[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <A2975661238FB949B60364EF0F2C25743A183EB3@SHSMSX104.ccr.corp.intel.com>
Date: Thu, 16 Jan 2020 12:33:06 +0000
From: "Liu, Yi L" <yi.l.liu@...el.com>
To: Alex Williamson <alex.williamson@...hat.com>
CC: "kwankhede@...dia.com" <kwankhede@...dia.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"kvm@...r.kernel.org" <kvm@...r.kernel.org>,
"Tian, Kevin" <kevin.tian@...el.com>,
"joro@...tes.org" <joro@...tes.org>,
"peterx@...hat.com" <peterx@...hat.com>,
"baolu.lu@...ux.intel.com" <baolu.lu@...ux.intel.com>,
Masahiro Yamada <yamada.masahiro@...ionext.com>
Subject: RE: [PATCH v4 11/12] samples: add vfio-mdev-pci driver
> From: Alex Williamson [mailto:alex.williamson@...hat.com]
> Sent: Friday, January 10, 2020 6:49 AM
> To: Liu, Yi L <yi.l.liu@...el.com>
> Subject: Re: [PATCH v4 11/12] samples: add vfio-mdev-pci driver
>
> On Tue, 7 Jan 2020 20:01:48 +0800
> Liu Yi L <yi.l.liu@...el.com> wrote:
>
> > This patch adds sample driver named vfio-mdev-pci. It is to wrap
> > a PCI device as a mediated device. For a pci device, once bound
> > to vfio-mdev-pci driver, user space access of this device will
> > go through vfio mdev framework. The usage of the device follows
> > mdev management method. e.g. user should create a mdev before
> > exposing the device to user-space.
> >
> > Benefit of this new driver would be acting as a sample driver
> > for recent changes from "vfio/mdev: IOMMU aware mediated device"
> > patchset. Also it could be a good experiment driver for future
> > device specific mdev migration support. This sample driver only
> > supports singleton iommu groups, for non-singleton iommu groups,
> > this sample driver doesn't work. It will fail when trying to assign
> > the non-singleton iommu group to VMs.
> >
> > To use this driver:
> > a) build and load vfio-mdev-pci.ko module
> > execute "make menuconfig" and config CONFIG_SAMPLE_VFIO_MDEV_PCI
> > then load it with following command:
> > > sudo modprobe vfio
> > > sudo modprobe vfio-pci
> > > sudo insmod samples/vfio-mdev-pci/vfio-mdev-pci.ko
> >
> > b) unbind original device driver
> > e.g. use following command to unbind its original driver
> > > echo $dev_bdf > /sys/bus/pci/devices/$dev_bdf/driver/unbind
> >
> > c) bind vfio-mdev-pci driver to the physical device
> > > echo $vend_id $dev_id > /sys/bus/pci/drivers/vfio-mdev-pci/new_id
> >
> > d) check the supported mdev instances
> > > ls /sys/bus/pci/devices/$dev_bdf/mdev_supported_types/
> > vfio-mdev-pci-type_name
> > > ls /sys/bus/pci/devices/$dev_bdf/mdev_supported_types/\
> > vfio-mdev-pci-type_name/
> > available_instances create device_api devices name
> >
> > e) create mdev on this physical device (only 1 instance)
> > > echo "83b8f4f2-509f-382f-3c1e-e6bfe0fa1003" > \
> > /sys/bus/pci/devices/$dev_bdf/mdev_supported_types/\
> > vfio-mdev-pci-type_name/create
> >
> > f) passthru the mdev to guest
> > add the following line in QEMU boot command
> > -device vfio-pci,\
> > sysfsdev=/sys/bus/mdev/devices/83b8f4f2-509f-382f-3c1e-e6bfe0fa1003
> >
> > g) destroy mdev
> > > echo 1 > /sys/bus/mdev/devices/83b8f4f2-509f-382f-3c1e-e6bfe0fa1003/\
> > remove
> >
> > Cc: Kevin Tian <kevin.tian@...el.com>
> > Cc: Lu Baolu <baolu.lu@...ux.intel.com>
> > Cc: Masahiro Yamada <yamada.masahiro@...ionext.com>
> > Suggested-by: Alex Williamson <alex.williamson@...hat.com>
> > Signed-off-by: Liu Yi L <yi.l.liu@...el.com>
> > ---
> > samples/Kconfig | 10 +
> > samples/Makefile | 1 +
> > samples/vfio-mdev-pci/Makefile | 4 +
> > samples/vfio-mdev-pci/vfio_mdev_pci.c | 397
> ++++++++++++++++++++++++++++++++++
> > 4 files changed, 412 insertions(+)
> > create mode 100644 samples/vfio-mdev-pci/Makefile
> > create mode 100644 samples/vfio-mdev-pci/vfio_mdev_pci.c
> >
> > diff --git a/samples/Kconfig b/samples/Kconfig
> > index 9d236c3..50d207c 100644
> > --- a/samples/Kconfig
> > +++ b/samples/Kconfig
> > @@ -190,5 +190,15 @@ config SAMPLE_INTEL_MEI
> > help
> > Build a sample program to work with mei device.
