Message-ID: <DS7PR11MB6104D1246DA5ED88325D2686EEC3A@DS7PR11MB6104.namprd11.prod.outlook.com>
Date: Fri, 7 Nov 2025 09:38:05 +0000
From: "Muqthyar Ahmed, Syed Abdul" <syed.abdul.muqthyar.ahmed@...el.com>
To: "Winiarski, Michal" <michal.winiarski@...el.com>, Alex Williamson
	<alex@...zbot.org>, "De Marchi, Lucas" <lucas.demarchi@...el.com>,
	Thomas Hellström <thomas.hellstrom@...ux.intel.com>,
	"Vivi, Rodrigo" <rodrigo.vivi@...el.com>, Jason Gunthorpe <jgg@...pe.ca>,
	Yishai Hadas <yishaih@...dia.com>, "Tian, Kevin" <kevin.tian@...el.com>,
	Shameer Kolothum <skolothumtho@...dia.com>, "intel-xe@...ts.freedesktop.org"
	<intel-xe@...ts.freedesktop.org>, "linux-kernel@...r.kernel.org"
	<linux-kernel@...r.kernel.org>, "kvm@...r.kernel.org" <kvm@...r.kernel.org>,
	"Brost, Matthew" <matthew.brost@...el.com>, "Wajdeczko, Michal"
	<Michal.Wajdeczko@...el.com>
CC: "dri-devel@...ts.freedesktop.org" <dri-devel@...ts.freedesktop.org>, "Jani
 Nikula" <jani.nikula@...ux.intel.com>, Joonas Lahtinen
	<joonas.lahtinen@...ux.intel.com>, Tvrtko Ursulin <tursulin@...ulin.net>,
	David Airlie <airlied@...il.com>, Simona Vetter <simona@...ll.ch>, "Laguna,
 Lukasz" <lukasz.laguna@...el.com>, Christoph Hellwig <hch@...radead.org>,
	"Winiarski, Michal" <michal.winiarski@...el.com>
Subject: RE: [PATCH v3 28/28] vfio/xe: Add device specific vfio_pci driver
 variant for Intel graphics



> -----Original Message-----
> From: Intel-xe <intel-xe-bounces@...ts.freedesktop.org> On Behalf Of Michał
> Winiarski
> Sent: Friday, October 31, 2025 2:02 AM
> To: Alex Williamson <alex@...zbot.org>; De Marchi, Lucas
> <lucas.demarchi@...el.com>; Thomas Hellström
> <thomas.hellstrom@...ux.intel.com>; Vivi, Rodrigo <rodrigo.vivi@...el.com>;
> Jason Gunthorpe <jgg@...pe.ca>; Yishai Hadas <yishaih@...dia.com>; Tian,
> Kevin <kevin.tian@...el.com>; Shameer Kolothum
> <skolothumtho@...dia.com>; intel-xe@...ts.freedesktop.org; linux-
> kernel@...r.kernel.org; kvm@...r.kernel.org; Brost, Matthew
> <matthew.brost@...el.com>; Wajdeczko, Michal
> <Michal.Wajdeczko@...el.com>
> Cc: dri-devel@...ts.freedesktop.org; Jani Nikula <jani.nikula@...ux.intel.com>;
> Joonas Lahtinen <joonas.lahtinen@...ux.intel.com>; Tvrtko Ursulin
> <tursulin@...ulin.net>; David Airlie <airlied@...il.com>; Simona Vetter
> <simona@...ll.ch>; Laguna, Lukasz <lukasz.laguna@...el.com>; Christoph
> Hellwig <hch@...radead.org>; Winiarski, Michal
> <michal.winiarski@...el.com>
> Subject: [PATCH v3 28/28] vfio/xe: Add device specific vfio_pci driver variant
> for Intel graphics
> 
> In addition to generic VFIO PCI functionality, the driver implements VFIO
> migration uAPI, allowing userspace to enable migration for Intel Graphics SR-
> IOV Virtual Functions.
