linux/drivers/vfio/vfio.h
Jason Gunthorpe ca5f21b257 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: 9ac8545199 ("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>
2022-09-27 09:01:23 -06:00

136 lines
4.1 KiB
C

/* 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/device.h>
#include <linux/cdev.h>
#include <linux/module.h>
struct iommu_group;
struct vfio_device;
struct vfio_container;
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;
/*
* 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;
refcount_t users;
struct completion users_comp;
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;
struct list_head container_next;
enum vfio_group_type type;
struct rw_semaphore group_rwsem;
struct kvm *kvm;
struct file *opened_file;
struct blocking_notifier_head notifier;
};
/* events for the backend driver notify callback */
enum vfio_iommu_notify_type {
VFIO_IOMMU_CONTAINER_CLOSE = 0,
};
/**
* 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);
void (*notify)(void *iommu_data,
enum vfio_iommu_notify_type event);
};
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);
bool vfio_assert_device_open(struct vfio_device *device);
struct vfio_container *vfio_container_from_file(struct file *filep);
int vfio_device_assign_container(struct vfio_device *device);
void vfio_device_unassign_container(struct vfio_device *device);
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);
long vfio_container_ioctl_check_extension(struct vfio_container *container,
unsigned long arg);
int __init vfio_container_init(void);
void vfio_container_cleanup(void);
#ifdef CONFIG_VFIO_NOIOMMU
extern bool vfio_noiommu __read_mostly;
#else
enum { vfio_noiommu = false };
#endif
#endif