> >
> > +config SAMPLE_VFIO_MDEV_PCI
> > + tristate "Sample driver for wrapping PCI device as a mdev"
> > + select VFIO_PCI_COMMON
> > + select VFIO_PCI
> > + depends on VFIO_MDEV && VFIO_MDEV_DEVICE
> > + help
> > + Sample driver for wrapping a PCI device as a mdev. Once bound to
> > + this driver, device passthru should through mdev path.
> > +
> > + If you don't know what to do here, say N.
> >
> > endif # SAMPLES
> > diff --git a/samples/Makefile b/samples/Makefile
> > index 5ce50ef..84faced 100644
> > --- a/samples/Makefile
> > +++ b/samples/Makefile
> > @@ -21,5 +21,6 @@ obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace/
> > obj-$(CONFIG_SAMPLE_TRACE_ARRAY) += ftrace/
> > obj-$(CONFIG_VIDEO_PCI_SKELETON) += v4l/
> > obj-y += vfio-mdev/
> > +obj-y += vfio-mdev-pci/
>
> I think we could just lump this into vfio-mdev rather than making
> another directory.
sure. will move it. :-)
>
> > subdir-$(CONFIG_SAMPLE_VFS) += vfs
> > obj-$(CONFIG_SAMPLE_INTEL_MEI) += mei/
> > diff --git a/samples/vfio-mdev-pci/Makefile b/samples/vfio-mdev-pci/Makefile
> > new file mode 100644
> > index 0000000..41b2139
> > --- /dev/null
> > +++ b/samples/vfio-mdev-pci/Makefile
> > @@ -0,0 +1,4 @@
> > +# SPDX-License-Identifier: GPL-2.0-only
> > +vfio-mdev-pci-y := vfio_mdev_pci.o
> > +
> > +obj-$(CONFIG_SAMPLE_VFIO_MDEV_PCI) += vfio-mdev-pci.o
> > diff --git a/samples/vfio-mdev-pci/vfio_mdev_pci.c b/samples/vfio-mdev-
> pci/vfio_mdev_pci.c
> > new file mode 100644
> > index 0000000..b180356
> > --- /dev/null
> > +++ b/samples/vfio-mdev-pci/vfio_mdev_pci.c
> > @@ -0,0 +1,397 @@
> > +/*
> > + * Copyright © 2020 Intel Corporation.
> > + * Author: Liu Yi L <yi.l.liu@...el.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.
> > + *
> > + * Derived from original vfio_pci.c:
> > + * Copyright (C) 2012 Red Hat, Inc. All rights reserved.
> > + * Author: Alex Williamson <alex.williamson@...hat.com>
> > + *
> > + * Derived from original vfio:
> > + * Copyright 2010 Cisco Systems, Inc. All rights reserved.
