diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index ca28a135b967..2fdff04000b3 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -5,6 +5,7 @@ iommufd-y := \ io_pagetable.o \ ioas.o \ main.o \ - pages.o + pages.o \ + vfio_compat.o obj-$(CONFIG_IOMMUFD) += iommufd.o diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 40302cc0da36..8fe5f162ccbc 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -18,6 +18,7 @@ struct iommufd_ctx { struct xarray objects; u8 account_mode; + struct iommufd_ioas *vfio_ioas; }; /* @@ -92,6 +93,9 @@ struct iommufd_ucmd { void *cmd; }; +int iommufd_vfio_ioctl(struct iommufd_ctx *ictx, unsigned int cmd, + unsigned long arg); + /* Copy the response in ucmd->cmd back to userspace. */ static inline int iommufd_ucmd_respond(struct iommufd_ucmd *ucmd, size_t cmd_len) @@ -222,6 +226,8 @@ int iommufd_ioas_option(struct iommufd_ucmd *ucmd); int iommufd_option_rlimit_mode(struct iommu_option *cmd, struct iommufd_ctx *ictx); +int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd); + /* * A HW pagetable is called an iommu_domain inside the kernel. This user object * allows directly creating and inspecting the domains. Domains that have kernel diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 4153f6a20255..5cf69c4d591d 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -133,6 +133,8 @@ bool iommufd_object_destroy_user(struct iommufd_ctx *ictx, return false; } __xa_erase(&ictx->objects, obj->id); + if (ictx->vfio_ioas && &ictx->vfio_ioas->obj == obj) + ictx->vfio_ioas = NULL; xa_unlock(&ictx->objects); up_write(&obj->destroy_rwsem); @@ -271,27 +273,31 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { length), IOCTL_OP(IOMMU_OPTION, iommufd_option, struct iommu_option, val64), + IOCTL_OP(IOMMU_VFIO_IOAS, iommufd_vfio_ioas, struct iommu_vfio_ioas, + __reserved), }; static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { + struct iommufd_ctx *ictx = filp->private_data; const struct iommufd_ioctl_op *op; struct iommufd_ucmd ucmd = {}; union ucmd_buffer buf; unsigned int nr; int ret; - ucmd.ictx = filp->private_data; + nr = _IOC_NR(cmd); + if (nr < IOMMUFD_CMD_BASE || + (nr - IOMMUFD_CMD_BASE) >= ARRAY_SIZE(iommufd_ioctl_ops)) + return iommufd_vfio_ioctl(ictx, cmd, arg); + + ucmd.ictx = ictx; ucmd.ubuffer = (void __user *)arg; ret = get_user(ucmd.user_size, (u32 __user *)ucmd.ubuffer); if (ret) return ret; - nr = _IOC_NR(cmd); - if (nr < IOMMUFD_CMD_BASE || - (nr - IOMMUFD_CMD_BASE) >= ARRAY_SIZE(iommufd_ioctl_ops)) - return -ENOIOCTLCMD; op = &iommufd_ioctl_ops[nr - IOMMUFD_CMD_BASE]; if (op->ioctl_num != cmd) return -ENOIOCTLCMD; diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c new file mode 100644 index 000000000000..3ceca0e8311c --- /dev/null +++ b/drivers/iommu/iommufd/vfio_compat.c @@ -0,0 +1,472 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "iommufd_private.h" + +static struct iommufd_ioas *get_compat_ioas(struct iommufd_ctx *ictx) +{ + struct iommufd_ioas *ioas = ERR_PTR(-ENODEV); + + xa_lock(&ictx->objects); + if (!ictx->vfio_ioas || !iommufd_lock_obj(&ictx->vfio_ioas->obj)) + goto out_unlock; + ioas = ictx->vfio_ioas; +out_unlock: + xa_unlock(&ictx->objects); + return ioas; +} + +/** + * iommufd_vfio_compat_ioas_id - Return the IOAS ID that vfio should use + * @ictx: Context to operate on + * @out_ioas_id: The ioas_id the caller should use + * + * The compatibility IOAS is the IOAS that the vfio compatibility ioctls operate + * on since they do not have an IOAS ID input in their ABI. Only attaching a + * group should