linux_dsm_epyc7002/virt/kvm/vfio.c
Wanpeng Li 571ee1b685 kvm: vfio: fix unregister kvm_device_ops of vfio
After commit 80ce163 (KVM: VFIO: register kvm_device_ops dynamically),
kvm_device_ops of vfio can be registered dynamically. Commit 3c3c29fd
(kvm-vfio: do not use module_init) move the dynamic register invoked by
kvm_init in order to fix broke unloading of the kvm module. However,
kvm_device_ops of vfio is unregistered after rmmod kvm-intel module
which lead to device type collision detection warning after kvm-intel
module reinsmod.

    WARNING: CPU: 1 PID: 10358 at /root/cathy/kvm/arch/x86/kvm/../../../virt/kvm/kvm_main.c:3289 kvm_init+0x234/0x282 [kvm]()
    Modules linked in: kvm_intel(O+) kvm(O) nfsv3 nfs_acl auth_rpcgss oid_registry nfsv4 dns_resolver nfs fscache lockd sunrpc pci_stub bridge stp llc autofs4 8021q cpufreq_ondemand ipv6 joydev microcode pcspkr igb i2c_algo_bit ehci_pci ehci_hcd e1000e i2c_i801 ixgbe ptp pps_core hwmon mdio tpm_tis tpm ipmi_si ipmi_msghandler acpi_cpufreq isci libsas scsi_transport_sas button dm_mirror dm_region_hash dm_log dm_mod [last unloaded: kvm_intel]
    CPU: 1 PID: 10358 Comm: insmod Tainted: G        W  O   3.17.0-rc1 
    Hardware name: Intel Corporation S2600CP/S2600CP, BIOS RMLSDP.86I.00.29.D696.1311111329 11/11/2013
     0000000000000cd9 ffff880ff08cfd18 ffffffff814a61d9 0000000000000cd9
     0000000000000000 ffff880ff08cfd58 ffffffff810417b7 ffff880ff08cfd48
     ffffffffa045bcac ffffffffa049c420 0000000000000040 00000000000000ff
    Call Trace:
     [<ffffffff814a61d9>] dump_stack+0x49/0x60
     [<ffffffff810417b7>] warn_slowpath_common+0x7c/0x96
     [<ffffffffa045bcac>] ? kvm_init+0x234/0x282 [kvm]
     [<ffffffff810417e6>] warn_slowpath_null+0x15/0x17
     [<ffffffffa045bcac>] kvm_init+0x234/0x282 [kvm]
     [<ffffffffa016e995>] vmx_init+0x1bf/0x42a [kvm_intel]
     [<ffffffffa016e7d6>] ? vmx_check_processor_compat+0x64/0x64 [kvm_intel]
     [<ffffffff810002ab>] do_one_initcall+0xe3/0x170
     [<ffffffff811168a9>] ? __vunmap+0xad/0xb8
     [<ffffffff8109c58f>] do_init_module+0x2b/0x174
     [<ffffffff8109d414>] load_module+0x43e/0x569
     [<ffffffff8109c6d8>] ? do_init_module+0x174/0x174
     [<ffffffff8109c75a>] ? copy_module_from_user+0x39/0x82
     [<ffffffff8109b7dd>] ? module_sect_show+0x20/0x20
     [<ffffffff8109d65f>] SyS_init_module+0x54/0x81
     [<ffffffff814a9a12>] system_call_fastpath+0x16/0x1b
    ---[ end trace 0626f4a3ddea56f3 ]---

The bug can be reproduced by:

    rmmod kvm_intel.ko
    insmod kvm_intel.ko

without rmmod/insmod kvm.ko
This patch fixes the bug by unregistering kvm_device_ops of vfio when the
kvm-intel module is removed.

Reported-by: Liu Rongrong <rongrongx.liu@intel.com>
Fixes: 3c3c29fd0d
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-10-24 13:30:47 +02:00

