,10 @@ 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 : + r =copy_to_user (argp, &v->vdpa->ngroups, +sizeof (v->vdpa->ngroups)); +break ;case VHOST_SET_LOG_BASE :case VHOST_SET_LOG_FD : r = -ENOIOCTLCMD ;include/uapi/linux/vhost.h +3
-0@@ -145,4 +145,7 @@/* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x79, unsigned int) +#endif Signature · 1 line
2.25.1
Re: [PATCH 12/21] vhost-vdpa: introduce uAPI to get the number of virtqueue groups
Quoted 5 lines · Eli Cohen
Quoted 3 lines · Jason Wang
Follows the vDPA support for multiple address spaces, this patch introduce uAPI for the userspace to know the number of virtqueue groups supported by the vDPA device.
Can you explain what exactly you mean be userspace?
It's the userspace that uses the uAPI introduced in this patch.
Quoted 2 lines
Is it just qemu or
is it destined to thevirtio_netdriver run by the qemu process?
It could be Qemu, DPDK or other userspace program.
The guest virtio-net driver will not use this but talks to the virtio device emulated by Qemu.
Quoted 1 line
Also can you say for what purpose?
This can be used for facilitate the checking of whether the control vq could be supported.
E.g if the device support less than 2 groups, qemu won't advertise control vq.
Yes, #groups could be inferred from GET_VRING_GROUP. But it's not straightforward as this.
Thanks
Quoted 29 lines
Quoted 29 lines
Signed-off-by Jason Wang <[email protected]>--- drivers/vhost/vdpa.c | 4 ++++ include/uapi/linux/vhost.h | 3 +++ 2 files changed, 7 insertions(+)drivers/vhost/vdpa.c +4
-0@@ -536,6 +536,10 @@ 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 : + r =copy_to_user (argp, &v->vdpa->ngroups, +sizeof (v->vdpa->ngroups)); +break ;case VHOST_SET_LOG_BASE :case VHOST_SET_LOG_FD : r = -ENOIOCTLCMD ;include/uapi/linux/vhost.h +0
-0@@ -145,4 +145,7 @@/* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \
Quoted 8 lines
Quoted 8 lines
include/uapi/linux/vhost.h +3
-0struct vhost_vdpa_iova_range) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x79, unsigned int) +#endif Signature · 1 line
2.25.1
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 12/21] vhost-vdpa: introduce uAPI to get the number of virtqueue groups
In reply to Jason WangQuoted 15 lines · Jason Wang
Follows the vDPA support for multiple address spaces, this patch introduce uAPI for the userspace to know the number of virtqueue groups supported by the vDPA device.
Signed-off-by Jason Wang <[email protected]>--- drivers/vhost/vdpa.c | 4 ++++ include/uapi/linux/vhost.h | 3 +++ 2 files changed, 7 insertions(+)drivers/vhost/vdpa.c +0
-0
drivers/vhost/vdpa.c static long vhost_vdpa_unlocked_ioctl(struct file *filep, · line 542
Quoted 7 lines
drivers/vhost/vdpa.c +4
-0@@ -536,6 +536,10 @@ 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 : + r =copy_to_user (argp, &v->vdpa->ngroups, +sizeof (v->vdpa->ngroups)); +break ;
Is this and other ioctls already supported in qemu?
Quoted 18 lines
drivers/vhost/vdpa.c +0
-0case VHOST_SET_LOG_BASE :case VHOST_SET_LOG_FD : r = -ENOIOCTLCMD ;include/uapi/linux/vhost.h +3
-0@@ -145,4 +145,7 @@/* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x79, unsigned int) +#endif Signature · 1 line
2.25.1
Re: [PATCH 12/21] vhost-vdpa: introduce uAPI to get the number of virtqueue groups
Quoted 11 lines · Eli Cohen
Quoted 10 lines · Jason Wang
Follows the vDPA support for multiple address spaces, this patch introduce uAPI for the userspace to know the number of virtqueue groups supported by the vDPA device.
Signed-off-by Jason Wang<[email protected]>--- drivers/vhost/vdpa.c | 4 ++++ include/uapi/linux/vhost.h | 3 +++ 2 files changed, 7 insertions(+)
Quoted 13 lines
drivers/vhost/vdpa.c static long vhost_vdpa_unlocked_ioctl(struct file *filep, · line 542
Quoted 12 lines
drivers/vhost/vdpa.c +4
-0@@ -536,6 +536,10 @@ 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 : + r =copy_to_user (argp, &v->vdpa->ngroups, +sizeof (v->vdpa->ngroups)); +break ;Is this and other ioctls already supported in qemu?
Not yet, the prototype is under development.
I test the series with a small and dedicated userspace program.
Thanks
Quoted 1 line
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 13/21 vhost-vdpa: introduce uAPI to get the number of address spaces
In reply to Jason WangThis patch introduces the uAPI for getting the number of address spaces supported by this vDPA device.
--- drivers/vhost/vdpa.c | 3 +++ include/uapi/linux/vhost.h | 2 ++ 2 files changed, 5 insertions(+)
drivers/vhost/vdpa.c +3 -0
@@ -540,6 +540,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, r =copy_to_user (argp, &v->vdpa->ngroups,sizeof (v->vdpa->ngroups));break ; +case VHOST_VDPA_GET_AS_NUM : + r =copy_to_user (argp, &v->vdpa->nas,sizeof (v->vdpa->nas)); +break ;case VHOST_SET_LOG_BASE :case VHOST_SET_LOG_FD : r = -ENOIOCTLCMD ;
include/uapi/linux/vhost.h +2 -0
@@ -148,4 +148,6 @@/* Get the number of virtqueue groups. */ #define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x79, unsigned int) +/* Get the number of address spaces. */ +#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int)#endif
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 14/21 vhost-vdpa: uAPI to get virtqueue group id
In reply to Jason WangFollows the support for virtqueue group in vDPA. This patches introduces uAPI to get the virtqueue group ID for a specific virtqueue in vhost-vdpa.
--- drivers/vhost/vdpa.c | 8 ++++++++ include/uapi/linux/vhost.h | 8 ++++++++ 2 files changed, 16 insertions(+)
drivers/vhost/vdpa.c +8 -0
@@ -442,6 +442,14 @@ 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 : + 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_GET_VRING_BASE : r = ops->get_vq_state (v->vdpa, idx, &vq_state);if (r)
include/uapi/linux/vhost.h +8 -0
@@ -150,4 +150,12 @@/* 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)#endif
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 15/21 vhost-vdpa: introduce uAPI to set group ASID
In reply to Jason WangFollows the vDPA support for associating ASID to a specific virtqueue group. This patch adds a uAPI to support setting them from userspace.
--- drivers/vhost/vdpa.c | 8 ++++++++ include/uapi/linux/vhost.h | 7 +++++++ 2 files changed, 15 insertions(+)
drivers/vhost/vdpa.c +8 -0
@@ -450,6 +450,14 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,else if (copy_to_user (argp, &s,sizeof s))return -EFAULT ;return 0 ; +case VHOST_VDPA_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 -ENOTSUPP ; +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)
include/uapi/linux/vhost.h +7 -0
@@ -158,4 +158,11 @@*/ #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) +#endif
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 16/21 vhost-vdpa: support ASID based IOTLB API
In reply to Jason WangThis patch extends the vhost-vdpa to support ASID based IOTLB API. The vhost-vdpa device will allocated multple IOTLBs for vDPA device that supports multiple address spaces. The IOTLBs and vDPA device memory mappings is determined and maintained through ASID.
Note that we still don't support vDPA device with more than one address spaces that depends on platform IOMMU. This work will be done by moving the IOMMU logic from vhost-vDPA to vDPA device driver.
--- drivers/vhost/vdpa.c | 127 ++++++++++++++++++++++++++++++++---------- drivers/vhost/vhost.c | 4 +- 2 files changed, 99 insertions(+), 32 deletions(-)
drivers/vhost/vdpa.c +97 -30
@@ -28,7 +28,8 @@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)
@@ -57,13 +58,20 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; -int used_as; +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 ];
@@ -76,6 +84,16 @@ static struct vhost_vdpa_as *asid_to_as(struct vhost_vdpa *v, u32 asid)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 ];
@@ -84,6 +102,9 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid)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 ;
@@ -91,18 +112,24 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid)vhost_iotlb_init (&as->iotlb,0 ,0 ); as->id = asid;hlist_add_head (&as->hash_link, head); - ++v->used_as;return as; } -static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) +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); -/* Remove default address space is not allowed */ -if (asid ==0 ) -return -EINVAL ; +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 ;
@@ -110,7 +137,6 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)hlist_del (&as->hash_link);vhost_iotlb_reset (&as->iotlb);kfree (as); - --v->used_as;return 0 ; }
@@ -636,6 +662,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,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(iotlb, iova, iova + size - 1,
@@ -644,10 +671,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r;if (ops->dma_map) { - r = ops->dma_map (vdpa,0 , iova, size, pa, perm); + r = ops->dma_map (vdpa, asid, iova, size, pa, perm); }else if (ops->set_map) {if (!v->in_batch) - r = ops->set_map (vdpa,0 , iotlb); + r = ops->set_map (vdpa, asid, iotlb); }else { r =iommu_map (v->domain, iova, pa, size,perm_to_iommu_flags (perm));
@@ -661,23 +688,35 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r; } -static void vhost_vdpa_unmap (struct vhost_vdpa *v, -struct vhost_iotlb *iotlb, -u64 iova,u64 size) +static int vhost_vdpa_unmap (struct vhost_vdpa *v, +struct vhost_iotlb *iotlb, +u64 iova,u64 size) {struct vdpa_device *vdpa = v->vdpa;const struct vdpa_config_ops *ops = vdpa->config; +u32 asid =iotlb_to_asid (iotlb); + +if (!iotlb) +return -EINVAL ;vhost_vdpa_iotlb_unmap (v, iotlb, iova, iova + size -1 );if (ops->dma_map) { - ops->dma_unmap (vdpa,0 , iova, size); + ops->dma_unmap (vdpa, asid, iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa,0 , 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); + +return 0 ; } static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
@@ -819,31 +858,52 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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_vdpa_as *as =asid_to_as (v,0 ); -struct vhost_iotlb *iotlb = &as->iotlb; +struct vhost_iotlb *iotlb =NULL ; +struct vhost_vdpa_as *as =NULL ;int r =0 ; -if (asid !=0 ) -return -EINVAL ; - r =vhost_dev_check_owner (dev);if (r)return r; +if (msg->type ==VHOST_IOTLB_UPDATE || + msg->type ==VHOST_IOTLB_BATCH_BEGIN ) { + as =vhost_vdpa_find_alloc_as (v, asid); +if (!as) { +printk ("can't find and alloc asid %d\n" , asid); +return -EINVAL ; + } + 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) { +printk ("batch id %d asid %d\n" , + v->batch_asid, asid); + } +if (!iotlb) +printk ("no iotlb for asid %d\n" , asid); +return -EINVAL ; + } +switch (msg->type) {case VHOST_IOTLB_UPDATE : r =vhost_vdpa_process_iotlb_update (v, iotlb, msg);break ;case VHOST_IOTLB_INVALIDATE : -vhost_vdpa_unmap (v, iotlb, msg->iova, msg->size); + r =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,0 , iotlb); + ops->set_map (vdpa, asid, iotlb); v->in_batch = false; +if (!iotlb->nmaps) +vhost_vdpa_remove_as (v, asid);break ;default : r = -EINVAL ;
@@ -933,9 +993,17 @@ 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); -vhost_vdpa_remove_as (v,0 ); + +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)
@@ -968,12 +1036,9 @@ 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); -if (!vhost_vdpa_alloc_as (v,0 )) - goto err_alloc_as; - r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_as; + goto err_alloc_domain;vhost_vdpa_set_iova_range (v);
@@ -981,7 +1046,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_as: +err_alloc_domain:vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);
@@ -1109,8 +1174,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int i, r; -/* Only support 1 address space and 1 groups */ -if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +/* 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 -ENOTSUPP ;/* Currently, we only accept the network devices. */
drivers/vhost/vhost.c +2 -2
@@ -1138,7 +1138,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,struct vhost_iotlb_msg msg;size_t offset;int type, ret; -u16 asid =0 ; +u32 asid =0 ; ret =copy_from_iter (&type,sizeof (type), from);if (ret !=sizeof (type)) {
@@ -1161,7 +1161,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, ret = -EINVAL ; goto done; } - offset =sizeof (__u16); + offset =0 ; }else offset =sizeof (__u32);break ;
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 17/21 vdpa_sim: split vdpasim_virtqueue's iov field in out_iov and in_iov
In reply to Jason WangFrom: Stefano Garzarella <[email protected]>
vringh_getdesc_iotlb() manages 2 iovs for writable and readable descriptors. This is very useful for the block device, where for each request we have both types of descriptor.
Let's split the vdpasim_virtqueue's iov field in out_iov and in_iov to use them with vringh_getdesc_iotlb().
We are using VIRTIO terminology for "out" (readable by the device) and "in" (writable by the device) descriptors.
--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)
drivers/vdpa/vdpa_sim/vdpa_sim.c +6 -5
@@ -44,7 +44,8 @@ MODULE_PARM_DESC(macaddr, "Ethernet MAC address");struct vdpasim_virtqueue {struct vringh vring; -struct vringh_kiov iov; +struct vringh_kiov in_iov; +struct vringh_kiov out_iov;unsigned short head;bool ready;u64 desc_addr;
@@ -178,12 +179,12 @@ static void vdpasim_work(struct work_struct *work)while (true) { total_write =0 ; - err =vringh_getdesc_iotlb (&txq->vring, &txq->iov,NULL , + err =vringh_getdesc_iotlb (&txq->vring, &txq->out_iov,NULL , &txq->head,GFP_ATOMIC );if (err <=0 )break ; - err =vringh_getdesc_iotlb (&rxq->vring,NULL , &rxq->iov, + err =vringh_getdesc_iotlb (&rxq->vring,NULL , &rxq->in_iov, &rxq->head,GFP_ATOMIC );if (err <=0 ) {vringh_complete_iotlb (&txq->vring, txq->head,0 );
@@ -191,13 +192,13 @@ static void vdpasim_work(struct work_struct *work) }while (true) { - read =vringh_iov_pull_iotlb (&txq->vring, &txq->iov, + read =vringh_iov_pull_iotlb (&txq->vring, &txq->out_iov, vdpasim->buffer,PAGE_SIZE );if (read <=0 )break ; - write =vringh_iov_push_iotlb (&rxq->vring, &rxq->iov, + write =vringh_iov_push_iotlb (&rxq->vring, &rxq->in_iov, vdpasim->buffer, read);if (write <=0 )break ;
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 18/21 vdpa_sim: advertise VIRTIO_NET_F_MTU
In reply to Jason WangWe've already reported maximum mtu via config space, so let's advertise the feature.
--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/vdpa/vdpa_sim/vdpa_sim.c +2 -1
@@ -66,7 +66,8 @@ struct vdpasim_virtqueue {static u64 vdpasim_features = (1ULL <<VIRTIO_F_ANY_LAYOUT ) | (1ULL <<VIRTIO_F_VERSION_1 ) | (1ULL <<VIRTIO_F_ACCESS_PLATFORM ) | - (1ULL <<VIRTIO_NET_F_MAC ); + (1ULL <<VIRTIO_NET_F_MAC ) | + (1ULL <<VIRTIO_NET_F_MTU );/* State of each vdpasim device */ struct vdpasim {
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 19/21 vdpa_sim: factor out buffer completion logic
In reply to Jason Wang--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 33 +++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-)
drivers/vdpa/vdpa_sim/vdpa_sim.c +18 -15
@@ -159,6 +159,22 @@ static void vdpasim_reset(struct vdpasim *vdpasim) ++vdpasim->generation; } +static void vdpasim_complete (struct vdpasim_virtqueue *vq,size_t len) +{ +/* Make sure data is wrote before advancing index */ +smp_wmb (); + +vringh_complete_iotlb (&vq->vring, vq->head, len); + +/* Make sure used is visible before rasing the interrupt. */ +smp_wmb (); + +local_bh_disable (); +if (vq->cb) + vq->cb (vq->private); +local_bh_enable (); +} +static void vdpasim_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct
@@ -207,21 +223,8 @@ static void vdpasim_work(struct work_struct *work) total_write += write; } -/* Make sure data is wrote before advancing index */ -smp_wmb (); - -vringh_complete_iotlb (&txq->vring, txq->head,0 ); -vringh_complete_iotlb (&rxq->vring, rxq->head, total_write); - -/* Make sure used is visible before rasing the interrupt. */ -smp_wmb (); - -local_bh_disable (); -if (txq->cb) - txq->cb (txq->private); -if (rxq->cb) - rxq->cb (rxq->private); -local_bh_enable (); +vdpasim_complete (txq,0 ); +vdpasim_complete (rxq, total_write);if (++pkts >4 ) {schedule_work (&vdpasim->work);
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 20/21 vdpa_sim: filter destination mac address
In reply to Jason WangThis patch implements a simple unicast filter for vDPA simulator.
--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 49 ++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 18 deletions(-)
drivers/vdpa/vdpa_sim/vdpa_sim.c +31 -18
@@ -175,6 +175,22 @@ static void vdpasim_complete(struct vdpasim_virtqueue *vq, size_t len)local_bh_enable (); } +static bool receive_filter (struct vdpasim *vdpasim,size_t len) +{ +bool modern = vdpasim->features & (1ULL <<VIRTIO_F_VERSION_1 ); +size_t hdr_len = modern ?sizeof (struct virtio_net_hdr_v1 ) : +sizeof (struct virtio_net_hdr ); + +if (len <ETH_ALEN + hdr_len) +return false; + +if (!strncmp (vdpasim->buffer + hdr_len, + vdpasim->config.mac,ETH_ALEN )) +return true; + +return false; +} +static void vdpasim_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct
@@ -182,7 +198,6 @@ static void vdpasim_work(struct work_struct *work)struct vdpasim_virtqueue *txq = &vdpasim->vqs[1 ];struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0 ];ssize_t read, write; -size_t total_write;int pkts =0 ;int err;
@@ -195,36 +210,34 @@ static void vdpasim_work(struct work_struct *work) goto out;while (true) { - total_write =0 ; err =vringh_getdesc_iotlb (&txq->vring, &txq->out_iov,NULL , &txq->head,GFP_ATOMIC );if (err <=0 )break ; + read =vringh_iov_pull_iotlb (&txq->vring, &txq->out_iov, + vdpasim->buffer, +PAGE_SIZE ); + +if (!receive_filter (vdpasim, read)) { +vdpasim_complete (txq,0 ); +continue ; + } + err =vringh_getdesc_iotlb (&rxq->vring,NULL , &rxq->in_iov, &rxq->head,GFP_ATOMIC );if (err <=0 ) { -vringh_complete_iotlb (&txq->vring, txq->head,0 ); +vdpasim_complete (txq,0 );break ; } -while (true) { - read =vringh_iov_pull_iotlb (&txq->vring, &txq->out_iov, - vdpasim->buffer, -PAGE_SIZE ); -if (read <=0 ) -break ; - - write =vringh_iov_push_iotlb (&rxq->vring, &rxq->in_iov, - vdpasim->buffer, read); -if (write <=0 ) -break ; - - total_write += write; - } + write =vringh_iov_push_iotlb (&rxq->vring, &rxq->in_iov, + vdpasim->buffer, read); +if (write <=0 ) +break ;vdpasim_complete (txq,0 ); -vdpasim_complete (rxq, total_write); +vdpasim_complete (rxq, write);if (++pkts >4 ) {schedule_work (&vdpasim->work);
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
PATCH 21/21 vdpasim: control virtqueue support
In reply to Jason WangThis patch introduces the control virtqueue support for vDPA simulator. This is a requirement for supporting advanced features like multiqueue.
A requirement for control virtqueue is to isolate its memory access from the rx/tx virtqueues. This is because when using vDPA device for VM, the control virqueue is not directly assigned to VM. Userspace (Qemu) will present a shadow control virtqueue to control for recording the device states.
The isolation is done via the virtqueue groups and ASID support in vDPA through vhost-vdpa. The simulator is extended to have:
1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue)
2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 contains CVQ
3) two address spaces and the simulator simply implements the address spaces by mapping it 1:1 to IOTLB.
For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 to group 1. So we have:
1) The IOTLB for virtqueue group 0 contains the mappings of guest, so RX and TX can be assigned to guest directly.
2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which is the buffers that allocated and managed by VMM only. So CVQ of vhost-vdpa is visible to VMM only. And Guest can not access the CVQ of vhost-vdpa.
For the other use cases, since AS 0 is associated to all virtqueue groups by default. All virtqueues share the same mapping by default.
To demonstrate the function, VIRITO_NET_F_CTRL_MACADDR is implemented in the simulator for the driver to set mac address.
--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 189 +++++++++++++++++++++++++++---- 1 file changed, 166 insertions(+), 23 deletions(-)
drivers/vdpa/vdpa_sim/vdpa_sim.c +166 -23
@@ -60,14 +60,18 @@ struct vdpasim_virtqueue {#define VDPASIM_QUEUE_MAX 256#define VDPASIM_DEVICE_ID 0x1#define VDPASIM_VENDOR_ID 0 -#define VDPASIM_VQ_NUM 0x2 +#define VDPASIM_VQ_NUM 0x3 +#define VDPASIM_AS_NUM 0x2 +#define VDPASIM_GROUP_NUM 0x2#define VDPASIM_NAME "vdpasim-netdev"static u64 vdpasim_features = (1ULL <<VIRTIO_F_ANY_LAYOUT ) | (1ULL <<VIRTIO_F_VERSION_1 ) | (1ULL <<VIRTIO_F_ACCESS_PLATFORM ) | + (1ULL <<VIRTIO_NET_F_MTU ) | (1ULL <<VIRTIO_NET_F_MAC ) | - (1ULL <<VIRTIO_NET_F_MTU ); + (1ULL <<VIRTIO_NET_F_CTRL_VQ ) | + (1ULL <<VIRTIO_NET_F_CTRL_MAC_ADDR );/* State of each vdpasim device */ struct vdpasim {
@@ -147,11 +151,17 @@ static void vdpasim_reset(struct vdpasim *vdpasim) {int i; -for (i =0 ; i <VDPASIM_VQ_NUM ; i++) +spin_lock (&vdpasim->iommu_lock); + +for (i =0 ; i <VDPASIM_VQ_NUM ; i++) {vdpasim_vq_reset (&vdpasim->vqs[i]); +vringh_set_iotlb (&vdpasim->vqs[i].vring, + &vdpasim->iommu[0 ]); + } -spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu); +for (i =0 ; i <VDPASIM_AS_NUM ; i++) { +vhost_iotlb_reset (&vdpasim->iommu[i]); + }spin_unlock (&vdpasim->iommu_lock); vdpasim->features =0 ;
@@ -191,6 +201,81 @@ static bool receive_filter(struct vdpasim *vdpasim, size_t len)return false; } +virtio_net_ctrl_ack vdpasim_handle_ctrl_mac (struct vdpasim *vdpasim, +u8 cmd) +{ +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +size_t read; + +switch (cmd) { +case VIRTIO_NET_CTRL_MAC_ADDR_SET : + read =vringh_iov_pull_iotlb (&cvq->vring, &cvq->in_iov, + (void *)vdpasim->config.mac, +ETH_ALEN ); +if (read ==ETH_ALEN ) + status =VIRTIO_NET_OK ; +break ; +default : +break ; + } + +return status; +} + +static void vdpasim_handle_cvq (struct vdpasim *vdpasim) +{ +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +struct virtio_net_ctrl_hdr ctrl; +size_t read, write; +int err; + +if (!(vdpasim->features & (1ULL <<VIRTIO_NET_F_CTRL_VQ ))) +return ; + +if (!cvq->ready) +return ; + +while (true) { + err =vringh_getdesc_iotlb (&cvq->vring, &cvq->in_iov, + &cvq->out_iov, + &cvq->head,GFP_ATOMIC ); +if (err <=0 ) +break ; + + read =vringh_iov_pull_iotlb (&cvq->vring, &cvq->in_iov, &ctrl, +sizeof (ctrl)); +if (read !=sizeof (ctrl)) +break ; + +switch (ctrl.class) { +case VIRTIO_NET_CTRL_MAC : + status =vdpasim_handle_ctrl_mac (vdpasim, ctrl.cmd); +break ; +default : +break ; + } + +/* Make sure data is wrote before advancing index */ +smp_wmb (); + + write =vringh_iov_push_iotlb (&cvq->vring, &cvq->out_iov, + &status,sizeof (status)); +vringh_complete_iotlb (&cvq->vring, cvq->head, write); +vringh_kiov_cleanup (&cvq->in_iov); +vringh_kiov_cleanup (&cvq->out_iov); + +/* Make sure used is visible before rasing the interrupt. */ +smp_wmb (); + +local_bh_disable (); +if (cvq->cb) + cvq->cb (cvq->private); +local_bh_enable (); + } +} +static void vdpasim_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct
@@ -276,7 +361,7 @@ static dma_addr_t vdpasim_map_page(struct device *dev, struct page *page, unsigned long attrs) {struct vdpasim *vdpasim =dev_to_sim (dev); -struct vhost_iotlb *iommu = vdpasim->iommu; +struct vhost_iotlb *iommu = &vdpasim->iommu[0 ];u64 pa = (page_to_pfn (page) <<PAGE_SHIFT ) + offset;int ret, perm =dir_to_perm (dir);
@@ -301,7 +386,7 @@ static void vdpasim_unmap_page(struct device *dev, dma_addr_t dma_addr, unsigned long attrs) {struct vdpasim *vdpasim =dev_to_sim (dev); -struct vhost_iotlb *iommu = vdpasim->iommu; +struct vhost_iotlb *iommu = &vdpasim->iommu[0 ];spin_lock (&vdpasim->iommu_lock); vhost_iotlb_del_range(iommu, (u64)dma_addr,
@@ -314,7 +399,7 @@ static void *vdpasim_alloc_coherent(struct device *dev, size_t size, unsigned long attrs) {struct vdpasim *vdpasim =dev_to_sim (dev); -struct vhost_iotlb *iommu = vdpasim->iommu; +struct vhost_iotlb *iommu = &vdpasim->iommu[0 ];void *addr =kmalloc (size, flag);int ret;
@@ -344,7 +429,7 @@ static void vdpasim_free_coherent(struct device *dev, size_t size, unsigned long attrs) {struct vdpasim *vdpasim =dev_to_sim (dev); -struct vhost_iotlb *iommu = vdpasim->iommu; +struct vhost_iotlb *iommu = &vdpasim->iommu[0 ];spin_lock (&vdpasim->iommu_lock); vhost_iotlb_del_range(iommu, (u64)dma_addr,
@@ -370,14 +455,17 @@ static struct vdpasim *vdpasim_create(void)struct vdpasim *vdpasim;struct device *dev;int ret = -ENOMEM ; +int i;if (batch_mapping) ops = &vdpasim_net_batch_config_ops;else ops = &vdpasim_net_config_ops; +/* 3 virtqueues, 2 address spaces, 2 virtqueue groups */ vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, -VDPASIM_VQ_NUM ,1 ,1 ); +VDPASIM_VQ_NUM ,VDPASIM_AS_NUM , +VDPASIM_GROUP_NUM );if (!vdpasim) goto err_alloc;
@@ -391,10 +479,14 @@ static struct vdpasim *vdpasim_create(void) goto err_iommu;set_dma_ops (dev, &vdpasim_dma_ops); - vdpasim->iommu =vhost_iotlb_alloc (2048 ,0 ); + vdpasim->iommu =kmalloc_array (VDPASIM_AS_NUM , +sizeof (*vdpasim->iommu),GFP_KERNEL );if (!vdpasim->iommu) goto err_iommu; +for (i =0 ; i <VDPASIM_AS_NUM ; i++) +vhost_iotlb_init (&vdpasim->iommu[i],0 ,0 ); + vdpasim->buffer =kmalloc (PAGE_SIZE ,GFP_KERNEL );if (!vdpasim->buffer) goto err_iommu;
@@ -409,8 +501,9 @@ static struct vdpasim *vdpasim_create(void)eth_random_addr (vdpasim->config.mac); } -vringh_set_iotlb (&vdpasim->vqs[0 ].vring, vdpasim->iommu); -vringh_set_iotlb (&vdpasim->vqs[1 ].vring, vdpasim->iommu); +/* Make sure that default ASID is zero */ +for (i =0 ; i <VDPASIM_VQ_NUM ; i++) +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ]); vdpasim->vdpa.dma_dev = dev; ret =vdpa_register_device (&vdpasim->vdpa);
@@ -452,7 +545,14 @@ static void vdpasim_kick_vq(struct vdpa_device *vdpa, u16 idx)struct vdpasim *vdpasim =vdpa_to_sim (vdpa);struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; -if (vq->ready) +if (idx ==2 ) { +/* Kernel virtio driver will do busy waiting for the +* result, so we can't handle cvq in the workqueue. +*/ +spin_lock (&vdpasim->lock); +vdpasim_handle_cvq (vdpasim); +spin_unlock (&vdpasim->lock); + }else if (vq->ready)schedule_work (&vdpasim->work); }
@@ -518,7 +618,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)static u32 vdpasim_get_vq_group (struct vdpa_device *vdpa,u16 idx) { -return 0 ; +/* RX and TX belongs to group 0, CVQ belongs to group 1 */ +if (idx ==2 ) +return 1 ; +else +return 0 ; }static u64 vdpasim_get_features (struct vdpa_device *vdpa)
@@ -624,20 +728,52 @@ static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)return range; } +int vdpasim_set_group_asid (struct vdpa_device *vdpa,unsigned int group, +unsigned int asid) +{ +struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +struct vhost_iotlb *iommu; +int i; + +if (group >VDPASIM_GROUP_NUM ) +return -EINVAL ; + +if (asid >VDPASIM_AS_NUM ) +return -EINVAL ; + + iommu = &vdpasim->iommu[asid]; + +spin_lock (&vdpasim->lock); + +for (i =0 ; i <VDPASIM_VQ_NUM ; i++) +if (vdpasim_get_vq_group (vdpa, i) == group) +vringh_set_iotlb (&vdpasim->vqs[i].vring, iommu); + +spin_unlock (&vdpasim->lock); + +return 0 ; +} +static int vdpasim_set_map (struct vdpa_device *vdpa,unsigned int asid,struct vhost_iotlb *iotlb) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);struct vhost_iotlb_map *map; +struct vhost_iotlb *iommu;u64 start =0ULL , last =0ULL -1 ;int ret; +if (asid >=VDPASIM_AS_NUM ) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu); + + iommu = &vdpasim->iommu[asid]; +vhost_iotlb_reset (iommu);for (map =vhost_iotlb_itree_first (iotlb, start, last); map; map =vhost_iotlb_itree_next (map, start, last)) { - ret =vhost_iotlb_add_range (vdpasim->iommu, map->start, + ret =vhost_iotlb_add_range (iommu, map->start, map->last, map->addr, map->perm);if (ret) goto err;
@@ -646,7 +782,7 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,return 0 ; err: -vhost_iotlb_reset (vdpasim->iommu); +vhost_iotlb_reset (iommu);spin_unlock (&vdpasim->iommu_lock);return ret; }
@@ -658,9 +794,12 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,struct vdpasim *vdpasim =vdpa_to_sim (vdpa);int ret; +if (asid >=VDPASIM_AS_NUM ) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range (vdpasim->iommu, iova, iova + size -1 , pa, - perm); + ret =vhost_iotlb_add_range (&vdpasim->iommu[asid], iova, + iova + size -1 , pa, perm);spin_unlock (&vdpasim->iommu_lock);return ret;
@@ -671,8 +810,11 @@ static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid, {struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +if (asid >=VDPASIM_AS_NUM ) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, iova, iova + size -1 ); +vhost_iotlb_del_range (&vdpasim->iommu[asid], iova, iova + size -1 );spin_unlock (&vdpasim->iommu_lock);return 0 ;
@@ -684,8 +826,7 @@ static void vdpasim_free(struct vdpa_device *vdpa)cancel_work_sync (&vdpasim->work);kfree (vdpasim->buffer); -if (vdpasim->iommu) -vhost_iotlb_free (vdpasim->iommu); +vhost_iotlb_free (vdpasim->iommu); }static const struct vdpa_config_ops vdpasim_net_config_ops = {
@@ -711,6 +852,7 @@ static const struct vdpa_config_ops vdpasim_net_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .dma_map = vdpasim_dma_map, .dma_unmap = vdpasim_dma_unmap, .free = vdpasim_free,
@@ -739,6 +881,7 @@ static const struct vdpa_config_ops vdpasim_net_batch_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .set_map = vdpasim_set_map, .free = vdpasim_free, };
Signature · 6 lines
2.25.1 _______________________________________________ Virtualization mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/virtualization
kernel test robot
build botRe: [PATCH 21/21] vdpasim: control virtqueue support
I love your patch! Perhaps something to improve:
Hi Jason,
I love your patch! Perhaps something to improve:
[auto build test WARNING on vhost/linux-next]
[also build test WARNING on linus/master v5.10]
[cannot apply to next-20201217]
[If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Jason-Wang/Control-VQ-support-in-vDPA/20201216-150025 base: https://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git linux-next config: x86_64-randconfig-a014-20201217 (attached as .config) compiler: clang version 12.0.0 (https://github.com/llvm/llvm-project cee1e7d14f4628d6174b33640d502bff3b54ae45)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross
# install x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
# https://github.com/0day-ci/linux/commit/157796e1c075942914d2096899f4a9b7cf824373
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Jason-Wang/Control-VQ-support-in-vDPA/20201216-150025 git checkout 157796e1c075942914d2096899f4a9b7cf824373
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
If you fix the issue, kindly add following tag as appropriate
All warnings (new ones prefixed by >>):
>> drivers/vdpa/vdpa_sim/vdpa_sim.c:204:21: warning: no previous prototype for function 'vdpasim_handle_ctrl_mac' [-Wmissing-prototypes]
virtio_net_ctrl_ack vdpasim_handle_ctrl_mac(struct vdpasim *vdpasim,
^
drivers/vdpa/vdpa_sim/vdpa_sim.c:204:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
virtio_net_ctrl_ack vdpasim_handle_ctrl_mac(struct vdpasim *vdpasim,
^
static
>> drivers/vdpa/vdpa_sim/vdpa_sim.c:731:5: warning: no previous prototype for function 'vdpasim_set_group_asid' [-Wmissing-prototypes]
int vdpasim_set_group_asid(struct vdpa_device *vdpa, unsigned int group,
^
drivers/vdpa/vdpa_sim/vdpa_sim.c:731:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
int vdpasim_set_group_asid(struct vdpa_device *vdpa, unsigned int group,
^
static
drivers/vdpa/vdpa_sim/vdpa_sim.c:101:19: warning: unused function 'vdpasim16_to_cpu' [-Wunused-function]
static inline u16 vdpasim16_to_cpu(struct vdpasim *vdpasim, __virtio16 val)
^3 warnings generated.