> > + * Author: Tom Lyon, pugs@...co.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/pci.h>
> > +#include <linux/pm_runtime.h>
> > +#include <linux/slab.h>
> > +#include <linux/types.h>
> > +#include <linux/uaccess.h>
> > +#include <linux/vfio.h>
> > +#include <linux/vgaarb.h>
> > +#include <linux/nospec.h>
> > +#include <linux/mdev.h>
> > +#include <linux/vfio_pci_common.h>
> > +
> > +#define DRIVER_VERSION "0.1"
> > +#define DRIVER_AUTHOR "Liu Yi L <yi.l.liu@...el.com>"
> > +#define DRIVER_DESC "VFIO Mdev PCI - Sample driver for PCI device as a
> mdev"
> > +
> > +#define VFIO_MDEV_PCI_NAME "vfio-mdev-pci"
> > +
> > +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-mdev-pci 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@...r.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-
> mdev-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 struct pci_driver vfio_mdev_pci_driver;
> > +
> > +static ssize_t
> > +name_show(struct kobject *kobj, struct device *dev, char *buf)
> > +{
> > + return sprintf(buf, "%s-type1\n", dev_name(dev));
> > +}
> > +
> > +MDEV_TYPE_ATTR_RO(name);
> > +
> > +static ssize_t
> > +available_instances_show(struct kobject *kobj, struct device *dev, char *buf)
> > +{
> > + return sprintf(buf, "%d\n", 1);
> > +}
> > +
> > +MDEV_TYPE_ATTR_RO(available_instances);
> > +
> > +static ssize_t device_api_show(struct kobject *kobj, struct device *dev,
> > + char *buf)
> > +{
> > + return sprintf(buf, "%s\n", VFIO_DEVICE_API_PCI_STRING);
> > +}
> > +
> > +MDEV_TYPE_ATTR_RO(device_api);
> > +
> > +static struct attribute *vfio_mdev_pci_types_attrs[] = {
> > + &mdev_type_attr_name.attr,
> > + &mdev_type_attr_device_api.attr,
> > + &mdev_type_attr_available_instances.attr,
> > + NULL,
> > +};
> > +
> > +static struct attribute_group vfio_mdev_pci_type_group1 = {
> > + .name = "type1",
> > + .attrs = vfio_mdev_pci_types_attrs,
> > +};
> > +
> > +struct attribute_group *vfio_mdev_pci_type_groups[] = {
> > + &vfio_mdev_pci_type_group1,
> > + NULL,
> > +};
> > +
> > +struct vfio_mdev_pci {
> > + struct vfio_pci_device *vdev;
> > + struct mdev_device *mdev;
> > + unsigned long handle;
> > +};
> > +
> > +static int vfio_mdev_pci_create(struct kobject *kobj, struct mdev_device *mdev)
> > +{
> > + struct device *pdev;
> > + struct vfio_pci_device *vdev;
> > + struct vfio_mdev_pci *pmdev;
> > + int ret;
> > +
> > + pdev = mdev_parent_dev(mdev);
> > + vdev = dev_get_drvdata(pdev);
> > + pmdev = kzalloc(sizeof(struct vfio_mdev_pci), GFP_KERNEL);
> > + if (pmdev == NULL) {
> > + ret = -EBUSY;
> > + goto out;
> > + }
> > +
> > + pmdev->mdev = mdev;
> > + pmdev->vdev = vdev;
> > + mdev_set_drvdata(mdev, pmdev);
> > + ret = mdev_set_iommu_device(mdev_dev(mdev), pdev);
> > + if (ret) {
> > + pr_info("%s, failed to config iommu isolation for mdev: %s on
> pf: %s\n",
> > + __func__, dev_name(mdev_dev(mdev)), dev_name(pdev));
> > + goto out;
> > + }
> > +
> > + pr_info("%s, creation succeeded for mdev: %s\n", __func__,
> > + dev_name(mdev_dev(mdev)));
> > +out:
> > + return ret;
> > +}
> > +
> > +static int vfio_mdev_pci_remove(struct mdev_device *mdev)
> > +{
> > + struct vfio_mdev_pci *pmdev = mdev_get_drvdata(mdev);
> > +
> > + kfree(pmdev);
> > + pr_info("%s, succeeded for mdev: %s\n", __func__,
> > + dev_name(mdev_dev(mdev)));
> > +
> > + return 0;
> > +}
> > +
> > +static int vfio_mdev_pci_open(struct mdev_device *mdev)
> > +{
> > + struct vfio_mdev_pci *pmdev = mdev_get_drvdata(mdev);
> > + struct vfio_pci_device *vdev = pmdev->vdev;
> > + int ret = 0;
> > +
> > + if (!try_module_get(THIS_MODULE))
> > + return -ENODEV;
> > +
> > + vfio_pci_refresh_config(vdev, nointxmask, disable_idle_d3);
> > +
> > + mutex_lock(&vdev->reflck->lock);
> > +
> > + if (!vdev->refcnt) {
> > + ret = vfio_pci_enable(vdev);
> > + if (ret)
> > + goto error;
> > +
> > + vfio_spapr_pci_eeh_open(vdev->pdev);
> > + }
> > + vdev->refcnt++;
> > +error:
> > + mutex_unlock(&vdev->reflck->lock);
> > + if (!ret)
> > + pr_info("Succeeded to open mdev: %s on pf: %s\n",
> > + dev_name(mdev_dev(mdev)), dev_name(&pmdev->vdev->pdev-
> >dev));
> > + else {
> > + pr_info("Failed to open mdev: %s on pf: %s\n",
> > + dev_name(mdev_dev(mdev)), dev_name(&pmdev->vdev->pdev-
> >dev));
> > + module_put(THIS_MODULE);
> > + }
> > + return ret;
> > +}
> > +
> > +static void vfio_mdev_pci_release(struct mdev_device *mdev)
> > +{
> > + struct vfio_mdev_pci *pmdev = mdev_get_drvdata(mdev);
> > + struct vfio_pci_device *vdev = pmdev->vdev;
> > +
> > + pr_info("Release mdev: %s on pf: %s\n",
> > + dev_name(mdev_dev(mdev)), dev_name(&pmdev->vdev->pdev-
> >dev));
> > +
> > + mutex_lock(&vdev->reflck->lock);
> > +
> > + if (!(--vdev->refcnt)) {
> > + vfio_spapr_pci_eeh_release(vdev->pdev);
> > + vfio_pci_disable(vdev);
> > + }
> > +
> > + mutex_unlock(&vdev->reflck->lock);
> > +
> > + module_put(THIS_MODULE);
> > +}
>
> open() and release() here are almost identical between vfio_pci and
> vfio_mdev_pci, which suggests maybe there should be common functions to
> call into like we do for the below.
