linux/drivers/vfio/pci/vfio_pci.c
Jason Gunthorpe 445ad495f0 vfio: Have the core code decode the VFIO_DEVICE_FEATURE ioctl
Invoke a new device op 'device_feature' to handle just the data array
portion of the command. This lifts the ioctl validation to the core code
and makes it simpler for either the core code, or layered drivers, to
implement their own feature values.

Provide vfio_check_feature() to consolidate checking the flags/etc against
what the driver supports.

Link: https://lore.kernel.org/all/20220224142024.147653-9-yishaih@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
2022-03-03 12:54:43 +02:00

274 lines
7.2 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved
*
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
* Author: Alex Williamson <alex.williamson@redhat.com>
*
* Derived from original vfio:
* Copyright 2010 Cisco Systems, Inc. All rights reserved.
* Author: Tom Lyon, pugs@cisco.com
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/device.h>
#include <linux/eventfd.h>
#include <linux/file.h>
#include <linux/interrupt.h>
#include <linux/iommu.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/notifier.h>
#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/vfio_pci_core.h>
#define DRIVER_AUTHOR "Alex Williamson <alex.williamson@redhat.com>"
#define DRIVER_DESC "VFIO PCI - User Level meta-driver"
static char ids[1024] __initdata;
module_param_string(ids, ids, sizeof(ids), 0);
MODULE_PARM_DESC(ids, "Initial PCI IDs to add to the vfio driver, format is \"vendor:device[:subvendor[:subdevice[:class[:class_mask]]]]\" and multiple comma separated entries can be specified");
static bool nointxmask;
module_param_named(nointxmask, nointxmask, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(nointxmask,
"Disable support for PCI 2.3 style INTx masking. If this resolves problems for specific devices, report lspci -vvvxxx to linux-pci@vger.kernel.org so the device can be fixed automatically via the broken_intx_masking flag.");
#ifdef CONFIG_VFIO_PCI_VGA
static bool disable_vga;
module_param(disable_vga, bool, S_IRUGO);
MODULE_PARM_DESC(disable_vga, "Disable VGA resource access through vfio-pci");
#endif
static bool disable_idle_d3;
module_param(disable_idle_d3, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(disable_idle_d3,
"Disable using the PCI D3 low power state for idle, unused devices");
static bool enable_sriov;
#ifdef CONFIG_PCI_IOV
module_param(enable_sriov, bool, 0644);
MODULE_PARM_DESC(enable_sriov, "Enable support for SR-IOV configuration. Enabling SR-IOV on a PF typically requires support of the userspace PF driver, enabling VFs without such support may result in non-functional VFs or PF.");
#endif
static bool disable_denylist;
module_param(disable_denylist, bool, 0444);
MODULE_PARM_DESC(disable_denylist, "Disable use of device denylist. Disabling the denylist allows binding to devices with known errata that may lead to exploitable stability or security issues when accessed by untrusted users.");
static bool vfio_pci_dev_in_denylist(struct pci_dev *pdev)
{
switch (pdev->vendor) {
case PCI_VENDOR_ID_INTEL:
switch (pdev->device) {
case PCI_DEVICE_ID_INTEL_QAT_C3XXX:
case PCI_DEVICE_ID_INTEL_QAT_C3XXX_VF:
case PCI_DEVICE_ID_INTEL_QAT_C62X:
case PCI_DEVICE_ID_INTEL_QAT_C62X_VF:
case PCI_DEVICE_ID_INTEL_QAT_DH895XCC:
case PCI_DEVICE_ID_INTEL_QAT_DH895XCC_VF:
return true;
default:
return false;
}
}
return false;
}
static bool vfio_pci_is_denylisted(struct pci_dev *pdev)
{
if (!vfio_pci_dev_in_denylist(pdev))
return false;
if (disable_denylist) {
pci_warn(pdev,
"device denylist disabled - allowing device %04x:%04x.\n",
pdev->vendor, pdev->device);
return false;
}
pci_warn(pdev, "%04x:%04x exists in vfio-pci device denylist, driver probing disallowed.\n",
pdev->vendor, pdev->device);