cause a default creation of the internal ioas, this returns the + * existing ioas if it has already been assigned somehow. + */ +int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id) +{ + struct iommufd_ioas *ioas = NULL; + struct iommufd_ioas *out_ioas; + + ioas = iommufd_ioas_alloc(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + xa_lock(&ictx->objects); + if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) + out_ioas = ictx->vfio_ioas; + else { + out_ioas = ioas; + ictx->vfio_ioas = ioas; + } + xa_unlock(&ictx->objects); + + *out_ioas_id = out_ioas->obj.id; + if (out_ioas != ioas) { + iommufd_put_object(&out_ioas->obj); + iommufd_object_abort(ictx, &ioas->obj); + return 0; + } + /* + * An automatically created compat IOAS is treated as a userspace + * created object. Userspace can learn the ID via IOMMU_VFIO_IOAS_GET, + * and if not manually destroyed it will be destroyed automatically + * at iommufd release. + */ + iommufd_object_finalize(ictx, &ioas->obj); + return 0; +} +EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_id, IOMMUFD_VFIO); + +int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd) +{ + struct iommu_vfio_ioas *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + + if (cmd->__reserved) + return -EOPNOTSUPP; + switch (cmd->op) { + case IOMMU_VFIO_IOAS_GET: + ioas = get_compat_ioas(ucmd->ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + cmd->ioas_id = ioas->obj.id; + iommufd_put_object(&ioas->obj); + return iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + + case IOMMU_VFIO_IOAS_SET: + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + xa_lock(&ucmd->ictx->objects); + ucmd->ictx->vfio_ioas = ioas; + xa_unlock(&ucmd->ictx->objects); + iommufd_put_object(&ioas->obj); + return 0; + + case IOMMU_VFIO_IOAS_CLEAR: + xa_lock(&ucmd->ictx->objects); + ucmd->ictx->vfio_ioas = NULL; + xa_unlock(&ucmd->ictx->objects); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int iommufd_vfio_map_dma(struct iommufd_ctx *ictx, unsigned int cmd, + void __user *arg) +{ + u32 supported_flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE; + size_t minsz = offsetofend(struct vfio_iommu_type1_dma_map, size); + struct vfio_iommu_type1_dma_map map; + int iommu_prot = IOMMU_CACHE; + struct iommufd_ioas *ioas; + unsigned long iova; + int rc; + + if (copy_from_user(&map, arg, minsz)) + return -EFAULT; + + if (map.argsz < minsz || map.flags & ~supported_flags) + return -EINVAL; + + if (map.flags & VFIO_DMA_MAP_FLAG_READ) + iommu_prot |= IOMMU_READ; + if (map.flags & VFIO_DMA_MAP_FLAG_WRITE) + iommu_prot |= IOMMU_WRITE; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + /* + * Maps created through the legacy interface always use VFIO compatible + * rlimit accounting. If the user wishes to use the faster user based + * rlimit accounting then they must use the new interface. + */ + iova = map.iova; + rc = iopt_map_user_pages(ictx, &ioas->iopt, &iova, u64_to_user_ptr(map.vaddr), + map.size, iommu_prot, 0); + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_vfio_unmap_dma(struct iommufd_ctx *ictx, unsigned int cmd, + void __user *arg) +{ + size_t minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size); + /* + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is obsoleted by the new + * dirty tracking direction: + * https://lore.kernel.org/kvm/20220731125503.142683-1-yishaih@nvidia.com/ + * https://lore.kernel.org/kvm/20220428210933.3583-1-joao.m.martins@oracle.com/ + */ + u32 supported_flags = VFIO_DMA_UNMAP_FLAG_ALL; + struct vfio_iommu_type1_dma_unmap