> The driver binds to VF device, and uses API exposed by Xe driver bound to PF
> device to control VF device state and transfer the migration data.
> 
> Signed-off-by: Michał Winiarski <michal.winiarski@...el.com>
> ---
>  MAINTAINERS                  |   7 +
>  drivers/vfio/pci/Kconfig     |   2 +
>  drivers/vfio/pci/Makefile    |   2 +
>  drivers/vfio/pci/xe/Kconfig  |  12 +
>  drivers/vfio/pci/xe/Makefile |   3 +
>  drivers/vfio/pci/xe/main.c   | 552 +++++++++++++++++++++++++++++++++++
>  6 files changed, 578 insertions(+)
>  create mode 100644 drivers/vfio/pci/xe/Kconfig  create mode 100644
> drivers/vfio/pci/xe/Makefile  create mode 100644 drivers/vfio/pci/xe/main.c
> 
> diff --git a/MAINTAINERS b/MAINTAINERS
> index b890ff265f03f..d73348c5f3f3e 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -27008,6 +27008,13 @@ L:	virtualization@...ts.linux.dev
>  S:	Maintained
>  F:	drivers/vfio/pci/virtio
> 
> +VFIO XE PCI DRIVER
> +M:	Michał Winiarski <michal.winiarski@...el.com>
> +L:	kvm@...r.kernel.org
> +L:	intel-xe@...ts.freedesktop.org
> +S:	Supported
> +F:	drivers/vfio/pci/xe
> +
>  VGA_SWITCHEROO
>  R:	Lukas Wunner <lukas@...ner.de>
>  S:	Maintained
> diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index
> 2b0172f546652..c100f0ab87f2d 100644
> --- a/drivers/vfio/pci/Kconfig
> +++ b/drivers/vfio/pci/Kconfig
> @@ -67,4 +67,6 @@ source "drivers/vfio/pci/nvgrace-gpu/Kconfig"
> 
>  source "drivers/vfio/pci/qat/Kconfig"
> 
> +source "drivers/vfio/pci/xe/Kconfig"
> +
>  endmenu
> diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index
> cf00c0a7e55c8..f5d46aa9347b9 100644
> --- a/drivers/vfio/pci/Makefile
> +++ b/drivers/vfio/pci/Makefile
> @@ -19,3 +19,5 @@ obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio/
>  obj-$(CONFIG_NVGRACE_GPU_VFIO_PCI) += nvgrace-gpu/
> 
>  obj-$(CONFIG_QAT_VFIO_PCI) += qat/
> +
> +obj-$(CONFIG_XE_VFIO_PCI) += xe/
> diff --git a/drivers/vfio/pci/xe/Kconfig b/drivers/vfio/pci/xe/Kconfig new file
> mode 100644 index 0000000000000..787be88268685
> --- /dev/null
> +++ b/drivers/vfio/pci/xe/Kconfig
> @@ -0,0 +1,12 @@
> +# SPDX-License-Identifier: GPL-2.0-only config XE_VFIO_PCI
> +	tristate "VFIO support for Intel Graphics"
> +	depends on DRM_XE
> +	select VFIO_PCI_CORE
Shall we make it default enabled with "default m " so that config gets enabled for first timers and no need to enable explicitly. 

> +	help
> +	  This option enables vendor-specific VFIO driver for Intel Graphics.
> +	  In addition to generic VFIO PCI functionality, it implements VFIO
> +	  migration uAPI allowing userspace to enable migration for
> +	  Intel Graphics SR-IOV Virtual Functions supported by the Xe driver.
> +
> +	  If you don't know what to do here, say N.
