diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 18:49:45 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 18:49:45 +0000 |
commit | 2c3c1048746a4622d8c89a29670120dc8fab93c4 (patch) | |
tree | 848558de17fb3008cdf4d861b01ac7781903ce39 /drivers/vdpa/vdpa_sim | |
parent | Initial commit. (diff) | |
download | linux-upstream.tar.xz linux-upstream.zip |
Adding upstream version 6.1.76.upstream/6.1.76upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to '')
-rw-r--r-- | drivers/vdpa/vdpa_sim/Makefile | 4 | ||||
-rw-r--r-- | drivers/vdpa/vdpa_sim/vdpa_sim.c | 780 | ||||
-rw-r--r-- | drivers/vdpa/vdpa_sim/vdpa_sim.h | 114 | ||||
-rw-r--r-- | drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 458 | ||||
-rw-r--r-- | drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 338 |
5 files changed, 1694 insertions, 0 deletions
diff --git a/drivers/vdpa/vdpa_sim/Makefile b/drivers/vdpa/vdpa_sim/Makefile new file mode 100644 index 000000000..d45810330 --- /dev/null +++ b/drivers/vdpa/vdpa_sim/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_VDPA_SIM) += vdpa_sim.o +obj-$(CONFIG_VDPA_SIM_NET) += vdpa_sim_net.o +obj-$(CONFIG_VDPA_SIM_BLOCK) += vdpa_sim_blk.o diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c new file mode 100644 index 000000000..61bde476c --- /dev/null +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -0,0 +1,780 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VDPA device simulator core. + * + * Copyright (c) 2020, Red Hat Inc. All rights reserved. + * Author: Jason Wang <jasowang@redhat.com> + * + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/dma-map-ops.h> +#include <linux/vringh.h> +#include <linux/vdpa.h> +#include <linux/vhost_iotlb.h> +#include <linux/iova.h> +#include <uapi/linux/vdpa.h> + +#include "vdpa_sim.h" + +#define DRV_VERSION "0.1" +#define DRV_AUTHOR "Jason Wang <jasowang@redhat.com>" +#define DRV_DESC "vDPA Device Simulator core" +#define DRV_LICENSE "GPL v2" + +static int batch_mapping = 1; +module_param(batch_mapping, int, 0444); +MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable"); + +static int max_iotlb_entries = 2048; +module_param(max_iotlb_entries, int, 0444); +MODULE_PARM_DESC(max_iotlb_entries, + "Maximum number of iotlb entries for each address space. 0 means unlimited. (default: 2048)"); + +#define VDPASIM_QUEUE_ALIGN PAGE_SIZE +#define VDPASIM_QUEUE_MAX 256 +#define VDPASIM_VENDOR_ID 0 + +static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa) +{ + return container_of(vdpa, struct vdpasim, vdpa); +} + +static struct vdpasim *dev_to_sim(struct device *dev) +{ + struct vdpa_device *vdpa = dev_to_vdpa(dev); + + return vdpa_to_sim(vdpa); +} + +static void vdpasim_vq_notify(struct vringh *vring) +{ + struct vdpasim_virtqueue *vq = + container_of(vring, struct vdpasim_virtqueue, vring); + + if (!vq->cb) + return; + + vq->cb(vq->private); +} + +static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) +{ + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + uint16_t last_avail_idx = vq->vring.last_avail_idx; + + vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false, + (struct vring_desc *)(uintptr_t)vq->desc_addr, + (struct vring_avail *) + (uintptr_t)vq->driver_addr, + (struct vring_used *) + (uintptr_t)vq->device_addr); + + vq->vring.last_avail_idx = last_avail_idx; + + /* + * Since vdpa_sim does not support receive inflight descriptors as a + * destination of a migration, let's set both avail_idx and used_idx + * the same at vq start. This is how vhost-user works in a + * VHOST_SET_VRING_BASE call. + * + * Although the simple fix is to set last_used_idx at + * vdpasim_set_vq_state, it would be reset at vdpasim_queue_ready. + */ + vq->vring.last_used_idx = last_avail_idx; + vq->vring.notify = vdpasim_vq_notify; +} + +static void vdpasim_vq_reset(struct vdpasim *vdpasim, + struct vdpasim_virtqueue *vq) +{ + vq->ready = false; + vq->desc_addr = 0; + vq->driver_addr = 0; + vq->device_addr = 0; + vq->cb = NULL; + vq->private = NULL; + vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features, + VDPASIM_QUEUE_MAX, false, NULL, NULL, NULL); + + vq->vring.notify = NULL; +} + +static void vdpasim_do_reset(struct vdpasim *vdpasim) +{ + int 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]); + + vdpasim->running = true; + spin_unlock(&vdpasim->iommu_lock); + + vdpasim->features = 0; + vdpasim->status = 0; + ++vdpasim->generation; +} + +static int dir_to_perm(enum dma_data_direction dir) +{ + int perm = -EFAULT; + + switch (dir) { + case DMA_FROM_DEVICE: + perm = VHOST_MAP_WO; + break; + case DMA_TO_DEVICE: + perm = VHOST_MAP_RO; + break; + case DMA_BIDIRECTIONAL: + perm = VHOST_MAP_RW; + break; + default: + break; + } + + return perm; +} + +static dma_addr_t vdpasim_map_range(struct vdpasim *vdpasim, phys_addr_t paddr, + size_t size, unsigned int perm) +{ + struct iova *iova; + dma_addr_t dma_addr; + int ret; + + /* We set the limit_pfn to the maximum (ULONG_MAX - 1) */ + iova = alloc_iova(&vdpasim->iova, size >> iova_shift(&vdpasim->iova), + ULONG_MAX - 1, true); + if (!iova) + return DMA_MAPPING_ERROR; + + dma_addr = iova_dma_addr(&vdpasim->iova, iova); + + spin_lock(&vdpasim->iommu_lock); + ret = vhost_iotlb_add_range(&vdpasim->iommu[0], (u64)dma_addr, + (u64)dma_addr + size - 1, (u64)paddr, perm); + spin_unlock(&vdpasim->iommu_lock); + + if (ret) { + __free_iova(&vdpasim->iova, iova); + return DMA_MAPPING_ERROR; + } + + return dma_addr; +} + +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[0], (u64)dma_addr, + (u64)dma_addr + size - 1); + spin_unlock(&vdpasim->iommu_lock); + + free_iova(&vdpasim->iova, iova_pfn(&vdpasim->iova, dma_addr)); +} + +static dma_addr_t vdpasim_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + unsigned long attrs) +{ + struct vdpasim *vdpasim = dev_to_sim(dev); + phys_addr_t paddr = page_to_phys(page) + offset; + int perm = dir_to_perm(dir); + + if (perm < 0) + return DMA_MAPPING_ERROR; + + return vdpasim_map_range(vdpasim, paddr, size, perm); +} + +static void vdpasim_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + struct vdpasim *vdpasim = dev_to_sim(dev); + + vdpasim_unmap_range(vdpasim, dma_addr, size); +} + +static void *vdpasim_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_addr, gfp_t flag, + unsigned long attrs) +{ + struct vdpasim *vdpasim = dev_to_sim(dev); + phys_addr_t paddr; + void *addr; + + addr = kmalloc(size, flag); + if (!addr) { + *dma_addr = DMA_MAPPING_ERROR; + return NULL; + } + + paddr = virt_to_phys(addr); + + *dma_addr = vdpasim_map_range(vdpasim, paddr, size, VHOST_MAP_RW); + if (*dma_addr == DMA_MAPPING_ERROR) { + kfree(addr); + return NULL; + } + + return addr; +} + +static void vdpasim_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + unsigned long attrs) +{ + struct vdpasim *vdpasim = dev_to_sim(dev); + + vdpasim_unmap_range(vdpasim, dma_addr, size); + + kfree(vaddr); +} + +static const struct dma_map_ops vdpasim_dma_ops = { + .map_page = vdpasim_map_page, + .unmap_page = vdpasim_unmap_page, + .alloc = vdpasim_alloc_coherent, + .free = vdpasim_free_coherent, +}; + +static const struct vdpa_config_ops vdpasim_config_ops; +static const struct vdpa_config_ops vdpasim_batch_config_ops; + +struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, + const struct vdpa_dev_set_config *config) +{ + const struct vdpa_config_ops *ops; + struct vdpasim *vdpasim; + struct device *dev; + int i, ret = -ENOMEM; + + if (config->mask & BIT_ULL(VDPA_ATTR_DEV_FEATURES)) { + if (config->device_features & + ~dev_attr->supported_features) + return ERR_PTR(-EINVAL); + dev_attr->supported_features = + config->device_features; + } + + if (batch_mapping) + ops = &vdpasim_batch_config_ops; + else + ops = &vdpasim_config_ops; + + 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; + } + + vdpasim->dev_attr = *dev_attr; + INIT_WORK(&vdpasim->work, dev_attr->work_fn); + spin_lock_init(&vdpasim->lock); + spin_lock_init(&vdpasim->iommu_lock); + + dev = &vdpasim->vdpa.dev; + dev->dma_mask = &dev->coherent_dma_mask; + if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) + goto err_iommu; + set_dma_ops(dev, &vdpasim_dma_ops); + vdpasim->vdpa.mdev = dev_attr->mgmt_dev; + + vdpasim->config = kzalloc(dev_attr->config_size, GFP_KERNEL); + if (!vdpasim->config) + goto err_iommu; + + vdpasim->vqs = kcalloc(dev_attr->nvqs, sizeof(struct vdpasim_virtqueue), + GFP_KERNEL); + if (!vdpasim->vqs) + goto err_iommu; + + 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], max_iotlb_entries, 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[0], + &vdpasim->iommu_lock); + + ret = iova_cache_get(); + if (ret) + goto err_iommu; + + /* For simplicity we use an IOVA allocator with byte granularity */ + init_iova_domain(&vdpasim->iova, 1, 0); + + vdpasim->vdpa.dma_dev = dev; + + return vdpasim; + +err_iommu: + put_device(dev); +err_alloc: + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(vdpasim_create); + +static int vdpasim_set_vq_address(struct vdpa_device *vdpa, u16 idx, + u64 desc_area, u64 driver_area, + u64 device_area) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + vq->desc_addr = desc_area; + vq->driver_addr = driver_area; + vq->device_addr = device_area; + + return 0; +} + +static void vdpasim_set_vq_num(struct vdpa_device *vdpa, u16 idx, u32 num) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + vq->num = num; +} + +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) + schedule_work(&vdpasim->work); +} + +static void vdpasim_set_vq_cb(struct vdpa_device *vdpa, u16 idx, + struct vdpa_callback *cb) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + vq->cb = cb->callback; + vq->private = cb->private; +} + +static void vdpasim_set_vq_ready(struct vdpa_device *vdpa, u16 idx, bool ready) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + bool old_ready; + + spin_lock(&vdpasim->lock); + old_ready = vq->ready; + vq->ready = ready; + if (vq->ready && !old_ready) { + vdpasim_queue_ready(vdpasim, idx); + } + spin_unlock(&vdpasim->lock); +} + +static bool vdpasim_get_vq_ready(struct vdpa_device *vdpa, u16 idx) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + + return vq->ready; +} + +static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, + const struct vdpa_vq_state *state) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + struct vringh *vrh = &vq->vring; + + spin_lock(&vdpasim->lock); + vrh->last_avail_idx = state->split.avail_index; + spin_unlock(&vdpasim->lock); + + return 0; +} + +static int vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx, + struct vdpa_vq_state *state) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + struct vringh *vrh = &vq->vring; + + state->split.avail_index = vrh->last_avail_idx; + return 0; +} + +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) +{ + /* 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) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vdpasim->dev_attr.supported_features; +} + +static int vdpasim_set_driver_features(struct vdpa_device *vdpa, u64 features) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + /* DMA mapping must be done by driver */ + if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) + return -EINVAL; + + vdpasim->features = features & vdpasim->dev_attr.supported_features; + + return 0; +} + +static u64 vdpasim_get_driver_features(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vdpasim->features; +} + +static void vdpasim_set_config_cb(struct vdpa_device *vdpa, + struct vdpa_callback *cb) +{ + /* We don't support config interrupt */ +} + +static u16 vdpasim_get_vq_num_max(struct vdpa_device *vdpa) +{ + return VDPASIM_QUEUE_MAX; +} + +static u32 vdpasim_get_device_id(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vdpasim->dev_attr.id; +} + +static u32 vdpasim_get_vendor_id(struct vdpa_device *vdpa) +{ + return VDPASIM_VENDOR_ID; +} + +static u8 vdpasim_get_status(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + u8 status; + + spin_lock(&vdpasim->lock); + status = vdpasim->status; + spin_unlock(&vdpasim->lock); + + return status; +} + +static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + spin_lock(&vdpasim->lock); + vdpasim->status = status; + spin_unlock(&vdpasim->lock); +} + +static int vdpasim_reset(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + spin_lock(&vdpasim->lock); + vdpasim->status = 0; + vdpasim_do_reset(vdpasim); + spin_unlock(&vdpasim->lock); + + return 0; +} + +static int vdpasim_suspend(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + spin_lock(&vdpasim->lock); + vdpasim->running = false; + spin_unlock(&vdpasim->lock); + + return 0; +} + +static size_t vdpasim_get_config_size(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vdpasim->dev_attr.config_size; +} + +static void vdpasim_get_config(struct vdpa_device *vdpa, unsigned int offset, + void *buf, unsigned int len) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + if (offset + len > vdpasim->dev_attr.config_size) + return; + + if (vdpasim->dev_attr.get_config) + vdpasim->dev_attr.get_config(vdpasim, vdpasim->config); + + memcpy(buf, vdpasim->config + offset, len); +} + +static void vdpasim_set_config(struct vdpa_device *vdpa, unsigned int offset, + const void *buf, unsigned int len) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + if (offset + len > vdpasim->dev_attr.config_size) + return; + + memcpy(vdpasim->config + offset, buf, len); + + if (vdpasim->dev_attr.set_config) + vdpasim->dev_attr.set_config(vdpasim, vdpasim->config); +} + +static u32 vdpasim_get_generation(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vdpasim->generation; +} + +static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa) +{ + struct vdpa_iova_range range = { + .first = 0ULL, + .last = ULLONG_MAX, + }; + + 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, iommu, + &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); + + 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(iommu, map->start, + map->last, map->addr, map->perm); + if (ret) + goto err; + } + spin_unlock(&vdpasim->iommu_lock); + return 0; + +err: + vhost_iotlb_reset(iommu); + spin_unlock(&vdpasim->iommu_lock); + return ret; +} + +static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid, + u64 iova, u64 size, + u64 pa, u32 perm, void *opaque) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + int ret; + + if (asid >= vdpasim->dev_attr.nas) + return -EINVAL; + + spin_lock(&vdpasim->iommu_lock); + ret = vhost_iotlb_add_range_ctx(&vdpasim->iommu[asid], iova, + iova + size - 1, pa, perm, opaque); + spin_unlock(&vdpasim->iommu_lock); + + return ret; +} + +static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid, + u64 iova, u64 size) +{ + 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[asid], iova, iova + size - 1); + spin_unlock(&vdpasim->iommu_lock); + + return 0; +} + +static void vdpasim_free(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + int i; + + cancel_work_sync(&vdpasim->work); + + for (i = 0; i < vdpasim->dev_attr.nvqs; i++) { + vringh_kiov_cleanup(&vdpasim->vqs[i].out_iov); + vringh_kiov_cleanup(&vdpasim->vqs[i].in_iov); + } + + if (vdpa_get_dma_dev(vdpa)) { + put_iova_domain(&vdpasim->iova); + iova_cache_put(); + } + + kvfree(vdpasim->buffer); + for (i = 0; i < vdpasim->dev_attr.nas; i++) + vhost_iotlb_reset(&vdpasim->iommu[i]); + kfree(vdpasim->iommu); + kfree(vdpasim->vqs); + kfree(vdpasim->config); +} + +static const struct vdpa_config_ops vdpasim_config_ops = { + .set_vq_address = vdpasim_set_vq_address, + .set_vq_num = vdpasim_set_vq_num, + .kick_vq = vdpasim_kick_vq, + .set_vq_cb = vdpasim_set_vq_cb, + .set_vq_ready = vdpasim_set_vq_ready, + .get_vq_ready = vdpasim_get_vq_ready, + .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, + .set_config_cb = vdpasim_set_config_cb, + .get_vq_num_max = vdpasim_get_vq_num_max, + .get_device_id = vdpasim_get_device_id, + .get_vendor_id = vdpasim_get_vendor_id, + .get_status = vdpasim_get_status, + .set_status = vdpasim_set_status, + .reset = vdpasim_reset, + .suspend = vdpasim_suspend, + .get_config_size = vdpasim_get_config_size, + .get_config = vdpasim_get_config, + .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, +}; + +static const struct vdpa_config_ops vdpasim_batch_config_ops = { + .set_vq_address = vdpasim_set_vq_address, + .set_vq_num = vdpasim_set_vq_num, + .kick_vq = vdpasim_kick_vq, + .set_vq_cb = vdpasim_set_vq_cb, + .set_vq_ready = vdpasim_set_vq_ready, + .get_vq_ready = vdpasim_get_vq_ready, + .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, + .set_config_cb = vdpasim_set_config_cb, + .get_vq_num_max = vdpasim_get_vq_num_max, + .get_device_id = vdpasim_get_device_id, + .get_vendor_id = vdpasim_get_vendor_id, + .get_status = vdpasim_get_status, + .set_status = vdpasim_set_status, + .reset = vdpasim_reset, + .suspend = vdpasim_suspend, + .get_config_size = vdpasim_get_config_size, + .get_config = vdpasim_get_config, + .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, +}; + +MODULE_VERSION(DRV_VERSION); +MODULE_LICENSE(DRV_LICENSE); +MODULE_AUTHOR(DRV_AUTHOR); +MODULE_DESCRIPTION(DRV_DESC); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h new file mode 100644 index 000000000..0e78737dc --- /dev/null +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020, Red Hat Inc. All rights reserved. + */ + +#ifndef _VDPA_SIM_H +#define _VDPA_SIM_H + +#include <linux/iova.h> +#include <linux/vringh.h> +#include <linux/vdpa.h> +#include <linux/virtio_byteorder.h> +#include <linux/vhost_iotlb.h> +#include <uapi/linux/virtio_config.h> + +#define VDPASIM_FEATURES ((1ULL << VIRTIO_F_ANY_LAYOUT) | \ + (1ULL << VIRTIO_F_VERSION_1) | \ + (1ULL << VIRTIO_F_ACCESS_PLATFORM)) + +struct vdpasim; + +struct vdpasim_virtqueue { + struct vringh vring; + struct vringh_kiov in_iov; + struct vringh_kiov out_iov; + unsigned short head; + bool ready; + u64 desc_addr; + u64 device_addr; + u64 driver_addr; + u32 num; + void *private; + irqreturn_t (*cb)(void *data); +}; + +struct vdpasim_dev_attr { + struct vdpa_mgmt_dev *mgmt_dev; + const char *name; + u64 supported_features; + size_t config_size; + 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); + void (*set_config)(struct vdpasim *vdpasim, const void *config); +}; + +/* State of each vdpasim device */ +struct vdpasim { + struct vdpa_device vdpa; + struct vdpasim_virtqueue *vqs; + struct work_struct work; + struct vdpasim_dev_attr dev_attr; + /* spinlock to synchronize virtqueue state */ + spinlock_t lock; + /* virtio config according to device type */ + void *config; + struct vhost_iotlb *iommu; + struct iova_domain iova; + void *buffer; + u32 status; + u32 generation; + u64 features; + u32 groups; + bool running; + /* spinlock to synchronize iommu table */ + spinlock_t iommu_lock; +}; + +struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *attr, + const struct vdpa_dev_set_config *config); + +/* TODO: cross-endian support */ +static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim) +{ + return virtio_legacy_is_little_endian() || + (vdpasim->features & (1ULL << VIRTIO_F_VERSION_1)); +} + +static inline u16 vdpasim16_to_cpu(struct vdpasim *vdpasim, __virtio16 val) +{ + return __virtio16_to_cpu(vdpasim_is_little_endian(vdpasim), val); +} + +static inline __virtio16 cpu_to_vdpasim16(struct vdpasim *vdpasim, u16 val) +{ + return __cpu_to_virtio16(vdpasim_is_little_endian(vdpasim), val); +} + +static inline u32 vdpasim32_to_cpu(struct vdpasim *vdpasim, __virtio32 val) +{ + return __virtio32_to_cpu(vdpasim_is_little_endian(vdpasim), val); +} + +static inline __virtio32 cpu_to_vdpasim32(struct vdpasim *vdpasim, u32 val) +{ + return __cpu_to_virtio32(vdpasim_is_little_endian(vdpasim), val); +} + +static inline u64 vdpasim64_to_cpu(struct vdpasim *vdpasim, __virtio64 val) +{ + return __virtio64_to_cpu(vdpasim_is_little_endian(vdpasim), val); +} + +static inline __virtio64 cpu_to_vdpasim64(struct vdpasim *vdpasim, u64 val) +{ + return __cpu_to_virtio64(vdpasim_is_little_endian(vdpasim), val); +} + +#endif diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c new file mode 100644 index 000000000..f74592623 --- /dev/null +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -0,0 +1,458 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VDPA simulator for block device. + * + * Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved. + * Copyright (c) 2021, Red Hat Inc. All rights reserved. + * + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/blkdev.h> +#include <linux/vringh.h> +#include <linux/vdpa.h> +#include <uapi/linux/virtio_blk.h> + +#include "vdpa_sim.h" + +#define DRV_VERSION "0.1" +#define DRV_AUTHOR "Max Gurtovoy <mgurtovoy@nvidia.com>" +#define DRV_DESC "vDPA Device Simulator for block device" +#define DRV_LICENSE "GPL v2" + +#define VDPASIM_BLK_FEATURES (VDPASIM_FEATURES | \ + (1ULL << VIRTIO_BLK_F_FLUSH) | \ + (1ULL << VIRTIO_BLK_F_SIZE_MAX) | \ + (1ULL << VIRTIO_BLK_F_SEG_MAX) | \ + (1ULL << VIRTIO_BLK_F_BLK_SIZE) | \ + (1ULL << VIRTIO_BLK_F_TOPOLOGY) | \ + (1ULL << VIRTIO_BLK_F_MQ) | \ + (1ULL << VIRTIO_BLK_F_DISCARD) | \ + (1ULL << VIRTIO_BLK_F_WRITE_ZEROES)) + +#define VDPASIM_BLK_CAPACITY 0x40000 +#define VDPASIM_BLK_SIZE_MAX 0x1000 +#define VDPASIM_BLK_SEG_MAX 32 +#define VDPASIM_BLK_DWZ_MAX_SECTORS UINT_MAX + +/* 1 virtqueue, 1 address space, 1 virtqueue group */ +#define VDPASIM_BLK_VQ_NUM 1 +#define VDPASIM_BLK_AS_NUM 1 +#define VDPASIM_BLK_GROUP_NUM 1 + +static char vdpasim_blk_id[VIRTIO_BLK_ID_BYTES] = "vdpa_blk_sim"; + +static bool vdpasim_blk_check_range(struct vdpasim *vdpasim, u64 start_sector, + u64 num_sectors, u64 max_sectors) +{ + if (start_sector > VDPASIM_BLK_CAPACITY) { + dev_dbg(&vdpasim->vdpa.dev, + "starting sector exceeds the capacity - start: 0x%llx capacity: 0x%x\n", + start_sector, VDPASIM_BLK_CAPACITY); + } + + if (num_sectors > max_sectors) { + dev_dbg(&vdpasim->vdpa.dev, + "number of sectors exceeds the max allowed in a request - num: 0x%llx max: 0x%llx\n", + num_sectors, max_sectors); + return false; + } + + if (num_sectors > VDPASIM_BLK_CAPACITY - start_sector) { + dev_dbg(&vdpasim->vdpa.dev, + "request exceeds the capacity - start: 0x%llx num: 0x%llx capacity: 0x%x\n", + start_sector, num_sectors, VDPASIM_BLK_CAPACITY); + return false; + } + + return true; +} + +/* Returns 'true' if the request is handled (with or without an I/O error) + * and the status is correctly written in the last byte of the 'in iov', + * 'false' otherwise. + */ +static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, + struct vdpasim_virtqueue *vq) +{ + size_t pushed = 0, to_pull, to_push; + struct virtio_blk_outhdr hdr; + bool handled = false; + ssize_t bytes; + loff_t offset; + u64 sector; + u8 status; + u32 type; + int ret; + + ret = vringh_getdesc_iotlb(&vq->vring, &vq->out_iov, &vq->in_iov, + &vq->head, GFP_ATOMIC); + if (ret != 1) + return false; + + if (vq->out_iov.used < 1 || vq->in_iov.used < 1) { + dev_dbg(&vdpasim->vdpa.dev, "missing headers - out_iov: %u in_iov %u\n", + vq->out_iov.used, vq->in_iov.used); + goto err; + } + + if (vq->in_iov.iov[vq->in_iov.used - 1].iov_len < 1) { + dev_dbg(&vdpasim->vdpa.dev, "request in header too short\n"); + goto err; + } + + /* The last byte is the status and we checked if the last iov has + * enough