return true;
}
static int vfio_pci_open_device(struct vfio_device *core_vdev)
{
struct vfio_pci_core_device *vdev =
container_of(core_vdev, struct vfio_pci_core_device, vdev);
struct pci_dev *pdev = vdev->pdev;
int ret;
ret = vfio_pci_core_enable(vdev);
if (ret)
return ret;
if (vfio_pci_is_vga(pdev) &&
pdev->vendor == PCI_VENDOR_ID_INTEL &&
IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
ret = vfio_pci_igd_init(vdev);
if (ret && ret != -ENODEV) {
pci_warn(pdev, "Failed to setup Intel IGD regions\n");
vfio_pci_core_disable(vdev);
return ret;
}
}
vfio_pci_core_finish_enable(vdev);
return 0;
}
static const struct vfio_device_ops vfio_pci_ops = {
.name = "vfio-pci",
.open_device = vfio_pci_open_device,
.close_device = vfio_pci_core_close_device,
.ioctl = vfio_pci_core_ioctl,
.device_feature = vfio_pci_core_ioctl_feature,
.read = vfio_pci_core_read,
.write = vfio_pci_core_write,
.mmap = vfio_pci_core_mmap,
.request = vfio_pci_core_request,
.match = vfio_pci_core_match,
};
static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct vfio_pci_core_device *vdev;
int ret;
if (vfio_pci_is_denylisted(pdev))
return -EINVAL;
vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
if (!vdev)
return -ENOMEM;
vfio_pci_core_init_device(vdev, pdev, &vfio_pci_ops);
ret = vfio_pci_core_register_device(vdev);
if (ret)
goto out_free;
dev_set_drvdata(&pdev->dev, vdev);
return 0;
out_free:
vfio_pci_core_uninit_device(vdev);
kfree(vdev);
return ret;
}
static void vfio_pci_remove(struct pci_dev *pdev)
{
struct vfio_pci_core_device *vdev = dev_get_drvdata(&pdev->dev);
vfio_pci_core_unregister_device(vdev);
vfio_pci_core_uninit_device(vdev);
kfree(vdev);
}
static int vfio_pci_sriov_configure(struct pci_dev *pdev, int nr_virtfn)
{
if (!enable_sriov)
return -ENOENT;
return vfio_pci_core_sriov_configure(pdev, nr_virtfn);
}
static const struct pci_device_id vfio_pci_table[] = {
{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_ANY_ID, PCI_ANY_ID) }, /* match all by default */
{}
};
MODULE_DEVICE_TABLE(pci, vfio_pci_table);
static struct pci_driver vfio_pci_driver = {
.name = "vfio-pci",
.id_table = vfio_pci_table,
.probe = vfio_pci_probe,
.remove = vfio_pci_remove,
.sriov_configure = vfio_pci_sriov_configure,
.err_handler = &vfio_pci_core_err_handlers,
};
static void __init vfio_pci_fill_ids(void)
{
char *p, *id;
int rc;
/* no ids passed actually */
if (ids[0] == '\0')
return;
/* add ids specified in the module parameter */
p = ids;
while ((id = strsep(&p, ","))) {
unsigned int vendor, device, subvendor = PCI_ANY_ID,
subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
int fields;
if (!strlen(id))
continue;
fields = sscanf(id, "%x:%x:%x:%x:%x:%x",
&vendor, &device, &subvendor, &subdevice,
&class, &class_mask);
if (fields < 2) {
pr_warn("invalid id string \"%s\"\n", id);
continue;
}
rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
subvendor, subdevice, class, class_mask, 0);
if (rc)
pr_warn("failed to add dynamic id [%04x:%04x[%04x:%04x]] class %#08x/%08x (%d)\n",
vendor, device, subvendor, subdevice,
class, class_mask, rc);
else
pr_info("add [%04x:%04x[%04x:%04x]] class %#08x/%08x\n",
vendor, device, subvendor, subdevice,
class, class_mask);
}
}
static int __init vfio_pci_init(void)
{
int ret;
bool is_disable_vga = true;
#ifdef CONFIG_VFIO_PCI_VGA
is_disable_vga = disable_vga;
#endif
vfio_pci_core_set_params(nointxmask, is_disable_vga, disable_idle_d3);
/* Register and scan for devices */
ret = pci_register_driver(&vfio_pci_driver);
if (ret)
return ret;
vfio_pci_fill_ids();
if (disable_denylist)
pr_warn("device denylist disabled.\n");
return 0;
}
module_init(vfio_pci_init);
static void __exit vfio_pci_cleanup(void)
{
pci_unregister_driver(&vfio_pci_driver);
}
module_exit(vfio_pci_cleanup);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);