OpenCloudOS-Kernel/include/linux/iommufd.h

99 lines
2.8 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2021 Intel Corporation
* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES
*/
#ifndef __LINUX_IOMMUFD_H
#define __LINUX_IOMMUFD_H
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/err.h>
struct device;
struct iommufd_device;
struct page;
struct iommufd_ctx;
struct iommufd_access;
struct file;
struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
struct device *dev, u32 *id);
void iommufd_device_unbind(struct iommufd_device *idev);
int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id);
void iommufd_device_detach(struct iommufd_device *idev);
struct iommufd_access_ops {
u8 needs_pin_pages : 1;
void (*unmap)(void *data, unsigned long iova, unsigned long length);
};
iommufd: PFN handling for iopt_pages The top of the data structure provides an IO Address Space (IOAS) that is similar to a VFIO container. The IOAS allows map/unmap of memory into ranges of IOVA called iopt_areas. Multiple IOMMU domains (IO page tables) and in-kernel accesses (like VFIO mdevs) can be attached to the IOAS to access the PFNs that those IOVA areas cover. The IO Address Space (IOAS) datastructure is composed of: - struct io_pagetable holding the IOVA map - struct iopt_areas representing populated portions of IOVA - struct iopt_pages representing the storage of PFNs - struct iommu_domain representing each IO page table in the system IOMMU - struct iopt_pages_access representing in-kernel accesses of PFNs (ie VFIO mdevs) - struct xarray pinned_pfns holding a list of pages pinned by in-kernel accesses This patch introduces the lowest part of the datastructure - the movement of PFNs in a tiered storage scheme: 1) iopt_pages::pinned_pfns xarray 2) Multiple iommu_domains 3) The origin of the PFNs, i.e. the userspace pointer PFN have to be copied between all combinations of tiers, depending on the configuration. The interface is an iterator called a 'pfn_reader' which determines which tier each PFN is stored and loads it into a list of PFNs held in a struct pfn_batch. Each step of the iterator will fill up the pfn_batch, then the caller can use the pfn_batch to send the PFNs to the required destination. Repeating this loop will read all the PFNs in an IOVA range. The pfn_reader and pfn_batch also keep track of the pinned page accounting. While PFNs are always stored and accessed as full PAGE_SIZE units the iommu_domain tier can store with a sub-page offset/length to support IOMMUs with a smaller IOPTE size than PAGE_SIZE. Link: https://lore.kernel.org/r/8-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com Reviewed-by: Kevin Tian <kevin.tian@intel.com> Tested-by: Nicolin Chen <nicolinc@nvidia.com> Tested-by: Yi Liu <yi.l.liu@intel.com> Tested-by: Lixiao Yang <lixiao.yang@intel.com> Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-11-30 04:29:31 +08:00
enum {
IOMMUFD_ACCESS_RW_READ = 0,
IOMMUFD_ACCESS_RW_WRITE = 1 << 0,
/* Set if the caller is in a kthread then rw will use kthread_use_mm() */
IOMMUFD_ACCESS_RW_KTHREAD = 1 << 1,
/* Only for use by selftest */
__IOMMUFD_ACCESS_RW_SLOW_PATH = 1 << 2,
iommufd: PFN handling for iopt_pages The top of the data structure provides an IO Address Space (IOAS) that is similar to a VFIO container. The IOAS allows map/unmap of memory into ranges of IOVA called iopt_areas. Multiple IOMMU domains (IO page tables) and in-kernel accesses (like VFIO mdevs) can be attached to the IOAS to access the PFNs that those IOVA areas cover. The IO Address Space (IOAS) datastructure is composed of: - struct io_pagetable holding the IOVA map - struct iopt_areas representing populated portions of IOVA - struct iopt_pages representing the storage of PFNs - struct iommu_domain representing each IO page table in the system IOMMU - struct iopt_pages_access representing in-kernel accesses of PFNs (ie VFIO mdevs) - struct xarray pinned_pfns holding a list of pages pinned by in-kernel accesses This patch introduces the lowest part of the datastructure - the movement of PFNs in a tiered storage scheme: 1) iopt_pages::pinned_pfns xarray 2) Multiple iommu_domains 3) The origin of the PFNs, i.e. the userspace pointer PFN have to be copied between all combinations of tiers, depending on the configuration. The interface is an iterator called a 'pfn_reader' which determines which tier each PFN is stored and loads it into a list of PFNs held in a struct pfn_batch. Each step of the iterator will fill up the pfn_batch, then the caller can use the pfn_batch to send the PFNs to the required destination. Repeating this loop will read all the PFNs in an IOVA range. The pfn_reader and pfn_batch also keep track of the pinned page accounting. While PFNs are always stored and accessed as full PAGE_SIZE units the iommu_domain tier can store with a sub-page offset/length to support IOMMUs with a smaller IOPTE size than PAGE_SIZE. Link: https://lore.kernel.org/r/8-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com Reviewed-by: Kevin Tian <kevin.tian@intel.com> Tested-by: Nicolin Chen <nicolinc@nvidia.com> Tested-by: Yi Liu <yi.l.liu@intel.com> Tested-by: Lixiao Yang <lixiao.yang@intel.com> Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-11-30 04:29:31 +08:00
};
struct iommufd_access *
iommufd_access_create(struct iommufd_ctx *ictx, u32 ioas_id,
const struct iommufd_access_ops *ops, void *data);
void iommufd_access_destroy(struct iommufd_access *access);
void iommufd_ctx_get(struct iommufd_ctx *ictx);
#if IS_ENABLED(CONFIG_IOMMUFD)
struct iommufd_ctx *iommufd_ctx_from_file(struct file *file);
void iommufd_ctx_put(struct iommufd_ctx *ictx);
int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova,
unsigned long length, struct page **out_pages,
unsigned int flags);