unmap; + unsigned long unmapped = 0; + struct iommufd_ioas *ioas; + int rc; + + if (copy_from_user(&unmap, arg, minsz)) + return -EFAULT; + + if (unmap.argsz < minsz || unmap.flags & ~supported_flags) + return -EINVAL; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + if (unmap.flags & VFIO_DMA_UNMAP_FLAG_ALL) { + if (unmap.iova != 0 || unmap.size != 0) { + rc = -EINVAL; + goto err_put; + } + rc = iopt_unmap_all(&ioas->iopt, &unmapped); + } else { + if (READ_ONCE(ioas->iopt.disable_large_pages)) { + /* + * Create cuts at the start and last of the requested + * range. If the start IOVA is 0 then it doesn't need to + * be cut. + */ + unsigned long iovas[] = { unmap.iova + unmap.size - 1, + unmap.iova - 1 }; + + rc = iopt_cut_iova(&ioas->iopt, iovas, + unmap.iova ? 2 : 1); + if (rc) + goto err_put; + } + rc = iopt_unmap_iova(&ioas->iopt, unmap.iova, unmap.size, + &unmapped); + } + unmap.size = unmapped; + if (copy_to_user(arg, &unmap, minsz)) + rc = -EFAULT; + +err_put: + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_vfio_cc_iommu(struct iommufd_ctx *ictx) +{ + struct iommufd_hw_pagetable *hwpt; + struct iommufd_ioas *ioas; + int rc = 1; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + mutex_lock(&ioas->mutex); + list_for_each_entry(hwpt, &ioas->hwpt_list, hwpt_item) { + if (!hwpt->enforce_cache_coherency) { + rc = 0; + break; + } + } + mutex_unlock(&ioas->mutex); + + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx, + unsigned long type) +{ + switch (type) { + case VFIO_TYPE1_IOMMU: + case VFIO_TYPE1v2_IOMMU: + case VFIO_UNMAP_ALL: + return 1; + + case VFIO_DMA_CC_IOMMU: + return iommufd_vfio_cc_iommu(ictx); + + /* + * This is obsolete, and to be removed from VFIO. It was an incomplete + * idea that got merged. + * https://lore.kernel.org/kvm/0-v1-0093c9b0e345+19-vfio_no_nesting_jgg@nvidia.com/ + */ + case VFIO_TYPE1_NESTING_IOMMU: + return 0; + + /* + * VFIO_DMA_MAP_FLAG_VADDR + * https://lore.kernel.org/kvm/1611939252-7240-1-git-send-email-steven.sistare@oracle.com/ + * https://lore.kernel.org/all/Yz777bJZjTyLrHEQ@nvidia.com/ + * + * It is hard to see how this could be implemented safely. + */ + case VFIO_UPDATE_VADDR: + default: + return 0; + } +} + +static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type) +{ + struct iommufd_ioas *ioas = NULL; + int rc = 0; + + if (type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU) + return -EINVAL; + + /* VFIO fails the set_iommu if there is no group */ + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + /* + * The difference between TYPE1 and TYPE1v2 is the ability to unmap in + * the middle of mapped ranges. This is complicated by huge page support + * which creates single large IOPTEs that cannot be split by the iommu + * driver. TYPE1 is very old at this point and likely nothing uses it, + * however it is simple enough to emulate by simply disabling the + * problematic large IOPTEs. Then we can safely unmap within any range. + */ + if (type == VFIO_TYPE1_IOMMU) + rc = iopt_disable_large_pages(&ioas->iopt); + iommufd_put_object(&ioas->obj); + return rc; +} + +static unsigned long iommufd_get_pagesizes(struct iommufd_ioas *ioas) +{ + struct io_pagetable *iopt = &ioas->iopt; + unsigned long pgsize_bitmap = ULONG_MAX; + struct iommu_domain *domain; + unsigned long index; + + down_read(&iopt->domains_rwsem); + xa_for_each(&iopt->domains, index, domain) + pgsize_bitmap &= domain->pgsize_bitmap; + + /* See vfio_update_pgsize_bitmap() */ + if (pgsize_bitmap & ~PAGE_MASK) { + pgsize_bitmap &= PAGE_MASK; + pgsize_bitmap |= PAGE_SIZE; + } + pgsize_bitmap = max(pgsize_bitmap, ioas->iopt.iova_alignment); + up_read(&iopt->domains_rwsem); + return pgsize_bitmap; +} + +static int iommufd_fill_cap_iova(struct iommufd_ioas *ioas, + struct vfio_info_cap_header __user *cur, + size_t avail) +{ + struct vfio_iommu_type1_info_cap_iova_range __user *ucap_iovas = + container_of(cur, + struct vfio_iommu_type1_info_cap_iova_range __user, + header); + struct vfio_iommu_type1_info_cap_iova_range cap_iovas = { + .header = { + .id = VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE, + .version = 1, + }, + }; + struct interval_tree_span_iter span; + + interval_tree_for_each_span(&span, &ioas->iopt.reserved_itree, 0, + ULONG_MAX) { + struct vfio_iova_range range; + + if (!span.is_hole) + continue; + range.start = span.start_hole; + range.end = span.last_hole; + if (avail >= struct_size(&cap_iovas, iova_ranges, + cap_iovas.nr_iovas + 1) && + copy_to_user(&ucap_iovas->iova_ranges[cap_iovas.nr_iovas], + &range, sizeof(range))) + return -EFAULT; + cap_iovas.nr_iovas++; + } + if (avail >= struct_size(&cap_iovas, iova_ranges, cap_iovas.nr_iovas) && + copy_to_user(ucap_iovas, &cap_iovas, sizeof(cap_iovas))) + return -EFAULT; + return struct_size(&cap_iovas, iova_ranges, cap_iovas.nr_iovas); +} + +static int iommufd_fill_cap_dma_avail(struct iommufd_ioas *ioas, + struct vfio_info_cap_header __user *cur, + size_t avail) +{ + struct vfio_iommu_type1_info_dma_avail cap_dma = { + .header = { + .id = VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL, + .version = 1, + }, + /* + * iommufd's limit is based on the cgroup's memory limit. + * Normally vfio would return U16_MAX here, and provide a module + * parameter to adjust it. Since S390 qemu userspace actually + * pays attention and needs a value bigger than U16_MAX return + * U32_MAX. + */ + .avail = U32_MAX, + }; + + if (avail >= sizeof(cap_dma) && + copy_to_user(cur, &cap_dma, sizeof(cap_dma))) + return -EFAULT; + return sizeof(cap_dma); +} + +static int iommufd_vfio_iommu_get_info(struct iommufd_ctx *ictx, + void __user *arg) +{ + typedef int (*fill_cap_fn)(struct iommufd_ioas *ioas, + struct vfio_info_cap_header __user *cur, + size_t avail); + static const fill_cap_fn fill_fns[] = { + iommufd_fill_cap_dma_avail, + iommufd_fill_cap_iova, + }; + size_t minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes); + struct vfio_info_cap_header __user *last_cap = NULL; + struct vfio_iommu_type1_info info; + struct iommufd_ioas *ioas; + size_t total_cap_size; + int rc; + int i; + + if (copy_from_user(&info, arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + minsz = min_t(size_t, info.argsz, sizeof(info)); + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + info.flags = VFIO_IOMMU_INFO_PGSIZES; + info.iova_pgsizes = iommufd_get_pagesizes(ioas); + info.cap_offset = 0; + + down_read(&ioas->iopt.iova_rwsem); + total_cap_size = sizeof(info); + for (i = 0; i != ARRAY_SIZE(fill_fns); i++) { + int cap_size; + + if (info.argsz > total_cap_size) + cap_size = fill_fns[i](ioas, arg + total_cap_size, + info.argsz - total_cap_size); + else + cap_size = fill_fns[i](ioas, NULL, 0); + if (cap_size < 0) { + rc = cap_size; + goto out_put; + } + if (last_cap && info.argsz >= total_cap_size && + put_user(total_cap_size, &last_cap->next)) { + rc = -EFAULT; + goto out_put; + } + last_cap = arg + total_cap_size; + total_cap_size += cap_size; + } + + /* + * If the user did not provide enough space then only some caps are + * returned and the argsz will be updated to the