vim +/vdpasim_handle_ctrl_mac +204 drivers/vdpa/vdpa_sim/vdpa_sim.c
203
> 204 virtio_net_ctrl_ack vdpasim_handle_ctrl_mac(struct vdpasim *vdpasim,
205 u8 cmd)
206 {
207 struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2];
208 virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
209 size_t read;
210
211 switch (cmd) {
212 case VIRTIO_NET_CTRL_MAC_ADDR_SET:
213 read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->in_iov,
214 (void *)vdpasim->config.mac,
215 ETH_ALEN);
216 if (read == ETH_ALEN)
217 status = VIRTIO_NET_OK;
218 break;
219 default:
220 break;
221 }
222
223 return status;
224 }
225
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org
Re: [PATCH 21/21] vdpasim: control virtqueue support
In reply to Jason WangQuoted 29 lines · Jason Wang
This patch introduces the control virtqueue support for vDPA simulator. This is a requirement for supporting advanced features like multiqueue.
A requirement for control virtqueue is to isolate its memory access from the rx/tx virtqueues. This is because when using vDPA device for VM, the control virqueue is not directly assigned to VM. Userspace (Qemu) will present a shadow control virtqueue to control for recording the device states.
The isolation is done via the virtqueue groups and ASID support in vDPA through vhost-vdpa. The simulator is extended to have:
1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue)
2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 contains CVQ
3) two address spaces and the simulator simply implements the address spaces by mapping it 1:1 to IOTLB.For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 to group 1. So we have:
1) The IOTLB for virtqueue group 0 contains the mappings of guest, so RX and TX can be assigned to guest directly.
2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which is the buffers that allocated and managed by VMM only. So CVQ of vhost-vdpa is visible to VMM only. And Guest can not access the CVQ of vhost-vdpa.
Quoted 6 lines
For the other use cases, since AS 0 is associated to all virtqueue groups by default. All virtqueues share the same mapping by default.
To demonstrate the function,
VIRITO_NET_F_CTRL_MACADDRis implemented in the simulator for the driver to set mac address.
Hi Jason,
is there any version of qemu/libvirt available that I can see the control virtqueue working in action?
Quoted 366 lines
Signed-off-by Jason Wang <[email protected]>--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 189 +++++++++++++++++++++++++++---- 1 file changed, 166 insertions(+), 23 deletions(-)drivers/vdpa/vdpa_sim/vdpa_sim.c +166
-23@@ -60,14 +60,18 @@ struct vdpasim_virtqueue {#define VDPASIM_QUEUE_MAX 256#define VDPASIM_DEVICE_ID 0x1#define VDPASIM_VENDOR_ID 0 -#define VDPASIM_VQ_NUM 0x2 +#define VDPASIM_VQ_NUM 0x3 +#define VDPASIM_AS_NUM 0x2 +#define VDPASIM_GROUP_NUM 0x2#define VDPASIM_NAME "vdpasim-netdev"static u64 vdpasim_features = (1ULL <<VIRTIO_F_ANY_LAYOUT ) | (1ULL <<VIRTIO_F_VERSION_1 ) | (1ULL <<VIRTIO_F_ACCESS_PLATFORM ) | + (1ULL <<VIRTIO_NET_F_MTU ) | (1ULL <<VIRTIO_NET_F_MAC ) | - (1ULL <<VIRTIO_NET_F_MTU ); + (1ULL <<VIRTIO_NET_F_CTRL_VQ ) | + (1ULL <<VIRTIO_NET_F_CTRL_MAC_ADDR );/* State of each vdpasim device */ struct vdpasim {@@ -147,11 +151,17 @@ static void vdpasim_reset(struct vdpasim *vdpasim) {int i; -for (i =0 ; i <VDPASIM_VQ_NUM ; i++) +spin_lock (&vdpasim->iommu_lock); + +for (i =0 ; i <VDPASIM_VQ_NUM ; i++) {vdpasim_vq_reset (&vdpasim->vqs[i]); +vringh_set_iotlb (&vdpasim->vqs[i].vring, + &vdpasim->iommu[0 ]); + } -spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu); +for (i =0 ; i <VDPASIM_AS_NUM ; i++) { +vhost_iotlb_reset (&vdpasim->iommu[i]); + }spin_unlock (&vdpasim->iommu_lock); vdpasim->features =0 ;@@ -191,6 +201,81 @@ static bool receive_filter(struct vdpasim *vdpasim, size_t len)return false; } +virtio_net_ctrl_ack vdpasim_handle_ctrl_mac (struct vdpasim *vdpasim, +u8 cmd) +{ +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +size_t read; + +switch (cmd) { +case VIRTIO_NET_CTRL_MAC_ADDR_SET : + read =vringh_iov_pull_iotlb (&cvq->vring, &cvq->in_iov, + (void *)vdpasim->config.mac, +ETH_ALEN ); +if (read ==ETH_ALEN ) + status =VIRTIO_NET_OK ; +break ; +default : +break ; + } + +return status; +} + +static void vdpasim_handle_cvq (struct vdpasim *vdpasim) +{ +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +struct virtio_net_ctrl_hdr ctrl; +size_t read, write; +int err; + +if (!(vdpasim->features & (1ULL <<VIRTIO_NET_F_CTRL_VQ ))) +return ; + +if (!cvq->ready) +return ; + +while (true) { + err =vringh_getdesc_iotlb (&cvq->vring, &cvq->in_iov, + &cvq->out_iov, + &cvq->head,GFP_ATOMIC ); +if (err <=0 ) +break ; + + read =vringh_iov_pull_iotlb (&cvq->vring, &cvq->in_iov, &ctrl, +sizeof (ctrl)); +if (read !=sizeof (ctrl)) +break ; + +switch (ctrl.class) { +case VIRTIO_NET_CTRL_MAC : + status =vdpasim_handle_ctrl_mac (vdpasim, ctrl.cmd); +break ; +default : +break ; + } + +/* Make sure data is wrote before advancing index */ +smp_wmb (); + + write =vringh_iov_push_iotlb (&cvq->vring, &cvq->out_iov, + &status,sizeof (status)); +vringh_complete_iotlb (&cvq->vring, cvq->head, write); +vringh_kiov_cleanup (&cvq->in_iov); +vringh_kiov_cleanup (&cvq->out_iov); + +/* Make sure used is visible before rasing the interrupt. */ +smp_wmb (); + +local_bh_disable (); +if (cvq->cb) + cvq->cb (cvq->private); +local_bh_enable (); + } +} +static void vdpasim_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct@@ -276,7 +361,7 @@ static dma_addr_t vdpasim_map_page(struct device *dev, struct page *page, unsigned long attrs) {struct vdpasim *vdpasim =dev_to_sim (dev); -struct vhost_iotlb *iommu = vdpasim->iommu; +struct vhost_iotlb *iommu = &vdpasim->iommu[0 ];u64 pa = (page_to_pfn (page) <<PAGE_SHIFT ) + offset;int ret, perm =dir_to_perm (dir);@@ -301,7 +386,7 @@ static void vdpasim_unmap_page(struct device *dev, dma_addr_t dma_addr, unsigned long attrs) {struct vdpasim *vdpasim =dev_to_sim (dev); -struct vhost_iotlb *iommu = vdpasim->iommu; +struct vhost_iotlb *iommu = &vdpasim->iommu[0 ];spin_lock (&vdpasim->iommu_lock); vhost_iotlb_del_range(iommu, (u64)dma_addr,@@ -314,7 +399,7 @@ static void *vdpasim_alloc_coherent(struct device *dev, size_t size, unsigned long attrs) {struct vdpasim *vdpasim =dev_to_sim (dev); -struct vhost_iotlb *iommu = vdpasim->iommu; +struct vhost_iotlb *iommu = &vdpasim->iommu[0 ];void *addr =kmalloc (size, flag);int ret;@@ -344,7 +429,7 @@ static void vdpasim_free_coherent(struct device *dev, size_t size, unsigned long attrs) {struct vdpasim *vdpasim =dev_to_sim (dev); -struct vhost_iotlb *iommu = vdpasim->iommu; +struct vhost_iotlb *iommu = &vdpasim->iommu[0 ];spin_lock (&vdpasim->iommu_lock); vhost_iotlb_del_range(iommu, (u64)dma_addr,@@ -370,14 +455,17 @@ static struct vdpasim *vdpasim_create(void)struct vdpasim *vdpasim;struct device *dev;int ret = -ENOMEM ; +int i;if (batch_mapping) ops = &vdpasim_net_batch_config_ops;else ops = &vdpasim_net_config_ops; +/* 3 virtqueues, 2 address spaces, 2 virtqueue groups */ vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, -VDPASIM_VQ_NUM ,1 ,1 ); +VDPASIM_VQ_NUM ,VDPASIM_AS_NUM , +VDPASIM_GROUP_NUM );if (!vdpasim) goto err_alloc;@@ -391,10 +479,14 @@ static struct vdpasim *vdpasim_create(void) goto err_iommu;set_dma_ops (dev, &vdpasim_dma_ops); - vdpasim->iommu =vhost_iotlb_alloc (2048 ,0 ); + vdpasim->iommu =kmalloc_array (VDPASIM_AS_NUM , +sizeof (*vdpasim->iommu),GFP_KERNEL );if (!vdpasim->iommu) goto err_iommu; +for (i =0 ; i <VDPASIM_AS_NUM ; i++) +vhost_iotlb_init (&vdpasim->iommu[i],0 ,0 ); + vdpasim->buffer =kmalloc (PAGE_SIZE ,GFP_KERNEL );if (!vdpasim->buffer) goto err_iommu;@@ -409,8 +501,9 @@ static struct vdpasim *vdpasim_create(void)eth_random_addr (vdpasim->config.mac); } -vringh_set_iotlb (&vdpasim->vqs[0 ].vring, vdpasim->iommu); -vringh_set_iotlb (&vdpasim->vqs[1 ].vring, vdpasim->iommu); +/* Make sure that default ASID is zero */ +for (i =0 ; i <VDPASIM_VQ_NUM ; i++) +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ]); vdpasim->vdpa.dma_dev = dev; ret =vdpa_register_device (&vdpasim->vdpa);@@ -452,7 +545,14 @@ static void vdpasim_kick_vq(struct vdpa_device *vdpa, u16 idx)struct vdpasim *vdpasim =vdpa_to_sim (vdpa);struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; -if (vq->ready) +if (idx ==2 ) { +/* Kernel virtio driver will do busy waiting for the +* result, so we can't handle cvq in the workqueue. +*/ +spin_lock (&vdpasim->lock); +vdpasim_handle_cvq (vdpasim); +spin_unlock (&vdpasim->lock); + }else if (vq->ready)schedule_work (&vdpasim->work); }@@ -518,7 +618,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)static u32 vdpasim_get_vq_group (struct vdpa_device *vdpa,u16 idx) { -return 0 ; +/* RX and TX belongs to group 0, CVQ belongs to group 1 */ +if (idx ==2 ) +return 1 ; +else +return 0 ; }static u64 vdpasim_get_features (struct vdpa_device *vdpa)@@ -624,20 +728,52 @@ static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)return range; } +int vdpasim_set_group_asid (struct vdpa_device *vdpa,unsigned int group, +unsigned int asid) +{ +struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +struct vhost_iotlb *iommu; +int i; + +if (group >VDPASIM_GROUP_NUM ) +return -EINVAL ; + +if (asid >VDPASIM_AS_NUM ) +return -EINVAL ; + + iommu = &vdpasim->iommu[asid]; + +spin_lock (&vdpasim->lock); + +for (i =0 ; i <VDPASIM_VQ_NUM ; i++) +if (vdpasim_get_vq_group (vdpa, i) == group) +vringh_set_iotlb (&vdpasim->vqs[i].vring, iommu); + +spin_unlock (&vdpasim->lock); + +return 0 ; +} +static int vdpasim_set_map (struct vdpa_device *vdpa,unsigned int asid,struct vhost_iotlb *iotlb) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);struct vhost_iotlb_map *map; +struct vhost_iotlb *iommu;u64 start =0ULL , last =0ULL -1 ;int ret; +if (asid >=VDPASIM_AS_NUM ) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu); + + iommu = &vdpasim->iommu[asid]; +vhost_iotlb_reset (iommu);for (map =vhost_iotlb_itree_first (iotlb, start, last); map; map =vhost_iotlb_itree_next (map, start, last)) { - ret =vhost_iotlb_add_range (vdpasim->iommu, map->start, + ret =vhost_iotlb_add_range (iommu, map->start, map->last, map->addr, map->perm);if (ret) goto err;@@ -646,7 +782,7 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,return 0 ; err: -vhost_iotlb_reset (vdpasim->iommu); +vhost_iotlb_reset (iommu);spin_unlock (&vdpasim->iommu_lock);return ret; }@@ -658,9 +794,12 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,struct vdpasim *vdpasim =vdpa_to_sim (vdpa);int ret; +if (asid >=VDPASIM_AS_NUM ) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range (vdpasim->iommu, iova, iova + size -1 , pa, - perm); + ret =vhost_iotlb_add_range (&vdpasim->iommu[asid], iova, + iova + size -1 , pa, perm);spin_unlock (&vdpasim->iommu_lock);return ret;@@ -671,8 +810,11 @@ static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid, {struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +if (asid >=VDPASIM_AS_NUM ) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, iova, iova + size -1 ); +vhost_iotlb_del_range (&vdpasim->iommu[asid], iova, iova + size -1 );spin_unlock (&vdpasim->iommu_lock);return 0 ;@@ -684,8 +826,7 @@ static void vdpasim_free(struct vdpa_device *vdpa)cancel_work_sync (&vdpasim->work);kfree (vdpasim->buffer); -if (vdpasim->iommu) -vhost_iotlb_free (vdpasim->iommu); +vhost_iotlb_free (vdpasim->iommu); }static const struct vdpa_config_ops vdpasim_net_config_ops = {@@ -711,6 +852,7 @@ static const struct vdpa_config_ops vdpasim_net_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .dma_map = vdpasim_dma_map, .dma_unmap = vdpasim_dma_unmap, .free = vdpasim_free,@@ -739,6 +881,7 @@ static const struct vdpa_config_ops vdpasim_net_batch_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .set_map = vdpasim_set_map, .free = vdpasim_free, };Signature · 1 line
2.25.1
Re: [PATCH 21/21] vdpasim: control virtqueue support
Quoted 33 lines · Eli Cohen
Quoted 32 lines · Jason Wang
This patch introduces the control virtqueue support for vDPA simulator. This is a requirement for supporting advanced features like multiqueue.
A requirement for control virtqueue is to isolate its memory access from the rx/tx virtqueues. This is because when using vDPA device for VM, the control virqueue is not directly assigned to VM. Userspace (Qemu) will present a shadow control virtqueue to control for recording the device states.
The isolation is done via the virtqueue groups and ASID support in vDPA through vhost-vdpa. The simulator is extended to have:
1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue)
2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 contains CVQ
3) two address spaces and the simulator simply implements the address spaces by mapping it 1:1 to IOTLB.For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 to group 1. So we have:
1) The IOTLB for virtqueue group 0 contains the mappings of guest, so RX and TX can be assigned to guest directly.
2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which is the buffers that allocated and managed by VMM only. So CVQ of vhost-vdpa is visible to VMM only. And Guest can not access the CVQ of vhost-vdpa.For the other use cases, since AS 0 is associated to all virtqueue groups by default. All virtqueues share the same mapping by default.
Quoted 7 lines
Quoted 3 lines
To demonstrate the function,
VIRITO_NET_F_CTRL_MACADDRis implemented in the simulator for the driver to set mac address.Hi Jason,
is there any version of qemu/libvirt available that I can see the control virtqueue working in action?
Not yet, the qemu part depends on the shadow virtqueue work of Eugenio. But it will work as:
1) qemu will use a separated address space for the control virtqueue (shadow) exposed through vhost-vDPA
2) the commands sent through control virtqueue by guest driver will intercept by qemu
3) Qemu will send those commands to the shadow control virtqueue
Eugenio, any ETA for the new version of shadow virtqueue support in Qemu?
Thanks
Quoted 1 line
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Eugenio Perez Martin
maintainerRe: [PATCH 21/21] vdpasim: control virtqueue support
Quoted 48 lines · Jason Wang
Quoted 33 lines · Eli Cohen
Quoted 32 lines · Jason Wang
This patch introduces the control virtqueue support for vDPA simulator. This is a requirement for supporting advanced features like multiqueue.
A requirement for control virtqueue is to isolate its memory access from the rx/tx virtqueues. This is because when using vDPA device for VM, the control virqueue is not directly assigned to VM. Userspace (Qemu) will present a shadow control virtqueue to control for recording the device states.
The isolation is done via the virtqueue groups and ASID support in vDPA through vhost-vdpa. The simulator is extended to have:
1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue)
2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 contains CVQ
3) two address spaces and the simulator simply implements the address spaces by mapping it 1:1 to IOTLB.For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 to group 1. So we have:
1) The IOTLB for virtqueue group 0 contains the mappings of guest, so RX and TX can be assigned to guest directly.
2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which is the buffers that allocated and managed by VMM only. So CVQ of vhost-vdpa is visible to VMM only. And Guest can not access the CVQ of vhost-vdpa.For the other use cases, since AS 0 is associated to all virtqueue groups by default. All virtqueues share the same mapping by default.
Quoted 7 lines
Quoted 3 lines
To demonstrate the function,
VIRITO_NET_F_CTRL_MACADDRis implemented in the simulator for the driver to set mac address.Hi Jason,
is there any version of qemu/libvirt available that I can see the control virtqueue working in action?
Not yet, the qemu part depends on the shadow virtqueue work of Eugenio. But it will work as:
Quoted 8 lines
1) qemu will use a separated address space for the control virtqueue (shadow) exposed through vhost-vDPA
2) the commands sent through control virtqueue by guest driver will intercept by qemu
3) Qemu will send those commands to the shadow control virtqueueEugenio, any ETA for the new version of shadow virtqueue support in Qemu?
Hi Jason. Sorry for the late response.
For the notification part I have addressed all the issues of the RFC [1], except the potential race conditions Stefan pointed, and tested with vdpa devices. You can find at
https://github.com/eugpermar/qemu/tree/vdpa_sw_live_migration.d/notifications.rfc
. Since the shadow path is activated only through QMP and does not interfere with regular operation, I could post to the qemu list if you prefer. The series will be smaller if merged in steps.
Adding the buffer forwarding on top should not take long.
[1] https://lkml.org/lkml/2020/9/23/1243
Thanks!
Re: [PATCH 21/21] vdpasim: control virtqueue support
Quoted 57 lines · Eugenio Perez Martin
Quoted 46 lines · Jason Wang
Quoted 33 lines · Eli Cohen
Quoted 32 lines · Jason Wang
This patch introduces the control virtqueue support for vDPA simulator. This is a requirement for supporting advanced features like multiqueue.
A requirement for control virtqueue is to isolate its memory access from the rx/tx virtqueues. This is because when using vDPA device for VM, the control virqueue is not directly assigned to VM. Userspace (Qemu) will present a shadow control virtqueue to control for recording the device states.
The isolation is done via the virtqueue groups and ASID support in vDPA through vhost-vdpa. The simulator is extended to have:
1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue)
2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 contains CVQ
3) two address spaces and the simulator simply implements the address spaces by mapping it 1:1 to IOTLB.For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 to group 1. So we have:
1) The IOTLB for virtqueue group 0 contains the mappings of guest, so RX and TX can be assigned to guest directly.
2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which is the buffers that allocated and managed by VMM only. So CVQ of vhost-vdpa is visible to VMM only. And Guest can not access the CVQ of vhost-vdpa.For the other use cases, since AS 0 is associated to all virtqueue groups by default. All virtqueues share the same mapping by default.
Quoted 7 lines
Quoted 3 lines
To demonstrate the function,
VIRITO_NET_F_CTRL_MACADDRis implemented in the simulator for the driver to set mac address.Hi Jason,
is there any version of qemu/libvirt available that I can see the control virtqueue working in action?
Not yet, the qemu part depends on the shadow virtqueue work of Eugenio. But it will work as:
Quoted 8 lines
1) qemu will use a separated address space for the control virtqueue (shadow) exposed through vhost-vDPA
2) the commands sent through control virtqueue by guest driver will intercept by qemu
3) Qemu will send those commands to the shadow control virtqueueEugenio, any ETA for the new version of shadow virtqueue support in Qemu?
Hi Jason. Sorry for the late response.
Quoted 7 lines
For the notification part I have addressed all the issues of the RFC [1], except the potential race conditions Stefan pointed, and tested with vdpa devices. You can find at
https://github.com/eugpermar/qemu/tree/vdpa_sw_live_migration.d/notifications.rfc
. Since the shadow path is activated only through QMP and does not interfere with regular operation, I could post to the qemu list if you prefer. The series will be smaller if merged in steps.
Sure. Please post them.
Quoted 6 lines
Adding the buffer forwarding on top should not take long.
[1] https://lkml.org/lkml/2020/9/23/1243
Thanks!
Thanks
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Michael S. Tsirkin
maintainerQuoted 13 lines · Jason Wang
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
Quoted 8 lines
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accesing it directly. To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address space
How will this support the pretty common case where control vq is programmed by the kernel through the PF, and others by the VFs?
I actually thought the way to support it is by exposing something like an "inject buffers" API which sends data to a given VQ. Maybe an ioctl, and maybe down the road uio ring can support batching these ....
Quoted 80 lines
Device needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groupsThe mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commandsThis will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking invhost_vdpa_unmap()Thanks
Jason Wang (20):
vhost: move the backend feature bits tovhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: add the missing comment for nvqs in structvdpa_device
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertiseVIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue supportStefano Garzarella (1):
vdpa_sim: split vdpasim_virtqueue's iov field inout_iovandin_iov
Quoted 17 lines
drivers/vdpa/ifcvf/ifcvf_main.c | 9 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 8 +- drivers/vdpa/vdpa_sim/vdpa_sim.c | 292 ++++++++++++++++++++++++------ drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 246 ++++++++++++++++++++----- drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 42 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 10 +- 13 files changed, 561 insertions(+), 136 deletions(-)Signature · 1 line
2.25.1
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Quoted 18 lines · Michael S. Tsirkin
Quoted 17 lines · Jason Wang
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accesing it directly. To achieve this, vDPA introduce two new abstractions:
Quoted 6 lines
Quoted 4 lines
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address spaceHow will this support the pretty common case where control vq is programmed by the kernel through the PF, and others by the VFs?
In this case, the VF parent need to provide a software control vq and decode the command then send them to VF.
Quoted 6 lines
I actually thought the way to support it is by exposing something like an "inject buffers" API which sends data to a given VQ. Maybe an ioctl, and maybe down the road uio ring can support batching these ....
So the virtuqueue allows the request to be processed asynchronously (e.g driver may choose to use interrupt for control vq). This means we need to support that in uAPI level. And if we manage to do that, it's just another type of virtqueue.
For virtio-vDPA, this also means the extensions for queue processing which is a functional duplication. Using what proposed in this series, we don't need any changes for kernel virtio drivers.
What's more important, this series could be used for future features that requires DMA isolation between virtqueues:
- report dirty pages via virtqueue
- sub function level device slicing
...