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);
iommufd: vfio container FD ioctl compatibility iommufd can directly implement the /dev/vfio/vfio container IOCTLs by mapping them into io_pagetable operations. A userspace application can test against iommufd and confirm compatibility then simply make a small change to open /dev/iommu instead of /dev/vfio/vfio. For testing purposes /dev/vfio/vfio can be symlinked to /dev/iommu and then all applications will use the compatibility path with no code changes. A later series allows /dev/vfio/vfio to be directly provided by iommufd, which allows the rlimit mode to work the same as well. This series just provides the iommufd side of compatibility. Actually linking this to VFIO_SET_CONTAINER is a followup series, with a link in the cover letter. Internally the compatibility API uses a normal IOAS object that, like vfio, is automatically allocated when the first device is attached. Userspace can also query or set this IOAS object directly using the IOMMU_VFIO_IOAS ioctl. This allows mixing and matching new iommufd only features while still using the VFIO style map/unmap ioctls. While this is enough to operate qemu, it has a few differences: - Resource limits rely on memory cgroups to bound what userspace can do instead of the module parameter dma_entry_limit. - VFIO P2P is not implemented. The DMABUF patches for vfio are a start at a solution where iommufd would import a special DMABUF. This is to avoid further propogating the follow_pfn() security problem. - A full audit for pedantic compatibility details (eg errnos, etc) has not yet been done - powerpc SPAPR is left out, as it is not connected to the iommu_domain framework. It seems interest in SPAPR is minimal as it is currently non-working in v6.1-rc1. They will have to convert to the iommu subsystem framework to enjoy iommfd. The following are not going to be implemented and we expect to remove them from VFIO type1: - SW access 'dirty tracking'. As discussed in the cover letter this will be done in VFIO. - VFIO_TYPE1_NESTING_IOMMU https://lore.kernel.org/all/0-v1-0093c9b0e345+19-vfio_no_nesting_jgg@nvidia.com/ - VFIO_DMA_MAP_FLAG_VADDR https://lore.kernel.org/all/Yz777bJZjTyLrHEQ@nvidia.com/ Link: https://lore.kernel.org/r/15-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com Tested-by: Nicolin Chen <nicolinc@nvidia.com> Tested-by: Yi Liu <yi.l.liu@intel.com> Tested-by: Lixiao Yang <lixiao.yang@intel.com> Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-11-30 04:29:38 +08:00
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)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void iommufd_ctx_put(struct iommufd_ctx *ictx)
{
}
static inline int iommufd_access_pin_pages(struct iommufd_access *access,
unsigned long iova,
unsigned long length,
struct page **out_pages,
unsigned int flags)
{
return -EOPNOTSUPP;
}
static inline void iommufd_access_unpin_pages(struct iommufd_access *access,
unsigned long iova,
unsigned long length)
{
}
static inline int iommufd_access_rw(struct iommufd_access *access, unsigned long iova,
void *data, size_t len, unsigned int flags)
{
return -EOPNOTSUPP;
}
iommufd: vfio container FD ioctl compatibility iommufd can directly implement the /dev/vfio/vfio container IOCTLs by mapping them into io_pagetable operations. A userspace application can test against iommufd and confirm compatibility then simply make a small change to open /dev/iommu instead of /dev/vfio/vfio. For testing purposes /dev/vfio/vfio can be symlinked to /dev/iommu and then all applications will use the compatibility path with no code changes. A later series allows /dev/vfio/vfio to be directly provided by iommufd, which allows the rlimit mode to work the same as well. This series just provides the iommufd side of compatibility. Actually linking this to VFIO_SET_CONTAINER is a followup series, with a link in the cover letter. Internally the compatibility API uses a normal IOAS object that, like vfio, is automatically allocated when the first device is attached. Userspace can also query or set this IOAS object directly using the IOMMU_VFIO_IOAS ioctl. This allows mixing and matching new iommufd only features while still using the VFIO style map/unmap ioctls. While this is enough to operate qemu, it has a few differences: - Resource limits rely on memory cgroups to bound what userspace can do instead of the module parameter dma_entry_limit. - VFIO P2P is not implemented. The DMABUF patches for vfio are a start at a solution where iommufd would import a special DMABUF. This is to avoid further propogating the follow_pfn() security problem. - A full audit for pedantic compatibility details (eg errnos, etc) has not yet been done - powerpc SPAPR is left out, as it is not connected to the iommu_domain framework. It seems interest in SPAPR is minimal as it is currently non-working in v6.1-rc1. They will have to convert to the iommu subsystem framework to enjoy iommfd. The following are not going to be implemented and we expect to remove them from VFIO type1: - SW access 'dirty tracking'. As discussed in the cover letter this will be done in VFIO. - VFIO_TYPE1_NESTING_IOMMU https://lore.kernel.org/all/0-v1-0093c9b0e345+19-vfio_no_nesting_jgg@nvidia.com/ - VFIO_DMA_MAP_FLAG_VADDR https://lore.kernel.org/all/Yz777bJZjTyLrHEQ@nvidia.com/ Link: https://lore.kernel.org/r/15-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com Tested-by: Nicolin Chen <nicolinc@nvidia.com> Tested-by: Yi Liu <yi.l.liu@intel.com> Tested-by: Lixiao Yang <lixiao.yang@intel.com> Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
2022-11-30 04:29:38 +08:00
static inline int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx,
u32 *out_ioas_id)
{
return -EOPNOTSUPP;
}
#endif /* CONFIG_IOMMUFD */
#endif