yes, let me have more study and do better abstract in next version. :-)
> > +static long vfio_mdev_pci_ioctl(struct mdev_device *mdev, unsigned int cmd,
> > + unsigned long arg)
> > +{
> > + struct vfio_mdev_pci *pmdev = mdev_get_drvdata(mdev);
> > +
> > + return vfio_pci_ioctl(pmdev->vdev, cmd, arg);
> > +}
> > +
> > +static int vfio_mdev_pci_mmap(struct mdev_device *mdev,
> > + struct vm_area_struct *vma)
> > +{
> > + struct vfio_mdev_pci *pmdev = mdev_get_drvdata(mdev);
> > +
> > + return vfio_pci_mmap(pmdev->vdev, vma);
> > +}
> > +
> > +static ssize_t vfio_mdev_pci_read(struct mdev_device *mdev, char __user *buf,
> > + size_t count, loff_t *ppos)
> > +{
> > + struct vfio_mdev_pci *pmdev = mdev_get_drvdata(mdev);
> > +
> > + return vfio_pci_read(pmdev->vdev, buf, count, ppos);
> > +}
> > +
> > +static ssize_t vfio_mdev_pci_write(struct mdev_device *mdev,
> > + const char __user *buf,
> > + size_t count, loff_t *ppos)
> > +{
> > + struct vfio_mdev_pci *pmdev = mdev_get_drvdata(mdev);
> > +
> > + return vfio_pci_write(pmdev->vdev, (char __user *)buf, count, ppos);
> > +}
> > +
> > +static const struct mdev_parent_ops vfio_mdev_pci_ops = {
> > + .supported_type_groups = vfio_mdev_pci_type_groups,
> > + .create = vfio_mdev_pci_create,
> > + .remove = vfio_mdev_pci_remove,
> > +
> > + .open = vfio_mdev_pci_open,
> > + .release = vfio_mdev_pci_release,
> > +
> > + .read = vfio_mdev_pci_read,
> > + .write = vfio_mdev_pci_write,
> > + .mmap = vfio_mdev_pci_mmap,
> > + .ioctl = vfio_mdev_pci_ioctl,
> > +};
> > +
> > +static int vfio_mdev_pci_driver_probe(struct pci_dev *pdev,
> > + const struct pci_device_id *id)
> > +{
> > + struct vfio_pci_device *vdev;
> > + int ret;
> > +
> > + if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
> > + return -EINVAL;
> > +
> > + /*
> > + * Prevent binding to PFs with VFs enabled, this too easily allows
> > + * userspace instance with VFs and PFs from the same device, which
> > + * cannot work. Disabling SR-IOV here would initiate removing the
> > + * VFs, which would unbind the driver, which is prone to blocking
> > + * if that VF is also in use by vfio-pci or vfio-mdev-pci. Just
> > + * reject these PFs and let the user sort it out.
> > + */
> > + if (pci_num_vf(pdev)) {
> > + pci_warn(pdev, "Cannot bind to PF with SR-IOV enabled\n");
> > + return -EBUSY;
> > + }
> > +
> > + vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
> > + if (!vdev)
> > + return -ENOMEM;
> > +
> > + vdev->pdev = pdev;
> > + vdev->irq_type = VFIO_PCI_NUM_IRQS;
> > + mutex_init(&vdev->igate);
> > + spin_lock_init(&vdev->irqlock);
> > + mutex_init(&vdev->ioeventfds_lock);
> > + INIT_LIST_HEAD(&vdev->ioeventfds_list);
> > + vdev->nointxmask = nointxmask;
> > +#ifdef CONFIG_VFIO_PCI_VGA
> > + vdev->disable_vga = disable_vga;
> > +#endif
> > + vdev->disable_idle_d3 = disable_idle_d3;
> > +
> > + pci_set_drvdata(pdev, vdev);
> > +
> > + ret = vfio_pci_reflck_attach(vdev);
> > + if (ret) {
> > + pci_set_drvdata(pdev, NULL);
> > + kfree(vdev);
> > + return ret;
> > + }
> > +
> > + if (vfio_pci_is_vga(pdev)) {
> > + vga_client_register(pdev, vdev, NULL, vfio_pci_set_vga_decode);
> > + vga_set_legacy_decoding(pdev,
> > + vfio_pci_set_vga_decode(vdev, false));
> > + }
> > +
> > + vfio_pci_probe_power_state(vdev);
> > +
> > + if (!vdev->disable_idle_d3) {
> > + /*
> > + * pci-core sets the device power state to an unknown value at
> > + * bootup and after being removed from a driver. The only
> > + * transition it allows from this unknown state is to D0, which
> > + * typically happens when a driver calls pci_enable_device().