Thanks
Quoted 96 lines
Quoted 96 lines
Device needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groupsThe mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commandsThis will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking invhost_vdpa_unmap()Thanks
Jason Wang (20):
vhost: move the backend feature bits tovhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: add the missing comment for nvqs in structvdpa_device
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertiseVIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue supportStefano Garzarella (1):
vdpa_sim: split vdpasim_virtqueue's iov field inout_iovandin_iovdrivers/vdpa/ifcvf/ifcvf_main.c | 9 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 8 +- drivers/vdpa/vdpa_sim/vdpa_sim.c | 292 ++++++++++++++++++++++++------ drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 246 ++++++++++++++++++++----- drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 42 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 10 +- 13 files changed, 561 insertions(+), 136 deletions(-)
Quoted 2 lines
Quoted 2 lines
Signature · 1 line
2.25.1
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Michael S. Tsirkin
maintainerQuoted 24 lines · Jason Wang
Quoted 22 lines · Michael S. Tsirkin
Quoted 21 lines · Jason Wang
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accesing it directly. To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address space
Quoted 6 lines
Quoted 2 lines
How will this support the pretty common case where control vq is programmed by the kernel through the PF, and others by the VFs?
In this case, the VF parent need to provide a software control vq and decode the command then send them to VF.
But how does that tie to the address space infrastructure?
Quoted 9 lines
Quoted 7 lines
I actually thought the way to support it is by exposing something like an "inject buffers" API which sends data to a given VQ. Maybe an ioctl, and maybe down the road uio ring can support batching these ....
Quoted 3 lines
So the virtuqueue allows the request to be processed asynchronously (e.g driver may choose to use interrupt for control vq). This means we need to support that in uAPI level.
I don't think we need to make it async, just a regular ioctl will do. In fact no guest uses the asynchronous property.
Quoted 5 lines
And if we manage to do that, it's just another
type of virtqueue.For virtio-vDPA, this also means the extensions for queue processing which is a functional duplication.
I don't see why, just send it to the actual control vq :)
Quoted 8 lines
Using what proposed in this series, we don't
need any changes for kernel virtio drivers.What's more important, this series could be used for future features that requires DMA isolation between virtqueues:
- report dirty pages via virtqueue
- sub function level device slicing
I agree these are nice to have, but I am not sure basic control vq must be tied to that.
Quoted 103 lines
...
Thanks
Quoted 98 lines
Quoted 98 lines
Device needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groupsThe mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commandsThis will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking invhost_vdpa_unmap()Thanks
Jason Wang (20):
vhost: move the backend feature bits tovhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: add the missing comment for nvqs in structvdpa_device
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertiseVIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue supportStefano Garzarella (1):
vdpa_sim: split vdpasim_virtqueue's iov field inout_iovandin_iovdrivers/vdpa/ifcvf/ifcvf_main.c | 9 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 8 +- drivers/vdpa/vdpa_sim/vdpa_sim.c | 292 ++++++++++++++++++++++++------ drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 246 ++++++++++++++++++++----- drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 42 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 10 +- 13 files changed, 561 insertions(+), 136 deletions(-)Signature · 1 line
2.25.1
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Quoted 24 lines · Michael S. Tsirkin
Quoted 23 lines · Jason Wang
Quoted 22 lines · Michael S. Tsirkin
Quoted 21 lines · Jason Wang
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accesing it directly. To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address space
Quoted 7 lines
Quoted 5 lines
Quoted 2 lines
How will this support the pretty common case where control vq is programmed by the kernel through the PF, and others by the VFs?
In this case, the VF parent need to provide a software control vq and decode the command then send them to VF.
But how does that tie to the address space infrastructure?
In this case, address space is not a must. But the idea is to make control vq works for all types of hardware:
1) control virtqueue is implemented via VF/PF communication
2) control virtqueue is implemented by VF but not through DMA
3) control virtqueue is implemented by VF DMA, it could be either a hardware control virtqueue or other type of DMA
The address space is a must for 3) to work and can work for both 1) and 2).
Quoted 9 lines
Quoted 9 lines
Quoted 8 lines
I actually thought the way to support it is by exposing something like an "inject buffers" API which sends data to a given VQ. Maybe an ioctl, and maybe down the road uio ring can support batching these ....
Quoted 5 lines
Quoted 3 lines
So the virtuqueue allows the request to be processed asynchronously (e.g driver may choose to use interrupt for control vq). This means we need to support that in uAPI level.
I don't think we need to make it async, just a regular ioctl will do. In fact no guest uses the asynchronous property.
It was not forbidden by the spec then we need to support that. E.g we can not assume driver doesn't assign interrupt for cvq.
Quoted 8 lines
Quoted 7 lines
And if we manage to do that, it's just another
type of virtqueue.For virtio-vDPA, this also means the extensions for queue processing which is a functional duplication.
I don't see why, just send it to the actual control vq :)
But in the case you've pointed out, there's no hardware control vq in fact.
Quoted 4 lines
Quoted 4 lines
Using what proposed in this series, we don't
need any changes for kernel virtio drivers.
Quoted 8 lines
Quoted 5 lines
What's more important, this series could be used for future features that requires DMA isolation between virtqueues:
- report dirty pages via virtqueue
- sub function level device slicingI agree these are nice to have, but I am not sure basic control vq must be tied to that.
If the control virtqueue is implemented via DMA through VF, it looks like a must.
Thanks
Quoted 101 lines
Quoted 101 lines
...
Thanks
Quoted 95 lines
Quoted 95 lines
Device needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groupsThe mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commandsThis will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking invhost_vdpa_unmap()Thanks
Jason Wang (20):
vhost: move the backend feature bits tovhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: add the missing comment for nvqs in structvdpa_device
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertiseVIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue supportStefano Garzarella (1):
vdpa_sim: split vdpasim_virtqueue's iov field inout_iovandin_iovdrivers/vdpa/ifcvf/ifcvf_main.c | 9 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 8 +- drivers/vdpa/vdpa_sim/vdpa_sim.c | 292 ++++++++++++++++++++++++------ drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 246 ++++++++++++++++++++----- drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 42 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 10 +- 13 files changed, 561 insertions(+), 136 deletions(-)
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Signature · 1 line
2.25.1
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Michael S. Tsirkin
maintainerQuoted 29 lines · Jason Wang
Quoted 27 lines · Michael S. Tsirkin
Quoted 26 lines · Jason Wang
Quoted 24 lines · Michael S. Tsirkin
Quoted 13 lines · Jason Wang
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
Quoted 8 lines
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accesing it directly. To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address spaceHow will this support the pretty common case where control vq is programmed by the kernel through the PF, and others by the VFs?
Quoted 7 lines
Quoted 4 lines
Quoted 2 lines
In this case, the VF parent need to provide a software control vq and decode the command then send them to VF.
But how does that tie to the address space infrastructure?
In this case, address space is not a must.
That's ok, problem is I don't see how address space is going to work in this case at all.
There's no address space there that userspace/guest can control.
Quoted 54 lines
But the idea is to make control
vq works for all types of hardware:1) control virtqueue is implemented via VF/PF communication
2) control virtqueue is implemented by VF but not through DMA
3) control virtqueue is implemented by VF DMA, it could be either a hardware control virtqueue or other type of DMAThe address space is a must for 3) to work and can work for both 1) and 2).
Quoted 9 lines
Quoted 9 lines
Quoted 8 lines
I actually thought the way to support it is by exposing something like an "inject buffers" API which sends data to a given VQ. Maybe an ioctl, and maybe down the road uio ring can support batching these ....
Quoted 5 lines
Quoted 3 lines
So the virtuqueue allows the request to be processed asynchronously (e.g driver may choose to use interrupt for control vq). This means we need to support that in uAPI level.
I don't think we need to make it async, just a regular ioctl will do. In fact no guest uses the asynchronous property.
It was not forbidden by the spec then we need to support that. E.g we can not assume driver doesn't assign interrupt for cvq.
Quoted 8 lines
Quoted 7 lines
And if we manage to do that, it's just another
type of virtqueue.For virtio-vDPA, this also means the extensions for queue processing which is a functional duplication.
I don't see why, just send it to the actual control vq :)
But in the case you've pointed out, there's no hardware control vq in fact.
Quoted 10 lines
Quoted 9 lines
Using what proposed in this series, we don't
need any changes for kernel virtio drivers.What's more important, this series could be used for future features that requires DMA isolation between virtqueues:
- report dirty pages via virtqueue
- sub function level device slicing
Quoted 113 lines
Quoted 2 lines
I agree these are nice to have, but I am not sure basic control vq must be tied to that.
If the control virtqueue is implemented via DMA through VF, it looks like a must.
Thanks
Quoted 103 lines
Quoted 103 lines
...
Thanks
Quoted 97 lines
Quoted 97 lines
Device needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groupsThe mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commandsThis will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking invhost_vdpa_unmap()Thanks
Jason Wang (20):
vhost: move the backend feature bits tovhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: add the missing comment for nvqs in structvdpa_device
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertiseVIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue supportStefano Garzarella (1):
vdpa_sim: split vdpasim_virtqueue's iov field inout_iovandin_iovdrivers/vdpa/ifcvf/ifcvf_main.c | 9 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 8 +- drivers/vdpa/vdpa_sim/vdpa_sim.c | 292 ++++++++++++++++++++++++------ drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 246 ++++++++++++++++++++----- drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 42 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 10 +- 13 files changed, 561 insertions(+), 136 deletions(-)Signature · 1 line
2.25.1
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Quoted 28 lines · Michael S. Tsirkin
Quoted 27 lines · Jason Wang
Quoted 26 lines · Michael S. Tsirkin
Quoted 25 lines · Jason Wang
Quoted 24 lines · Michael S. Tsirkin
Quoted 13 lines · Jason Wang
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
Quoted 8 lines
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accesing it directly. To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address spaceHow will this support the pretty common case where control vq is programmed by the kernel through the PF, and others by the VFs?
Quoted 9 lines
Quoted 4 lines
Quoted 3 lines
Quoted 2 lines
In this case, the VF parent need to provide a software control vq and decode the command then send them to VF.
But how does that tie to the address space infrastructure?
In this case, address space is not a must.
That's ok, problem is I don't see how address space is going to work in this case at all.
There's no address space there that userspace/guest can control.
The virtqueue group is mandated by parent but the association between virtqueue group and address space is under the control of userspace (Qemu).
A simple but common case is that:
1) Device advertise two virtqueue groups: group 0 contains RX and TX, group 1 contains CVQ.
2) Device advertise two address spaces
Then, for vhost-vDPA using by VM:
1) associate group 0 with as 0, group 1 with as 1 (via vhost-vDPA VHOST_VDPA_SET_GROUP_ASID)
2) Publish guest memory mapping via IOTLB asid 0
3) Publish control virtqueue mapping via IOTLB asid 1
Then the DMA is totally isolated in this case.
For vhost-vDPA using by DPDK or virtio-vDPA
1) associate group 0 and group 1 with as 0
since we don't need DMA isolation in this case.
In order to let it be controlled by Guest, we need extend virtio spec to support those concepts.
Thanks
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
On Wed, Dec 16, 2020 at 02:47:57PM +0800, Jason Wang wrote:
Hi Jason,
I saw the patchset and will start reviewing it starting Dec 27. I am out of office next week.
Quoted 120 lines
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accesing it directly.
To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address spaceDevice needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groupsThe mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commandsThis will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking invhost_vdpa_unmap()Thanks
Jason Wang (20):
vhost: move the backend feature bits tovhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: add the missing comment for nvqs in structvdpa_device
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertiseVIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue supportStefano Garzarella (1):
vdpa_sim: split vdpasim_virtqueue's iov field inout_iovandin_iovdrivers/vdpa/ifcvf/ifcvf_main.c | 9 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 8 +- drivers/vdpa/vdpa_sim/vdpa_sim.c | 292 ++++++++++++++++++++++++------ drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 246 ++++++++++++++++++++----- drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 42 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 10 +- 13 files changed, 561 insertions(+), 136 deletions(-)Signature · 1 line
2.25.1
v2 cover Control VQ support in vDPA
In reply to Jason WangHi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accessing it directly.
To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address space
Device needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groups
The mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.
vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commands
This will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since v1:
- Rebased the v1 patch series on vhost branch of MST vhost git repo git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git/log/?h=vhost
- Updates to accommodate vdpa_sim changes from monolithic module in kernel used v1 patch series to current modularized class (net, block) based approach.
- Added new attributes (ngroups and nas) to "vdpasim_dev_attr" and propagated them from vdpa_sim_net to vdpa_sim
- Widened the data-type for "asid" member of vhost_msg_v2 to __u32 to accommodate PASID
- Fixed the buildbot warnings
- Resolved all checkpatch.pl errors and warnings
- Tested both control and datapath with Xilinx Smartnic SN1000 series device using QEMU implementing the Shadow virtqueue and support for VQ groups and ASID available at:
github.com/eugpermar/qemu/releases/tag/vdpa_sw_live_migration.d%2F asid_groups-v1.d%2F00
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking in vhost_vdpa_unmap()
Thanks
Gautam Dawar (19):
vhost: move the backend feature bits to vhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertise VIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue support
drivers/vdpa/ifcvf/ifcvf_main.c | 8 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 5 + drivers/vdpa/vdpa_sim/vdpa_sim.c | 100 ++++++++-- drivers/vdpa/vdpa_sim/vdpa_sim.h | 3 + drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 169 +++++++++++++---- drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 272 +++++++++++++++++++++------ drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 46 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 11 +- 15 files changed, 566 insertions(+), 138 deletions(-)
Signature · 1 line
2.25.0
RFC PATCH v2 1/19 vhost: move the backend feature bits to vhost_types.h
We should store feature bits in vhost_types.h as what has been done for e.g VHOST_F_LOG_ALL.
--- include/uapi/linux/vhost.h | 5 ----- include/uapi/linux/vhost_types.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-)
include/uapi/linux/vhost.h +0 -5
@@ -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)
include/uapi/linux/vhost_types.h +5 -0
@@ -153,4 +153,9 @@ 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 +#endif
Signature · 1 line
2.25.0
RFC PATCH v2 2/19 virtio-vdpa: don't set callback if virtio doesn't need it
In reply to Gautam DawarThere's no need for setting callbacks for the driver that doesn't care about that.
--- drivers/virtio/virtio_vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/virtio/virtio_vdpa.c +1 -1
@@ -184,7 +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));
Signature · 1 line
2.25.0
RFC PATCH v2 3/19 vhost-vdpa: passing iotlb to IOMMU mapping helpers
In reply to Gautam DawarTo prepare for the ASID support for vhost-vdpa, try to pass IOTLB object to dma helpers. No functional changes, it's just a preparation for support multiple IOTLBs.
--- drivers/vhost/vdpa.c | 67 ++++++++++++++++++++++++-------------------- 1 file changed, 37 insertions(+), 30 deletions(-)
drivers/vhost/vdpa.c +37 -30
@@ -503,10 +503,11 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,return r; } -static void vhost_vdpa_pa_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;
@@ -525,10 +526,10 @@ static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, u64 start, u64 last) } } -static void vhost_vdpa_va_unmap (struct vhost_vdpa *v,u64 start,u64 last) +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 *iotlb = dev->iotlb;struct vhost_iotlb_map *map;struct vdpa_map_file *map_file;
@@ -540,21 +541,24 @@ static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, u64 start, u64 last) } } -static void vhost_vdpa_iotlb_unmap (struct vhost_vdpa *v,u64 start,u64 last) +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, start, last); +return vhost_vdpa_va_unmap (v, iotlb, start, last); -return vhost_vdpa_pa_unmap (v, start, last); +return vhost_vdpa_pa_unmap (v, iotlb, start, last); }static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) {struct vhost_dev *dev = &v->vdev; +struct vhost_iotlb *iotlb = dev->iotlb; -vhost_vdpa_iotlb_unmap (v,0ULL ,0ULL -1 ); +vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 );kfree (dev->iotlb); dev->iotlb =NULL ; }
@@ -581,15 +585,15 @@ 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,void *opaque) +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;int r =0 ; - r =vhost_iotlb_add_range_ctx (dev->iotlb, iova, iova + size -1 , + r =vhost_iotlb_add_range_ctx (iotlb, iova, iova + size -1 , pa, perm, opaque);if (r)return r;
@@ -598,13 +602,13 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, u64 iova, r = ops->dma_map (vdpa, 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, iotlb); }else { r =iommu_map (v->domain, iova, pa, size,perm_to_iommu_flags (perm)); }if (r) { -vhost_iotlb_del_range (dev->iotlb, iova, iova + size -1 ); +vhost_iotlb_del_range (iotlb, iova, iova + size -1 );return r; }
@@ -614,25 +618,27 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, u64 iova,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; -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); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa, dev->iotlb); + ops->set_map (vdpa, iotlb); }else {iommu_unmap (v->domain, iova, size); } }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;
@@ -662,7 +668,7 @@ static int vhost_vdpa_va_map(struct vhost_vdpa *v, 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, map_iova, map_size, uaddr, + ret =vhost_vdpa_map (v, iotlb, map_iova, map_size, uaddr, perm, map_file);if (ret) {fput (map_file->file);
@@ -675,7 +681,7 @@ static int vhost_vdpa_va_map(struct vhost_vdpa *v, map_iova += map_size; }if (ret) -vhost_vdpa_unmap (v, iova, map_iova - iova); +vhost_vdpa_unmap (v, iotlb, iova, map_iova - iova);mmap_read_unlock (dev->mm);
@@ -683,6 +689,7 @@ static int vhost_vdpa_va_map(struct vhost_vdpa *v, }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;
@@ -746,7 +753,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v,if (last_pfn && (this_pfn != last_pfn +1 )) {/* Pin a contiguous chunk of memory */ csize =PFN_PHYS (last_pfn - map_pfn +1 ); - ret =vhost_vdpa_map (v, iova, csize, + ret =vhost_vdpa_map (v, iotlb, iova, csize,PFN_PHYS (map_pfn), perm,NULL );if (ret) {
@@ -776,7 +783,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v, }/* Pin the rest chunk */ - ret =vhost_vdpa_map (v, iova,PFN_PHYS (last_pfn - map_pfn +1 ), + ret =vhost_vdpa_map (v, iotlb, iova,PFN_PHYS (last_pfn - map_pfn +1 ),PFN_PHYS (map_pfn), perm,NULL ); out:if (ret) {
@@ -796,7 +803,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v,for (pfn = map_pfn; pfn <= last_pfn; pfn++)unpin_user_page (pfn_to_page (pfn)); } -vhost_vdpa_unmap (v, start, size); +vhost_vdpa_unmap (v, iotlb, start, size); } unlock:mmap_read_unlock (dev->mm);
@@ -807,11 +814,10 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v, }static int vhost_vdpa_process_iotlb_update (struct vhost_vdpa *v, +struct vhost_iotlb *iotlb,struct vhost_iotlb_msg *msg) { -struct vhost_dev *dev = &v->vdev;struct vdpa_device *vdpa = v->vdpa; -struct vhost_iotlb *iotlb = dev->iotlb; if (msg->iova < v->range.first || !msg->size || msg->iova > U64_MAX - msg->size + 1 ||
@@ -823,10 +829,10 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,return -EEXIST ;if (vdpa->use_va) -return vhost_vdpa_va_map (v, msg->iova, msg->size, +return vhost_vdpa_va_map (v, iotlb, msg->iova, msg->size, msg->uaddr, msg->perm); -return vhost_vdpa_pa_map (v, msg->iova, msg->size, msg->uaddr, +return vhost_vdpa_pa_map (v, iotlb, msg->iova, msg->size, msg->uaddr, msg->perm); }
@@ -836,6 +842,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, 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 = dev->iotlb;int r =0 ;mutex_lock (&dev->mutex);
@@ -846,17 +853,17 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,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->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, iotlb); v->in_batch = false;break ;default :
Signature · 1 line
2.25.0
RFC PATCH v2 4/19 vhost-vdpa: switch to use vhost-vdpa specific IOTLB
In reply to Gautam DawarTo ease the implementation of per group ASID support for vDPA device. This patch switches to use a vhost-vdpa specific IOTLB to avoid the unnecessary refactoring of the vhost core.
--- drivers/vhost/vdpa.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)
drivers/vhost/vdpa.c +10 -8
@@ -39,6 +39,7 @@ struct vhost_vdpa {struct vhost_virtqueue *vqs;struct completion completion;struct vdpa_device *vdpa; +struct vhost_iotlb *iotlb;struct device dev;struct cdev cdev;atomic_t opened;
@@ -555,12 +556,11 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) { -struct vhost_dev *dev = &v->vdev; -struct vhost_iotlb *iotlb = dev->iotlb; +struct vhost_iotlb *iotlb = v->iotlb;vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 ); -kfree (dev->iotlb); - dev->iotlb =NULL ; +kfree (v->iotlb); + v->iotlb =NULL ; }static int perm_to_iommu_flags (u32 perm)
@@ -842,7 +842,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, 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 = dev->iotlb; +struct vhost_iotlb *iotlb = v->iotlb;int r =0 ;mutex_lock (&dev->mutex);
@@ -982,15 +982,15 @@ 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) { + v->iotlb =vhost_iotlb_alloc (0 ,0 ); +if (!v->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);
@@ -998,6 +998,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; +err_alloc_domain: +vhost_vdpa_iotlb_free (v); err_init_iotlb:vhost_dev_cleanup (&v->vdev);kfree (vqs);
Signature · 1 line
2.25.0
RFC PATCH v2 5/19 vdpa: introduce virtqueue groups
In reply to Gautam DawarThis patch introduces virtqueue groups to vDPA device. The virtqueue group is the minimal set of virtqueues that must share an address space. And the address space identifier could only be attached to a specific virtqueue group.
--- drivers/vdpa/ifcvf/ifcvf_main.c | 8 +++++++- drivers/vdpa/mlx5/net/mlx5_vnet.c | 8 +++++++- drivers/vdpa/vdpa.c | 3 +++ drivers/vdpa/vdpa_sim/vdpa_sim.c | 9 ++++++++- drivers/vdpa/vdpa_sim/vdpa_sim.h | 1 + include/linux/vdpa.h | 16 ++++++++++++---- 6 files changed, 38 insertions(+), 7 deletions(-)
drivers/vdpa/ifcvf/ifcvf_main.c +7 -1
@@ -378,6 +378,11 @@ static size_t ifcvf_vdpa_get_config_size(struct vdpa_device *vdpa_dev)return vf->config_size; } +static u32 ifcvf_vdpa_get_vq_group (struct vdpa_device *vdpa,u16 idx) +{ +return 0 ; +} +static void ifcvf_vdpa_get_config (struct vdpa_device *vdpa_dev,unsigned int offset,void *buf,unsigned int len)
@@ -453,6 +458,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = { .get_device_id = ifcvf_vdpa_get_device_id, .get_vendor_id = ifcvf_vdpa_get_vendor_id, .get_vq_align = ifcvf_vdpa_get_vq_align, + .get_vq_group = ifcvf_vdpa_get_vq_group, .get_config_size = ifcvf_vdpa_get_config_size, .get_config = ifcvf_vdpa_get_config, .set_config = ifcvf_vdpa_set_config,
@@ -507,7 +513,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, pdev = ifcvf_mgmt_dev->pdev; dev = &pdev->dev; adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops, name, false); + dev, &ifc_vdpa_ops,1 , name, false);if (IS_ERR (adapter)) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" );return PTR_ERR (adapter);
drivers/vdpa/mlx5/net/mlx5_vnet.c +7 -1
@@ -1847,6 +1847,11 @@ static u32 mlx5_vdpa_get_vq_align(struct vdpa_device *vdev)return PAGE_SIZE ; } +static u32 mlx5_vdpa_get_vq_group (struct vdpa_device *vdpa,u16 idx) +{ +return 0 ; +} +enum {MLX5_VIRTIO_NET_F_GUEST_CSUM =1 <<9 ,MLX5_VIRTIO_NET_F_CSUM =1 <<10 ,MLX5_VIRTIO_NET_F_HOST_TSO6 =1 <<11 ,
@@ -2363,6 +2368,7 @@ 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_vq_group = mlx5_vdpa_get_vq_group, .get_device_features = mlx5_vdpa_get_device_features, .set_driver_features = mlx5_vdpa_set_driver_features, .get_driver_features = mlx5_vdpa_get_driver_features,
@@ -2575,7 +2581,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, } ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, - name, false); +1 , name, false);if (IS_ERR (ndev))return PTR_ERR (ndev);
drivers/vdpa/vdpa.c +3 -0
@@ -159,6 +159,7 @@ 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 * @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
@@ -171,6 +172,7 @@ static void vdpa_release_dev(struct device *d)*/ struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, +unsigned int ngroups,size_t size,const char *name,bool use_va) {
@@ -203,6 +205,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->config = config; vdev->features_valid = false; vdev->use_va = use_va; + vdev->ngroups = ngroups;if (name) err =dev_set_name (&vdev->dev,"%s" , name);
drivers/vdpa/vdpa_sim/vdpa_sim.c +8 -1
@@ -250,7 +250,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)else ops = &vdpasim_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim);
@@ -399,6 +399,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)return VDPASIM_QUEUE_ALIGN ; } +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);
@@ -620,6 +625,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_vq_state = vdpasim_set_vq_state, .get_vq_state = vdpasim_get_vq_state, .get_vq_align = vdpasim_get_vq_align, + .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,
@@ -650,6 +656,7 @@ static const struct vdpa_config_ops vdpasim_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_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,
drivers/vdpa/vdpa_sim/vdpa_sim.h +1 -0
@@ -63,6 +63,7 @@ struct vdpasim {u32 status;u32 generation;u64 features; +u32 groups;/* spinlock to synchronize iommu table */ spinlock_t iommu_lock; };
include/linux/vdpa.h +12 -4
@@ -85,6 +85,7 @@ struct vdpa_device {bool use_va;int nvqs;struct vdpa_mgmt_dev *mdev; +unsigned int ngroups; };/**
@@ -172,6 +173,10 @@ struct vdpa_map_file {* for the device * @vdev: vdpa device * Returns virtqueue algin requirement +* @get_vq_group: Get the group id for a specific virtqueue +* @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
@@ -282,6 +287,7 @@ struct vdpa_config_ops {/* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); +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);
@@ -314,6 +320,7 @@ struct vdpa_config_ops {struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, +unsigned int ngroups,size_t size,const char *name,bool use_va);
@@ -324,17 +331,18 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,* @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 * @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, name, use_va) \ - container_of(__vdpa_alloc_device( \ - parent, config, \ +#define vdpa_alloc_device (dev_struct, member, parent, config, ngroups, name, use_va) \ + container_of((__vdpa_alloc_device( \ + parent, config, ngroups, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va), \ + dev_struct, member)), name, use_va)), \ dev_struct, member)int vdpa_register_device (struct vdpa_device *vdev,int nvqs);
Signature · 1 line
2.25.0
Re: [RFC PATCH v2 05/19] vdpa: introduce virtqueue groups
Quoted 7 lines · Gautam Dawar
This patch introduces virtqueue groups to vDPA device. The virtqueue group is the minimal set of virtqueues that must share an address space. And the address space identifier could only be attached to a specific virtqueue group.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>
Quoted 8 lines
--- drivers/vdpa/ifcvf/ifcvf_main.c | 8 +++++++- drivers/vdpa/mlx5/net/mlx5_vnet.c | 8 +++++++- drivers/vdpa/vdpa.c | 3 +++ drivers/vdpa/vdpa_sim/vdpa_sim.c | 9 ++++++++- drivers/vdpa/vdpa_sim/vdpa_sim.h | 1 + include/linux/vdpa.h | 16 ++++++++++++---- 6 files changed, 38 insertions(+), 7 deletions(-)
We had three more parents now, so we should convert them as well:
vp_vdpa, VDUSE and eni_vdpa.