> diff --git a/drivers/vfio/pci/xe/Makefile b/drivers/vfio/pci/xe/Makefile new file
> mode 100644 index 0000000000000..13aa0fd192cd4
> --- /dev/null
> +++ b/drivers/vfio/pci/xe/Makefile
> @@ -0,0 +1,3 @@
> +# SPDX-License-Identifier: GPL-2.0-only
> +obj-$(CONFIG_XE_VFIO_PCI) += xe-vfio-pci.o xe-vfio-pci-y := main.o
> diff --git a/drivers/vfio/pci/xe/main.c b/drivers/vfio/pci/xe/main.c new file
> mode 100644 index 0000000000000..4892c6648c0a7
> --- /dev/null
> +++ b/drivers/vfio/pci/xe/main.c
> @@ -0,0 +1,552 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Copyright © 2025 Intel Corporation
> + */
> +
> +#include <linux/anon_inodes.h>
> +#include <linux/delay.h>
> +#include <linux/file.h>
> +#include <linux/module.h>
> +#include <linux/pci.h>
> +#include <linux/sizes.h>
> +#include <linux/types.h>
> +#include <linux/vfio.h>
> +#include <linux/vfio_pci_core.h>
> +
> +#include <drm/intel/xe_sriov_vfio.h>
> +#include <drm/intel/pciids.h>
> +
> +struct xe_vfio_pci_migration_file {
> +	struct file *filp;
> +	/* serializes accesses to migration data */
> +	struct mutex lock;
> +	struct xe_vfio_pci_core_device *xe_vdev; };
> +
> +struct xe_vfio_pci_core_device {
> +	struct vfio_pci_core_device core_device;
> +	struct xe_device *xe;
> +	/* VF number used by PF, Xe HW/FW components use vfid indexing
> starting from 1 */
> +	unsigned int vfid;
> +	u8 migrate_cap:1;
> +	u8 deferred_reset:1;
> +	/* protects migration state */
> +	struct mutex state_mutex;
> +	enum vfio_device_mig_state mig_state;
> +	/* protects the reset_done flow */
> +	spinlock_t reset_lock;
> +	struct xe_vfio_pci_migration_file *migf; };
> +
> +#define xe_vdev_to_dev(xe_vdev) (&(xe_vdev)->core_device.pdev->dev)
> +
> +static void xe_vfio_pci_disable_file(struct xe_vfio_pci_migration_file
> +*migf) {
> +	struct xe_vfio_pci_core_device *xe_vdev = migf->xe_vdev;
> +
> +	mutex_lock(&migf->lock);
> +	xe_vdev->migf = NULL;
> +	mutex_unlock(&migf->lock);
> +}
> +
> +static void xe_vfio_pci_reset(struct xe_vfio_pci_core_device *xe_vdev)
> +{
> +	if (xe_vdev->migf)
> +		xe_vfio_pci_disable_file(xe_vdev->migf);
> +
> +	xe_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING; }
> +
> +static void xe_vfio_pci_state_mutex_lock(struct xe_vfio_pci_core_device
> +*xe_vdev) {
> +	mutex_lock(&xe_vdev->state_mutex);
> +}
> +
> +/*
> + * This function is called in all state_mutex unlock cases to
> + * handle a 'deferred_reset' if exists.
> + */
> +static void xe_vfio_pci_state_mutex_unlock(struct
> +xe_vfio_pci_core_device *xe_vdev) {
> +again:
> +	spin_lock(&xe_vdev->reset_lock);
> +	if (xe_vdev->deferred_reset) {
> +		xe_vdev->deferred_reset = false;
> +		spin_unlock(&xe_vdev->reset_lock);
> +		xe_vfio_pci_reset(xe_vdev);
> +		goto again;
> +	}
> +	mutex_unlock(&xe_vdev->state_mutex);
> +	spin_unlock(&xe_vdev->reset_lock);
> +}
> +
> +static void xe_vfio_pci_reset_done(struct pci_dev *pdev) {
> +	struct xe_vfio_pci_core_device *xe_vdev = pci_get_drvdata(pdev);
> +	int ret;
> +
> +	if (!xe_vdev->vfid)
> +		return;
> +
> +	/*
> +	 * VF FLR requires additional processing done by PF driver.
