linux/drivers/vfio/vfio.h

357 lines
9.7 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.com>
*/
#ifndef __VFIO_VFIO_H__
#define __VFIO_VFIO_H__
#include <linux/file.h>
#include <linux/device.h>
#include <linux/cdev.h>
#include <linux/module.h>
#include <linux/vfio.h>
struct iommufd_ctx;
struct iommu_group;
struct vfio_container;
struct vfio_device_file {
struct vfio_device *device;
struct vfio_group *group;
vfio: Block device access via device fd until device is opened Allow the vfio_device file to be in a state where the device FD is opened but the device cannot be used by userspace (i.e. its .open_device() hasn't been called). This inbetween state is not used when the device FD is spawned from the group FD, however when we create the device FD directly by opening a cdev it will be opened in the blocked state. The reason for the inbetween state is that userspace only gets a FD but doesn't gain access permission until binding the FD to an iommufd. So in the blocked state, only the bind operation is allowed. Completing bind will allow user to further access the device. This is implemented by adding a flag in struct vfio_device_file to mark the blocked state and using a simple smp_load_acquire() to obtain the flag value and serialize all the device setup with the thread accessing this device. Following this lockless scheme, it can safely handle the device FD unbound->bound but it cannot handle bound->unbound. To allow this we'd need to add a lock on all the vfio ioctls which seems costly. So once device FD is bound, it remains bound until the FD is closed. Suggested-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Terrence Xu <terrence.xu@intel.com> Tested-by: Nicolin Chen <nicolinc@nvidia.com> Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> Tested-by: Yanting Jiang <yanting.jiang@intel.com> Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com> Tested-by: Zhenzhong Duan <zhenzhong.duan@intel.com> Signed-off-by: Yi Liu <yi.l.liu@intel.com> Link: https://lore.kernel.org/r/20230718135551.6592-8-yi.l.liu@intel.com Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2023-07-18 13:55:32 +00:00
u8 access_granted;
u32 devid; /* only valid when iommufd is valid */
spinlock_t kvm_ref_lock; /* protect kvm field */
struct kvm *kvm;
struct iommufd_ctx *iommufd; /* protected by struct vfio_device_set::lock */
};
void vfio_device_put_registration(struct vfio_device *device);
bool vfio_device_try_get_registration(struct vfio_device *device);
int vfio_df_open(struct vfio_device_file *df);
void vfio_df_close(struct vfio_device_file *df);
struct vfio_device_file *
vfio_allocate_device_file(struct vfio_device *device);
extern const struct file_operations vfio_device_fops;
enum vfio_group_type {
/*
* Physical device with IOMMU backing.
*/
VFIO_IOMMU,
/*
* Virtual device without IOMMU backing. The VFIO core fakes up an
* iommu_group as the iommu_group sysfs interface is part of the
* userspace ABI. The user of these devices must not be able to
* directly trigger unmediated DMA.
*/
VFIO_EMULATED_IOMMU,
/*
* Physical device without IOMMU backing. The VFIO core fakes up an
* iommu_group as the iommu_group sysfs interface is part of the
* userspace ABI. Users can trigger unmediated DMA by the device,
* usage is highly dangerous, requires an explicit opt-in and will
* taint the kernel.