room for it. + */ + to_push = vringh_kiov_length(&vq->in_iov) - 1; + + to_pull = vringh_kiov_length(&vq->out_iov); + + bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->out_iov, &hdr, + sizeof(hdr)); + if (bytes != sizeof(hdr)) { + dev_dbg(&vdpasim->vdpa.dev, "request out header too short\n"); + goto err; + } + + to_pull -= bytes; + + type = vdpasim32_to_cpu(vdpasim, hdr.type); + sector = vdpasim64_to_cpu(vdpasim, hdr.sector); + offset = sector << SECTOR_SHIFT; + status = VIRTIO_BLK_S_OK; + + if (type != VIRTIO_BLK_T_IN && type != VIRTIO_BLK_T_OUT && + sector != 0) { + dev_dbg(&vdpasim->vdpa.dev, + "sector must be 0 for %u request - sector: 0x%llx\n", + type, sector); + status = VIRTIO_BLK_S_IOERR; + goto err_status; + } + + switch (type) { + case VIRTIO_BLK_T_IN: + if (!vdpasim_blk_check_range(vdpasim, sector, + to_push >> SECTOR_SHIFT, + VDPASIM_BLK_SIZE_MAX * VDPASIM_BLK_SEG_MAX)) { + status = VIRTIO_BLK_S_IOERR; + break; + } + + bytes = vringh_iov_push_iotlb(&vq->vring, &vq->in_iov, + vdpasim->buffer + offset, + to_push); + if (bytes < 0) { + dev_dbg(&vdpasim->vdpa.dev, + "vringh_iov_push_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n", + bytes, offset, to_push); + status = VIRTIO_BLK_S_IOERR; + break; + } + + pushed += bytes; + break; + + case VIRTIO_BLK_T_OUT: + if (!vdpasim_blk_check_range(vdpasim, sector, + to_pull >> SECTOR_SHIFT, + VDPASIM_BLK_SIZE_MAX * VDPASIM_BLK_SEG_MAX)) { + status = VIRTIO_BLK_S_IOERR; + break; + } + + bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->out_iov, + vdpasim->buffer + offset, + to_pull); + if (bytes < 0) { + dev_dbg(&vdpasim->vdpa.dev, + "vringh_iov_pull_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n", + bytes, offset, to_pull); + status = VIRTIO_BLK_S_IOERR; + break; + } + break; + + case VIRTIO_BLK_T_GET_ID: + bytes = vringh_iov_push_iotlb(&vq->vring, &vq->in_iov, + vdpasim_blk_id, + VIRTIO_BLK_ID_BYTES); + if (bytes < 0) { + dev_dbg(&vdpasim->vdpa.dev, + "vringh_iov_push_iotlb() error: %zd\n", bytes); + status = VIRTIO_BLK_S_IOERR; + break; + } + + pushed += bytes; + break; + + case VIRTIO_BLK_T_FLUSH: + /* nothing to do */ + break; + + case VIRTIO_BLK_T_DISCARD: + case VIRTIO_BLK_T_WRITE_ZEROES: { + struct virtio_blk_discard_write_zeroes range; + u32 num_sectors, flags; + + if (to_pull != sizeof(range)) { + dev_dbg(&vdpasim->vdpa.dev, + "discard/write_zeroes header len: 0x%zx [expected: 0x%zx]\n", + to_pull, sizeof(range)); + status = VIRTIO_BLK_S_IOERR; + break; + } + + bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->out_iov, &range, + to_pull); + if (bytes < 0) { + dev_dbg(&vdpasim->vdpa.dev, + "vringh_iov_pull_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n", + bytes, offset, to_pull); + status = VIRTIO_BLK_S_IOERR; + break; + } + + sector = le64_to_cpu(range.sector); + offset = sector << SECTOR_SHIFT; + num_sectors = le32_to_cpu(range.num_sectors); + flags = le32_to_cpu(range.flags); + + if (type == VIRTIO_BLK_T_DISCARD && flags != 0) { + dev_dbg(&vdpasim->vdpa.dev, + "discard unexpected flags set - flags: 0x%x\n", + flags); + status = VIRTIO_BLK_S_UNSUPP; + break; + } + + if (type == VIRTIO_BLK_T_WRITE_ZEROES && + flags & ~VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) { + dev_dbg(&vdpasim->vdpa.dev, + "write_zeroes unexpected flags set - flags: 0x%x\n", + flags); + status = VIRTIO_BLK_S_UNSUPP; + break; + } + + if (!vdpasim_blk_check_range(vdpasim, sector, num_sectors, + VDPASIM_BLK_DWZ_MAX_SECTORS)) { + status = VIRTIO_BLK_S_IOERR; + break; + } + + if (type == VIRTIO_BLK_T_WRITE_ZEROES) { + memset(vdpasim->buffer + offset, 0, + num_sectors << SECTOR_SHIFT); + } + + break; + } + default: + dev_dbg(&vdpasim->vdpa.dev, + "Unsupported request type %d\n", type); + status = VIRTIO_BLK_S_IOERR; + break; + } + +err_status: + /* If some operations fail, we need to skip the remaining bytes + * to put the status in the last byte + */ + if (to_push - pushed > 0) + vringh_kiov_advance(&vq->in_iov, to_push - pushed); + + /* Last byte is the status */ + bytes = vringh_iov_push_iotlb(&vq->vring, &vq->in_iov, &status, 1); + if (bytes != 1) + goto err; + + pushed += bytes; + + /* Make sure data is wrote before advancing index */ + smp_wmb(); + + handled = true; + +err: + vringh_complete_iotlb(&vq->vring, vq->head, pushed); + + return handled; +} + +static void vdpasim_blk_work(struct work_struct *work) +{ + struct vdpasim *vdpasim = container_of(work, struct vdpasim, work); + bool reschedule = false; + int i; + + spin_lock(&vdpasim->lock); + + if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto out; + + if (!vdpasim->running) + goto out; + + for (i = 0; i < VDPASIM_BLK_VQ_NUM; i++) { + struct vdpasim_virtqueue *vq = &vdpasim->vqs[i]; + int reqs = 0; + + if (!vq->ready) + continue; + + while (vdpasim_blk_handle_req(vdpasim, vq)) { + /* 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(); + + if (++reqs > 4) { + reschedule = true; + break; + } + } + } +out: + spin_unlock(&vdpasim->lock); + + if (reschedule) + schedule_work(&vdpasim->work); +} + +static void vdpasim_blk_get_config(struct vdpasim *vdpasim, void *config) +{ + struct virtio_blk_config *blk_config = config; + + memset(config, 0, sizeof(struct virtio_blk_config)); + + blk_config->capacity = cpu_to_vdpasim64(vdpasim, VDPASIM_BLK_CAPACITY); + blk_config->size_max = cpu_to_vdpasim32(vdpasim, VDPASIM_BLK_SIZE_MAX); + blk_config->seg_max = cpu_to_vdpasim32(vdpasim, VDPASIM_BLK_SEG_MAX); + blk_config->num_queues = cpu_to_vdpasim16(vdpasim, VDPASIM_BLK_VQ_NUM); + blk_config->min_io_size = cpu_to_vdpasim16(vdpasim, 1); + blk_config->opt_io_size = cpu_to_vdpasim32(vdpasim, 1); + blk_config->blk_size = cpu_to_vdpasim32(vdpasim, SECTOR_SIZE); + /* VIRTIO_BLK_F_DISCARD */ + blk_config->discard_sector_alignment = + cpu_to_vdpasim32(vdpasim, SECTOR_SIZE); + blk_config->max_discard_sectors = + cpu_to_vdpasim32(vdpasim, VDPASIM_BLK_DWZ_MAX_SECTORS); + blk_config->max_discard_seg = cpu_to_vdpasim32(vdpasim, 1); + /* VIRTIO_BLK_F_WRITE_ZEROES */ + blk_config->max_write_zeroes_sectors = + cpu_to_vdpasim32(vdpasim, VDPASIM_BLK_DWZ_MAX_SECTORS); + blk_config->max_write_zeroes_seg = cpu_to_vdpasim32(vdpasim, 1); + +} + +static void vdpasim_blk_mgmtdev_release(struct device *dev) +{ +} + +static struct device vdpasim_blk_mgmtdev = { + .init_name = "vdpasim_blk", + .release = vdpasim_blk_mgmtdev_release, +}; + +static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config) +{ + struct vdpasim_dev_attr dev_attr = {}; + struct vdpasim *simdev; + int ret; + + dev_attr.mgmt_dev = mdev; + dev_attr.name = name; + dev_attr.id = VIRTIO_ID_BLOCK; + dev_attr.supported_features = VDPASIM_BLK_FEATURES; + dev_attr.nvqs = VDPASIM_BLK_VQ_NUM; + dev_attr.ngroups = VDPASIM_BLK_GROUP_NUM; + dev_attr.nas = VDPASIM_BLK_AS_NUM; + dev_attr.config_size = sizeof(struct virtio_blk_config); + dev_attr.get_config = vdpasim_blk_get_config; + dev_attr.work_fn = vdpasim_blk_work; + dev_attr.buffer_size = VDPASIM_BLK_CAPACITY << SECTOR_SHIFT; + + simdev = vdpasim_create(&dev_attr, config); + if (IS_ERR(simdev)) + return PTR_ERR(simdev); + + ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_BLK_VQ_NUM); + if (ret) + goto put_dev; + + return 0; + +put_dev: + put_device(&simdev->vdpa.dev); + return ret; +} + +static void vdpasim_blk_dev_del(struct vdpa_mgmt_dev *mdev, + struct vdpa_device *dev) +{ + struct vdpasim *simdev = container_of(dev, struct vdpasim, vdpa); + + _vdpa_unregister_device(&simdev->vdpa); +} + +static const struct vdpa_mgmtdev_ops vdpasim_blk_mgmtdev_ops = { + .dev_add = vdpasim_blk_dev_add, + .dev_del = vdpasim_blk_dev_del +}; + +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct vdpa_mgmt_dev mgmt_dev = { + .device = &vdpasim_blk_mgmtdev, + .id_table = id_table, + .ops = &vdpasim_blk_mgmtdev_ops, +}; + +static int __init vdpasim_blk_init(void) +{ + int ret; + + ret = device_register(&vdpasim_blk_mgmtdev); + if (ret) { + put_device(&vdpasim_blk_mgmtdev); + return ret; + } + + ret = vdpa_mgmtdev_register(&mgmt_dev); + if (ret) + goto parent_err; + + return 0; + +parent_err: + device_unregister(&vdpasim_blk_mgmtdev); + return ret; +} + +static void __exit vdpasim_blk_exit(void) +{ + vdpa_mgmtdev_unregister(&mgmt_dev); + device_unregister(&vdpasim_blk_mgmtdev); +} + +module_init(vdpasim_blk_init) +module_exit(vdpasim_blk_exit) + +MODULE_VERSION(DRV_VERSION); +MODULE_LICENSE(DRV_LICENSE); +MODULE_AUTHOR(DRV_AUTHOR); +MODULE_DESCRIPTION(DRV_DESC); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c new file mode 100644 index 000000000..584b975a9 --- /dev/null +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -0,0 +1,338 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VDPA simulator for networking device. + * + * Copyright (c) 2020, Red Hat Inc. All rights reserved. + * Author: Jason Wang <jasowang@redhat.com> + * + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/etherdevice.h> +#include <linux/vringh.h> +#include <linux/vdpa.h> +#include <uapi/linux/virtio_net.h> +#include <uapi/linux/vdpa.h> + +#include "vdpa_sim.h" + +#define DRV_VERSION "0.1" +#define DRV_AUTHOR "Jason Wang <jasowang@redhat.com>" +#define DRV_DESC "vDPA Device Simulator for networking device" +#define DRV_LICENSE "GPL v2" + +#define VDPASIM_NET_FEATURES (VDPASIM_FEATURES | \ + (1ULL << VIRTIO_NET_F_MAC) | \ + (1ULL << VIRTIO_NET_F_MTU) | \ + (1ULL << VIRTIO_NET_F_CTRL_VQ) | \ + (1ULL << VIRTIO_NET_F_CTRL_MAC_ADDR)) + +/* 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_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 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); + struct virtio_net_config *vio_config = vdpasim->config; + + if (len < ETH_ALEN + hdr_len) + return false; + + if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) || + is_multicast_ether_addr(vdpasim->buffer + hdr_len)) + return true; + if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN)) + return true; + + return false; +} + +static virtio_net_ctrl_ack vdpasim_handle_ctrl_mac(struct vdpasim *vdpasim, + u8 cmd) +{ + struct virtio_net_config *vio_config = vdpasim->config; + 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, + vio_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); + struct vdpasim_virtqueue *txq = &vdpasim->vqs[1]; + struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0]; + ssize_t read, write; + int pkts = 0; + int err; + + spin_lock(&vdpasim->lock); + + if (!vdpasim->running) + goto out; + + if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto out; + + vdpasim_handle_cvq(vdpasim); + + if (!txq->ready || !rxq->ready) + goto out; + + while (true) { + 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_net_complete(txq, 0); + continue; + } + + err = vringh_getdesc_iotlb(&rxq->vring, NULL, &rxq->in_iov, + &rxq->head, GFP_ATOMIC); + if (err <= 0) { + vdpasim_net_complete(txq, 0); + break; + } + + 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, write); + + if (++pkts > 4) { + schedule_work(&vdpasim->work); + goto out; + } + } + +out: + spin_unlock(&vdpasim->lock); +} + +static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config) +{ + struct virtio_net_config *net_config = config; + + net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP); +} + +static void vdpasim_net_setup_config(struct vdpasim *vdpasim, + const struct vdpa_dev_set_config *config) +{ + struct virtio_net_config *vio_config = vdpasim->config; + + if (config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR)) + memcpy(vio_config->mac, config->net.mac, ETH_ALEN); + if (config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MTU)) + vio_config->mtu = cpu_to_vdpasim16(vdpasim, config->net.mtu); + else + /* Setup default MTU to be 1500 */ + vio_config->mtu = cpu_to_vdpasim16(vdpasim, 1500); +} + +static void vdpasim_net_mgmtdev_release(struct device *dev) +{ +} + +static struct device vdpasim_net_mgmtdev = { + .init_name = "vdpasim_net", + .release = vdpasim_net_mgmtdev_release, +}; + +static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config) +{ + struct vdpasim_dev_attr dev_attr = {}; + struct vdpasim *simdev; + int ret; + + dev_attr.mgmt_dev = mdev; + dev_attr.name = 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; + dev_attr.buffer_size = PAGE_SIZE; + + simdev = vdpasim_create(&dev_attr, config); + if (IS_ERR(simdev)) + return PTR_ERR(simdev); + + vdpasim_net_setup_config(simdev, config); + + ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM); + if (ret) + goto reg_err; + + return 0; + +reg_err: + put_device(&simdev->vdpa.dev); + return ret; +} + +static void vdpasim_net_dev_del(struct vdpa_mgmt_dev *mdev, + struct vdpa_device *dev) +{ + struct vdpasim *simdev = container_of(dev, struct vdpasim, vdpa); + + _vdpa_unregister_device(&simdev->vdpa); +} + +static const struct vdpa_mgmtdev_ops vdpasim_net_mgmtdev_ops = { + .dev_add = vdpasim_net_dev_add, + .dev_del = vdpasim_net_dev_del +}; + +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct vdpa_mgmt_dev mgmt_dev = { + .device = &vdpasim_net_mgmtdev, + .id_table = id_table, + .ops = &vdpasim_net_mgmtdev_ops, + .config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR | + 1 << VDPA_ATTR_DEV_NET_CFG_MTU | + 1 << VDPA_ATTR_DEV_FEATURES), + .max_supported_vqs = VDPASIM_NET_VQ_NUM, + .supported_features = VDPASIM_NET_FEATURES, +}; + +static int __init vdpasim_net_init(void) +{ + int ret; + + ret = device_register(&vdpasim_net_mgmtdev); + if (ret) { + put_device(&vdpasim_net_mgmtdev); + return ret; + } + + ret = vdpa_mgmtdev_register(&mgmt_dev); + if (ret) + goto parent_err; + return 0; + +parent_err: + device_unregister(&vdpasim_net_mgmtdev); + return ret; +} + +static void __exit vdpasim_net_exit(void) +{ + vdpa_mgmtdev_unregister(&mgmt_dev); + device_unregister(&vdpasim_net_mgmtdev); +} + +module_init(vdpasim_net_init); +module_exit(vdpasim_net_exit); + +MODULE_VERSION(DRV_VERSION); +MODULE_LICENSE(DRV_LICENSE); +MODULE_AUTHOR(DRV_AUTHOR); +MODULE_DESCRIPTION(DRV_DESC); |