> +	 * The processing is done after FLR is already finished from PCIe
> +	 * perspective.
> +	 * In order to avoid a scenario where VF is used while PF processing
> +	 * is still in progress, additional synchronization point is needed.
> +	 */
> +	ret = xe_sriov_vfio_wait_flr_done(xe_vdev->xe, xe_vdev->vfid);
> +	if (ret)
> +		dev_err(&pdev->dev, "Failed to wait for FLR: %d\n", ret);
> +
> +	if (!xe_vdev->migrate_cap)
> +		return;
> +
> +	/*
> +	 * As the higher VFIO layers are holding locks across reset and using
> +	 * those same locks with the mm_lock we need to prevent ABBA
> deadlock
> +	 * with the state_mutex and mm_lock.
> +	 * In case the state_mutex was taken already we defer the cleanup
> work
> +	 * to the unlock flow of the other running context.
> +	 */
> +	spin_lock(&xe_vdev->reset_lock);
> +	xe_vdev->deferred_reset = true;
> +	if (!mutex_trylock(&xe_vdev->state_mutex)) {
> +		spin_unlock(&xe_vdev->reset_lock);
> +		return;
> +	}
> +	spin_unlock(&xe_vdev->reset_lock);
> +	xe_vfio_pci_state_mutex_unlock(xe_vdev);
> +
> +	xe_vfio_pci_reset(xe_vdev);
> +}
> +
> +static const struct pci_error_handlers xe_vfio_pci_err_handlers = {
> +	.reset_done = xe_vfio_pci_reset_done,
> +	.error_detected = vfio_pci_core_aer_err_detected, };
> +
> +static int xe_vfio_pci_open_device(struct vfio_device *core_vdev) {
> +	struct xe_vfio_pci_core_device *xe_vdev =
> +		container_of(core_vdev, struct xe_vfio_pci_core_device,
> core_device.vdev);
> +	struct vfio_pci_core_device *vdev = &xe_vdev->core_device;
> +	int ret;
> +
> +	ret = vfio_pci_core_enable(vdev);
> +	if (ret)
> +		return ret;
> +
> +	vfio_pci_core_finish_enable(vdev);
> +
> +	return 0;
> +}
> +
> +static int xe_vfio_pci_release_file(struct inode *inode, struct file
> +*filp) {
> +	struct xe_vfio_pci_migration_file *migf = filp->private_data;
> +
> +	xe_vfio_pci_disable_file(migf);
> +	mutex_destroy(&migf->lock);
> +	kfree(migf);
> +
> +	return 0;
> +}
> +
> +static ssize_t xe_vfio_pci_save_read(struct file *filp, char __user
> +*buf, size_t len, loff_t *pos) {
> +	struct xe_vfio_pci_migration_file *migf = filp->private_data;
> +	ssize_t ret;
> +
> +	if (pos)
> +		return -ESPIPE;
> +
> +	mutex_lock(&migf->lock);
> +	ret = xe_sriov_vfio_data_read(migf->xe_vdev->xe, migf->xe_vdev-
> >vfid, buf, len);
> +	mutex_unlock(&migf->lock);
> +
> +	return ret;
> +}
> +
> +static const struct file_operations xe_vfio_pci_save_fops = {
> +	.owner = THIS_MODULE,
> +	.read = xe_vfio_pci_save_read,
> +	.release = xe_vfio_pci_release_file,
> +	.llseek = noop_llseek,
> +};
> +
> +static ssize_t xe_vfio_pci_resume_write(struct file *filp, const char __user
> *buf,
> +					size_t len, loff_t *pos)