Thanks
Quoted 210 lines
drivers/vdpa/ifcvf/ifcvf_main.c +7
-1@@ -378,6 +378,11 @@ static size_t ifcvf_vdpa_get_config_size(struct vdpa_device *vdpa_dev)return vf->config_size; } +static u32 ifcvf_vdpa_get_vq_group (struct vdpa_device *vdpa,u16 idx) +{ +return 0 ; +} +static void ifcvf_vdpa_get_config (struct vdpa_device *vdpa_dev,unsigned int offset,void *buf,unsigned int len)@@ -453,6 +458,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = { .get_device_id = ifcvf_vdpa_get_device_id, .get_vendor_id = ifcvf_vdpa_get_vendor_id, .get_vq_align = ifcvf_vdpa_get_vq_align, + .get_vq_group = ifcvf_vdpa_get_vq_group, .get_config_size = ifcvf_vdpa_get_config_size, .get_config = ifcvf_vdpa_get_config, .set_config = ifcvf_vdpa_set_config,@@ -507,7 +513,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, pdev = ifcvf_mgmt_dev->pdev; dev = &pdev->dev; adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops, name, false); + dev, &ifc_vdpa_ops,1 , name, false);if (IS_ERR (adapter)) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" );return PTR_ERR (adapter);drivers/vdpa/mlx5/net/mlx5_vnet.c +7
-1@@ -1847,6 +1847,11 @@ static u32 mlx5_vdpa_get_vq_align(struct vdpa_device *vdev)return PAGE_SIZE ; } +static u32 mlx5_vdpa_get_vq_group (struct vdpa_device *vdpa,u16 idx) +{ +return 0 ; +} +enum {MLX5_VIRTIO_NET_F_GUEST_CSUM =1 <<9 ,MLX5_VIRTIO_NET_F_CSUM =1 <<10 ,MLX5_VIRTIO_NET_F_HOST_TSO6 =1 <<11 ,@@ -2363,6 +2368,7 @@ 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_vq_group = mlx5_vdpa_get_vq_group, .get_device_features = mlx5_vdpa_get_device_features, .set_driver_features = mlx5_vdpa_set_driver_features, .get_driver_features = mlx5_vdpa_get_driver_features,@@ -2575,7 +2581,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, } ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, - name, false); +1 , name, false);if (IS_ERR (ndev))return PTR_ERR (ndev);drivers/vdpa/vdpa.c +3
-0@@ -159,6 +159,7 @@ 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 * @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 @@ -171,6 +172,7 @@ static void vdpa_release_dev(struct device *d)*/ struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, +unsigned int ngroups,size_t size,const char *name,bool use_va) {@@ -203,6 +205,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->config = config; vdev->features_valid = false; vdev->use_va = use_va; + vdev->ngroups = ngroups;if (name) err =dev_set_name (&vdev->dev,"%s" , name);drivers/vdpa/vdpa_sim/vdpa_sim.c +8
-1@@ -250,7 +250,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)else ops = &vdpasim_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim);@@ -399,6 +399,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)return VDPASIM_QUEUE_ALIGN ; } +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);@@ -620,6 +625,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_vq_state = vdpasim_set_vq_state, .get_vq_state = vdpasim_get_vq_state, .get_vq_align = vdpasim_get_vq_align, + .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,@@ -650,6 +656,7 @@ static const struct vdpa_config_ops vdpasim_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_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,drivers/vdpa/vdpa_sim/vdpa_sim.h +1
-0@@ -63,6 +63,7 @@ struct vdpasim {u32 status;u32 generation;u64 features; +u32 groups;/* spinlock to synchronize iommu table */ spinlock_t iommu_lock; };include/linux/vdpa.h +12
-4@@ -85,6 +85,7 @@ struct vdpa_device {bool use_va;int nvqs;struct vdpa_mgmt_dev *mdev; +unsigned int ngroups; };/** @@ -172,6 +173,10 @@ struct vdpa_map_file {* for the device * @vdev: vdpa device * Returns virtqueue algin requirement +* @get_vq_group: Get the group id for a specific virtqueue +* @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 @@ -282,6 +287,7 @@ struct vdpa_config_ops {/* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); +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);@@ -314,6 +320,7 @@ struct vdpa_config_ops {struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, +unsigned int ngroups,size_t size,const char *name,bool use_va);@@ -324,17 +331,18 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,* @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 * @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, name, use_va) \ - container_of(__vdpa_alloc_device( \ - parent, config, \ +#define vdpa_alloc_device (dev_struct, member, parent, config, ngroups, name, use_va) \ + container_of((__vdpa_alloc_device( \ + parent, config, ngroups, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va), \ + dev_struct, member)), name, use_va)), \ dev_struct, member)int vdpa_register_device (struct vdpa_device *vdev,int nvqs);
RE: [RFC PATCH v2 05/19] vdpa: introduce virtqueue groups
Quoted 7 lines · Gautam Dawar
This patch introduces virtqueue groups to vDPA device. The virtqueue group is the minimal set of virtqueues that must share an address space. And the address space identifier could only be attached to a specific virtqueue group.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>
Quoted 8 lines
--- drivers/vdpa/ifcvf/ifcvf_main.c | 8 +++++++- drivers/vdpa/mlx5/net/mlx5_vnet.c | 8 +++++++- drivers/vdpa/vdpa.c | 3 +++ drivers/vdpa/vdpa_sim/vdpa_sim.c | 9 ++++++++- drivers/vdpa/vdpa_sim/vdpa_sim.h | 1 + include/linux/vdpa.h | 16 ++++++++++++---- 6 files changed, 38 insertions(+), 7 deletions(-)
We had three more parents now, so we should convert them as well:
vp_vdpa, VDUSE and eni_vdpa.
[GD>>] I agree. However, the intention of publishing this as a RFC series is to gather feedback on the approach in the cover letter and at the same time to test its integration with both a simulator (vdpa_sim) and an actual (Xilinx SmartNIC) HW device with a development build of QEMU supporting Shadow virtqueue by Eugnio. Once this is approved, we can move to the actual patch series covering all other vdpa parent drivers.
Thanks
Quoted 212 lines
(quoted diff) +0
-0
b/drivers/vdpa/ifcvf/ifcvf_main.cindexd1a6b5ab543c..c815a2e62440100644drivers/vdpa/ifcvf/ifcvf_main.c renamed from drivers/vdpa/ifcvf/ifcvf_m +7
-1@@ -378,6 +378,11 @@ static size_t ifcvf_vdpa_get_config_size(struct vdpa_device *vdpa_dev)return vf->config_size; } +static u32 ifcvf_vdpa_get_vq_group (struct vdpa_device *vdpa,u16 idx) +{ +return 0 ; +} +static void ifcvf_vdpa_get_config (struct vdpa_device *vdpa_dev,unsigned int offset,void *buf,unsigned int len)@@ -453,6 +458,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = { .get_device_id = ifcvf_vdpa_get_device_id, .get_vendor_id = ifcvf_vdpa_get_vendor_id, .get_vq_align = ifcvf_vdpa_get_vq_align, + .get_vq_group = ifcvf_vdpa_get_vq_group, .get_config_size = ifcvf_vdpa_get_config_size, .get_config = ifcvf_vdpa_get_config, .set_config = ifcvf_vdpa_set_config,@@ -507,7 +513,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, pdev = ifcvf_mgmt_dev->pdev; dev = &pdev->dev; adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops, name, false); + dev, &ifc_vdpa_ops,1 , name, false);if (IS_ERR (adapter)) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" );return PTR_ERR (adapter);drivers/vdpa/mlx5/net/mlx5_vnet.c +5
-0@@ -1847,6 +1847,11 @@ static u32 mlx5_vdpa_get_vq_align(struct vdpa_device *vdev)return PAGE_SIZE ; } +static u32 mlx5_vdpa_get_vq_group (struct vdpa_device *vdpa,u16 idx) +{ +return 0 ; +} +enum {MLX5_VIRTIO_NET_F_GUEST_CSUM =1 <<9 ,MLX5_VIRTIO_NET_F_CSUM =1 <<10 , MLX5_VIRTIO_NET_F_HOST_TSO6 = 1 << 11, @@ -2363,6 +2368,7 @@ staticconst struct
vdpa_config_opsmlx5_vdpa_ops= {
.get_vq_notification =mlx5_get_vq_notification, .get_vq_irq =mlx5_get_vq_irq, .get_vq_align =mlx5_vdpa_get_vq_align,drivers/vdpa/mlx5/net/mlx5_vnet.c +3
-1+ .get_vq_group = mlx5_vdpa_get_vq_group, .get_device_features = mlx5_vdpa_get_device_features, .set_driver_features = mlx5_vdpa_set_driver_features, .get_driver_features = mlx5_vdpa_get_driver_features, @@ -2575,7 +2581,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, } ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, - name, false); +1 , name, false);if (IS_ERR (ndev))return PTR_ERR (ndev);drivers/vdpa/vdpa.c index renamed from drivers/vdpa/vdpa.c +0
-0
9846c9de4bfa..a07bf0130559100644drivers/vdpa/vdpa.c +1
-0@@ -159,6 +159,7 @@ 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 * @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 @@ -171,6 +172,7 @@ static void
vdpa_release_dev(struct device *d)
*/
structvdpa_device*__vdpa_alloc_device(struct device *parent,
const structvdpa_config_ops*config,drivers/vdpa/vdpa.c +2
-0+unsigned int ngroups, size_t size, const char *name, bool use_va) {@@ -203,6 +205,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->config = config; vdev->features_valid = false; vdev->use_va = use_va; + vdev->ngroups = ngroups;if (name) err = dev_set_name(&vdev->dev, "%s", name); diff --git
a/drivers/vdpa/vdpa_sim/vdpa_sim.cb/drivers/vdpa/vdpa_sim/vdpa_sim.cindexddbe142af09a..c98cb1f869fa100644drivers/vdpa/vdpa_sim/vdpa_sim.c +5
-1@@ -250,7 +250,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)else ops = &vdpasim_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim);@@ -399,6 +399,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)return VDPASIM_QUEUE_ALIGN ; } +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); @@ -620,6 +625,7 @@static const struct
vdpa_config_opsvdpasim_config_ops= {.set_vq_state = vdpasim_set_vq_state, .get_vq_state = vdpasim_get_vq_state, .get_vq_align = vdpasim_get_vq_align,drivers/vdpa/vdpa_sim/vdpa_sim.c +2
-0+ .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,@@ -650,6 +656,7 @@ static const struct vdpa_config_ops vdpasim_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_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,drivers/vdpa/vdpa_sim/vdpa_sim.h +1
-0@@ -63,6 +63,7 @@ struct vdpasim {u32 status;u32 generation;u64 features; +u32 groups;/* spinlock to synchronize iommu table */ spinlock_t iommu_lock; };include/linux/vdpa.h index renamed from include/linux/vdpa.h +0
-0
2de442ececae..026b7ad72ed7100644include/linux/vdpa.h +13
-4@@ -85,6 +85,7 @@ struct vdpa_device {bool use_va;int nvqs;struct vdpa_mgmt_dev *mdev; +unsigned int ngroups; };/** @@ -172,6 +173,10 @@ struct vdpa_map_file {* for the device * @vdev: vdpa device * Returns virtqueue algin requirement +* @get_vq_group: Get the group id for a specific virtqueue +* @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 @@ -282,6 +287,7 @@ struct vdpa_config_ops {/* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); +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); @@ -314,6 +320,7 @@ struct vdpa_config_ops {struct vdpa_device *__vdpa_alloc_device(struct device *parent,const struct vdpa_config_ops *config, +unsigned int ngroups,size_t size,const char *name,bool use_va);@@ -324,17 +331,18 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,* @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 * @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, name, use_va) \ - container_of(__vdpa_alloc_device( \ - parent, config, \ +#define vdpa_alloc_device (dev_struct, member, parent, config, ngroups, name, use_va) \ + container_of((__vdpa_alloc_device( \ + parent, config, ngroups, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va), \ + dev_struct, member)), name, use_va)), \ dev_struct, member)int vdpa_register_device (struct vdpa_device *vdev,int nvqs);
RFC PATCH v2 6/19 vdpa: multiple address spaces support
In reply to Gautam DawarThis patches introduces the multiple address spaces support for vDPA device. This idea is to identify a specific address space via an dedicated identifier - ASID.
During vDPA device allocation, vDPA device driver needs to report the number of address spaces supported by the device then the DMA mapping ops of the vDPA device needs to be extended to support ASID.
This helps to isolate the environments for the virtqueue that will not be assigned directly. E.g in the case of virtio-net, the control virtqueue will not be assigned directly to guest.
As a start, simply claim 1 virtqueue groups and 1 address spaces for all vDPA devices. And vhost-vDPA will simply reject the device with more than 1 virtqueue groups or address spaces.
--- drivers/vdpa/ifcvf/ifcvf_main.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 +++-- drivers/vdpa/vdpa.c | 4 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 10 ++++++---- drivers/vhost/vdpa.c | 14 +++++++++----- include/linux/vdpa.h | 28 +++++++++++++++++++--------- 6 files changed, 41 insertions(+), 22 deletions(-)
drivers/vdpa/ifcvf/ifcvf_main.c +1 -1
@@ -513,7 +513,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, pdev = ifcvf_mgmt_dev->pdev; dev = &pdev->dev; adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops,1 , name, false); + dev, &ifc_vdpa_ops,1 ,1 , name, false);if (IS_ERR (adapter)) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" );return PTR_ERR (adapter);
drivers/vdpa/mlx5/net/mlx5_vnet.c +3 -2
@@ -2282,7 +2282,8 @@ 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);bool change_map;
@@ -2581,7 +2582,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, } ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, -1 , name, false); +1 ,1 , name, false);if (IS_ERR (ndev))return PTR_ERR (ndev);
drivers/vdpa/vdpa.c +3 -1
@@ -160,6 +160,7 @@ static void vdpa_release_dev(struct device *d)* @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
@@ -172,7 +173,7 @@ static void vdpa_release_dev(struct device *d)*/ struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, -unsigned int ngroups, +unsigned int ngroups,unsigned int nas,size_t size,const char *name,bool use_va) {
@@ -206,6 +207,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, 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);
drivers/vdpa/vdpa_sim/vdpa_sim.c +6 -4
@@ -251,7 +251,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) ops = &vdpasim_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, - dev_attr->name, false); +1 , dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim); goto err_alloc;
@@ -539,7 +539,7 @@ 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);
@@ -566,7 +566,8 @@ static int vdpasim_set_map(struct vdpa_device *vdpa,return ret; } -static int vdpasim_dma_map (struct vdpa_device *vdpa,u64 iova,u64 size, +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);
@@ -580,7 +581,8 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,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);
drivers/vhost/vdpa.c +9 -5
@@ -599,10 +599,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r;if (ops->dma_map) { - r = ops->dma_map (vdpa, iova, size, pa, perm, opaque); + r = ops->dma_map (vdpa,0 , iova, size, pa, perm, opaque); }else if (ops->set_map) {if (!v->in_batch) - r = ops->set_map (vdpa, iotlb); + r = ops->set_map (vdpa,0 , iotlb); }else { r =iommu_map (v->domain, iova, pa, size,perm_to_iommu_flags (perm));
@@ -628,10 +628,10 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v,vhost_vdpa_iotlb_unmap (v, iotlb, iova, iova + size -1 );if (ops->dma_map) { - ops->dma_unmap (vdpa, iova, size); + ops->dma_unmap (vdpa,0 , iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); }else {iommu_unmap (v->domain, iova, size); }
@@ -863,7 +863,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,break ;case VHOST_IOTLB_BATCH_END :if (v->in_batch && ops->set_map) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); v->in_batch = false;break ;default :
@@ -1128,6 +1128,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int r; +/* Only support 1 address space and 1 groups */ +if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +return -EOPNOTSUPP ; + v =kzalloc (sizeof (*v),GFP_KERNEL | __GFP_RETRY_MAYFAIL);if (!v)return -ENOMEM ;
include/linux/vdpa.h +19 -9
@@ -69,6 +69,8 @@ struct vdpa_mgmt_dev;* @cf_mutex: 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
@@ -86,6 +88,7 @@ struct vdpa_device {int nvqs;struct vdpa_mgmt_dev *mdev;unsigned int ngroups; +unsigned int nas; };/**
@@ -240,6 +243,7 @@ struct vdpa_map_file {* 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)
@@ -248,6 +252,7 @@ struct vdpa_map_file {* 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
@@ -259,6 +264,7 @@ struct vdpa_map_file {* 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)
@@ -309,10 +315,12 @@ 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,void *opaque); -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);/* Free device resources */ void (*free)(struct vdpa_device *vdev);
@@ -320,7 +328,7 @@ struct vdpa_config_ops {struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, -unsigned int ngroups, +unsigned int ngroups,unsigned int nas,size_t size,const char *name,bool use_va);
@@ -332,17 +340,19 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,* @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, name, use_va) \ +#define vdpa_alloc_device (dev_struct, member, parent, config, ngroups, nas, \ + name, use_va) \ container_of((__vdpa_alloc_device( \ - parent, config, ngroups, \ - sizeof(dev_struct) + \ + parent, config, ngroups, nas, \ + (sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va)), \ + dev_struct, member))), name, use_va)), \ dev_struct, member)int vdpa_register_device (struct vdpa_device *vdev,int nvqs);
Signature · 1 line
2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 06/19] vdpa: multiple address spaces support
Quoted 264 lines · Gautam Dawar
This patches introduces the multiple address spaces support for vDPA device. This idea is to identify a specific address space via an dedicated identifier - ASID.
During vDPA device allocation, vDPA device driver needs to report the number of address spaces supported by the device then the DMA mapping ops of the vDPA device needs to be extended to support ASID.
This helps to isolate the environments for the virtqueue that will not be assigned directly. E.g in the case of virtio-net, the control virtqueue will not be assigned directly to guest.
As a start, simply claim 1 virtqueue groups and 1 address spaces for all vDPA devices. And vhost-vDPA will simply reject the device with more than 1 virtqueue groups or address spaces.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vdpa/ifcvf/ifcvf_main.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 +++-- drivers/vdpa/vdpa.c | 4 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 10 ++++++---- drivers/vhost/vdpa.c | 14 +++++++++----- include/linux/vdpa.h | 28 +++++++++++++++++++--------- 6 files changed, 41 insertions(+), 22 deletions(-)drivers/vdpa/ifcvf/ifcvf_main.c +1
-1@@ -513,7 +513,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, pdev = ifcvf_mgmt_dev->pdev; dev = &pdev->dev; adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops,1 , name, false); + dev, &ifc_vdpa_ops,1 ,1 , name, false);if (IS_ERR (adapter)) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" );return PTR_ERR (adapter);drivers/vdpa/mlx5/net/mlx5_vnet.c +3
-2@@ -2282,7 +2282,8 @@ 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);bool change_map;@@ -2581,7 +2582,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, } ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, -1 , name, false); +1 ,1 , name, false);if (IS_ERR (ndev))return PTR_ERR (ndev);drivers/vdpa/vdpa.c +3
-1@@ -160,6 +160,7 @@ static void vdpa_release_dev(struct device *d)* @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 @@ -172,7 +173,7 @@ static void vdpa_release_dev(struct device *d)*/ struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, -unsigned int ngroups, +unsigned int ngroups,unsigned int nas,size_t size,const char *name,bool use_va) {@@ -206,6 +207,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, 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);drivers/vdpa/vdpa_sim/vdpa_sim.c +6
-4@@ -251,7 +251,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) ops = &vdpasim_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, - dev_attr->name, false); +1 , dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim); goto err_alloc;@@ -539,7 +539,7 @@ 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);@@ -566,7 +566,8 @@ static int vdpasim_set_map(struct vdpa_device *vdpa,return ret; } -static int vdpasim_dma_map (struct vdpa_device *vdpa,u64 iova,u64 size, +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);@@ -580,7 +581,8 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,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);drivers/vhost/vdpa.c +9
-5@@ -599,10 +599,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r;if (ops->dma_map) { - r = ops->dma_map (vdpa, iova, size, pa, perm, opaque); + r = ops->dma_map (vdpa,0 , iova, size, pa, perm, opaque); }else if (ops->set_map) {if (!v->in_batch) - r = ops->set_map (vdpa, iotlb); + r = ops->set_map (vdpa,0 , iotlb); }else { r =iommu_map (v->domain, iova, pa, size,perm_to_iommu_flags (perm));@@ -628,10 +628,10 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v,vhost_vdpa_iotlb_unmap (v, iotlb, iova, iova + size -1 );if (ops->dma_map) { - ops->dma_unmap (vdpa, iova, size); + ops->dma_unmap (vdpa,0 , iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); }else {iommu_unmap (v->domain, iova, size); }@@ -863,7 +863,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,break ;case VHOST_IOTLB_BATCH_END :if (v->in_batch && ops->set_map) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); v->in_batch = false;break ;default :@@ -1128,6 +1128,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int r; +/* Only support 1 address space and 1 groups */ +if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +return -EOPNOTSUPP ; + v =kzalloc (sizeof (*v),GFP_KERNEL | __GFP_RETRY_MAYFAIL);if (!v)return -ENOMEM ;include/linux/vdpa.h +14
-5@@ -69,6 +69,8 @@ struct vdpa_mgmt_dev;* @cf_mutex: 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 @@ -86,6 +88,7 @@ struct vdpa_device {int nvqs;struct vdpa_mgmt_dev *mdev;unsigned int ngroups; +unsigned int nas; };/** @@ -240,6 +243,7 @@ struct vdpa_map_file {* 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) @@ -248,6 +252,7 @@ struct vdpa_map_file {* 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 @@ -259,6 +264,7 @@ struct vdpa_map_file {* 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) @@ -309,10 +315,12 @@ 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,void *opaque); -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);/* Free device resources */ void (*free)(struct vdpa_device *vdev);@@ -320,7 +328,7 @@ struct vdpa_config_ops {struct vdpa_device *__vdpa_alloc_device (struct device *parent,const struct vdpa_config_ops *config, -unsigned int ngroups, +unsigned int ngroups,unsigned int nas,size_t size,const char *name,bool use_va);@@ -332,17 +340,19 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,* @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 *
include/linux/vdpa.h struct vdpa_device *__vdpa_alloc_device(struct device *parent, · line 353
Quoted 10 lines
include/linux/vdpa.h +4
-3* Return allocated data structure or ERR_PTR upon error */ -#define vdpa_alloc_device (dev_struct, member, parent, config, ngroups, name, use_va) \ +#define vdpa_alloc_device (dev_struct, member, parent, config, ngroups, nas, \ + name, use_va) \ container_of((__vdpa_alloc_device( \ - parent, config, ngroups, \ - sizeof(dev_struct) + \ + parent, config, ngroups, nas, \ + (sizeof(dev_struct) + \
Maybe too nitpick or I'm missing something, but do we need to add the parentheses around (sizeof(dev_struct) + BUILD_BUG_ON_ZERO(...)) ?
Quoted 9 lines
include/linux/vdpa.h +1
-2BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va)), \ + dev_struct, member))), name, use_va)), \ dev_struct, member)int vdpa_register_device (struct vdpa_device *vdev,int nvqs); --2.25.0
RE: [RFC PATCH v2 06/19] vdpa: multiple address spaces support
-----Original Message-----
From: Eugenio Perez Martin <[email protected]>
Sent: Friday, March 4, 2022 1:10 AM
To: Gautam Dawar <[email protected]>
Cc: Gautam Dawar <[email protected]>; Martin Petrus Hubertus Habets <[email protected]>; Harpreet Singh Anand <[email protected]>; Tanuj Murlidhar Kamde <[email protected]>; Jason Wang <[email protected]>; Michael S. Tsirkin <[email protected]>; Zhu Lingshan <[email protected]>; Stefano Garzarella <[email protected]>; Xie Yongji <[email protected]>; Eli Cohen <[email protected]>; Si-Wei Liu <[email protected]>; Parav Pandit <[email protected]>; Longpeng <[email protected]>; virtualization <[email protected]>; [email protected]; kvm list <[email protected]>; [email protected]
Subject: Re: [RFC PATCH v2 06/19] vdpa: multiple address spaces support
Quoted 272 lines · Gautam Dawar
This patches introduces the multiple address spaces support for vDPA device. This idea is to identify a specific address space via an dedicated identifier - ASID.
During vDPA device allocation, vDPA device driver needs to report the number of address spaces supported by the device then the DMA mapping ops of the vDPA device needs to be extended to support ASID.
This helps to isolate the environments for the virtqueue that will not be assigned directly. E.g in the case of virtio-net, the control virtqueue will not be assigned directly to guest.
As a start, simply claim 1 virtqueue groups and 1 address spaces for all vDPA devices. And vhost-vDPA will simply reject the device with more than 1 virtqueue groups or address spaces.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vdpa/ifcvf/ifcvf_main.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 +++-- drivers/vdpa/vdpa.c | 4 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 10 ++++++---- drivers/vhost/vdpa.c | 14 +++++++++----- include/linux/vdpa.h | 28 +++++++++++++++++++--------- 6 files changed, 41 insertions(+), 22 deletions(-)(quoted diff) +0
-0
b/drivers/vdpa/ifcvf/ifcvf_main.cindexc815a2e62440..a4815c5612f9100644drivers/vdpa/ifcvf/ifcvf_main.c +2
-1@@ -513,7 +513,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, pdev = ifcvf_mgmt_dev->pdev; dev = &pdev->dev; adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops,1 , name, false); + dev, &ifc_vdpa_ops,1 ,1 , name, + false);if (IS_ERR (adapter)) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" ); return PTR_ERR(adapter); diff --git
a/drivers/vdpa/mlx5/net/mlx5_vnet.cb/drivers/vdpa/mlx5/net/mlx5_vnet.c
indexfcfc28460b72..a76417892ef3100644drivers/vdpa/mlx5/net/mlx5_vnet.c +2
-1@@ -2282,7 +2282,8 @@ 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);bool change_map;drivers/vdpa/mlx5/net/mlx5_vnet.c +1
-1@@ -2581,7 +2582,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, } ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, -1 , name, false); +1 ,1 , name, false);if (IS_ERR (ndev))return PTR_ERR (ndev);drivers/vdpa/vdpa.c index renamed from drivers/vdpa/vdpa.c +0
-0
a07bf0130559..1793dc12b208100644drivers/vdpa/vdpa.c +1
-0@@ -160,6 +160,7 @@ static void vdpa_release_dev(struct device *d)* @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 @@ -172,7 +173,7 @@ static void
vdpa_release_dev(struct device *d)
*/
structvdpa_device*__vdpa_alloc_device(struct device *parent,
const structvdpa_config_ops*config,drivers/vdpa/vdpa.c +4
-1-unsigned int ngroups, +unsigned int ngroups, unsigned + int nas, size_t size, const char *name, bool use_va) { @@ -206,6 +207,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, 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); diff --git
a/drivers/vdpa/vdpa_sim/vdpa_sim.cb/drivers/vdpa/vdpa_sim/vdpa_sim.cindexc98cb1f869fa..659e2e2e4b0c100644drivers/vdpa/vdpa_sim/vdpa_sim.c +3
-2@@ -251,7 +251,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) ops = &vdpasim_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, - dev_attr->name, false); +1 , dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim); goto err_alloc;@@ -539,7 +539,7 @@ 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); @@ -566,7 +566,8@@ static int vdpasim_set_map(struct
vdpa_device*vdpa,return ret;}
-static int vdpasim_dma_map(struct
vdpa_device*vdpa, u64 iova, u64 size,drivers/vdpa/vdpa_sim/vdpa_sim.c +2
-0+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); @@ -580,7 +581,8@@ static int vdpasim_dma_map(struct
vdpa_device*vdpa, u64 iova, u64 size,return ret;}
-static int
vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size)drivers/vdpa/vdpa_sim/vdpa_sim.c +2
-0+static int vdpasim_dma_unmap (struct vdpa_device *vdpa,unsigned int asid, +u64 iova,u64 size) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);drivers/vhost/vdpa.c index renamed from drivers/vhost/vdpa.c +0
-0
655ff7029401..6bf755f84d26100644drivers/vhost/vdpa.c +11
-5@@ -599,10 +599,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r;if (ops->dma_map) { - r = ops->dma_map (vdpa, iova, size, pa, perm, opaque); + r = ops->dma_map (vdpa,0 , iova, size, pa, perm, + opaque); }else if (ops->set_map) {if (!v->in_batch) - r = ops->set_map (vdpa, iotlb); + r = ops->set_map (vdpa,0 , iotlb); }else { r =iommu_map (v->domain, iova, pa, size, perm_to_iommu_flags(perm)); @@ -628,10 +628,10 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);if (ops->dma_map) { - ops->dma_unmap (vdpa, iova, size); + ops->dma_unmap (vdpa,0 , iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); }else {iommu_unmap (v->domain, iova, size); }@@ -863,7 +863,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,break ;case VHOST_IOTLB_BATCH_END :if (v->in_batch && ops->set_map) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); v->in_batch = false;break ;default :@@ -1128,6 +1128,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int r; +/* Only support 1 address space and 1 groups */ +if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +return -EOPNOTSUPP ; + v =kzalloc (sizeof (*v),GFP_KERNEL | __GFP_RETRY_MAYFAIL);if (!v)return -ENOMEM ;include/linux/vdpa.h index renamed from include/linux/vdpa.h +0
-0
026b7ad72ed7..de22ca1a8ef3100644include/linux/vdpa.h +2
-0@@ -69,6 +69,8 @@ struct vdpa_mgmt_dev;* @cf_mutex: 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 @@ -86,6 +88,7 @@ struct vdpa_device { int nvqs; struct vdpa_mgmt_dev *mdev; unsigned int ngroups;include/linux/vdpa.h +10
-4+unsigned int nas; };/** @@ -240,6 +243,7 @@ struct vdpa_map_file {* 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) @@ -248,6 +252,7 @@ struct vdpa_map_file {* 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 @@ -259,6 +264,7 @@ struct vdpa_map_file {* 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) @@ -309,10 +315,12 @@ 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,void *opaque); -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);/* Free device resources */ void (*free)(struct vdpa_device *vdev); @@ -320,7 +328,7 @@struct
vdpa_config_ops{struct
vdpa_device*__vdpa_alloc_device(struct device *parent,
const structvdpa_config_ops*config,include/linux/vdpa.h +3
-1-unsigned int ngroups, +unsigned int ngroups, unsigned + int nas, size_t size, const char *name, bool use_va);@@ -332,17 +340,19 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,* @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 *
include/linux/vdpa.h struct vdpa_device *__vdpa_alloc_device(struct device *parent, · line 353
Quoted 10 lines
include/linux/vdpa.h +4
-3* Return allocated data structure or ERR_PTR upon error */ -#define vdpa_alloc_device (dev_struct, member, parent, config, ngroups, name, use_va) \ +#define vdpa_alloc_device (dev_struct, member, parent, config, ngroups, nas, \ + name, use_va) \ container_of((__vdpa_alloc_device( \ - parent, config, ngroups, \ - sizeof(dev_struct) + \ + parent, config, ngroups, nas, \ + (sizeof(dev_struct) + \
Maybe too nitpick or I'm missing something, but do we need to add the parentheses around (sizeof(dev_struct) + BUILD_BUG_ON_ZERO(...)) ? [GD>>] Yes, that's required as without it checkpatch reports "ERROR: Macros with complex values should be enclosed in parentheses"
Quoted 10 lines
include/linux/vdpa.h +2
-2BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va)), \ + dev_struct, member))), name, + use_va)), \ dev_struct, member)int vdpa_register_device (struct vdpa_device *vdev,int nvqs); --2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 06/19] vdpa: multiple address spaces support
Quoted 286 lines · Gautam Dawar
-----Original Message-----
From: Eugenio Perez Martin <[email protected]>
Sent: Friday, March 4, 2022 1:10 AM
To: Gautam Dawar <[email protected]>
Cc: Gautam Dawar <[email protected]>; Martin Petrus Hubertus Habets <[email protected]>; Harpreet Singh Anand <[email protected]>; Tanuj Murlidhar Kamde <[email protected]>; Jason Wang <[email protected]>; Michael S. Tsirkin <[email protected]>; Zhu Lingshan <[email protected]>; Stefano Garzarella <[email protected]>; Xie Yongji <[email protected]>; Eli Cohen <[email protected]>; Si-Wei Liu <[email protected]>; Parav Pandit <[email protected]>; Longpeng <[email protected]>; virtualization <[email protected]>; [email protected]; kvm list <[email protected]>; [email protected]
Subject: Re: [RFC PATCH v2 06/19] vdpa: multiple address spaces supportQuoted 277 lines · Gautam Dawar
This patches introduces the multiple address spaces support for vDPA device. This idea is to identify a specific address space via an dedicated identifier - ASID.