291 lines
6.0 KiB
C

/*
* VFIO-KVM bridge pseudo device
*
* Copyright (C) 2013 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/kvm_host.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include "vfio.h"
struct kvm_vfio_group {
struct list_head node;
struct vfio_group *vfio_group;
};
struct kvm_vfio {
struct list_head group_list;
struct mutex lock;
bool noncoherent;
};
static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
{
struct vfio_group *vfio_group;
struct vfio_group *(*fn)(struct file *);
fn = symbol_get(vfio_group_get_external_user);
if (!fn)
return ERR_PTR(-EINVAL);
vfio_group = fn(filep);
symbol_put(vfio_group_get_external_user);
return vfio_group;
}
static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
{
void (*fn)(struct vfio_group *);
fn = symbol_get(vfio_group_put_external_user);
if (!fn)
return;
fn(vfio_group);
symbol_put(vfio_group_put_external_user);
}
static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
{
long (*fn)(struct vfio_group *, unsigned long);
long ret;
fn = symbol_get(vfio_external_check_extension);
if (!fn)
return false;
ret = fn(vfio_group, VFIO_DMA_CC_IOMMU);
symbol_put(vfio_external_check_extension);
return ret > 0;
}
/*
* Groups can use the same or different IOMMU domains. If the same then
* adding a new group may change the coherency of groups we've previously
* been told about. We don't want to care about any of that so we retest
* each group and bail as soon as we find one that's noncoherent. This
* means we only ever [un]register_noncoherent_dma once for the whole device.
*/
static void kvm_vfio_update_coherency(struct kvm_device *dev)
{
struct kvm_vfio *kv = dev->private;
bool noncoherent = false;
struct kvm_vfio_group *kvg;
mutex_lock(&kv->lock);
list_for_each_entry(kvg, &kv->group_list, node) {
if (!kvm_vfio_group_is_coherent(kvg->vfio_group)) {
noncoherent = true;
break;
}
}
if (noncoherent != kv->noncoherent) {
kv->noncoherent = noncoherent;
if (kv->noncoherent)
kvm_arch_register_noncoherent_dma(dev->kvm);
else
kvm_arch_unregister_noncoherent_dma(dev->kvm);
}
mutex_unlock(&kv->lock);
}
static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
{
struct kvm_vfio *kv = dev->private;
struct vfio_group *vfio_group;
struct kvm_vfio_group *kvg;
int32_t __user *argp = (int32_t __user *)(unsigned long)arg;
struct fd f;
int32_t fd;
int ret;
switch (attr) {
case KVM_DEV_VFIO_GROUP_ADD:
if (get_user(fd, argp))
return -EFAULT;
f = fdget(fd);
if (!f.file)
return -EBADF;
vfio_group = kvm_vfio_group_get_external_user(f.file);
fdput(f);
if (IS_ERR(vfio_group))
return PTR_ERR(vfio_group);
mutex_lock(&kv->lock);
list_for_each_entry(kvg, &kv->group_list, node) {
if (kvg->vfio_group == vfio_group) {
mutex_unlock(&kv->lock);
kvm_vfio_group_put_external_user(vfio_group);
return -EEXIST;
}
}
kvg = kzalloc(sizeof(*kvg), GFP_KERNEL);
if (!kvg) {
mutex_unlock(&kv->lock);
kvm_vfio_group_put_external_user(vfio_group);
return -ENOMEM;
}
list_add_tail(&kvg->node, &kv->group_list);
kvg->vfio_group = vfio_group;
mutex_unlock(&kv->lock);
kvm_vfio_update_coherency(dev);
return 0;
case KVM_DEV_VFIO_GROUP_DEL:
if (get_user(fd, argp))
return -EFAULT;
f = fdget(fd);
if (!f.file)
return -EBADF;
vfio_group = kvm_vfio_group_get_external_user(f.file);
fdput(f);
if (IS_ERR(vfio_group))
return PTR_ERR(vfio_group);
ret = -ENOENT;
mutex_lock(&kv->lock);
list_for_each_entry(kvg, &kv->group_list, node) {
if (kvg->vfio_group != vfio_group)
continue;
list_del(&kvg->node);
kvm_vfio_group_put_external_user(kvg->vfio_group);
kfree(kvg);
ret = 0;
break;
}
mutex_unlock(&kv->lock);
kvm_vfio_group_put_external_user(vfio_group);
kvm_vfio_update_coherency(dev);
return ret;
}
return -ENXIO;
}
static int kvm_vfio_set_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
switch (attr->group) {
case KVM_DEV_VFIO_GROUP:
return kvm_vfio_set_group(dev, attr->attr, attr->addr);
}
return -ENXIO;
}
static int kvm_vfio_has_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
switch (attr->group) {
case KVM_DEV_VFIO_GROUP:
switch (attr->attr) {
case KVM_DEV_VFIO_GROUP_ADD:
case KVM_DEV_VFIO_GROUP_DEL:
return 0;
}
break;
}
return -ENXIO;
}
static void kvm_vfio_destroy(struct kvm_device *dev)
{
struct kvm_vfio *kv = dev->private;
struct kvm_vfio_group *kvg, *tmp;
list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
kvm_vfio_group_put_external_user(kvg->vfio_group);
list_del(&kvg->node);
kfree(kvg);
}
kvm_vfio_update_coherency(dev);
kfree(kv);
kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
}
static int kvm_vfio_create(struct kvm_device *dev, u32 type);
static struct kvm_device_ops kvm_vfio_ops = {
.name = "kvm-vfio",
.create = kvm_vfio_create,
.destroy = kvm_vfio_destroy,
.set_attr = kvm_vfio_set_attr,
.has_attr = kvm_vfio_has_attr,
};
static int kvm_vfio_create(struct kvm_device *dev, u32 type)
{
struct kvm_device *tmp;
struct kvm_vfio *kv;
/* Only one VFIO "device" per VM */
list_for_each_entry(tmp, &dev->kvm->devices, vm_node)
if (tmp->ops == &kvm_vfio_ops)
return -EBUSY;
kv = kzalloc(sizeof(*kv), GFP_KERNEL);
if (!kv)
return -ENOMEM;
INIT_LIST_HEAD(&kv->group_list);
mutex_init(&kv->lock);
dev->private = kv;
return 0;
}
int kvm_vfio_ops_init(void)
{
return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO);
}
void kvm_vfio_ops_exit(void)
{
kvm_unregister_device_ops(KVM_DEV_TYPE_VFIO);
}