*/
VFIO_NO_IOMMU,
};
struct vfio_group {
struct device dev;
struct cdev cdev;
vfio: Follow a strict lifetime for struct iommu_group The iommu_group comes from the struct device that a driver has been bound to and then created a struct vfio_device against. To keep the iommu layer sane we want to have a simple rule that only an attached driver should be using the iommu API. Particularly only an attached driver should hold ownership. In VFIO's case since it uses the group APIs and it shares between different drivers it is a bit more complicated, but the principle still holds. Solve this by waiting for all users of the vfio_group to stop before allowing vfio_unregister_group_dev() to complete. This is done with a new completion to know when the users go away and an additional refcount to keep track of how many device drivers are sharing the vfio group. The last driver to be unregistered will clean up the group. This solves crashes in the S390 iommu driver that come because VFIO ends up racing releasing ownership (which attaches the default iommu_domain to the device) with the removal of that same device from the iommu driver. This is a side case that iommu drivers should not have to cope with. iommu driver failed to attach the default/blocking domain WARNING: CPU: 0 PID: 5082 at drivers/iommu/iommu.c:1961 iommu_detach_group+0x6c/0x80 Modules linked in: macvtap macvlan tap vfio_pci vfio_pci_core irqbypass vfio_virqfd kvm nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables nfnetlink mlx5_ib sunrpc ib_uverbs ism smc uvdevice ib_core s390_trng eadm_sch tape_3590 tape tape_class vfio_ccw mdev vfio_iommu_type1 vfio zcrypt_cex4 sch_fq_codel configfs ghash_s390 prng chacha_s390 libchacha aes_s390 mlx5_core des_s390 libdes sha3_512_s390 nvme sha3_256_s390 sha512_s390 sha256_s390 sha1_s390 sha_common nvme_core zfcp scsi_transport_fc pkey zcrypt rng_core autofs4 CPU: 0 PID: 5082 Comm: qemu-system-s39 Tainted: G W 6.0.0-rc3 #5 Hardware name: IBM 3931 A01 782 (LPAR) Krnl PSW : 0704c00180000000 000000095bb10d28 (iommu_detach_group+0x70/0x80) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 RI:0 EA:3 Krnl GPRS: 0000000000000001 0000000900000027 0000000000000039 000000095c97ffe0 00000000fffeffff 00000009fc290000 00000000af1fda50 00000000af590b58 00000000af1fdaf0 0000000135c7a320 0000000135e52258 0000000135e52200 00000000a29e8000 00000000af590b40 000000095bb10d24 0000038004b13c98 Krnl Code: 000000095bb10d18: c020003d56fc larl %r2,000000095c2bbb10 000000095bb10d1e: c0e50019d901 brasl %r14,000000095be4bf20 #000000095bb10d24: af000000 mc 0,0 >000000095bb10d28: b904002a lgr %r2,%r10 000000095bb10d2c: ebaff0a00004 lmg %r10,%r15,160(%r15) 000000095bb10d32: c0f4001aa867 brcl 15,000000095be65e00 000000095bb10d38: c004002168e0 brcl 0,000000095bf3def8 000000095bb10d3e: eb6ff0480024 stmg %r6,%r15,72(%r15) Call Trace: [<000000095bb10d28>] iommu_detach_group+0x70/0x80 ([<000000095bb10d24>] iommu_detach_group+0x6c/0x80) [<000003ff80243b0e>] vfio_iommu_type1_detach_group+0x136/0x6c8 [vfio_iommu_type1] [<000003ff80137780>] __vfio_group_unset_container+0x58/0x158 [vfio] [<000003ff80138a16>] vfio_group_fops_unl_ioctl+0x1b6/0x210 [vfio] pci 0004:00:00.0: Removing from iommu group 4 [<000000095b5b62e8>] __s390x_sys_ioctl+0xc0/0x100 [<000000095be5d3b4>] __do_syscall+0x1d4/0x200 [<000000095be6c072>] system_call+0x82/0xb0 Last Breaking-Event-Address: [<000000095be4bf80>] __warn_printk+0x60/0x68 It indicates that domain->ops->attach_dev() failed because the driver has already passed the point of destructing the device. Fixes: 9ac8545199a1 ("iommu: Fix use-after-free in iommu_release_device") Reported-by: Matthew Rosato <mjrosato@linux.ibm.com> Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> Reviewed-by: Yi Liu <yi.l.liu@intel.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Link: https://lore.kernel.org/r/0-v2-a3c5f4429e2a+55-iommu_group_lifetime_jgg@nvidia.com Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2022-09-23 00:06:10 +00:00
/*
* When drivers is non-zero a driver is attached to the struct device
* that provided the iommu_group and thus the iommu_group is a valid
* pointer. When drivers is 0 the driver is being detached. Once users
* reaches 0 then the iommu_group is invalid.