correct amount to get + * all caps. + */ + if (info.argsz >= total_cap_size) + info.cap_offset = sizeof(info); + info.argsz = total_cap_size; + info.flags |= VFIO_IOMMU_INFO_CAPS; + if (copy_to_user(arg, &info, minsz)) { + rc = -EFAULT; + goto out_put; + } + rc = 0; + +out_put: + up_read(&ioas->iopt.iova_rwsem); + iommufd_put_object(&ioas->obj); + return rc; +} + +int iommufd_vfio_ioctl(struct iommufd_ctx *ictx, unsigned int cmd, + unsigned long arg) +{ + void __user *uarg = (void __user *)arg; + + switch (cmd) { + case VFIO_GET_API_VERSION: + return VFIO_API_VERSION; + case VFIO_SET_IOMMU: + return iommufd_vfio_set_iommu(ictx, arg); + case VFIO_CHECK_EXTENSION: + return iommufd_vfio_check_extension(ictx, arg); + case VFIO_IOMMU_GET_INFO: + return iommufd_vfio_iommu_get_info(ictx, uarg); + case VFIO_IOMMU_MAP_DMA: + return iommufd_vfio_map_dma(ictx, cmd, uarg); + case VFIO_IOMMU_UNMAP_DMA: + return iommufd_vfio_unmap_dma(ictx, cmd, uarg); + case VFIO_IOMMU_DIRTY_PAGES: + default: + return -ENOIOCTLCMD; + } + return -ENOIOCTLCMD; +} diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 46c481a26d79..84af9a239769 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -54,6 +54,7 @@ void iommufd_access_unpin_pages(struct iommufd_access *access, unsigned long iova, unsigned long length); int iommufd_access_rw(struct iommufd_access *access, unsigned long iova, void *data, size_t len, unsigned int flags); +int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id); #else /* !CONFIG_IOMMUFD */ static inline struct iommufd_ctx *iommufd_ctx_from_file(struct file *file) { @@ -84,5 +85,11 @@ static inline int iommufd_access_rw(struct iommufd_access *access, unsigned long { return -EOPNOTSUPP; } + +static inline int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, + u32 *out_ioas_id) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_IOMMUFD */ #endif diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 30cc5c5e2b34..98ebba80cfa1 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -44,6 +44,7 @@ enum { IOMMUFD_CMD_IOAS_MAP, IOMMUFD_CMD_IOAS_UNMAP, IOMMUFD_CMD_OPTION, + IOMMUFD_CMD_VFIO_IOAS, }; /** @@ -308,4 +309,39 @@ struct iommu_option { __aligned_u64 val64; }; #define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION) + +/** + * enum iommufd_vfio_ioas_op - IOMMU_VFIO_IOAS_* ioctls + * @IOMMU_VFIO_IOAS_GET: Get the current compatibility IOAS + * @IOMMU_VFIO_IOAS_SET: Change the current compatibility IOAS + * @IOMMU_VFIO_IOAS_CLEAR: Disable VFIO compatibility + */ +enum iommufd_vfio_ioas_op { + IOMMU_VFIO_IOAS_GET = 0, + IOMMU_VFIO_IOAS_SET = 1, + IOMMU_VFIO_IOAS_CLEAR = 2, +}; + +/** + * struct iommu_vfio_ioas - ioctl(IOMMU_VFIO_IOAS) + * @size: sizeof(struct iommu_vfio_ioas) + * @ioas_id: For IOMMU_VFIO_IOAS_SET the input IOAS ID to set + * For IOMMU_VFIO_IOAS_GET will output the IOAS ID + * @op: One of enum iommufd_vfio_ioas_op + * @__reserved: Must be 0 + * + * The VFIO compatibility support uses a single ioas because VFIO APIs do not + * support the ID field. Set or Get the IOAS that VFIO compatibility will use. + * When VFIO_GROUP_SET_CONTAINER is used on an iommufd it will get the + * compatibility ioas, either by taking what is already set, or auto creating + * one. From then on VFIO will continue to use that ioas and is not effected by + * this ioctl. SET or CLEAR does not destroy any auto-created IOAS. + */ +struct iommu_vfio_ioas { + __u32 size; + __u32 ioas_id; + __u16 op; + __u16 __reserved; +}; +#define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS) #endif