During vDPA device allocation, vDPA device driver needs to report the number of address spaces supported by the device then the DMA mapping ops of the vDPA device needs to be extended to support ASID.
This helps to isolate the environments for the virtqueue that will not be assigned directly. E.g in the case of virtio-net, the control virtqueue will not be assigned directly to guest.
As a start, simply claim 1 virtqueue groups and 1 address spaces for all vDPA devices. And vhost-vDPA will simply reject the device with more than 1 virtqueue groups or address spaces.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vdpa/ifcvf/ifcvf_main.c | 2 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 +++-- drivers/vdpa/vdpa.c | 4 +++- drivers/vdpa/vdpa_sim/vdpa_sim.c | 10 ++++++---- drivers/vhost/vdpa.c | 14 +++++++++----- include/linux/vdpa.h | 28 +++++++++++++++++++--------- 6 files changed, 41 insertions(+), 22 deletions(-)(quoted diff) +0
-0
b/drivers/vdpa/ifcvf/ifcvf_main.cindexc815a2e62440..a4815c5612f9100644drivers/vdpa/ifcvf/ifcvf_main.c +2
-1@@ -513,7 +513,7 @@ static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, pdev = ifcvf_mgmt_dev->pdev; dev = &pdev->dev; adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops,1 , name, false); + dev, &ifc_vdpa_ops,1 ,1 , name, + false);if (IS_ERR (adapter)) {IFCVF_ERR (pdev,"Failed to allocate vDPA structure" ); return PTR_ERR(adapter); diff --git
a/drivers/vdpa/mlx5/net/mlx5_vnet.cb/drivers/vdpa/mlx5/net/mlx5_vnet.c
indexfcfc28460b72..a76417892ef3100644drivers/vdpa/mlx5/net/mlx5_vnet.c +2
-1@@ -2282,7 +2282,8 @@ 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);bool change_map;drivers/vdpa/mlx5/net/mlx5_vnet.c +1
-1@@ -2581,7 +2582,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, } ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, -1 , name, false); +1 ,1 , name, false);if (IS_ERR (ndev))return PTR_ERR (ndev);drivers/vdpa/vdpa.c index renamed from drivers/vdpa/vdpa.c +0
-0
a07bf0130559..1793dc12b208100644drivers/vdpa/vdpa.c +1
-0@@ -160,6 +160,7 @@ static void vdpa_release_dev(struct device *d)* @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 @@ -172,7 +173,7 @@ static void
vdpa_release_dev(struct device *d)
*/
structvdpa_device*__vdpa_alloc_device(struct device *parent,
const structvdpa_config_ops*config,drivers/vdpa/vdpa.c +4
-1-unsigned int ngroups, +unsigned int ngroups, unsigned + int nas, size_t size, const char *name, bool use_va) { @@ -206,6 +207,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, 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); diff --git
a/drivers/vdpa/vdpa_sim/vdpa_sim.cb/drivers/vdpa/vdpa_sim/vdpa_sim.cindexc98cb1f869fa..659e2e2e4b0c100644drivers/vdpa/vdpa_sim/vdpa_sim.c +3
-2@@ -251,7 +251,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) ops = &vdpasim_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, - dev_attr->name, false); +1 , dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim); goto err_alloc;@@ -539,7 +539,7 @@ 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); @@ -566,7 +566,8@@ static int vdpasim_set_map(struct
vdpa_device*vdpa,return ret;}
-static int vdpasim_dma_map(struct
vdpa_device*vdpa, u64 iova, u64 size,drivers/vdpa/vdpa_sim/vdpa_sim.c +2
-0+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); @@ -580,7 +581,8@@ static int vdpasim_dma_map(struct
vdpa_device*vdpa, u64 iova, u64 size,return ret;}
-static int
vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size)drivers/vdpa/vdpa_sim/vdpa_sim.c +2
-0+static int vdpasim_dma_unmap (struct vdpa_device *vdpa,unsigned int asid, +u64 iova,u64 size) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);drivers/vhost/vdpa.c index renamed from drivers/vhost/vdpa.c +0
-0
655ff7029401..6bf755f84d26100644drivers/vhost/vdpa.c +11
-5@@ -599,10 +599,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r;if (ops->dma_map) { - r = ops->dma_map (vdpa, iova, size, pa, perm, opaque); + r = ops->dma_map (vdpa,0 , iova, size, pa, perm, + opaque); }else if (ops->set_map) {if (!v->in_batch) - r = ops->set_map (vdpa, iotlb); + r = ops->set_map (vdpa,0 , iotlb); }else { r =iommu_map (v->domain, iova, pa, size, perm_to_iommu_flags(perm)); @@ -628,10 +628,10 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);if (ops->dma_map) { - ops->dma_unmap (vdpa, iova, size); + ops->dma_unmap (vdpa,0 , iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); }else {iommu_unmap (v->domain, iova, size); }@@ -863,7 +863,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,break ;case VHOST_IOTLB_BATCH_END :if (v->in_batch && ops->set_map) - ops->set_map (vdpa, iotlb); + ops->set_map (vdpa,0 , iotlb); v->in_batch = false;break ;default :@@ -1128,6 +1128,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int r; +/* Only support 1 address space and 1 groups */ +if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +return -EOPNOTSUPP ; + v =kzalloc (sizeof (*v),GFP_KERNEL | __GFP_RETRY_MAYFAIL);if (!v)return -ENOMEM ;include/linux/vdpa.h index renamed from include/linux/vdpa.h +0
-0
026b7ad72ed7..de22ca1a8ef3100644include/linux/vdpa.h +2
-0@@ -69,6 +69,8 @@ struct vdpa_mgmt_dev;* @cf_mutex: 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 @@ -86,6 +88,7 @@ struct vdpa_device { int nvqs; struct vdpa_mgmt_dev *mdev; unsigned int ngroups;include/linux/vdpa.h +10
-4+unsigned int nas; };/** @@ -240,6 +243,7 @@ struct vdpa_map_file {* 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) @@ -248,6 +252,7 @@ struct vdpa_map_file {* 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 @@ -259,6 +264,7 @@ struct vdpa_map_file {* 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) @@ -309,10 +315,12 @@ 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,void *opaque); -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);/* Free device resources */ void (*free)(struct vdpa_device *vdev); @@ -320,7 +328,7 @@struct
vdpa_config_ops{struct
vdpa_device*__vdpa_alloc_device(struct device *parent,
const structvdpa_config_ops*config,include/linux/vdpa.h +5
-2-unsigned int ngroups, +unsigned int ngroups, unsigned + int nas, size_t size, const char *name, bool use_va);@@ -332,17 +340,19 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,* @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, name, use_va) \ +#define vdpa_alloc_device (dev_struct, member, parent, config, ngroups, nas, \ + name, use_va) \
Quoted 8 lines
include/linux/vdpa.h struct vdpa_device *__vdpa_alloc_device(struct device *parent, · line 353
Quoted 5 lines
include/linux/vdpa.h +2
-2container_of((__vdpa_alloc_device( \ - parent, config, ngroups, \ - sizeof(dev_struct) + \ + parent, config, ngroups, nas, \ + (sizeof(dev_struct) + \Maybe too nitpick or I'm missing something, but do we need to add the parentheses around (
sizeof(dev_struct)+BUILD_BUG_ON_ZERO(...)) ? [GD>>] Yes, that's required as without it checkpatch reports "ERROR: Macros with complex values should be enclosed in parentheses"
Interestingly, I cannot reproduce locally. But it's not something that matters a lot in my opinion.
Thanks!
Quoted 12 lines
Quoted 11 lines
include/linux/vdpa.h +2
-2BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va)), \ + dev_struct, member))), name, + use_va)), \ dev_struct, member)int vdpa_register_device (struct vdpa_device *vdev,int nvqs); --2.25.0
RFC PATCH v2 7/19 vdpa: introduce config operations for associating ASID to a virtqueue group
In reply to Gautam DawarThis patch introduces a new bus operation to allow the vDPA bus driver to associate an ASID to a virtqueue group.
--- include/linux/vdpa.h | 10 ++++++++++ 1 file changed, 10 insertions(+)
include/linux/vdpa.h +10 -0
@@ -239,6 +239,12 @@ struct vdpa_map_file {* @vdev: vdpa device * Returns the iova range supported by * the device. +* @set_group_asid: Set address space identifier for a +* virtqueue group +* @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)
@@ -321,6 +327,10 @@ struct vdpa_config_ops { 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);
Signature · 1 line
2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 07/19] vdpa: introduce config operations for associating ASID to a virtqueue group
Quoted 28 lines · Gautam Dawar
This patch introduces a new bus operation to allow the vDPA bus driver to associate an ASID to a virtqueue group.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- include/linux/vdpa.h | 10 ++++++++++ 1 file changed, 10 insertions(+)include/linux/vdpa.h +6
-0@@ -239,6 +239,12 @@ struct vdpa_map_file {* @vdev: vdpa device * Returns the iova range supported by * the device. +* @set_group_asid: Set address space identifier for a +* virtqueue group +* @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)
include/linux/vdpa.h struct vdpa_config_ops { · line 333
Quoted 7 lines
include/linux/vdpa.h +4
-0@@ -321,6 +327,10 @@ struct vdpa_config_ops { 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); + +
Nit again, and Jason's patch already contained these, but I think these two blank lines are introduced unintentionally.
Quoted 6 lines
include/linux/vdpa.h +0
-1/* Free device resources */ void (*free)(struct vdpa_device *vdev); --2.25.0
RE: [RFC PATCH v2 07/19] vdpa: introduce config operations for associating ASID to a virtqueue group
-----Original Message-----
From: Eugenio Perez Martin <[email protected]>
Sent: Friday, March 4, 2022 3:25 PM
To: Gautam Dawar <[email protected]>
Cc: Gautam Dawar <[email protected]>; Martin Petrus Hubertus Habets <[email protected]>; Harpreet Singh Anand <[email protected]>; Tanuj Murlidhar Kamde <[email protected]>; Jason Wang <[email protected]>; Michael S. Tsirkin <[email protected]>; Zhu Lingshan <[email protected]>; Stefano Garzarella <[email protected]>; Xie Yongji <[email protected]>; Eli Cohen <[email protected]>; Si-Wei Liu <[email protected]>; Parav Pandit <[email protected]>; Longpeng <[email protected]>; virtualization <[email protected]>; [email protected]; kvm list <[email protected]>; [email protected]
Subject: Re: [RFC PATCH v2 07/19] vdpa: introduce config operations for associating ASID to a virtqueue group
Quoted 28 lines · Gautam Dawar
This patch introduces a new bus operation to allow the vDPA bus driver to associate an ASID to a virtqueue group.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- include/linux/vdpa.h | 10 ++++++++++ 1 file changed, 10 insertions(+)include/linux/vdpa.h index renamed from include/linux/vdpa.h +0
-0
de22ca1a8ef3..7386860c3995100644include/linux/vdpa.h +6
-0@@ -239,6 +239,12 @@ struct vdpa_map_file {* @vdev: vdpa device * Returns the iova range supported by * the device. +* @set_group_asid: Set address space identifier for a +* virtqueue group +* @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)
include/linux/vdpa.h struct vdpa_config_ops { · line 333
Quoted 7 lines
include/linux/vdpa.h +4
-0@@ -321,6 +327,10 @@ struct vdpa_config_ops { 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); + +
Nit again, and Jason's patch already contained these, but I think these two blank lines are introduced unintentionally. [GD>>] Will fix this in the next revision.
Quoted 6 lines
include/linux/vdpa.h +0
-1/* Free device resources */ void (*free)(struct vdpa_device *vdev); --2.25.0
RFC PATCH v2 8/19 vhost_iotlb: split out IOTLB initialization
In reply to Gautam DawarThis patch splits out IOTLB initialization to make sure it could be reused by external modules.
--- drivers/vhost/iotlb.c | 23 ++++++++++++++++++----- include/linux/vhost_iotlb.h | 2 ++ 2 files changed, 20 insertions(+), 5 deletions(-)
drivers/vhost/iotlb.c +18 -5
@@ -110,6 +110,23 @@ 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
@@ -124,11 +141,7 @@ 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; }
include/linux/vhost_iotlb.h +2 -0
@@ -36,6 +36,8 @@ 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);
Signature · 1 line
2.25.0
RFC PATCH v2 9/19 vhost: support ASID in IOTLB API
In reply to Gautam DawarThis patches allows userspace to send ASID based IOTLB message to vhost. This idea is to use the reserved u32 field in the existing V2 IOTLB message. Vhost device should advertise this capability via VHOST_BACKEND_F_IOTLB_ASID backend feature.
--- drivers/vhost/vdpa.c | 5 ++++- drivers/vhost/vhost.c | 23 ++++++++++++++++++----- drivers/vhost/vhost.h | 4 ++-- include/uapi/linux/vhost_types.h | 6 +++++- 4 files changed, 29 insertions(+), 9 deletions(-)
drivers/vhost/vdpa.c +4 -1
@@ -836,7 +836,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, 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);
@@ -847,6 +847,9 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,mutex_lock (&dev->mutex); +if (asid !=0 ) +return -EINVAL ; + r =vhost_dev_check_owner (dev);if (r) goto unlock;
drivers/vhost/vhost.c +18 -5
@@ -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 =sizeof (__u16); + }else + offset =sizeof (__u32);break ;default : ret = -EINVAL ;
@@ -1171,9 +1184,9 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, }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;
drivers/vhost/vhost.h +2 -2
@@ -161,7 +161,7 @@ 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); };
@@ -169,7 +169,7 @@ 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);
include/uapi/linux/vhost_types.h +5 -1
@@ -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 ];
@@ -157,5 +157,9 @@ struct vhost_vdpa_iova_range {#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#endif
Signature · 1 line
2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 09/19] vhost: support ASID in IOTLB API
Quoted 29 lines · Gautam Dawar
This patches allows userspace to send ASID based IOTLB message to vhost. This idea is to use the reserved u32 field in the existing V2 IOTLB message. Vhost device should advertise this capability via
VHOST_BACKEND_F_IOTLB_ASIDbackend feature.Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vhost/vdpa.c | 5 ++++- drivers/vhost/vhost.c | 23 ++++++++++++++++++----- drivers/vhost/vhost.h | 4 ++-- include/uapi/linux/vhost_types.h | 6 +++++- 4 files changed, 29 insertions(+), 9 deletions(-)drivers/vhost/vdpa.c +1
-1@@ -836,7 +836,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, 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);
drivers/vhost/vdpa.c static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, · line 852
Quoted 6 lines
drivers/vhost/vdpa.c +3
-0@@ -847,6 +847,9 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,mutex_lock (&dev->mutex); +if (asid !=0 ) +return -EINVAL ; +
Should we check for asid != 0 before acquiring the mutex? Otherwise the code never releases it.
Quoted 118 lines
drivers/vhost/vdpa.c +0
-0r =vhost_dev_check_owner (dev);if (r) goto unlock;drivers/vhost/vhost.c +18
-5@@ -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 =sizeof (__u16); + }else + offset =sizeof (__u32);break ;default : ret = -EINVAL ;@@ -1171,9 +1184,9 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, }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;drivers/vhost/vhost.h +2
-2@@ -161,7 +161,7 @@ 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); };@@ -169,7 +169,7 @@ 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);include/uapi/linux/vhost_types.h +5
-2@@ -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 ];@@ -157,5 +157,9 @@ struct vhost_vdpa_iova_range {#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#endif --2.25.0
RE: [RFC PATCH v2 09/19] vhost: support ASID in IOTLB API
-----Original Message-----
From: Eugenio Perez Martin <[email protected]>
Sent: Friday, March 4, 2022 3:55 PM
To: Gautam Dawar <[email protected]>
Cc: Gautam Dawar <[email protected]>; Martin Petrus Hubertus Habets <[email protected]>; Harpreet Singh Anand <[email protected]>; Tanuj Murlidhar Kamde <[email protected]>; Jason Wang <[email protected]>; Michael S. Tsirkin <[email protected]>; Zhu Lingshan <[email protected]>; Stefano Garzarella <[email protected]>; Xie Yongji <[email protected]>; Eli Cohen <[email protected]>; Si-Wei Liu <[email protected]>; Parav Pandit <[email protected]>; Longpeng <[email protected]>; virtualization <[email protected]>; [email protected]; kvm list <[email protected]>; [email protected]
Subject: Re: [RFC PATCH v2 09/19] vhost: support ASID in IOTLB API
Quoted 33 lines · Gautam Dawar
This patches allows userspace to send ASID based IOTLB message to vhost. This idea is to use the reserved u32 field in the existing V2 IOTLB message. Vhost device should advertise this capability via
VHOST_BACKEND_F_IOTLB_ASIDbackend feature.Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vhost/vdpa.c | 5 ++++- drivers/vhost/vhost.c | 23 ++++++++++++++++++----- drivers/vhost/vhost.h | 4 ++-- include/uapi/linux/vhost_types.h | 6 +++++- 4 files changed, 29 insertions(+), 9 deletions(-)drivers/vhost/vdpa.c index renamed from drivers/vhost/vdpa.c +0
-0
6bf755f84d26..d0aacc0cc79a100644drivers/vhost/vdpa.c +2
-1@@ -836,7 +836,7 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, 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); @@ -847,6 +847,9 @@ static int vhost_vdpa_process_iotlb_msg(struct
vhost_dev*dev,mutex_lock(&dev->mutex);
drivers/vhost/vdpa.c static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, · line 852
Quoted 3 lines
drivers/vhost/vdpa.c +3
-0+if (asid !=0 ) +return -EINVAL ; +
Should we check for asid != 0 before acquiring the mutex? Otherwise the code never releases it. [GD>>] Yes, you are right. Will fix this in next revision.
Quoted 118 lines
r = vhost_dev_check_owner(dev); if (r) goto unlock;drivers/vhost/vhost.c index renamed from drivers/vhost/vhost.c +0
-0
59edb5a1ffe2..1f514d98f0de100644drivers/vhost/vhost.c +19
-5@@ -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 =sizeof (__u16); + }else + offset =sizeof (__u32);break ;default : ret = -EINVAL ;@@ -1171,9 +1184,9 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, }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;drivers/vhost/vhost.h index renamed from drivers/vhost/vhost.h +0
-0
638bb640d6b4..9f238d6c7b58100644drivers/vhost/vhost.h +3
-2@@ -161,7 +161,7 @@ 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); };@@ -169,7 +169,7 @@ 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); boolvhost_dev_has_owner(struct vhost_dev *dev); diff --gita/include/uapi/linux/vhost_types.hb/include/uapi/linux/vhost_types.hindex76ee7016c501..634cee485abb100644include/uapi/linux/vhost_types.h +1
-1@@ -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 ];@@ -157,5 +157,9 @@ struct vhost_vdpa_iova_range { #define
VHOST_BACKEND_F_IOTLB_MSG_V20x1
/* IOTLB can accept batching hints */ #defineVHOST_BACKEND_F_IOTLB_BATCH0x2include/uapi/linux/vhost_types.h +4
-1+/* IOTLB can accept address space identifier through V2 type of IOTLB +* message +*/ +#define VHOST_BACKEND_F_IOTLB_ASID 0x3#endif --2.25.0
RFC PATCH v2 10/19 vhost-vdpa: introduce asid based IOTLB
In reply to Gautam DawarThis patch converts the vhost-vDPA device to support multiple IOTLBs tagged via ASID via hlist. This will be used for supporting multiple address spaces in the following patches.
--- drivers/vhost/vdpa.c | 104 ++++++++++++++++++++++++++++++++----------- 1 file changed, 79 insertions(+), 25 deletions(-)
drivers/vhost/vdpa.c +79 -25
@@ -33,13 +33,21 @@ enum {#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 vhost_iotlb *iotlb; +struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS ];struct device dev;struct cdev cdev;atomic_t opened;
@@ -49,12 +57,64 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; +int used_as; };static DEFINE_IDA (vhost_vdpa_ida);static dev_t vhost_vdpa_major; +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_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 ; + + 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); + ++v->used_as; + +return as; +} + +static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) +{ +struct vhost_vdpa_as *as =asid_to_as (v, asid); + +/* Remove default address space is not allowed */ +if (asid ==0 ) +return -EINVAL ; + +if (!as) +return -EINVAL ; + +hlist_del (&as->hash_link); +vhost_iotlb_reset (&as->iotlb); +kfree (as); + --v->used_as; + +return 0 ; +} +static void handle_vq_kick (struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
@@ -554,15 +614,6 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,return vhost_vdpa_pa_unmap (v, iotlb, start, last); } -static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) -{ -struct vhost_iotlb *iotlb = v->iotlb; - -vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 ); -kfree (v->iotlb); - v->iotlb =NULL ; -} -static int perm_to_iommu_flags (u32 perm) {int flags =0 ;
@@ -842,7 +893,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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 = v->iotlb; +struct vhost_vdpa_as *as =asid_to_as (v,0 ); +struct vhost_iotlb *iotlb = &as->iotlb;int r =0 ;mutex_lock (&dev->mutex);
@@ -953,6 +1005,13 @@ static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v) } } +static void vhost_vdpa_cleanup (struct vhost_vdpa *v) +{ +vhost_dev_cleanup (&v->vdev); +kfree (v->vdev.vqs); +vhost_vdpa_remove_as (v,0 ); +} +static int vhost_vdpa_open (struct inode *inode,struct file *filep) {struct vhost_vdpa *v;
@@ -985,15 +1044,12 @@ 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); - v->iotlb =vhost_iotlb_alloc (0 ,0 ); -if (!v->iotlb) { - r = -ENOMEM ; - goto err_init_iotlb; - } +if (!vhost_vdpa_alloc_as (v,0 )) + goto err_alloc_as; r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_domain; + goto err_alloc_as;vhost_vdpa_set_iova_range (v);
@@ -1001,11 +1057,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_domain: -vhost_vdpa_iotlb_free (v); -err_init_iotlb: -vhost_dev_cleanup (&v->vdev); -kfree (vqs); +err_alloc_as: +vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);return r;
@@ -1029,11 +1082,9 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep)vhost_vdpa_clean_irq (v);vhost_vdpa_reset (v);vhost_dev_stop (&v->vdev); -vhost_vdpa_iotlb_free (v);vhost_vdpa_free_domain (v);vhost_vdpa_config_put (v);vhost_dev_cleanup (&v->vdev); -kfree (v->vdev.vqs);mutex_unlock (&d->mutex);atomic_dec (&v->opened);
@@ -1129,7 +1180,7 @@ 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;/* Only support 1 address space and 1 groups */ if (vdpa->ngroups !=1 || vdpa->nas !=1 )
@@ -1177,6 +1228,9 @@ 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:
Signature · 1 line
2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 10/19] vhost-vdpa: introduce asid based IOTLB
Quoted 39 lines · Gautam Dawar
This patch converts the vhost-vDPA device to support multiple IOTLBs tagged via ASID via hlist. This will be used for supporting multiple address spaces in the following patches.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vhost/vdpa.c | 104 ++++++++++++++++++++++++++++++++----------- 1 file changed, 79 insertions(+), 25 deletions(-)drivers/vhost/vdpa.c +9
-1@@ -33,13 +33,21 @@ enum {#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 vhost_iotlb *iotlb; +struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS ];struct device dev;struct cdev cdev;atomic_t opened;
drivers/vhost/vdpa.c struct vhost_vdpa { · line 60
Quoted 4 lines
drivers/vhost/vdpa.c +1
-0@@ -49,12 +57,64 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; +int used_as;
This member is only modified to count the number of AS, but is never read again. In patch 15/19 is deleted. Could we avoid introducing it in all the series?
This is also in the previous series, but it was declared useless if I recall correctly.
Quoted 35 lines
drivers/vhost/vdpa.c +29
-0};static DEFINE_IDA (vhost_vdpa_ida);static dev_t vhost_vdpa_major; +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_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 ; + + 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); + ++v->used_as; +
drivers/vhost/vdpa.c struct vhost_vdpa { · line 105
Quoted 10 lines
drivers/vhost/vdpa.c +10
-0+return as; +} + +static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) +{ +struct vhost_vdpa_as *as =asid_to_as (v, asid); + +/* Remove default address space is not allowed */ +if (asid ==0 ) +return -EINVAL ;
We must remove address space id 0 so we don't leak it at vhost_vdpa_cleanup. I think the check could go away with no need of moving it.
Quoted 122 lines
drivers/vhost/vdpa.c +30
-25+ +if (!as) +return -EINVAL ; + +hlist_del (&as->hash_link); +vhost_iotlb_reset (&as->iotlb); +kfree (as); + --v->used_as; + +return 0 ; +} +static void handle_vq_kick (struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,@@ -554,15 +614,6 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,return vhost_vdpa_pa_unmap (v, iotlb, start, last); } -static void vhost_vdpa_iotlb_free (struct vhost_vdpa *v) -{ -struct vhost_iotlb *iotlb = v->iotlb; - -vhost_vdpa_iotlb_unmap (v, iotlb,0ULL ,0ULL -1 ); -kfree (v->iotlb); - v->iotlb =NULL ; -} -static int perm_to_iommu_flags (u32 perm) {int flags =0 ;@@ -842,7 +893,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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 = v->iotlb; +struct vhost_vdpa_as *as =asid_to_as (v,0 ); +struct vhost_iotlb *iotlb = &as->iotlb;int r =0 ;mutex_lock (&dev->mutex);@@ -953,6 +1005,13 @@ static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v) } } +static void vhost_vdpa_cleanup (struct vhost_vdpa *v) +{ +vhost_dev_cleanup (&v->vdev); +kfree (v->vdev.vqs); +vhost_vdpa_remove_as (v,0 ); +} +static int vhost_vdpa_open (struct inode *inode,struct file *filep) {struct vhost_vdpa *v;@@ -985,15 +1044,12 @@ 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); - v->iotlb =vhost_iotlb_alloc (0 ,0 ); -if (!v->iotlb) { - r = -ENOMEM ; - goto err_init_iotlb; - } +if (!vhost_vdpa_alloc_as (v,0 )) + goto err_alloc_as; r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_domain; + goto err_alloc_as;vhost_vdpa_set_iova_range (v);@@ -1001,11 +1057,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_domain: -vhost_vdpa_iotlb_free (v); -err_init_iotlb: -vhost_dev_cleanup (&v->vdev); -kfree (vqs); +err_alloc_as: +vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);return r;@@ -1029,11 +1082,9 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep)vhost_vdpa_clean_irq (v);vhost_vdpa_reset (v);vhost_dev_stop (&v->vdev); -vhost_vdpa_iotlb_free (v);vhost_vdpa_free_domain (v);vhost_vdpa_config_put (v);vhost_dev_cleanup (&v->vdev); -kfree (v->vdev.vqs);mutex_unlock (&d->mutex);atomic_dec (&v->opened);@@ -1129,7 +1180,7 @@ 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;/* Only support 1 address space and 1 groups */ if (vdpa->ngroups !=1 || vdpa->nas !=1 )@@ -1177,6 +1228,9 @@ 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: --2.25.0
RE: [RFC PATCH v2 10/19] vhost-vdpa: introduce asid based IOTLB
-----Original Message-----
From: Eugenio Perez Martin <[email protected]>
Sent: Friday, March 4, 2022 11:26 PM
To: Gautam Dawar <[email protected]>
Cc: Gautam Dawar <[email protected]>; Martin Petrus Hubertus Habets <[email protected]>; Harpreet Singh Anand <[email protected]>; Tanuj Murlidhar Kamde <[email protected]>; Jason Wang <[email protected]>; Michael S. Tsirkin <[email protected]>; Zhu Lingshan <[email protected]>; Stefano Garzarella <[email protected]>; Xie Yongji <[email protected]>; Eli Cohen <[email protected]>; Si-Wei Liu <[email protected]>; Parav Pandit <[email protected]>; Longpeng <[email protected]>; virtualization <[email protected]>; [email protected]; kvm list <[email protected]>; [email protected]
Subject: Re: [RFC PATCH v2 10/19] vhost-vdpa: introduce asid based IOTLB
Quoted 40 lines · Gautam Dawar
This patch converts the vhost-vDPA device to support multiple IOTLBs tagged via ASID via hlist. This will be used for supporting multiple address spaces in the following patches.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vhost/vdpa.c | 104 ++++++++++++++++++++++++++++++++----------- 1 file changed, 79 insertions(+), 25 deletions(-)drivers/vhost/vdpa.c index renamed from drivers/vhost/vdpa.c +0
-0
d0aacc0cc79a..4e8b7c4809cd100644drivers/vhost/vdpa.c +9
-1@@ -33,13 +33,21 @@ enum {#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 vhost_iotlb *iotlb; +struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS ];struct device dev;struct cdev cdev;atomic_t opened;
drivers/vhost/vdpa.c struct vhost_vdpa { · line 60
Quoted 4 lines
drivers/vhost/vdpa.c +1
-0@@ -49,12 +57,64 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; +int used_as;
This member is only modified to count the number of AS, but is never read again. In patch 15/19 is deleted. Could we avoid introducing it in all the series?