*/
refcount_t drivers;
unsigned int container_users;
struct iommu_group *iommu_group;
struct vfio_container *container;
struct list_head device_list;
struct mutex device_lock;
struct list_head vfio_next;
#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
struct list_head container_next;
#endif
enum vfio_group_type type;
struct mutex group_lock;
struct kvm *kvm;
struct file *opened_file;
struct blocking_notifier_head notifier;
struct iommufd_ctx *iommufd;
spinlock_t kvm_ref_lock;
unsigned int cdev_device_open_cnt;
};
int vfio_device_block_group(struct vfio_device *device);
void vfio_device_unblock_group(struct vfio_device *device);
int vfio_device_set_group(struct vfio_device *device,
enum vfio_group_type type);
void vfio_device_remove_group(struct vfio_device *device);
void vfio_device_group_register(struct vfio_device *device);
void vfio_device_group_unregister(struct vfio_device *device);
int vfio_device_group_use_iommu(struct vfio_device *device);
void vfio_device_group_unuse_iommu(struct vfio_device *device);
void vfio_df_group_close(struct vfio_device_file *df);
struct vfio_group *vfio_group_from_file(struct file *file);
bool vfio_group_enforced_coherent(struct vfio_group *group);
void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm);
bool vfio_device_has_container(struct vfio_device *device);
int __init vfio_group_init(void);
void vfio_group_cleanup(void);
static inline bool vfio_device_is_noiommu(struct vfio_device *vdev)
{
return IS_ENABLED(CONFIG_VFIO_NOIOMMU) &&
vdev->group->type == VFIO_NO_IOMMU;
}
#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
/**
* struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks
*/
struct vfio_iommu_driver_ops {
char *name;
struct module *owner;
void *(*open)(unsigned long arg);
void (*release)(void *iommu_data);
long (*ioctl)(void *iommu_data, unsigned int cmd,
unsigned long arg);
int (*attach_group)(void *iommu_data,
struct iommu_group *group,
enum vfio_group_type);
void (*detach_group)(void *iommu_data,
struct iommu_group *group);
int (*pin_pages)(void *iommu_data,
struct iommu_group *group,
dma_addr_t user_iova,
int npage, int prot,
struct page **pages);
void (*unpin_pages)(void *iommu_data,
dma_addr_t user_iova, int npage);
void (*register_device)(void *iommu_data,
struct vfio_device *vdev);
void (*unregister_device)(void *iommu_data,
struct vfio_device *vdev);
int (*dma_rw)(void *iommu_data, dma_addr_t user_iova,
void *data, size_t count, bool write);
struct iommu_domain *(*group_iommu_domain)(void *iommu_data,
struct iommu_group *group);
};
struct vfio_iommu_driver {
const struct vfio_iommu_driver_ops *ops;
struct list_head vfio_next;
};
int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops);
struct vfio_container *vfio_container_from_file(struct file *filep);
int vfio_group_use_container(struct vfio_group *group);
void vfio_group_unuse_container(struct vfio_group *group);
int vfio_container_attach_group(struct vfio_container *container,
struct vfio_group *group);
void vfio_group_detach_container(struct vfio_group *group);
void vfio_device_container_register(struct vfio_device *device);
void vfio_device_container_unregister(struct vfio_device *device);
int vfio_device_container_pin_pages(struct vfio_device *device,
dma_addr_t iova, int npage,
int prot, struct page **pages);
void vfio_device_container_unpin_pages(struct vfio_device *device,
dma_addr_t iova, int npage);
int vfio_device_container_dma_rw(struct vfio_device *device,
dma_addr_t iova, void *data,
size_t len, bool write);
int __init vfio_container_init(void);
void vfio_container_cleanup(void);
#else
static inline struct vfio_container *
vfio_container_from_file(struct file *filep)
{
return NULL;
}
static inline int vfio_group_use_container(struct vfio_group *group)
{
return -EOPNOTSUPP;
}
static inline void vfio_group_unuse_container(struct vfio_group *group)
{
}
static inline int vfio_container_attach_group(struct vfio_container *container,
struct vfio_group *group)
{
return -EOPNOTSUPP;
}
static inline void vfio_group_detach_container(struct vfio_group *group)
{
}
static inline void vfio_device_container_register(struct vfio_device *device)
{
}
static inline void vfio_device_container_unregister(struct vfio_device *device)
{
}
static inline int vfio_device_container_pin_pages(struct vfio_device *device,
dma_addr_t iova, int npage,
int prot, struct page **pages)
{
return -EOPNOTSUPP;
}
static inline void vfio_device_container_unpin_pages(struct vfio_device *device,
dma_addr_t iova, int npage)
{
}
static inline int vfio_device_container_dma_rw(struct vfio_device *device,
dma_addr_t iova, void *data,
size_t len, bool write)
{
return -EOPNOTSUPP;
}
static inline int vfio_container_init(void)
{
return 0;
}
static inline void vfio_container_cleanup(void)
{
}
#endif
#if IS_ENABLED(CONFIG_IOMMUFD)
