mirror of
https://git.proxmox.com/git/mirror_ubuntu-kernels.git
synced 2026-01-06 20:44:11 +00:00
d624d6652a
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>
96 lines
2.7 KiB
C
96 lines
2.7 KiB
C
/* 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);
|
|
};
|
|
|
|
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,
|
|
};
|
|
|
|
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);
|
|
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;
|
|
}
|
|
|
|
static inline int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx,
|
|
u32 *out_ioas_id)
|
|
{
|
|
return -EOPNOTSUPP;
|
|
}
|
|
#endif /* CONFIG_IOMMUFD */
|
|
#endif
|