This is also in the previous series, but it was declared useless if I recall correctly. [GD>>] Yes, it makes sense to remove used_as structure member. Will do.
Quoted 34 lines
drivers/vhost/vdpa.c +28
-0};static DEFINE_IDA (vhost_vdpa_ida);static dev_t vhost_vdpa_major; +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_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 ; + + 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); + ++v->used_as;
drivers/vhost/vdpa.c struct vhost_vdpa { · line 105
Quoted 10 lines
drivers/vhost/vdpa.c +10
-0+ +return as; +} + +static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) { +struct vhost_vdpa_as *as =asid_to_as (v, asid); + +/* Remove default address space is not allowed */ +if (asid ==0 ) +return -EINVAL ;
We must remove address space id 0 so we don't leak it at vhost_vdpa_cleanup. I think the check could go away with no need of moving it. [GD>>] Good catch. Will remove this check to allow freeing "as" for asid 0 in vhost_vdpa_cleanup()
Quoted 118 lines
drivers/vhost/vdpa.c +25
-20+ +if (!as) +return -EINVAL ; + +hlist_del (&as->hash_link); +vhost_iotlb_reset (&as->iotlb); +kfree (as); + --v->used_as; + +return 0 ; +} +static void handle_vq_kick (struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, @@ -554,15 +614,6 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, return vhost_vdpa_pa_unmap(v, iotlb, start, last); } -static void vhost_vdpa_iotlb_free(struct vhost_vdpa *v) -{ - struct vhost_iotlb *iotlb = v->iotlb; - - vhost_vdpa_iotlb_unmap(v, iotlb, 0ULL, 0ULL - 1); - kfree(v->iotlb); - v->iotlb = NULL; -} - static int perm_to_iommu_flags(u32 perm) { int flags = 0;@@ -842,7 +893,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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 = v->iotlb; +struct vhost_vdpa_as *as =asid_to_as (v,0 ); +struct vhost_iotlb *iotlb = &as->iotlb;int r =0 ;mutex_lock (&dev->mutex);@@ -953,6 +1005,13 @@ static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v) } } +static void vhost_vdpa_cleanup (struct vhost_vdpa *v) { +vhost_dev_cleanup (&v->vdev); +kfree (v->vdev.vqs); +vhost_vdpa_remove_as (v,0 ); +} +static int vhost_vdpa_open (struct inode *inode,struct file *filep) {struct vhost_vdpa *v;@@ -985,15 +1044,12 @@ 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); - v->iotlb =vhost_iotlb_alloc (0 ,0 ); -if (!v->iotlb) { - r = -ENOMEM ; - goto err_init_iotlb; - } +if (!vhost_vdpa_alloc_as (v,0 )) + goto err_alloc_as; r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_domain; + goto err_alloc_as;vhost_vdpa_set_iova_range (v);@@ -1001,11 +1057,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_domain: -vhost_vdpa_iotlb_free (v); -err_init_iotlb: -vhost_dev_cleanup (&v->vdev); -kfree (vqs); +err_alloc_as: +vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);return r;drivers/vhost/vdpa.c +1
-3@@ -1029,11 +1082,9 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep)vhost_vdpa_clean_irq (v);vhost_vdpa_reset (v);vhost_dev_stop (&v->vdev); -vhost_vdpa_iotlb_free (v);vhost_vdpa_free_domain (v);vhost_vdpa_config_put (v);vhost_dev_cleanup (&v->vdev); -kfree (v->vdev.vqs);mutex_unlock (&d->mutex);atomic_dec (&v->opened);@@ -1129,7 +1180,7 @@ 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;/* Only support 1 address space and 1 groups */ if (vdpa->ngroups != 1 || vdpa->nas != 1) @@ -1177,6 +1228,9@@ static int
vhost_vdpa_probe(struct vdpa_device *vdpa)init_completion(&v->completion); vdpa_set_drvdata(vdpa, v);drivers/vhost/vdpa.c +3
-1+for (i =0 ; i <VHOST_VDPA_IOTLB_BUCKETS ; i++) +INIT_HLIST_HEAD (&v->as[i]); +return 0 ; err: --2.25.0
RFC PATCH v2 11/19 vhost-vdpa: introduce uAPI to get the number of virtqueue groups
In reply to Gautam DawarFollows the vDPA support for multiple address spaces, this patch introduce uAPI for the userspace to know the number of virtqueue groups supported by the vDPA device.
--- drivers/vhost/vdpa.c | 4 ++++ include/uapi/linux/vhost.h | 3 +++ 2 files changed, 7 insertions(+)
drivers/vhost/vdpa.c +4 -0
@@ -538,6 +538,10 @@ 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 : + r =copy_to_user (argp, &v->vdpa->ngroups, +sizeof (v->vdpa->ngroups)); +break ;case VHOST_SET_LOG_BASE :case VHOST_SET_LOG_FD : r = -ENOIOCTLCMD ;
include/uapi/linux/vhost.h +3 -0
@@ -145,4 +145,7 @@/* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x79, unsigned int) +#endif
Signature · 1 line
2.25.0
RFC PATCH v2 12/19 vhost-vdpa: introduce uAPI to get the number of address spaces
In reply to Gautam DawarThis patch introduces the uAPI for getting the number of address spaces supported by this vDPA device.
--- drivers/vhost/vdpa.c | 3 +++ include/uapi/linux/vhost.h | 2 ++ 2 files changed, 5 insertions(+)
drivers/vhost/vdpa.c +3 -0
@@ -542,6 +542,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, r =copy_to_user (argp, &v->vdpa->ngroups,sizeof (v->vdpa->ngroups));break ; +case VHOST_VDPA_GET_AS_NUM : + r =copy_to_user (argp, &v->vdpa->nas,sizeof (v->vdpa->nas)); +break ;case VHOST_SET_LOG_BASE :case VHOST_SET_LOG_FD : r = -ENOIOCTLCMD ;
include/uapi/linux/vhost.h +2 -0
@@ -148,4 +148,6 @@/* Get the number of virtqueue groups. */ #define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x79, unsigned int) +/* Get the number of address spaces. */ +#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int)#endif
Signature · 1 line
2.25.0
RFC PATCH v2 13/19 vhost-vdpa: uAPI to get virtqueue group id
In reply to Gautam DawarFollows the support for virtqueue group in vDPA. This patches introduces uAPI to get the virtqueue group ID for a specific virtqueue in vhost-vdpa.
--- drivers/vhost/vdpa.c | 8 ++++++++ include/uapi/linux/vhost.h | 8 ++++++++ 2 files changed, 16 insertions(+)
drivers/vhost/vdpa.c +8 -0
@@ -444,6 +444,14 @@ 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 : + 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_GET_VRING_BASE : r = ops->get_vq_state (v->vdpa, idx, &vq_state);if (r)
include/uapi/linux/vhost.h +8 -0
@@ -150,4 +150,12 @@/* 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)#endif
Signature · 1 line
2.25.0
RFC PATCH v2 14/19 vhost-vdpa: introduce uAPI to set group ASID
In reply to Gautam DawarFollows the vDPA support for associating ASID to a specific virtqueue group. This patch adds a uAPI to support setting them from userspace.
--- drivers/vhost/vdpa.c | 8 ++++++++ include/uapi/linux/vhost.h | 7 +++++++ 2 files changed, 15 insertions(+)
drivers/vhost/vdpa.c +8 -0
@@ -452,6 +452,14 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,else if (copy_to_user (argp, &s,sizeof (s)))return -EFAULT ;return 0 ; +case VHOST_VDPA_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)
include/uapi/linux/vhost.h +7 -0
@@ -158,4 +158,11 @@*/ #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) +#endif
Signature · 1 line
2.25.0
RFC PATCH v2 15/19 vhost-vdpa: support ASID based IOTLB API
In reply to Gautam DawarThis patch extends the vhost-vdpa to support ASID based IOTLB API. The vhost-vdpa device will allocated multiple IOTLBs for vDPA device that supports multiple address spaces. The IOTLBs and vDPA device memory mappings is determined and maintained through ASID.
Note that we still don't support vDPA device with more than one address spaces that depends on platform IOMMU. This work will be done by moving the IOMMU logic from vhost-vDPA to vDPA device driver.
--- drivers/vhost/vdpa.c | 129 ++++++++++++++++++++++++++++++++---------- drivers/vhost/vhost.c | 2 +- 2 files changed, 100 insertions(+), 31 deletions(-)
drivers/vhost/vdpa.c +99 -30
@@ -28,7 +28,8 @@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)
@@ -57,13 +58,20 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; -int used_as; +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 ];
@@ -76,6 +84,16 @@ static struct vhost_vdpa_as *asid_to_as(struct vhost_vdpa *v, u32 asid)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 ];
@@ -84,6 +102,9 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid)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 ;
@@ -91,18 +112,24 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid)vhost_iotlb_init (&as->iotlb,0 ,0 ); as->id = asid;hlist_add_head (&as->hash_link, head); - ++v->used_as;return as; } -static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) +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); -/* Remove default address space is not allowed */ -if (asid ==0 ) -return -EINVAL ; +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 ;
@@ -110,7 +137,6 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)hlist_del (&as->hash_link);vhost_iotlb_reset (&as->iotlb);kfree (as); - --v->used_as;return 0 ; }
@@ -665,6 +691,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,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_ctx(iotlb, iova, iova + size - 1,
@@ -673,10 +700,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r;if (ops->dma_map) { - r = ops->dma_map (vdpa,0 , iova, size, pa, perm, opaque); + 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,0 , iotlb); + r = ops->set_map (vdpa, asid, iotlb); }else { r =iommu_map (v->domain, iova, pa, size,perm_to_iommu_flags (perm));
@@ -692,23 +719,35 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return 0 ; } -static void vhost_vdpa_unmap (struct vhost_vdpa *v, -struct vhost_iotlb *iotlb, -u64 iova,u64 size) +static int vhost_vdpa_unmap (struct vhost_vdpa *v, +struct vhost_iotlb *iotlb, +u64 iova,u64 size) {struct vdpa_device *vdpa = v->vdpa;const struct vdpa_config_ops *ops = vdpa->config; +u32 asid =iotlb_to_asid (iotlb); + +if (!iotlb) +return -EINVAL ;vhost_vdpa_iotlb_unmap (v, iotlb, iova, iova + size -1 );if (ops->dma_map) { - ops->dma_unmap (vdpa,0 , iova, size); + ops->dma_unmap (vdpa, asid, iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa,0 , 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); + +return 0 ; } static int vhost_vdpa_va_map(struct vhost_vdpa *v,
@@ -916,33 +955,55 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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_vdpa_as *as =asid_to_as (v,0 ); -struct vhost_iotlb *iotlb = &as->iotlb; +struct vhost_iotlb *iotlb =NULL ; +struct vhost_vdpa_as *as =NULL ;int r =0 ;mutex_lock (&dev->mutex); -if (asid !=0 ) -return -EINVAL ; - r =vhost_dev_check_owner (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); +return -EINVAL ; + } + 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); +return -EINVAL ; + } +switch (msg->type) {case VHOST_IOTLB_UPDATE : r =vhost_vdpa_process_iotlb_update (v, iotlb, msg);break ;case VHOST_IOTLB_INVALIDATE : -vhost_vdpa_unmap (v, iotlb, msg->iova, msg->size); + r =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,0 , iotlb); + ops->set_map (vdpa, asid, iotlb); v->in_batch = false; +if (!iotlb->nmaps) +vhost_vdpa_remove_as (v, asid);break ;default : r = -EINVAL ;
@@ -1030,9 +1091,17 @@ 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); -vhost_vdpa_remove_as (v,0 ); + +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)
@@ -1067,12 +1136,9 @@ 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); -if (!vhost_vdpa_alloc_as (v,0 )) - goto err_alloc_as; - r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_as; + goto err_alloc_domain;vhost_vdpa_set_iova_range (v);
@@ -1080,7 +1146,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_as: +err_alloc_domain:vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);
@@ -1205,8 +1271,11 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int i, r; -/* Only support 1 address space and 1 groups */ -if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +/* 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);
drivers/vhost/vhost.c +1 -1
@@ -1167,7 +1167,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, ret = -EINVAL ; goto done; } - offset =sizeof (__u16); + offset =0 ; }else offset =sizeof (__u32);break ;
Signature · 1 line
2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 15/19] vhost-vdpa: support ASID based IOTLB API
Quoted 146 lines · Gautam Dawar
This patch extends the vhost-vdpa to support ASID based IOTLB API. The vhost-vdpa device will allocated multiple IOTLBs for vDPA device that supports multiple address spaces. The IOTLBs and vDPA device memory mappings is determined and maintained through ASID.
Note that we still don't support vDPA device with more than one address spaces that depends on platform IOMMU. This work will be done by moving the IOMMU logic from vhost-vDPA to vDPA device driver.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vhost/vdpa.c | 129 ++++++++++++++++++++++++++++++++---------- drivers/vhost/vhost.c | 2 +- 2 files changed, 100 insertions(+), 31 deletions(-)drivers/vhost/vdpa.c +37
-13@@ -28,7 +28,8 @@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)@@ -57,13 +58,20 @@ struct vhost_vdpa {struct eventfd_ctx *config_ctx;int in_batch;struct vdpa_iova_range range; -int used_as; +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 ];@@ -76,6 +84,16 @@ static struct vhost_vdpa_as *asid_to_as(struct vhost_vdpa *v, u32 asid)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 ];@@ -84,6 +102,9 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid)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 ;@@ -91,18 +112,24 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid)vhost_iotlb_init (&as->iotlb,0 ,0 ); as->id = asid;hlist_add_head (&as->hash_link, head); - ++v->used_as;return as; } -static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) +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); -/* Remove default address space is not allowed */ -if (asid ==0 ) -return -EINVAL ; +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 ;@@ -110,7 +137,6 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)hlist_del (&as->hash_link);vhost_iotlb_reset (&as->iotlb);kfree (as); - --v->used_as;return 0 ; }@@ -665,6 +691,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,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_ctx(iotlb, iova, iova + size - 1,@@ -673,10 +700,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return r;if (ops->dma_map) { - r = ops->dma_map (vdpa,0 , iova, size, pa, perm, opaque); + 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,0 , iotlb); + r = ops->set_map (vdpa, asid, iotlb); }else { r =iommu_map (v->domain, iova, pa, size,perm_to_iommu_flags (perm));@@ -692,23 +719,35 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,return 0 ; } -static void vhost_vdpa_unmap (struct vhost_vdpa *v, -struct vhost_iotlb *iotlb, -u64 iova,u64 size)
drivers/vhost/vdpa.c static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, · line 731
Quoted 10 lines
drivers/vhost/vdpa.c +7
-0+static int vhost_vdpa_unmap (struct vhost_vdpa *v, +struct vhost_iotlb *iotlb, +u64 iova,u64 size) {struct vdpa_device *vdpa = v->vdpa;const struct vdpa_config_ops *ops = vdpa->config; +u32 asid =iotlb_to_asid (iotlb); + +if (!iotlb) +return -EINVAL ;
I think there is no need of checking for this. Similar functions assume the caller will pass non-null arguments, and vhost_vdpa_process_iotlb_msg does it.
With that into account, I think there is little point in making this function return something different than void.
Apart from that, iotlb is already used before checking for NULL.
Quoted 159 lines
drivers/vhost/vdpa.c +55
-17vhost_vdpa_iotlb_unmap (v, iotlb, iova, iova + size -1 );if (ops->dma_map) { - ops->dma_unmap (vdpa,0 , iova, size); + ops->dma_unmap (vdpa, asid, iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa,0 , 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); + +return 0 ; } static int vhost_vdpa_va_map(struct vhost_vdpa *v,@@ -916,33 +955,55 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, 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_vdpa_as *as =asid_to_as (v,0 ); -struct vhost_iotlb *iotlb = &as->iotlb; +struct vhost_iotlb *iotlb =NULL ; +struct vhost_vdpa_as *as =NULL ;int r =0 ;mutex_lock (&dev->mutex); -if (asid !=0 ) -return -EINVAL ; - r =vhost_dev_check_owner (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); +return -EINVAL ; + } + 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); +return -EINVAL ; + } +switch (msg->type) {case VHOST_IOTLB_UPDATE : r =vhost_vdpa_process_iotlb_update (v, iotlb, msg);break ;case VHOST_IOTLB_INVALIDATE : -vhost_vdpa_unmap (v, iotlb, msg->iova, msg->size); + r =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,0 , iotlb); + ops->set_map (vdpa, asid, iotlb); v->in_batch = false; +if (!iotlb->nmaps) +vhost_vdpa_remove_as (v, asid);break ;default : r = -EINVAL ;@@ -1030,9 +1091,17 @@ 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); -vhost_vdpa_remove_as (v,0 ); + +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)@@ -1067,12 +1136,9 @@ 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); -if (!vhost_vdpa_alloc_as (v,0 )) - goto err_alloc_as; - r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_as; + goto err_alloc_domain;vhost_vdpa_set_iova_range (v);@@ -1080,7 +1146,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_as: +err_alloc_domain:vhost_vdpa_cleanup (v); err:atomic_dec (&v->opened);@@ -1205,8 +1271,11 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int i, r; -/* Only support 1 address space and 1 groups */ -if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +/* 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);drivers/vhost/vhost.c +1
-2@@ -1167,7 +1167,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, ret = -EINVAL ; goto done; } - offset =sizeof (__u16); + offset =0 ; }else offset =sizeof (__u32);break ; --2.25.0
RE: [RFC PATCH v2 15/19] vhost-vdpa: support ASID based IOTLB API
-----Original Message-----
From: Eugenio Perez Martin <[email protected]>
Sent: Friday, March 4, 2022 11:35 PM
To: Gautam Dawar <[email protected]>
Cc: Gautam Dawar <[email protected]>; Martin Petrus Hubertus Habets <[email protected]>; Harpreet Singh Anand <[email protected]>; Tanuj Murlidhar Kamde <[email protected]>; Jason Wang <[email protected]>; Michael S. Tsirkin <[email protected]>; Zhu Lingshan <[email protected]>; Stefano Garzarella <[email protected]>; Xie Yongji <[email protected]>; Eli Cohen <[email protected]>; Si-Wei Liu <[email protected]>; Parav Pandit <[email protected]>; Longpeng <[email protected]>; virtualization <[email protected]>; [email protected]; kvm list <[email protected]>; [email protected]
Subject: Re: [RFC PATCH v2 15/19] vhost-vdpa: support ASID based IOTLB API
Quoted 144 lines · Gautam Dawar
This patch extends the vhost-vdpa to support ASID based IOTLB API. The vhost-vdpa device will allocated multiple IOTLBs for vDPA device that supports multiple address spaces. The IOTLBs and vDPA device memory mappings is determined and maintained through ASID.
Note that we still don't support vDPA device with more than one address spaces that depends on platform IOMMU. This work will be done by moving the IOMMU logic from vhost-vDPA to vDPA device driver.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vhost/vdpa.c | 129 ++++++++++++++++++++++++++++++++---------- drivers/vhost/vhost.c | 2 +- 2 files changed, 100 insertions(+), 31 deletions(-)drivers/vhost/vdpa.c index renamed from drivers/vhost/vdpa.c +0
-0
47e6cf9d0881..4bcf824e3b12100644drivers/vhost/vdpa.c +2
-1@@ -28,7 +28,8 @@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) @@ -57,13 +58,20 @@struct vhost_vdpa { struct eventfd_ctx *config_ctx; int in_batch; struct vdpa_iova_range range;drivers/vhost/vdpa.c +7
-1-int used_as; +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, u32asid) { struct hlist_head *head = &v->as[asid % VHOST_VDPA_IOTLB_BUCKETS]; @@ -76,6 +84,16 @@ static struct vhost_vdpa_as *asid_to_as(struct vhost_vdpa *v, u32 asid) return NULL;}
drivers/vhost/vdpa.c +10
-0+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]; @@ -84,6 +102,9 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid) if (asid_to_as(v, asid)) return NULL;drivers/vhost/vdpa.c +17
-12+if (asid >= v->vdpa->nas) +return NULL ; + as =kmalloc (sizeof (*as),GFP_KERNEL );if (!as)return NULL ;@@ -91,18 +112,24 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid)vhost_iotlb_init (&as->iotlb,0 ,0 ); as->id = asid;hlist_add_head (&as->hash_link, head); - ++v->used_as;return as; } -static int vhost_vdpa_remove_as (struct vhost_vdpa *v,u32 asid) +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); -/* Remove default address space is not allowed */ -if (asid ==0 ) -return -EINVAL ; +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 ;@@ -110,7 +137,6 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)hlist_del (&as->hash_link);vhost_iotlb_reset (&as->iotlb);kfree (as); - --v->used_as;return 0 ; }@@ -665,6 +691,7 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,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_ctx(iotlb, iova, iova + size - 1, @@ -673,10 +700,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, return r;if (ops->dma_map) { - r = ops->dma_map(vdpa, 0, iova, size, pa, perm, opaque); + 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,0 , iotlb); + r = ops->set_map (vdpa, asid, iotlb); }else { r =iommu_map (v->domain, iova, pa, size, perm_to_iommu_flags(perm)); @@ -692,23 +719,35 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, return 0; } -static void vhost_vdpa_unmap (struct vhost_vdpa *v, -struct vhost_iotlb *iotlb, -u64 iova,u64 size)
drivers/vhost/vdpa.c static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
Quoted 10 lines
drivers/vhost/vdpa.c +7
-0+static int vhost_vdpa_unmap (struct vhost_vdpa *v, +struct vhost_iotlb *iotlb, +u64 iova,u64 size) {struct vdpa_device *vdpa = v->vdpa;const struct vdpa_config_ops *ops = vdpa->config; +u32 asid =iotlb_to_asid (iotlb); + +if (!iotlb) +return -EINVAL ;
I think there is no need of checking for this. Similar functions assume the caller will pass non-null arguments, and vhost_vdpa_process_iotlb_msg does it.
With that into account, I think there is little point in making this function return something different than void.
Apart from that, iotlb is already used before checking for NULL. [GD>>] Agreed. Will remove the unnecessary check and change the return type to void.
Quoted 160 lines
vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1); if (ops->dma_map) {drivers/vhost/vdpa.c +10
-2- ops->dma_unmap (vdpa,0 , iova, size); + ops->dma_unmap (vdpa, asid, iova, size); }else if (ops->set_map) {if (!v->in_batch) - ops->set_map (vdpa,0 , 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); + +return 0 ; } static int vhost_vdpa_va_map(struct vhost_vdpa *v, @@ -916,33 +955,55@@ static int vhost_vdpa_process_iotlb_msg(struct
vhost_dev*dev, u32 asid,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;drivers/vhost/vdpa.c +40
-13-struct vhost_vdpa_as *as =asid_to_as (v,0 ); -struct vhost_iotlb *iotlb = &as->iotlb; +struct vhost_iotlb *iotlb =NULL ; +struct vhost_vdpa_as *as =NULL ;int r =0 ;mutex_lock (&dev->mutex); -if (asid !=0 ) -return -EINVAL ; - r =vhost_dev_check_owner (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); +return -EINVAL ; + } + 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); +return -EINVAL ; + } +switch (msg->type) {case VHOST_IOTLB_UPDATE : r =vhost_vdpa_process_iotlb_update (v, iotlb, msg);break ;case VHOST_IOTLB_INVALIDATE : -vhost_vdpa_unmap (v, iotlb, msg->iova, msg->size); + r =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,0 , iotlb); + ops->set_map (vdpa, asid, iotlb); v->in_batch = false; +if (!iotlb->nmaps) +vhost_vdpa_remove_as (v, asid);break ;default : r = -EINVAL ;@@ -1030,9 +1091,17 @@ 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); -vhost_vdpa_remove_as (v,0 ); + +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)@@ -1067,12 +1136,9 @@ 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); -if (!vhost_vdpa_alloc_as (v,0 )) - goto err_alloc_as; - r =vhost_vdpa_alloc_domain (v);if (r) - goto err_alloc_as; + goto err_alloc_domain;vhost_vdpa_set_iova_range (v);@@ -1080,7 +1146,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)return 0 ; -err_alloc_as: +err_alloc_domain:vhost_vdpa_cleanup (v); err:atomic_dec(&v->opened);drivers/vhost/vdpa.c +5
-2@@ -1205,8 +1271,11 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)int minor;int i, r; -/* Only support 1 address space and 1 groups */ -if (vdpa->ngroups !=1 || vdpa->nas !=1 ) +/* 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);drivers/vhost/vhost.c index renamed from drivers/vhost/vhost.c +0
-0
1f514d98f0de..92eeb684c84d100644drivers/vhost/vhost.c +1
-2@@ -1167,7 +1167,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, ret = -EINVAL ; goto done; } - offset =sizeof (__u16); + offset =0 ; }else offset =sizeof (__u32);break ; --2.25.0
RFC PATCH v2 16/19 vdpa_sim: advertise VIRTIO_NET_F_MTU
In reply to Gautam DawarWe've already reported maximum mtu via config space, so let's advertise the feature.
--- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +2 -1
@@ -26,7 +26,8 @@#define DRV_LICENSE "GPL v2"#define VDPASIM_NET_FEATURES (VDPASIM_FEATURES | \ - (1ULL << VIRTIO_NET_F_MAC)) + (1ULL << VIRTIO_NET_F_MAC) | \ + (1ULL << VIRTIO_NET_F_MTU));#define VDPASIM_NET_VQ_NUM 2
Signature · 1 line
2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 16/19] vdpa_sim: advertise VIRTIO_NET_F_MTU
Quoted 15 lines · Gautam Dawar
We've already reported maximum mtu via config space, so let's advertise the feature.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)drivers/vdpa/vdpa_sim/vdpa_sim_net.c +0
-0
drivers/vdpa/vdpa_sim/vdpa_sim_net.c line 30
Quoted 6 lines
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +2
-1@@ -26,7 +26,8 @@#define DRV_LICENSE "GPL v2"#define VDPASIM_NET_FEATURES (VDPASIM_FEATURES | \ - (1ULL << VIRTIO_NET_F_MAC)) + (1ULL << VIRTIO_NET_F_MAC) | \ + (1ULL << VIRTIO_NET_F_MTU));
Extra semicolon at the end of macro.
Thanks.
Quoted 6 lines
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +0
-1#define VDPASIM_NET_VQ_NUM 2 --2.25.0
RFC PATCH v2 17/19 vdpa_sim: factor out buffer completion logic
In reply to Gautam DawarWrap up common buffer completion logic in to vdpasim_net_complete
--- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 33 +++++++++++++++------------- 1 file changed, 18 insertions(+), 15 deletions(-)
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +18 -15
@@ -31,6 +31,22 @@#define VDPASIM_NET_VQ_NUM 2 +static void vdpasim_net_complete (struct vdpasim_virtqueue *vq,size_t len) +{ +/* Make sure data is wrote before advancing index */ +smp_wmb (); + +vringh_complete_iotlb (&vq->vring, vq->head, len); + +/* Make sure used is visible before rasing the interrupt. */ +smp_wmb (); + +local_bh_disable (); +if (vringh_need_notify_iotlb (&vq->vring) >0 ) +vringh_notify (&vq->vring); +local_bh_enable (); +} +static void vdpasim_net_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);
@@ -78,21 +94,8 @@ static void vdpasim_net_work(struct work_struct *work) total_write += write; } -/* Make sure data is wrote before advancing index */ -smp_wmb (); - -vringh_complete_iotlb (&txq->vring, txq->head,0 ); -vringh_complete_iotlb (&rxq->vring, rxq->head, total_write); - -/* Make sure used is visible before rasing the interrupt. */ -smp_wmb (); - -local_bh_disable (); -if (vringh_need_notify_iotlb (&txq->vring) >0 ) -vringh_notify (&txq->vring); -if (vringh_need_notify_iotlb (&rxq->vring) >0 ) -vringh_notify (&rxq->vring); -local_bh_enable (); +vdpasim_net_complete (txq,0 ); +vdpasim_net_complete (rxq, total_write);if (++pkts >4 ) {schedule_work (&vdpasim->work);
Signature · 1 line
2.25.0
RFC PATCH v2 18/19 vdpa_sim: filter destination mac address
In reply to Gautam DawarThis patch implements a simple unicast filter for vDPA simulator.
--- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 49 ++++++++++++++++++---------- 1 file changed, 31 insertions(+), 18 deletions(-)
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +31 -18
@@ -47,13 +47,28 @@ static void vdpasim_net_complete(struct vdpasim_virtqueue *vq, size_t len)local_bh_enable (); } +static bool receive_filter (struct vdpasim *vdpasim,size_t len) +{ +bool modern = vdpasim->features & (1ULL <<VIRTIO_F_VERSION_1 ); +size_t hdr_len = modern ?sizeof (struct virtio_net_hdr_v1 ) : +sizeof (struct virtio_net_hdr ); + +if (len <ETH_ALEN + hdr_len) +return false; + +if (!strncmp (vdpasim->buffer + hdr_len, + vdpasim->config.mac,ETH_ALEN )) +return true; + +return false; +} +static void vdpasim_net_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);struct vdpasim_virtqueue *txq = &vdpasim->vqs[1 ];struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0 ];ssize_t read, write; -size_t total_write;int pkts =0 ;int err;
@@ -66,36 +81,34 @@ static void vdpasim_net_work(struct work_struct *work) goto out;while (true) { - total_write =0 ; err =vringh_getdesc_iotlb (&txq->vring, &txq->out_iov,NULL , &txq->head,GFP_ATOMIC );if (err <=0 )break ; + read =vringh_iov_pull_iotlb (&txq->vring, &txq->out_iov, + vdpasim->buffer, +PAGE_SIZE ); + +if (!receive_filter (vdpasim, read)) { +vdpasim_complete (txq,0 ); +continue ; + } + err =vringh_getdesc_iotlb (&rxq->vring,NULL , &rxq->in_iov, &rxq->head,GFP_ATOMIC );if (err <=0 ) { -vringh_complete_iotlb (&txq->vring, txq->head,0 ); +vdpasim_net_complete (txq,0 );break ; } -while (true) { - read =vringh_iov_pull_iotlb (&txq->vring, &txq->out_iov, - vdpasim->buffer, -PAGE_SIZE ); -if (read <=0 ) -break ; - - write =vringh_iov_push_iotlb (&rxq->vring, &rxq->in_iov, - vdpasim->buffer, read); -if (write <=0 ) -break ; - - total_write += write; - } + write =vringh_iov_push_iotlb (&rxq->vring, &rxq->in_iov, + vdpasim->buffer, read); +if (write <=0 ) +break ;vdpasim_net_complete (txq,0 ); -vdpasim_net_complete (rxq, total_write); +vdpasim_net_complete (rxq, write);if (++pkts >4 ) {schedule_work (&vdpasim->work);
Signature · 1 line
2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 18/19] vdpa_sim: filter destination mac address
Quoted 49 lines · Gautam Dawar
This patch implements a simple unicast filter for vDPA simulator.
Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 49 ++++++++++++++++++---------- 1 file changed, 31 insertions(+), 18 deletions(-)drivers/vdpa/vdpa_sim/vdpa_sim_net.c +16
-2@@ -47,13 +47,28 @@ static void vdpasim_net_complete(struct vdpasim_virtqueue *vq, size_t len)local_bh_enable (); } +static bool receive_filter (struct vdpasim *vdpasim,size_t len) +{ +bool modern = vdpasim->features & (1ULL <<VIRTIO_F_VERSION_1 ); +size_t hdr_len = modern ?sizeof (struct virtio_net_hdr_v1 ) : +sizeof (struct virtio_net_hdr ); + +if (len <ETH_ALEN + hdr_len) +return false; + +if (!strncmp (vdpasim->buffer + hdr_len, + vdpasim->config.mac,ETH_ALEN )) +return true; + +return false; +} +static void vdpasim_net_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);struct vdpasim_virtqueue *txq = &vdpasim->vqs[1 ];struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0 ];ssize_t read, write; -size_t total_write;int pkts =0 ;int err;@@ -66,36 +81,34 @@ static void vdpasim_net_work(struct work_struct *work) goto out;while (true) { - total_write =0 ; err = vringh_getdesc_iotlb(&txq->vring, &txq->out_iov, NULL,
drivers/vdpa/vdpa_sim/vdpa_sim_net.c static void vdpasim_net_work(struct work_struct *work) · line 94
Quoted 10 lines
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +6
-0&txq->head, GFP_ATOMIC);if (err <=0 )break ; + read =vringh_iov_pull_iotlb (&txq->vring, &txq->out_iov, + vdpasim->buffer, +PAGE_SIZE ); + +if (!receive_filter (vdpasim, read)) { +vdpasim_complete (txq,0 );
vdpasim_net_complete?
Thanks!
Quoted 39 lines
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +9
-17+continue ; + } + err =vringh_getdesc_iotlb (&rxq->vring,NULL , &rxq->in_iov, &rxq->head,GFP_ATOMIC );if (err <=0 ) { -vringh_complete_iotlb (&txq->vring, txq->head,0 ); +vdpasim_net_complete (txq,0 );break ; } -while (true) { - read =vringh_iov_pull_iotlb (&txq->vring, &txq->out_iov, - vdpasim->buffer, -PAGE_SIZE ); -if (read <=0 ) -break ; - - write =vringh_iov_push_iotlb (&rxq->vring, &rxq->in_iov, - vdpasim->buffer, read); -if (write <=0 ) -break ; - - total_write += write; - } + write =vringh_iov_push_iotlb (&rxq->vring, &rxq->in_iov, + vdpasim->buffer, read); +if (write <=0 ) +break ;vdpasim_net_complete (txq,0 ); -vdpasim_net_complete (rxq, total_write); +vdpasim_net_complete (rxq, write);if (++pkts >4 ) {schedule_work (&vdpasim->work); --2.25.0
RFC PATCH v2 19/19 vdpasim: control virtqueue support
In reply to Gautam DawarThis patch introduces the control virtqueue support for vDPA simulator. This is a requirement for supporting advanced features like multiqueue.
A requirement for control virtqueue is to isolate its memory access from the rx/tx virtqueues. This is because when using vDPA device for VM, the control virqueue is not directly assigned to VM. Userspace (Qemu) will present a shadow control virtqueue to control for recording the device states.
The isolation is done via the virtqueue groups and ASID support in vDPA through vhost-vdpa. The simulator is extended to have:
1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue)
2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 contains CVQ
3) two address spaces and the simulator simply implements the address spaces by mapping it 1:1 to IOTLB.
For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 to group 1. So we have:
1) The IOTLB for virtqueue group 0 contains the mappings of guest, so RX and TX can be assigned to guest directly.
2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which is the buffers that allocated and managed by VMM only. So CVQ of vhost-vdpa is visible to VMM only. And Guest can not access the CVQ of vhost-vdpa.
For the other use cases, since AS 0 is associated to all virtqueue groups by default. All virtqueues share the same mapping by default.
To demonstrate the function, VIRITO_NET_F_CTRL_MACADDR is implemented in the simulator for the driver to set mac address.
--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 91 ++++++++++++++++++++++------ drivers/vdpa/vdpa_sim/vdpa_sim.h | 2 + drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 88 ++++++++++++++++++++++++++- 3 files changed, 161 insertions(+), 20 deletions(-)
drivers/vdpa/vdpa_sim/vdpa_sim.c +73 -18
@@ -96,11 +96,17 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim) {int i; -for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) +spin_lock (&vdpasim->iommu_lock); + +for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) {vdpasim_vq_reset (vdpasim, &vdpasim->vqs[i]); +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ], + &vdpasim->iommu_lock); + } + +for (i =0 ; i < vdpasim->dev_attr.nas; i++) +vhost_iotlb_reset (&vdpasim->iommu[i]); -spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu);spin_unlock (&vdpasim->iommu_lock); vdpasim->features =0 ;
@@ -145,7 +151,7 @@ static dma_addr_t vdpasim_map_range(struct vdpasim *vdpasim, phys_addr_t paddr, dma_addr =iova_dma_addr (&vdpasim->iova, iova);spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range (vdpasim->iommu, (u64 )dma_addr, + ret =vhost_iotlb_add_range (&vdpasim->iommu[0 ], (u64 )dma_addr, (u64 )dma_addr + size -1 , (u64 )paddr, perm);spin_unlock (&vdpasim->iommu_lock);
@@ -161,7 +167,7 @@ static void vdpasim_unmap_range(struct vdpasim *vdpasim, dma_addr_t dma_addr, size_t size) {spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, (u64 )dma_addr, +vhost_iotlb_del_range (&vdpasim->iommu[0 ], (u64 )dma_addr, (u64 )dma_addr + size -1 );spin_unlock (&vdpasim->iommu_lock);
@@ -250,8 +256,9 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)else ops = &vdpasim_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, -1 , dev_attr->name, false); + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, + dev_attr->ngroups, dev_attr->nas, + dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim); goto err_alloc;
@@ -278,16 +285,20 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)if (!vdpasim->vqs) goto err_iommu; - vdpasim->iommu =vhost_iotlb_alloc (max_iotlb_entries,0 ); + vdpasim->iommu =kmalloc_array (vdpasim->dev_attr.nas, +sizeof (*vdpasim->iommu),GFP_KERNEL );if (!vdpasim->iommu) goto err_iommu; +for (i =0 ; i < vdpasim->dev_attr.nas; i++) +vhost_iotlb_init (&vdpasim->iommu[i],0 ,0 ); + vdpasim->buffer =kvmalloc (dev_attr->buffer_size,GFP_KERNEL );if (!vdpasim->buffer) goto err_iommu;for (i =0 ; i < dev_attr->nvqs; i++) -vringh_set_iotlb (&vdpasim->vqs[i].vring, vdpasim->iommu, +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ], &vdpasim->iommu_lock); ret =iova_cache_get ();
@@ -401,7 +412,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)static u32 vdpasim_get_vq_group (struct vdpa_device *vdpa,u16 idx) { -return 0 ; +/* RX and TX belongs to group 0, CVQ belongs to group 1 */ +if (idx ==2 ) +return 1 ; +else +return 0 ; }static u64 vdpasim_get_device_features (struct vdpa_device *vdpa)
@@ -539,20 +554,53 @@ static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)return range; } +static int vdpasim_set_group_asid (struct vdpa_device *vdpa,unsigned int group, +unsigned int asid) +{ +struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +struct vhost_iotlb *iommu; +int i; + +if (group > vdpasim->dev_attr.ngroups) +return -EINVAL ; + +if (asid > vdpasim->dev_attr.nas) +return -EINVAL ; + + iommu = &vdpasim->iommu[asid]; + +spin_lock (&vdpasim->lock); + +for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) +if (vdpasim_get_vq_group (vdpa, i) == group) +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ], + &vdpasim->iommu_lock); + +spin_unlock (&vdpasim->lock); + +return 0 ; +} +static int vdpasim_set_map (struct vdpa_device *vdpa,unsigned int asid,struct vhost_iotlb *iotlb) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);struct vhost_iotlb_map *map; +struct vhost_iotlb *iommu;u64 start =0ULL , last =0ULL -1 ;int ret; +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu); + + iommu = &vdpasim->iommu[asid]; +vhost_iotlb_reset (iommu);for (map =vhost_iotlb_itree_first (iotlb, start, last); map; map =vhost_iotlb_itree_next (map, start, last)) { - ret =vhost_iotlb_add_range (vdpasim->iommu, map->start, + ret =vhost_iotlb_add_range (iommu, map->start, map->last, map->addr, map->perm);if (ret) goto err;
@@ -561,7 +609,7 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,return 0 ; err: -vhost_iotlb_reset (vdpasim->iommu); +vhost_iotlb_reset (iommu);spin_unlock (&vdpasim->iommu_lock);return ret; }
@@ -573,9 +621,12 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,struct vdpasim *vdpasim =vdpa_to_sim (vdpa);int ret; +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range_ctx (vdpasim->iommu, iova, iova + size -1 , - pa, perm, opaque); + ret =vhost_iotlb_add_range_ctx (&vdpasim->iommu[asid], iova, + iova + size -1 , pa, perm, opaque);spin_unlock (&vdpasim->iommu_lock);return ret;
@@ -586,8 +637,11 @@ static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid, {struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, iova, iova + size -1 ); +vhost_iotlb_del_range (&vdpasim->iommu[asid], iova, iova + size -1 );spin_unlock (&vdpasim->iommu_lock);return 0 ;
@@ -611,8 +665,7 @@ static void vdpasim_free(struct vdpa_device *vdpa) }kvfree (vdpasim->buffer); -if (vdpasim->iommu) -vhost_iotlb_free (vdpasim->iommu); +vhost_iotlb_free (vdpasim->iommu);kfree (vdpasim->vqs);kfree (vdpasim->config); }
@@ -643,6 +696,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .dma_map = vdpasim_dma_map, .dma_unmap = vdpasim_dma_unmap, .free = vdpasim_free,
@@ -674,6 +728,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .set_map = vdpasim_set_map, .free = vdpasim_free, };
drivers/vdpa/vdpa_sim/vdpa_sim.h +2 -0
@@ -41,6 +41,8 @@ struct vdpasim_dev_attr {size_t buffer_size;int nvqs;u32 id; +u32 ngroups; +u32 nas;work_func_t work_fn;void (*get_config)(struct vdpasim *vdpasim,void *config);
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +86 -2
114 lines not on this page · raw message
Signature · 1 line
2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 19/19] vdpasim: control virtqueue support
Quoted 272 lines · Gautam Dawar
This patch introduces the control virtqueue support for vDPA simulator. This is a requirement for supporting advanced features like multiqueue.
A requirement for control virtqueue is to isolate its memory access from the rx/tx virtqueues. This is because when using vDPA device for VM, the control virqueue is not directly assigned to VM. Userspace (Qemu) will present a shadow control virtqueue to control for recording the device states.
The isolation is done via the virtqueue groups and ASID support in vDPA through vhost-vdpa. The simulator is extended to have:
1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue)
2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 contains CVQ
3) two address spaces and the simulator simply implements the address spaces by mapping it 1:1 to IOTLB.For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 to group 1. So we have:
1) The IOTLB for virtqueue group 0 contains the mappings of guest, so RX and TX can be assigned to guest directly.
2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which is the buffers that allocated and managed by VMM only. So CVQ of vhost-vdpa is visible to VMM only. And Guest can not access the CVQ of vhost-vdpa.For the other use cases, since AS 0 is associated to all virtqueue groups by default. All virtqueues share the same mapping by default.
To demonstrate the function,
VIRITO_NET_F_CTRL_MACADDRis implemented in the simulator for the driver to set mac address.Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 91 ++++++++++++++++++++++------ drivers/vdpa/vdpa_sim/vdpa_sim.h | 2 + drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 88 ++++++++++++++++++++++++++- 3 files changed, 161 insertions(+), 20 deletions(-)drivers/vdpa/vdpa_sim/vdpa_sim.c +73
-18@@ -96,11 +96,17 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim) {int i; -for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) +spin_lock (&vdpasim->iommu_lock); + +for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) {vdpasim_vq_reset (vdpasim, &vdpasim->vqs[i]); +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ], + &vdpasim->iommu_lock); + } + +for (i =0 ; i < vdpasim->dev_attr.nas; i++) +vhost_iotlb_reset (&vdpasim->iommu[i]); -spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu);spin_unlock (&vdpasim->iommu_lock); vdpasim->features =0 ;@@ -145,7 +151,7 @@ static dma_addr_t vdpasim_map_range(struct vdpasim *vdpasim, phys_addr_t paddr, dma_addr =iova_dma_addr (&vdpasim->iova, iova);spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range (vdpasim->iommu, (u64 )dma_addr, + ret =vhost_iotlb_add_range (&vdpasim->iommu[0 ], (u64 )dma_addr, (u64 )dma_addr + size -1 , (u64 )paddr, perm);spin_unlock (&vdpasim->iommu_lock);@@ -161,7 +167,7 @@ static void vdpasim_unmap_range(struct vdpasim *vdpasim, dma_addr_t dma_addr, size_t size) {spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, (u64 )dma_addr, +vhost_iotlb_del_range (&vdpasim->iommu[0 ], (u64 )dma_addr, (u64 )dma_addr + size -1 );spin_unlock (&vdpasim->iommu_lock);@@ -250,8 +256,9 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)else ops = &vdpasim_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, -1 , dev_attr->name, false); + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, + dev_attr->ngroups, dev_attr->nas, + dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim); goto err_alloc;@@ -278,16 +285,20 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)if (!vdpasim->vqs) goto err_iommu; - vdpasim->iommu =vhost_iotlb_alloc (max_iotlb_entries,0 ); + vdpasim->iommu =kmalloc_array (vdpasim->dev_attr.nas, +sizeof (*vdpasim->iommu),GFP_KERNEL );if (!vdpasim->iommu) goto err_iommu; +for (i =0 ; i < vdpasim->dev_attr.nas; i++) +vhost_iotlb_init (&vdpasim->iommu[i],0 ,0 ); + vdpasim->buffer =kvmalloc (dev_attr->buffer_size,GFP_KERNEL );if (!vdpasim->buffer) goto err_iommu;for (i =0 ; i < dev_attr->nvqs; i++) -vringh_set_iotlb (&vdpasim->vqs[i].vring, vdpasim->iommu, +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ], &vdpasim->iommu_lock); ret =iova_cache_get ();@@ -401,7 +412,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)static u32 vdpasim_get_vq_group (struct vdpa_device *vdpa,u16 idx) { -return 0 ; +/* RX and TX belongs to group 0, CVQ belongs to group 1 */ +if (idx ==2 ) +return 1 ; +else +return 0 ; }static u64 vdpasim_get_device_features (struct vdpa_device *vdpa)@@ -539,20 +554,53 @@ static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)return range; } +static int vdpasim_set_group_asid (struct vdpa_device *vdpa,unsigned int group, +unsigned int asid) +{ +struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +struct vhost_iotlb *iommu; +int i; + +if (group > vdpasim->dev_attr.ngroups) +return -EINVAL ; + +if (asid > vdpasim->dev_attr.nas) +return -EINVAL ; + + iommu = &vdpasim->iommu[asid]; + +spin_lock (&vdpasim->lock); + +for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) +if (vdpasim_get_vq_group (vdpa, i) == group) +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ], + &vdpasim->iommu_lock); + +spin_unlock (&vdpasim->lock); + +return 0 ; +} +static int vdpasim_set_map (struct vdpa_device *vdpa,unsigned int asid,struct vhost_iotlb *iotlb) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);struct vhost_iotlb_map *map; +struct vhost_iotlb *iommu;u64 start =0ULL , last =0ULL -1 ;int ret; +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu); + + iommu = &vdpasim->iommu[asid]; +vhost_iotlb_reset (iommu);for (map =vhost_iotlb_itree_first (iotlb, start, last); map; map =vhost_iotlb_itree_next (map, start, last)) { - ret =vhost_iotlb_add_range (vdpasim->iommu, map->start, + ret =vhost_iotlb_add_range (iommu, map->start, map->last, map->addr, map->perm);if (ret) goto err;@@ -561,7 +609,7 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,return 0 ; err: -vhost_iotlb_reset (vdpasim->iommu); +vhost_iotlb_reset (iommu);spin_unlock (&vdpasim->iommu_lock);return ret; }@@ -573,9 +621,12 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,struct vdpasim *vdpasim =vdpa_to_sim (vdpa);int ret; +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range_ctx (vdpasim->iommu, iova, iova + size -1 , - pa, perm, opaque); + ret =vhost_iotlb_add_range_ctx (&vdpasim->iommu[asid], iova, + iova + size -1 , pa, perm, opaque);spin_unlock (&vdpasim->iommu_lock);return ret;@@ -586,8 +637,11 @@ static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid, {struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, iova, iova + size -1 ); +vhost_iotlb_del_range (&vdpasim->iommu[asid], iova, iova + size -1 );spin_unlock (&vdpasim->iommu_lock);return 0 ;@@ -611,8 +665,7 @@ static void vdpasim_free(struct vdpa_device *vdpa) }kvfree (vdpasim->buffer); -if (vdpasim->iommu) -vhost_iotlb_free (vdpasim->iommu); +vhost_iotlb_free (vdpasim->iommu);kfree (vdpasim->vqs);kfree (vdpasim->config); }@@ -643,6 +696,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .dma_map = vdpasim_dma_map, .dma_unmap = vdpasim_dma_unmap, .free = vdpasim_free,@@ -674,6 +728,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .set_map = vdpasim_set_map, .free = vdpasim_free, };drivers/vdpa/vdpa_sim/vdpa_sim.h +2
-0@@ -41,6 +41,8 @@ struct vdpasim_dev_attr {size_t buffer_size;int nvqs;u32 id; +u32 ngroups; +u32 nas;work_func_t work_fn;void (*get_config)(struct vdpasim *vdpasim,void *config);drivers/vdpa/vdpa_sim/vdpa_sim_net.c +0
-0
drivers/vdpa/vdpa_sim/vdpa_sim_net.c line 29
Quoted 4 lines
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +1
-0@@ -26,10 +26,15 @@#define DRV_LICENSE "GPL v2"#define VDPASIM_NET_FEATURES (VDPASIM_FEATURES | \ + (1ULL << VIRTIO_NET_F_MTU) | \
Why the reorder here?
Quoted 18 lines
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +7
-2(1ULL <<VIRTIO_NET_F_MAC ) | \ - (1ULL << VIRTIO_NET_F_MTU)); + (1ULL <<VIRTIO_NET_F_CTRL_VQ ) | \ + (1ULL << VIRTIO_NET_F_CTRL_MAC_ADDR)); -#define VDPASIM_NET_VQ_NUM 2 +/* 3 virtqueues, 2 address spaces, 2 virtqueue groups */ +#define VDPASIM_NET_VQ_NUM 3 +#define VDPASIM_NET_AS_NUM 2 +#define VDPASIM_NET_GROUP_NUM 2static void vdpasim_net_complete (struct vdpasim_virtqueue *vq,size_t len) {@@ -63,6 +68,81 @@ static bool receive_filter(struct vdpasim *vdpasim, size_t len)return false; } +static virtio_net_ctrl_ack vdpasim_handle_ctrl_mac(struct vdpasim *vdpasim,
drivers/vdpa/vdpa_sim/vdpa_sim_net.c static bool receive_filter(struct vdpasim *vdpasim, size_t len) · line 81
Quoted 10 lines
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +10
-0+ u8 cmd) +{ +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +size_t read; + +switch (cmd) { +case VIRTIO_NET_CTRL_MAC_ADDR_SET : + read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->in_iov, + (void *)vdpasim->config.mac,
This is not valid anymore as config is of type void *. Need to convert to virtio_net_config. This also occurs in receive_filter.
You can copy how vdpasim_net_setup_config does it, for example.
Thanks!
Quoted 88 lines
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +68
-1+ ETH_ALEN); +if (read ==ETH_ALEN ) + status =VIRTIO_NET_OK ; +break ; +default : +break ; + } + +return status; +} + +static void vdpasim_handle_cvq (struct vdpasim *vdpasim) +{ +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +struct virtio_net_ctrl_hdr ctrl; +size_t read, write; +int err; + +if (!(vdpasim->features & (1ULL <<VIRTIO_NET_F_CTRL_VQ ))) +return ; + +if (!cvq->ready) +return ; + +while (true) { + err =vringh_getdesc_iotlb (&cvq->vring, &cvq->in_iov, + &cvq->out_iov, + &cvq->head,GFP_ATOMIC ); +if (err <=0 ) +break ; + + read =vringh_iov_pull_iotlb (&cvq->vring, &cvq->in_iov, &ctrl, +sizeof (ctrl)); +if (read !=sizeof (ctrl)) +break ; + +switch (ctrl.class) { +case VIRTIO_NET_CTRL_MAC : + status =vdpasim_handle_ctrl_mac (vdpasim, ctrl.cmd); +break ; +default : +break ; + } + +/* Make sure data is wrote before advancing index */ +smp_wmb (); + + write =vringh_iov_push_iotlb (&cvq->vring, &cvq->out_iov, + &status,sizeof (status)); +vringh_complete_iotlb (&cvq->vring, cvq->head, write); +vringh_kiov_cleanup (&cvq->in_iov); +vringh_kiov_cleanup (&cvq->out_iov); + +/* Make sure used is visible before rasing the interrupt. */ +smp_wmb (); + +local_bh_disable (); +if (cvq->cb) + cvq->cb (cvq->private); +local_bh_enable (); + } +} +static void vdpasim_net_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);@@ -77,6 +157,8 @@ static void vdpasim_net_work(struct work_struct *work)if (!(vdpasim->status &VIRTIO_CONFIG_S_DRIVER_OK )) goto out; +vdpasim_handle_cvq (vdpasim); +if (!txq->ready || !rxq->ready) goto out;@@ -162,6 +244,8 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, dev_attr.id =VIRTIO_ID_NET ; dev_attr.supported_features =VDPASIM_NET_FEATURES ; dev_attr.nvqs =VDPASIM_NET_VQ_NUM ; + dev_attr.ngroups =VDPASIM_NET_GROUP_NUM ; + dev_attr.nas =VDPASIM_NET_AS_NUM ; dev_attr.config_size =sizeof (struct virtio_net_config ); dev_attr.get_config = vdpasim_net_get_config; dev_attr.work_fn = vdpasim_net_work; --2.25.0
Eugenio Perez Martin
maintainerRe: [RFC PATCH v2 19/19] vdpasim: control virtqueue support
In reply to Gautam DawarQuoted 149 lines · Gautam Dawar
This patch introduces the control virtqueue support for vDPA simulator. This is a requirement for supporting advanced features like multiqueue.
A requirement for control virtqueue is to isolate its memory access from the rx/tx virtqueues. This is because when using vDPA device for VM, the control virqueue is not directly assigned to VM. Userspace (Qemu) will present a shadow control virtqueue to control for recording the device states.
The isolation is done via the virtqueue groups and ASID support in vDPA through vhost-vdpa. The simulator is extended to have:
1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue)
2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 contains CVQ
3) two address spaces and the simulator simply implements the address spaces by mapping it 1:1 to IOTLB.For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 to group 1. So we have:
1) The IOTLB for virtqueue group 0 contains the mappings of guest, so RX and TX can be assigned to guest directly.
2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which is the buffers that allocated and managed by VMM only. So CVQ of vhost-vdpa is visible to VMM only. And Guest can not access the CVQ of vhost-vdpa.For the other use cases, since AS 0 is associated to all virtqueue groups by default. All virtqueues share the same mapping by default.
To demonstrate the function,
VIRITO_NET_F_CTRL_MACADDRis implemented in the simulator for the driver to set mac address.Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 91 ++++++++++++++++++++++------ drivers/vdpa/vdpa_sim/vdpa_sim.h | 2 + drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 88 ++++++++++++++++++++++++++- 3 files changed, 161 insertions(+), 20 deletions(-)drivers/vdpa/vdpa_sim/vdpa_sim.c +35
-10@@ -96,11 +96,17 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim) {int i; -for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) +spin_lock (&vdpasim->iommu_lock); + +for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) {vdpasim_vq_reset (vdpasim, &vdpasim->vqs[i]); +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ], + &vdpasim->iommu_lock); + } + +for (i =0 ; i < vdpasim->dev_attr.nas; i++) +vhost_iotlb_reset (&vdpasim->iommu[i]); -spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu);spin_unlock (&vdpasim->iommu_lock); vdpasim->features =0 ;@@ -145,7 +151,7 @@ static dma_addr_t vdpasim_map_range(struct vdpasim *vdpasim, phys_addr_t paddr, dma_addr =iova_dma_addr (&vdpasim->iova, iova);spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range (vdpasim->iommu, (u64 )dma_addr, + ret =vhost_iotlb_add_range (&vdpasim->iommu[0 ], (u64 )dma_addr, (u64 )dma_addr + size -1 , (u64 )paddr, perm);spin_unlock (&vdpasim->iommu_lock);@@ -161,7 +167,7 @@ static void vdpasim_unmap_range(struct vdpasim *vdpasim, dma_addr_t dma_addr, size_t size) {spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, (u64 )dma_addr, +vhost_iotlb_del_range (&vdpasim->iommu[0 ], (u64 )dma_addr, (u64 )dma_addr + size -1 );spin_unlock (&vdpasim->iommu_lock);@@ -250,8 +256,9 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)else ops = &vdpasim_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, -1 , dev_attr->name, false); + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, + dev_attr->ngroups, dev_attr->nas, + dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim); goto err_alloc;@@ -278,16 +285,20 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)if (!vdpasim->vqs) goto err_iommu; - vdpasim->iommu =vhost_iotlb_alloc (max_iotlb_entries,0 ); + vdpasim->iommu =kmalloc_array (vdpasim->dev_attr.nas, +sizeof (*vdpasim->iommu),GFP_KERNEL );if (!vdpasim->iommu) goto err_iommu; +for (i =0 ; i < vdpasim->dev_attr.nas; i++) +vhost_iotlb_init (&vdpasim->iommu[i],0 ,0 ); + vdpasim->buffer =kvmalloc (dev_attr->buffer_size,GFP_KERNEL );if (!vdpasim->buffer) goto err_iommu;for (i =0 ; i < dev_attr->nvqs; i++) -vringh_set_iotlb (&vdpasim->vqs[i].vring, vdpasim->iommu, +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ], &vdpasim->iommu_lock); ret =iova_cache_get ();@@ -401,7 +412,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)static u32 vdpasim_get_vq_group (struct vdpa_device *vdpa,u16 idx) { -return 0 ; +/* RX and TX belongs to group 0, CVQ belongs to group 1 */ +if (idx ==2 ) +return 1 ; +else +return 0 ; }static u64 vdpasim_get_device_features (struct vdpa_device *vdpa)@@ -539,20 +554,53 @@ static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)return range; } +static int vdpasim_set_group_asid (struct vdpa_device *vdpa,unsigned int group, +unsigned int asid) +{ +struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +struct vhost_iotlb *iommu; +int i; + +if (group > vdpasim->dev_attr.ngroups) +return -EINVAL ; +
drivers/vdpa/vdpa_sim/vdpa_sim.c static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa) · line 576
Quoted 10 lines
drivers/vdpa/vdpa_sim/vdpa_sim.c +10
-0+if (asid > vdpasim->dev_attr.nas) +return -EINVAL ; + + iommu = &vdpasim->iommu[asid]; + +spin_lock (&vdpasim->lock); + +for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) +if (vdpasim_get_vq_group (vdpa, i) == group) + vringh_set_iotlb(&vdpasim->vqs[i].vring, &vdpasim->iommu[0],
The second argument to "vringh_set_iotlb" call must be simply "iommu". If not, we're effectively setting asid 0 to all virtqueue groups that match "group", making it impossible to change it.