bool vfio_iommufd_device_has_compat_ioas(struct vfio_device *vdev,
struct iommufd_ctx *ictx);
int vfio_df_iommufd_bind(struct vfio_device_file *df);
void vfio_df_iommufd_unbind(struct vfio_device_file *df);
int vfio_iommufd_compat_attach_ioas(struct vfio_device *device,
struct iommufd_ctx *ictx);
#else
static inline bool
vfio_iommufd_device_has_compat_ioas(struct vfio_device *vdev,
struct iommufd_ctx *ictx)
{
return false;
}
static inline int vfio_df_iommufd_bind(struct vfio_device_file *fd)
{
return -EOPNOTSUPP;
}
static inline void vfio_df_iommufd_unbind(struct vfio_device_file *df)
{
}
static inline int
vfio_iommufd_compat_attach_ioas(struct vfio_device *device,
struct iommufd_ctx *ictx)
{
return -EOPNOTSUPP;
}
#endif
vfio: Add cdev for vfio_device This adds cdev support for vfio_device. It allows the user to directly open a vfio device w/o using the legacy container/group interface, as a prerequisite for supporting new iommu features like nested translation and etc. The device fd opened in this manner doesn't have the capability to access the device as the fops open() doesn't open the device until the successful VFIO_DEVICE_BIND_IOMMUFD ioctl which will be added in a later patch. With this patch, devices registered to vfio core would have both the legacy group and the new device interfaces created. - group interface : /dev/vfio/$groupID - device interface: /dev/vfio/devices/vfioX - normal device ("X" is a unique number across vfio devices) For a given device, the user can identify the matching vfioX by searching the vfio-dev folder under the sysfs path of the device. Take PCI device (0000:6a:01.0) as an example, /sys/bus/pci/devices/0000\:6a\:01.0/vfio-dev/vfioX implies the matching vfioX under /dev/vfio/devices/, and vfio-dev/vfioX/dev contains the major:minor number of the matching /dev/vfio/devices/vfioX. The user can get device fd by opening the /dev/vfio/devices/vfioX. The vfio_device cdev logic in this patch: *) __vfio_register_dev() path ends up doing cdev_device_add() for each vfio_device if VFIO_DEVICE_CDEV configured. *) vfio_unregister_group_dev() path does cdev_device_del(); cdev interface does not support noiommu devices, so VFIO only creates the legacy group interface for the physical devices that do not have IOMMU. noiommu users should use the legacy group interface. Reviewed-by: Kevin Tian <kevin.tian@intel.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Tested-by: Terrence Xu <terrence.xu@intel.com> Tested-by: Nicolin Chen <nicolinc@nvidia.com> Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> Tested-by: Yanting Jiang <yanting.jiang@intel.com> Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com> Tested-by: Zhenzhong Duan <zhenzhong.duan@intel.com> Signed-off-by: Yi Liu <yi.l.liu@intel.com> Link: https://lore.kernel.org/r/20230718135551.6592-19-yi.l.liu@intel.com Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2023-07-18 13:55:43 +00:00
#if IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV)
void vfio_init_device_cdev(struct vfio_device *device);
static inline int vfio_device_add(struct vfio_device *device)
{
/* cdev does not support noiommu device */
if (vfio_device_is_noiommu(device))
return device_add(&device->device);
vfio_init_device_cdev(device);
return cdev_device_add(&device->cdev, &device->device);
}
static inline void vfio_device_del(struct vfio_device *device)
{
if (vfio_device_is_noiommu(device))
device_del(&device->device);
else
cdev_device_del(&device->cdev, &device->device);
}
int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep);
int vfio_cdev_init(struct class *device_class);
void vfio_cdev_cleanup(void);
#else
static inline void vfio_init_device_cdev(struct vfio_device *device)
{
}
static inline int vfio_device_add(struct vfio_device *device)
{
return device_add(&device->device);
}
static inline void vfio_device_del(struct vfio_device *device)
{
device_del(&device->device);
}
static inline int vfio_device_fops_cdev_open(struct inode *inode,
struct file *filep)
{
return 0;
}
static inline int vfio_cdev_init(struct class *device_class)
{
return 0;
}
static inline void vfio_cdev_cleanup(void)
{
}
#endif /* CONFIG_VFIO_DEVICE_CDEV */
#if IS_ENABLED(CONFIG_VFIO_VIRQFD)
int __init vfio_virqfd_init(void);
void vfio_virqfd_exit(void);
#else
static inline int __init vfio_virqfd_init(void)
{
return 0;
}
static inline void vfio_virqfd_exit(void)
{
}
#endif
#ifdef CONFIG_VFIO_NOIOMMU
extern bool vfio_noiommu __read_mostly;
#else
enum { vfio_noiommu = false };
#endif
#ifdef CONFIG_HAVE_KVM
void _vfio_device_get_kvm_safe(struct vfio_device *device, struct kvm *kvm);
void vfio_device_put_kvm(struct vfio_device *device);
#else
static inline void _vfio_device_get_kvm_safe(struct vfio_device *device,
struct kvm *kvm)
{
}
static inline void vfio_device_put_kvm(struct vfio_device *device)
{
}
#endif
#endif