> +{
> +	struct xe_vfio_pci_migration_file *migf = filp->private_data;
> +	ssize_t ret;
> +
> +	if (pos)
> +		return -ESPIPE;
> +
> +	mutex_lock(&migf->lock);
> +	ret = xe_sriov_vfio_data_write(migf->xe_vdev->xe, migf->xe_vdev-
> >vfid, buf, len);
> +	mutex_unlock(&migf->lock);
> +
> +	return ret;
> +}
> +
> +static const struct file_operations xe_vfio_pci_resume_fops = {
> +	.owner = THIS_MODULE,
> +	.write = xe_vfio_pci_resume_write,
> +	.release = xe_vfio_pci_release_file,
> +	.llseek = noop_llseek,
> +};
> +
> +static const char *vfio_dev_state_str(u32 state) {
> +	switch (state) {
> +	case VFIO_DEVICE_STATE_RUNNING: return "running";
> +	case VFIO_DEVICE_STATE_RUNNING_P2P: return "running_p2p";
> +	case VFIO_DEVICE_STATE_STOP_COPY: return "stopcopy";
> +	case VFIO_DEVICE_STATE_STOP: return "stop";
> +	case VFIO_DEVICE_STATE_RESUMING: return "resuming";
> +	case VFIO_DEVICE_STATE_ERROR: return "error";
> +	default: return "";
> +	}
> +}
> +
> +enum xe_vfio_pci_file_type {
> +	XE_VFIO_FILE_SAVE = 0,
> +	XE_VFIO_FILE_RESUME,
> +};
> +
> +static struct xe_vfio_pci_migration_file *
> +xe_vfio_pci_alloc_file(struct xe_vfio_pci_core_device *xe_vdev,
> +		       enum xe_vfio_pci_file_type type) {
> +	struct xe_vfio_pci_migration_file *migf;
> +	const struct file_operations *fops;
> +	int flags;
> +
> +	migf = kzalloc(sizeof(*migf), GFP_KERNEL);
> +	if (!migf)
> +		return ERR_PTR(-ENOMEM);
> +
> +	fops = type == XE_VFIO_FILE_SAVE ? &xe_vfio_pci_save_fops :
> &xe_vfio_pci_resume_fops;
> +	flags = type == XE_VFIO_FILE_SAVE ? O_RDONLY : O_WRONLY;
> +	migf->filp = anon_inode_getfile("xe_vfio_mig", fops, migf, flags);
> +	if (IS_ERR(migf->filp)) {
> +		kfree(migf);
> +		return ERR_CAST(migf->filp);
> +	}
> +
> +	mutex_init(&migf->lock);
> +	migf->xe_vdev = xe_vdev;
> +	xe_vdev->migf = migf;
> +
> +	stream_open(migf->filp->f_inode, migf->filp);
> +
> +	return migf;
> +}
> +
> +static struct file *
> +xe_vfio_set_state(struct xe_vfio_pci_core_device *xe_vdev, u32 new) {
> +	u32 cur = xe_vdev->mig_state;
> +	int ret;
> +
> +	dev_dbg(xe_vdev_to_dev(xe_vdev),
> +		"state: %s->%s\n", vfio_dev_state_str(cur),
> vfio_dev_state_str(new));
> +
> +	/*
> +	 * "STOP" handling is reused for "RUNNING_P2P", as the device
> doesn't
> +	 * have the capability to selectively block outgoing p2p DMA transfers.
> +	 * While the device is allowing BAR accesses when the VF is stopped,
> it
> +	 * is not processing any new workload requests, effectively stopping
> +	 * any outgoing DMA transfers (not just p2p).
> +	 * Any VRAM / MMIO accesses occurring during "RUNNING_P2P" are
> kept and
> +	 * will be migrated to target VF during stop-copy.