Thanks!
Quoted 233 lines
drivers/vdpa/vdpa_sim/vdpa_sim.c +28
-8+ &vdpasim->iommu_lock); + +spin_unlock (&vdpasim->lock); + +return 0 ; +} +static int vdpasim_set_map (struct vdpa_device *vdpa,unsigned int asid,struct vhost_iotlb *iotlb) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);struct vhost_iotlb_map *map; +struct vhost_iotlb *iommu;u64 start =0ULL , last =0ULL -1 ;int ret; +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu); + + iommu = &vdpasim->iommu[asid]; +vhost_iotlb_reset (iommu);for (map =vhost_iotlb_itree_first (iotlb, start, last); map; map =vhost_iotlb_itree_next (map, start, last)) { - ret =vhost_iotlb_add_range (vdpasim->iommu, map->start, + ret =vhost_iotlb_add_range (iommu, map->start, map->last, map->addr, map->perm);if (ret) goto err;@@ -561,7 +609,7 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,return 0 ; err: -vhost_iotlb_reset (vdpasim->iommu); +vhost_iotlb_reset (iommu);spin_unlock (&vdpasim->iommu_lock);return ret; }@@ -573,9 +621,12 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,struct vdpasim *vdpasim =vdpa_to_sim (vdpa);int ret; +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range_ctx (vdpasim->iommu, iova, iova + size -1 , - pa, perm, opaque); + ret =vhost_iotlb_add_range_ctx (&vdpasim->iommu[asid], iova, + iova + size -1 , pa, perm, opaque);spin_unlock (&vdpasim->iommu_lock);return ret;@@ -586,8 +637,11 @@ static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid, {struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, iova, iova + size -1 ); +vhost_iotlb_del_range (&vdpasim->iommu[asid], iova, iova + size -1 );spin_unlock (&vdpasim->iommu_lock);return 0 ;@@ -611,8 +665,7 @@ static void vdpasim_free(struct vdpa_device *vdpa) }kvfree (vdpasim->buffer); -if (vdpasim->iommu) -vhost_iotlb_free (vdpasim->iommu); +vhost_iotlb_free (vdpasim->iommu);kfree (vdpasim->vqs);kfree (vdpasim->config); }@@ -643,6 +696,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .dma_map = vdpasim_dma_map, .dma_unmap = vdpasim_dma_unmap, .free = vdpasim_free,@@ -674,6 +728,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .set_map = vdpasim_set_map, .free = vdpasim_free, };drivers/vdpa/vdpa_sim/vdpa_sim.h +2
-0@@ -41,6 +41,8 @@ struct vdpasim_dev_attr {size_t buffer_size;int nvqs;u32 id; +u32 ngroups; +u32 nas;work_func_t work_fn;void (*get_config)(struct vdpasim *vdpasim,void *config);drivers/vdpa/vdpa_sim/vdpa_sim_net.c +86
-3@@ -26,10 +26,15 @@#define DRV_LICENSE "GPL v2"#define VDPASIM_NET_FEATURES (VDPASIM_FEATURES | \ + (1ULL << VIRTIO_NET_F_MTU) | \ (1ULL << VIRTIO_NET_F_MAC) | \ - (1ULL << VIRTIO_NET_F_MTU)); + (1ULL << VIRTIO_NET_F_CTRL_VQ) | \ + (1ULL << VIRTIO_NET_F_CTRL_MAC_ADDR)); -#define VDPASIM_NET_VQ_NUM 2 +/* 3 virtqueues, 2 address spaces, 2 virtqueue groups */ +#define VDPASIM_NET_VQ_NUM 3 +#define VDPASIM_NET_AS_NUM 2 +#define VDPASIM_NET_GROUP_NUM 2static void vdpasim_net_complete (struct vdpasim_virtqueue *vq,size_t len) {@@ -63,6 +68,81 @@ static bool receive_filter(struct vdpasim *vdpasim, size_t len)return false; } +static virtio_net_ctrl_ack vdpasim_handle_ctrl_mac (struct vdpasim *vdpasim, +u8 cmd) +{ +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +size_t read; + +switch (cmd) { +case VIRTIO_NET_CTRL_MAC_ADDR_SET : + read =vringh_iov_pull_iotlb (&cvq->vring, &cvq->in_iov, + (void *)vdpasim->config.mac, +ETH_ALEN ); +if (read ==ETH_ALEN ) + status =VIRTIO_NET_OK ; +break ; +default : +break ; + } + +return status; +} + +static void vdpasim_handle_cvq (struct vdpasim *vdpasim) +{ +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +struct virtio_net_ctrl_hdr ctrl; +size_t read, write; +int err; + +if (!(vdpasim->features & (1ULL <<VIRTIO_NET_F_CTRL_VQ ))) +return ; + +if (!cvq->ready) +return ; + +while (true) { + err =vringh_getdesc_iotlb (&cvq->vring, &cvq->in_iov, + &cvq->out_iov, + &cvq->head,GFP_ATOMIC ); +if (err <=0 ) +break ; + + read =vringh_iov_pull_iotlb (&cvq->vring, &cvq->in_iov, &ctrl, +sizeof (ctrl)); +if (read !=sizeof (ctrl)) +break ; + +switch (ctrl.class) { +case VIRTIO_NET_CTRL_MAC : + status =vdpasim_handle_ctrl_mac (vdpasim, ctrl.cmd); +break ; +default : +break ; + } + +/* Make sure data is wrote before advancing index */ +smp_wmb (); + + write =vringh_iov_push_iotlb (&cvq->vring, &cvq->out_iov, + &status,sizeof (status)); +vringh_complete_iotlb (&cvq->vring, cvq->head, write); +vringh_kiov_cleanup (&cvq->in_iov); +vringh_kiov_cleanup (&cvq->out_iov); + +/* Make sure used is visible before rasing the interrupt. */ +smp_wmb (); + +local_bh_disable (); +if (cvq->cb) + cvq->cb (cvq->private); +local_bh_enable (); + } +} +static void vdpasim_net_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);@@ -77,6 +157,8 @@ static void vdpasim_net_work(struct work_struct *work)if (!(vdpasim->status &VIRTIO_CONFIG_S_DRIVER_OK )) goto out; +vdpasim_handle_cvq (vdpasim); +if (!txq->ready || !rxq->ready) goto out;@@ -162,6 +244,8 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, dev_attr.id =VIRTIO_ID_NET ; dev_attr.supported_features =VDPASIM_NET_FEATURES ; dev_attr.nvqs =VDPASIM_NET_VQ_NUM ; + dev_attr.ngroups =VDPASIM_NET_GROUP_NUM ; + dev_attr.nas =VDPASIM_NET_AS_NUM ; dev_attr.config_size =sizeof (struct virtio_net_config ); dev_attr.get_config = vdpasim_net_get_config; dev_attr.work_fn = vdpasim_net_work; --2.25.0
RE: [RFC PATCH v2 19/19] vdpasim: control virtqueue support
-----Original Message-----
From: Eugenio Perez Martin <[email protected]>
Sent: Friday, March 18, 2022 1:05 PM
To: Gautam Dawar <[email protected]>
Cc: Gautam Dawar <[email protected]>; Martin Petrus Hubertus Habets <[email protected]>; Harpreet Singh Anand <[email protected]>; Tanuj Murlidhar Kamde <[email protected]>; Jason Wang <[email protected]>; Michael S. Tsirkin <[email protected]>; Zhu Lingshan <[email protected]>; Stefano Garzarella <[email protected]>; Xie Yongji <[email protected]>; Eli Cohen <[email protected]>; Si-Wei Liu <[email protected]>; Parav Pandit <[email protected]>; Longpeng <[email protected]>; virtualization <[email protected]>; [email protected]; kvm list <[email protected]>; [email protected]
Subject: Re: [RFC PATCH v2 19/19] vdpasim: control virtqueue support
Quoted 151 lines · Gautam Dawar
This patch introduces the control virtqueue support for vDPA simulator. This is a requirement for supporting advanced features like multiqueue.
A requirement for control virtqueue is to isolate its memory access from the rx/tx virtqueues. This is because when using vDPA device for VM, the control virqueue is not directly assigned to VM. Userspace (Qemu) will present a shadow control virtqueue to control for recording the device states.
The isolation is done via the virtqueue groups and ASID support in vDPA through vhost-vdpa. The simulator is extended to have:
1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue)
2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 contains CVQ
3) two address spaces and the simulator simply implements the address spaces by mapping it 1:1 to IOTLB.For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 to group 1. So we have:
1) The IOTLB for virtqueue group 0 contains the mappings of guest, so RX and TX can be assigned to guest directly.
2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which is the buffers that allocated and managed by VMM only. So CVQ of vhost-vdpa is visible to VMM only. And Guest can not access the CVQ of vhost-vdpa.For the other use cases, since AS 0 is associated to all virtqueue groups by default. All virtqueues share the same mapping by default.
To demonstrate the function,
VIRITO_NET_F_CTRL_MACADDRis implemented in the simulator for the driver to set mac address.Signed-off-by Jason Wang <[email protected]>Signed-off-by Gautam Dawar <[email protected]>--- drivers/vdpa/vdpa_sim/vdpa_sim.c | 91 ++++++++++++++++++++++------ drivers/vdpa/vdpa_sim/vdpa_sim.h | 2 + drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 88 ++++++++++++++++++++++++++- 3 files changed, 161 insertions(+), 20 deletions(-)drivers/vdpa/vdpa_sim/vdpa_sim.c +37
-11@@ -96,11 +96,17 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim) {int i; -for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) +spin_lock (&vdpasim->iommu_lock); + +for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) {vdpasim_vq_reset (vdpasim, &vdpasim->vqs[i]); +vringh_set_iotlb (&vdpasim->vqs[i].vring, &vdpasim->iommu[0 ], + &vdpasim->iommu_lock); + } + +for (i =0 ; i < vdpasim->dev_attr.nas; i++) +vhost_iotlb_reset (&vdpasim->iommu[i]); -spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu);spin_unlock (&vdpasim->iommu_lock); vdpasim->features =0 ;@@ -145,7 +151,7 @@ static dma_addr_t vdpasim_map_range(struct vdpasim *vdpasim, phys_addr_t paddr, dma_addr =iova_dma_addr (&vdpasim->iova, iova);spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range (vdpasim->iommu, (u64 )dma_addr, + ret =vhost_iotlb_add_range (&vdpasim->iommu[0 ], (u64 )dma_addr, (u64 )dma_addr + size -1 , (u64 )paddr, perm);spin_unlock (&vdpasim->iommu_lock);@@ -161,7 +167,7 @@ static void vdpasim_unmap_range(struct vdpasim *vdpasim, dma_addr_t dma_addr, size_t size) {spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, (u64 )dma_addr, +vhost_iotlb_del_range (&vdpasim->iommu[0 ], (u64 )dma_addr, (u64 )dma_addr + size -1 );spin_unlock (&vdpasim->iommu_lock);@@ -250,8 +256,9 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)else ops = &vdpasim_config_ops; - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1, -1 , dev_attr->name, false); + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, + dev_attr->ngroups, dev_attr->nas, + dev_attr->name, false);if (IS_ERR (vdpasim)) { ret =PTR_ERR (vdpasim); goto err_alloc;@@ -278,16 +285,20 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)if (!vdpasim->vqs) goto err_iommu; - vdpasim->iommu =vhost_iotlb_alloc (max_iotlb_entries,0 ); + vdpasim->iommu =kmalloc_array (vdpasim->dev_attr.nas, +sizeof (*vdpasim->iommu), +GFP_KERNEL );if (!vdpasim->iommu) goto err_iommu; +for (i =0 ; i < vdpasim->dev_attr.nas; i++) +vhost_iotlb_init (&vdpasim->iommu[i],0 ,0 ); + vdpasim->buffer =kvmalloc (dev_attr->buffer_size,GFP_KERNEL );if (!vdpasim->buffer) goto err_iommu;for (i =0 ; i < dev_attr->nvqs; i++) -vringh_set_iotlb (&vdpasim->vqs[i].vring, vdpasim->iommu, +vringh_set_iotlb (&vdpasim->vqs[i].vring, + &vdpasim->iommu[0 ], &vdpasim->iommu_lock); ret =iova_cache_get ();@@ -401,7 +412,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)static u32 vdpasim_get_vq_group (struct vdpa_device *vdpa,u16 idx) { -return 0 ; +/* RX and TX belongs to group 0, CVQ belongs to group 1 */ +if (idx ==2 ) +return 1 ; +else +return 0 ; } static u64 vdpasim_get_device_features(struct vdpa_device *vdpa) @@ -539,20 +554,53 @@ static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)return range; } +static int vdpasim_set_group_asid (struct vdpa_device *vdpa,unsigned int group, +unsigned int asid) { +struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +struct vhost_iotlb *iommu; +int i; + +if (group > vdpasim->dev_attr.ngroups) +return -EINVAL ; + +if (asid > vdpasim->dev_attr.nas)
drivers/vdpa/vdpa_sim/vdpa_sim.c static u32 vdpasim_get_vq_align(struct
Quoted 10 lines
drivers/vdpa/vdpa_sim/vdpa_sim.c +10
-0+return -EINVAL ; + + iommu = &vdpasim->iommu[asid]; + +spin_lock (&vdpasim->lock); + +for (i =0 ; i < vdpasim->dev_attr.nvqs; i++) +if (vdpasim_get_vq_group (vdpa, i) == group) + vringh_set_iotlb(&vdpasim->vqs[i].vring, + &vdpasim->iommu[0],
The second argument to "vringh_set_iotlb" call must be simply "iommu".
If not, we're effectively setting asid 0 to all virtqueue groups that match "group", making it impossible to change it. [GD>>] I agree. Will fix this.
Thanks!
Quoted 234 lines
drivers/vdpa/vdpa_sim/vdpa_sim.c +30
-8+ &vdpasim->iommu_lock); + +spin_unlock (&vdpasim->lock); + +return 0 ; +} +static int vdpasim_set_map (struct vdpa_device *vdpa,unsigned int asid,struct vhost_iotlb *iotlb) {struct vdpasim *vdpasim =vdpa_to_sim (vdpa);struct vhost_iotlb_map *map; +struct vhost_iotlb *iommu;u64 start =0ULL , last =0ULL -1 ;int ret; +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_reset (vdpasim->iommu); + + iommu = &vdpasim->iommu[asid]; +vhost_iotlb_reset (iommu);for (map =vhost_iotlb_itree_first (iotlb, start, last); map; map =vhost_iotlb_itree_next (map, start, last)) { - ret =vhost_iotlb_add_range (vdpasim->iommu, map->start, + ret =vhost_iotlb_add_range (iommu, map->start, map->last, map->addr, map->perm);if (ret) goto err;@@ -561,7 +609,7 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,return 0 ; err: -vhost_iotlb_reset (vdpasim->iommu); +vhost_iotlb_reset (iommu);spin_unlock (&vdpasim->iommu_lock);return ret; }@@ -573,9 +621,12 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,struct vdpasim *vdpasim =vdpa_to_sim (vdpa);int ret; +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); - ret =vhost_iotlb_add_range_ctx (vdpasim->iommu, iova, iova + size -1 , - pa, perm, opaque); + ret =vhost_iotlb_add_range_ctx (&vdpasim->iommu[asid], iova, + iova + size -1 , pa, perm, + opaque);spin_unlock (&vdpasim->iommu_lock);return ret;@@ -586,8 +637,11 @@ static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid, {struct vdpasim *vdpasim =vdpa_to_sim (vdpa); +if (asid >= vdpasim->dev_attr.nas) +return -EINVAL ; +spin_lock (&vdpasim->iommu_lock); -vhost_iotlb_del_range (vdpasim->iommu, iova, iova + size -1 ); +vhost_iotlb_del_range (&vdpasim->iommu[asid], iova, iova + size + -1 );spin_unlock (&vdpasim->iommu_lock);return 0 ;@@ -611,8 +665,7 @@ static void vdpasim_free(struct vdpa_device *vdpa) }kvfree (vdpasim->buffer); -if (vdpasim->iommu) -vhost_iotlb_free (vdpasim->iommu); +vhost_iotlb_free (vdpasim->iommu);kfree (vdpasim->vqs);kfree (vdpasim->config); }@@ -643,6 +696,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .dma_map = vdpasim_dma_map, .dma_unmap = vdpasim_dma_unmap, .free = vdpasim_free,@@ -674,6 +728,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = { .set_config = vdpasim_set_config, .get_generation = vdpasim_get_generation, .get_iova_range = vdpasim_get_iova_range, + .set_group_asid = vdpasim_set_group_asid, .set_map = vdpasim_set_map, .free = vdpasim_free, };drivers/vdpa/vdpa_sim/vdpa_sim.h +2
-0@@ -41,6 +41,8 @@ struct vdpasim_dev_attr {size_t buffer_size;int nvqs;u32 id; +u32 ngroups; +u32 nas;work_func_t work_fn;void (*get_config)(struct vdpasim *vdpasim,void *config);drivers/vdpa/vdpa_sim/vdpa_sim_net.c +8
-2@@ -26,10 +26,15 @@#define DRV_LICENSE "GPL v2"#define VDPASIM_NET_FEATURES (VDPASIM_FEATURES | \ + (1ULL << VIRTIO_NET_F_MTU) | \ (1ULL << VIRTIO_NET_F_MAC) | \ - (1ULL << VIRTIO_NET_F_MTU)); + (1ULL << VIRTIO_NET_F_CTRL_VQ) | \ + (1ULL << + VIRTIO_NET_F_CTRL_MAC_ADDR)); -#define VDPASIM_NET_VQ_NUM 2 +/* 3 virtqueues, 2 address spaces, 2 virtqueue groups */ +#define VDPASIM_NET_VQ_NUM 3 +#define VDPASIM_NET_AS_NUM 2 +#define VDPASIM_NET_GROUP_NUM 2 static void vdpasim_net_complete(struct vdpasim_virtqueue *vq, size_tlen) { @@ -63,6 +68,81 @@ static bool
receive_filter(struct vdpasim *vdpasim, size_t len)return false;}
drivers/vdpa/vdpa_sim/vdpa_sim_net.c +73
-0+static virtio_net_ctrl_ack vdpasim_handle_ctrl_mac (struct vdpasim *vdpasim, +u8 cmd) { +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +size_t read; + +switch (cmd) { +case VIRTIO_NET_CTRL_MAC_ADDR_SET : + read =vringh_iov_pull_iotlb (&cvq->vring, &cvq->in_iov, + (void *)vdpasim->config.mac, +ETH_ALEN ); +if (read ==ETH_ALEN ) + status =VIRTIO_NET_OK ; +break ; +default : +break ; + } + +return status; +} + +static void vdpasim_handle_cvq (struct vdpasim *vdpasim) { +struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2 ]; +virtio_net_ctrl_ack status =VIRTIO_NET_ERR ; +struct virtio_net_ctrl_hdr ctrl; +size_t read, write; +int err; + +if (!(vdpasim->features & (1ULL <<VIRTIO_NET_F_CTRL_VQ ))) +return ; + +if (!cvq->ready) +return ; + +while (true) { + err =vringh_getdesc_iotlb (&cvq->vring, &cvq->in_iov, + &cvq->out_iov, + &cvq->head,GFP_ATOMIC ); +if (err <=0 ) +break ; + + read =vringh_iov_pull_iotlb (&cvq->vring, &cvq->in_iov, &ctrl, +sizeof (ctrl)); +if (read !=sizeof (ctrl)) +break ; + +switch (ctrl.class) { +case VIRTIO_NET_CTRL_MAC : + status =vdpasim_handle_ctrl_mac (vdpasim, ctrl.cmd); +break ; +default : +break ; + } + +/* Make sure data is wrote before advancing index */ +smp_wmb (); + + write =vringh_iov_push_iotlb (&cvq->vring, &cvq->out_iov, + &status,sizeof (status)); +vringh_complete_iotlb (&cvq->vring, cvq->head, write); +vringh_kiov_cleanup (&cvq->in_iov); +vringh_kiov_cleanup (&cvq->out_iov); + +/* Make sure used is visible before rasing the interrupt. */ +smp_wmb (); + +local_bh_disable (); +if (cvq->cb) + cvq->cb (cvq->private); +local_bh_enable (); + } +} +static void vdpasim_net_work (struct work_struct *work) { struct vdpasim *vdpasim = container_of(work, struct vdpasim,work); @@ -77,6 +157,8 @@ static void
vdpasim_net_work(struct work_struct *work)if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK)) goto out;drivers/vdpa/vdpa_sim/vdpa_sim_net.c +4
-1+vdpasim_handle_cvq (vdpasim); +if (!txq->ready || !rxq->ready) goto out;@@ -162,6 +244,8 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, dev_attr.id =VIRTIO_ID_NET ; dev_attr.supported_features =VDPASIM_NET_FEATURES ; dev_attr.nvqs =VDPASIM_NET_VQ_NUM ; + dev_attr.ngroups =VDPASIM_NET_GROUP_NUM ; + dev_attr.nas =VDPASIM_NET_AS_NUM ; dev_attr.config_size =sizeof (struct virtio_net_config ); dev_attr.get_config = vdpasim_net_get_config; dev_attr.work_fn = vdpasim_net_work; --2.25.0
Quoted 64 lines · Gautam Dawar
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accessing it directly.
To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address spaceDevice needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groupsThe mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commandsThis will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since v1:
Quoted 9 lines
- Rebased the v1 patch series on vhost branch of MST vhost git repo git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git/log/?h=vhost
- Updates to accommodatevdpa_simchanges from monolithic module in kernel used v1 patch series to current modularized class (net, block) based approach.
- Added new attributes (ngroups and nas) to "vdpasim_dev_attr" and propagated them fromvdpa_sim_nettovdpa_sim
- Widened the data-type for "asid" member ofvhost_msg_v2to__u32to accommodate PASID
This is great. Then the semantic matches exactly the PASID proposal here[1].
Quoted 7 lines
- Fixed the buildbot warnings
- Resolved all checkpatch.pl errors and warnings
- Tested both control and datapath with Xilinx Smartnic SN1000 series device using QEMU implementing the Shadow virtqueue and support for VQ groups and ASID available at:github.com/eugpermar/qemu/releases/tag/vdpa_sw_live_migration.d%2F asid_groups-v1.d%2F00
On top, we may extend the netlink protocol to report the mapping between virtqueue to its groups.
Thanks
[1] https://www.mail-archive.com/[email protected]/msg08077.html
Quoted 37 lines
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking invhost_vdpa_unmap()Thanks
Gautam Dawar (19):
vhost: move the backend feature bits tovhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertiseVIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue support
Quoted 17 lines
drivers/vdpa/ifcvf/ifcvf_main.c | 8 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 5 + drivers/vdpa/vdpa_sim/vdpa_sim.c | 100 ++++++++-- drivers/vdpa/vdpa_sim/vdpa_sim.h | 3 + drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 169 +++++++++++++---- drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 272 +++++++++++++++++++++------ drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 46 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 11 +- 15 files changed, 566 insertions(+), 138 deletions(-)
_______________________________________________
Virtualization mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Quoted 64 lines · Gautam Dawar
Hi All:
This series tries to add the support for control virtqueue in vDPA.
Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations.
When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is because Qemu needs to know the device state in order to start and stop device correctly (e.g for Live Migration).
This requies to isolate the memory mapping for control virtqueue presented by vhost-vDPA to prevent guest from accessing it directly.
To achieve this, vDPA introduce two new abstractions:
- address space: identified through address space id (ASID) and a set of memory mapping in maintained
- virtqueue group: the minimal set of virtqueues that must share an address spaceDevice needs to advertise the following attributes to vDPA:
- the number of address spaces supported in the device
- the number of virtqueue groups supported in the device
- the mappings from a specific virtqueue to its virtqueue groupsThe mappings from virtqueue to virtqueue groups is fixed and defined by vDPA device driver. E.g:
- For the device that has hardware ASID support, it can simply advertise a per virtqueue virtqueue group.
- For the device that does not have hardware ASID support, it can simply advertise a single virtqueue group that contains all virtqueues. Or if it wants a software emulated control virtqueue, it can advertise two virtqueue groups, one is for cvq, another is for the rest virtqueues.vDPA also allow to change the association between virtqueue group and address space. So in the case of control virtqueue, userspace VMM(Qemu) may use a dedicated address space for the control virtqueue group to isolate the memory mapping.
The vhost/vhost-vDPA is also extend for the userspace to:
- query the number of virtqueue groups and address spaces supported by the device
- query the virtqueue group for a specific virtqueue
- assocaite a virtqueue group with an address space
- send ASID based IOTLB commandsThis will help userspace VMM(Qemu) to detect whether the control vq could be supported and isolate memory mappings of control virtqueue from the others.
To demonstrate the usage, vDPA simulator is extended to support setting MAC address via a emulated control virtqueue.
Please review.
Changes since v1:
Quoted 9 lines
- Rebased the v1 patch series on vhost branch of MST vhost git repo git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git/log/?h=vhost
- Updates to accommodatevdpa_simchanges from monolithic module in kernel used v1 patch series to current modularized class (net, block) based approach.
- Added new attributes (ngroups and nas) to "vdpasim_dev_attr" and propagated them fromvdpa_sim_nettovdpa_sim
- Widened the data-type for "asid" member ofvhost_msg_v2to__u32to accommodate PASID
This is great. Then the semantic matches exactly the PASID proposal here[1].
Quoted 7 lines
- Fixed the buildbot warnings
- Resolved all checkpatch.pl errors and warnings
- Tested both control and datapath with Xilinx Smartnic SN1000 series device using QEMU implementing the Shadow virtqueue and support for VQ groups and ASID available at:github.com/eugpermar/qemu/releases/tag/vdpa_sw_live_migration.d%2F asid_groups-v1.d%2F00
On top, we may extend the netlink protocol to report the mapping between virtqueue to its groups. [GD>>] Yes, I've already discussed this with Eugenio. For testing purpose, I added the mapping in Xilinx netdriver "sfc".
Thanks
[1]
https://www.mail-archive.com/[email protected]/msg08077.html
Quoted 54 lines
Changes since RFC:
- tweak vhost uAPI documentation
- switch to use device specific IOTLB really in patch 4
- tweak the commit log
- fix that ASID in vhost is claimed to be 32 actually but 16bit actually
- fix use after free when using ASID with IOTLB batching requests
- switch to use Stefano's patch for having separated iov
- remove unused "used_as" variable
- fix the iotlb/asid checking invhost_vdpa_unmap()Thanks
Gautam Dawar (19):
vhost: move the backend feature bits tovhost_types.h
virtio-vdpa: don't set callback if virtio doesn't need it
vhost-vdpa: passing iotlb to IOMMU mapping helpers
vhost-vdpa: switch to use vhost-vdpa specific IOTLB
vdpa: introduce virtqueue groups
vdpa: multiple address spaces support
vdpa: introduce config operations for associating ASID to a virtqueue
group
vhost_iotlb: split out IOTLB initialization
vhost: support ASID in IOTLB API
vhost-vdpa: introduce asid based IOTLB
vhost-vdpa: introduce uAPI to get the number of virtqueue groups
vhost-vdpa: introduce uAPI to get the number of address spaces
vhost-vdpa: uAPI to get virtqueue group id
vhost-vdpa: introduce uAPI to set group ASID
vhost-vdpa: support ASID based IOTLB API
vdpa_sim: advertiseVIRTIO_NET_F_MTU
vdpa_sim: factor out buffer completion logic
vdpa_sim: filter destination mac address
vdpasim: control virtqueue supportdrivers/vdpa/ifcvf/ifcvf_main.c | 8 +- drivers/vdpa/mlx5/net/mlx5_vnet.c | 11 +- drivers/vdpa/vdpa.c | 5 + drivers/vdpa/vdpa_sim/vdpa_sim.c | 100 ++++++++-- drivers/vdpa/vdpa_sim/vdpa_sim.h | 3 + drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 169 +++++++++++++---- drivers/vhost/iotlb.c | 23 ++- drivers/vhost/vdpa.c | 272 +++++++++++++++++++++------ drivers/vhost/vhost.c | 23 ++- drivers/vhost/vhost.h | 4 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 46 ++++- include/linux/vhost_iotlb.h | 2 + include/uapi/linux/vhost.h | 25 ++- include/uapi/linux/vhost_types.h | 11 +- 15 files changed, 566 insertions(+), 138 deletions(-)