> > + * We're not ready to enable the device yet, but we do want to
> > + * be able to get to D3. Therefore first do a D0 transition
> > + * before going to D3.
> > + */
> > + vfio_pci_set_power_state(vdev, PCI_D0);
> > + vfio_pci_set_power_state(vdev, PCI_D3hot);
> > + }
>
> Ditto here and remove below, this seems like boilerplate that shouldn't
> be duplicated per leaf module. Thanks,
Sure, the code snippet above may also be abstracted to be a common API
provided by vfio-pci-common.ko. :-)
I have a confusion which may need confirm with you. Do you also want the
below code snippet be placed in the vfio-pci-common.ko and exposed out
as a wrapped API? Thus it can be used by sample driver and other future
drivers which want to wrap PCI device as a mdev. May be I misundstood
your comment. :-(
>
> Alex
Thanks,
Yi Liu
> > +
> > + ret = mdev_register_device(&pdev->dev, &vfio_mdev_pci_ops);
> > + if (ret)
> > + pr_err("Cannot register mdev for device %s\n",
> > + dev_name(&pdev->dev));
> > + else
> > + pr_info("Wrap device %s as a mdev\n", dev_name(&pdev->dev));
> > +
> > + return ret;
> > +}
> > +
> > +static void vfio_mdev_pci_driver_remove(struct pci_dev *pdev)
> > +{
> > + struct vfio_pci_device *vdev;
> > +
> > + vdev = pci_get_drvdata(pdev);
> > + if (!vdev)
> > + return;
> > +
> > + vfio_pci_reflck_put(vdev->reflck);
> > +
> > + kfree(vdev->region);
> > + mutex_destroy(&vdev->ioeventfds_lock);
> > +
> > + if (!disable_idle_d3)
> > + vfio_pci_set_power_state(vdev, PCI_D0);
> > +
> > + kfree(vdev->pm_save);
> > +
> > + if (vfio_pci_is_vga(pdev)) {
> > + vga_client_register(pdev, NULL, NULL, NULL);
> > + vga_set_legacy_decoding(pdev,
> > + VGA_RSRC_NORMAL_IO |
> VGA_RSRC_NORMAL_MEM |
> > + VGA_RSRC_LEGACY_IO |
> VGA_RSRC_LEGACY_MEM);
> > + }
> > +
> > + kfree(vdev);
> > +}
> > +
> > +static struct pci_driver vfio_mdev_pci_driver = {
> > + .name = VFIO_MDEV_PCI_NAME,
> > + .id_table = NULL, /* only dynamic ids */
> > + .probe = vfio_mdev_pci_driver_probe,
> > + .remove = vfio_mdev_pci_driver_remove,
> > + .err_handler = &vfio_pci_err_handlers,
> > +};
> > +
> > +static void __exit vfio_mdev_pci_cleanup(void)
> > +{
> > + pci_unregister_driver(&vfio_mdev_pci_driver);
> > +}
> > +
> > +static int __init vfio_mdev_pci_init(void)
> > +{
> > + int ret;
> > +
> > + /* Register and scan for devices */
> > + ret = pci_register_driver(&vfio_mdev_pci_driver);
> > + if (ret)
> > + return ret;
> > +
> > + vfio_pci_fill_ids(ids, &vfio_mdev_pci_driver);
> > +
> > + return 0;
> > +}
> > +
> > +module_init(vfio_mdev_pci_init);
> > +module_exit(vfio_mdev_pci_cleanup);
> > +
> > +MODULE_VERSION(DRIVER_VERSION);
> > +MODULE_LICENSE("GPL v2");
> > +MODULE_AUTHOR(DRIVER_AUTHOR);
> > +MODULE_DESCRIPTION(DRIVER_DESC);
Powered by blists - more mailing lists