> +	 */
> +	if (cur == VFIO_DEVICE_STATE_RUNNING && new ==
> VFIO_DEVICE_STATE_RUNNING_P2P) {
> +		ret = xe_sriov_vfio_suspend_device(xe_vdev->xe, xe_vdev-
> >vfid);
> +		if (ret)
> +			goto err;
> +
> +		return NULL;
> +	}
> +
> +	if ((cur == VFIO_DEVICE_STATE_RUNNING_P2P && new ==
> VFIO_DEVICE_STATE_STOP) ||
> +	    (cur == VFIO_DEVICE_STATE_STOP && new ==
> VFIO_DEVICE_STATE_RUNNING_P2P))
> +		return NULL;
> +
> +	if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new ==
> VFIO_DEVICE_STATE_RUNNING) {
> +		ret = xe_sriov_vfio_resume_device(xe_vdev->xe, xe_vdev-
> >vfid);
> +		if (ret)
> +			goto err;
> +
> +		return NULL;
> +	}
> +
> +	if (cur == VFIO_DEVICE_STATE_STOP && new ==
> VFIO_DEVICE_STATE_STOP_COPY) {
> +		struct xe_vfio_pci_migration_file *migf;
> +
> +		migf = xe_vfio_pci_alloc_file(xe_vdev, XE_VFIO_FILE_SAVE);
> +		if (IS_ERR(migf)) {
> +			ret = PTR_ERR(migf);
> +			goto err;
> +		}
> +		get_file(migf->filp);
> +
> +		ret = xe_sriov_vfio_stop_copy_enter(xe_vdev->xe, xe_vdev-
> >vfid);
> +		if (ret) {
> +			fput(migf->filp);
> +			goto err;
> +		}
> +
> +		return migf->filp;
> +	}
> +
> +	if (cur == VFIO_DEVICE_STATE_STOP_COPY && new ==
> VFIO_DEVICE_STATE_STOP) {
> +		if (xe_vdev->migf) {
> +			fput(xe_vdev->migf->filp);
> +			xe_vfio_pci_disable_file(xe_vdev->migf);
> +		}
> +
> +		ret = xe_sriov_vfio_stop_copy_exit(xe_vdev->xe, xe_vdev-
> >vfid);
> +		if (ret)
> +			goto err;
> +
> +		return NULL;
> +	}
> +
> +	if (cur == VFIO_DEVICE_STATE_STOP && new ==
> VFIO_DEVICE_STATE_RESUMING) {
> +		struct xe_vfio_pci_migration_file *migf;
> +
> +		migf = xe_vfio_pci_alloc_file(xe_vdev,
> XE_VFIO_FILE_RESUME);
> +		if (IS_ERR(migf)) {
> +			ret = PTR_ERR(migf);
> +			goto err;
> +		}
> +		get_file(migf->filp);
> +
> +		ret = xe_sriov_vfio_resume_data_enter(xe_vdev->xe,
> xe_vdev->vfid);
> +		if (ret) {
> +			fput(migf->filp);
> +			goto err;
> +		}
> +
> +		return migf->filp;
> +	}
> +
> +	if (cur == VFIO_DEVICE_STATE_RESUMING && new ==
> VFIO_DEVICE_STATE_STOP) {
> +		if (xe_vdev->migf) {
> +			fput(xe_vdev->migf->filp);
> +			xe_vfio_pci_disable_file(xe_vdev->migf);
> +		}
> +
> +		ret = xe_sriov_vfio_resume_data_exit(xe_vdev->xe, xe_vdev-
> >vfid);
> +		if (ret)
> +			goto err;
> +
> +		return NULL;
> +	}
> +
> +	WARN(true, "Unknown state transition %d->%d", cur, new);
> +	return ERR_PTR(-EINVAL);
> +
> +err:
> +	dev_dbg(xe_vdev_to_dev(xe_vdev),
> +		"Failed to transition state: %s->%s err=%d\n",
> +		vfio_dev_state_str(cur), vfio_dev_state_str(new), ret);
> +	return ERR_PTR(ret);
> +}
> +
> +static struct file *
> +xe_vfio_pci_set_device_state(struct vfio_device *core_vdev,
> +			     enum vfio_device_mig_state new_state) {
> +	struct xe_vfio_pci_core_device *xe_vdev =
> +		container_of(core_vdev, struct xe_vfio_pci_core_device,
> core_device.vdev);
> +	enum vfio_device_mig_state next_state;
> +	struct file *f = NULL;
> +	int ret;
> +
> +	xe_vfio_pci_state_mutex_lock(xe_vdev);
> +	while (new_state != xe_vdev->mig_state) {
> +		ret = vfio_mig_get_next_state(core_vdev, xe_vdev->mig_state,
> +					      new_state, &next_state);
> +		if (ret) {
> +			xe_sriov_vfio_error(xe_vdev->xe, xe_vdev->vfid);
> +			f = ERR_PTR(ret);
> +			break;
> +		}
> +		f = xe_vfio_set_state(xe_vdev, next_state);
> +		if (IS_ERR(f))
> +			break;
> +
> +		xe_vdev->mig_state = next_state;
> +
> +		/* Multiple state transitions with non-NULL file in the middle
> */
> +		if (f && new_state != xe_vdev->mig_state) {
> +			fput(f);
> +			f = ERR_PTR(-EINVAL);
> +			break;
> +		}
> +	}
> +	xe_vfio_pci_state_mutex_unlock(xe_vdev);
> +
> +	return f;
> +}
> +
> +static int xe_vfio_pci_get_device_state(struct vfio_device *core_vdev,
> +					enum vfio_device_mig_state
> *curr_state) {
> +	struct xe_vfio_pci_core_device *xe_vdev =
> +		container_of(core_vdev, struct xe_vfio_pci_core_device,
> +core_device.vdev);
> +
> +	xe_vfio_pci_state_mutex_lock(xe_vdev);
> +	*curr_state = xe_vdev->mig_state;
> +	xe_vfio_pci_state_mutex_unlock(xe_vdev);
> +
> +	return 0;
> +}
> +
> +static int xe_vfio_pci_get_data_size(struct vfio_device *vdev,
> +				     unsigned long *stop_copy_length) {
> +	struct xe_vfio_pci_core_device *xe_vdev =
> +		container_of(vdev, struct xe_vfio_pci_core_device,
> core_device.vdev);
> +
> +	xe_vfio_pci_state_mutex_lock(xe_vdev);
> +	*stop_copy_length = xe_sriov_vfio_stop_copy_size(xe_vdev->xe,
> xe_vdev->vfid);
> +	xe_vfio_pci_state_mutex_unlock(xe_vdev);
> +
> +	return 0;
> +}
> +
> +static const struct vfio_migration_ops xe_vfio_pci_migration_ops = {
> +	.migration_set_state = xe_vfio_pci_set_device_state,
> +	.migration_get_state = xe_vfio_pci_get_device_state,
> +	.migration_get_data_size = xe_vfio_pci_get_data_size, };
> +
> +static void xe_vfio_pci_migration_init(struct xe_vfio_pci_core_device
> +*xe_vdev) {
> +	struct vfio_device *core_vdev = &xe_vdev->core_device.vdev;
> +	struct pci_dev *pdev = to_pci_dev(core_vdev->dev);
> +	struct xe_device *xe = xe_sriov_vfio_get_xe_device(pdev);
> +	int ret;
> +
> +	if (!xe)
> +		return;
> +	if (!xe_sriov_vfio_migration_supported(xe))
> +		return;
> +
> +	ret = pci_iov_vf_id(pdev);
> +	if (ret < 0)
> +		return;
> +
> +	mutex_init(&xe_vdev->state_mutex);
> +	spin_lock_init(&xe_vdev->reset_lock);
> +
> +	/* Xe HW/FW components use vfid indexing starting from 1 */
> +	xe_vdev->vfid = ret + 1;
> +	xe_vdev->xe = xe;
> +	xe_vdev->migrate_cap = true;
> +
> +	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY |
> VFIO_MIGRATION_P2P;
> +	core_vdev->mig_ops = &xe_vfio_pci_migration_ops; }
> +
> +static void xe_vfio_pci_migration_fini(struct xe_vfio_pci_core_device
> +*xe_vdev) {
> +	if (!xe_vdev->migrate_cap)
> +		return;
> +
> +	mutex_destroy(&xe_vdev->state_mutex);
> +}
> +
> +static int xe_vfio_pci_init_dev(struct vfio_device *core_vdev) {
> +	struct xe_vfio_pci_core_device *xe_vdev =
> +		container_of(core_vdev, struct xe_vfio_pci_core_device,
> +core_device.vdev);
> +
> +	xe_vfio_pci_migration_init(xe_vdev);
> +
> +	return vfio_pci_core_init_dev(core_vdev);
> +}
> +
> +static void xe_vfio_pci_release_dev(struct vfio_device *core_vdev) {
> +	struct xe_vfio_pci_core_device *xe_vdev =
> +		container_of(core_vdev, struct xe_vfio_pci_core_device,
> +core_device.vdev);
> +
> +	xe_vfio_pci_migration_fini(xe_vdev);
> +}
> +
> +static const struct vfio_device_ops xe_vfio_pci_ops = {
> +	.name = "xe-vfio-pci",
> +	.init = xe_vfio_pci_init_dev,
> +	.release = xe_vfio_pci_release_dev,
> +	.open_device = xe_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,
> +	.match_token_uuid = vfio_pci_core_match_token_uuid,
> +	.bind_iommufd = vfio_iommufd_physical_bind,
> +	.unbind_iommufd = vfio_iommufd_physical_unbind,
> +	.attach_ioas = vfio_iommufd_physical_attach_ioas,
> +	.detach_ioas = vfio_iommufd_physical_detach_ioas,
> +};
> +
> +static int xe_vfio_pci_probe(struct pci_dev *pdev, const struct
> +pci_device_id *id) {
> +	struct xe_vfio_pci_core_device *xe_vdev;
> +	int ret;
> +
> +	xe_vdev = vfio_alloc_device(xe_vfio_pci_core_device,
> core_device.vdev, &pdev->dev,
> +				    &xe_vfio_pci_ops);
> +	if (IS_ERR(xe_vdev))
> +		return PTR_ERR(xe_vdev);
> +
> +	dev_set_drvdata(&pdev->dev, &xe_vdev->core_device);
> +
> +	ret = vfio_pci_core_register_device(&xe_vdev->core_device);
> +	if (ret) {
> +		vfio_put_device(&xe_vdev->core_device.vdev);
> +		return ret;
> +	}
> +
> +	return 0;
> +}
> +
> +static void xe_vfio_pci_remove(struct pci_dev *pdev) {
> +	struct xe_vfio_pci_core_device *xe_vdev = pci_get_drvdata(pdev);
> +
> +	vfio_pci_core_unregister_device(&xe_vdev->core_device);
> +	vfio_put_device(&xe_vdev->core_device.vdev);
> +}
> +
> +static const struct pci_device_id xe_vfio_pci_table[] = {
> +	INTEL_PTL_IDS(INTEL_VGA_VFIO_DEVICE, NULL),
> +	INTEL_WCL_IDS(INTEL_VGA_VFIO_DEVICE, NULL),
> +	INTEL_BMG_IDS(INTEL_VGA_VFIO_DEVICE, NULL),
> +	{}
> +};
> +MODULE_DEVICE_TABLE(pci, xe_vfio_pci_table);
> +
> +static struct pci_driver xe_vfio_pci_driver = {
> +	.name = "xe-vfio-pci",
> +	.id_table = xe_vfio_pci_table,
> +	.probe = xe_vfio_pci_probe,
> +	.remove = xe_vfio_pci_remove,
> +	.err_handler = &xe_vfio_pci_err_handlers,
> +	.driver_managed_dma = true,
> +};
> +module_pci_driver(xe_vfio_pci_driver);
> +
> +MODULE_LICENSE("GPL");
> +MODULE_AUTHOR("Michał Winiarski <michal.winiarski@...el.com>");
> +MODULE_DESCRIPTION("VFIO PCI driver with migration support for Intel
> +Graphics");
> --
> 2.50.1

Powered by blists - more mailing lists