[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <gsh5pvk4m3gosm3bbfnxkalj2jdd6xp3rq5qtu52ffqrhoudf7@kjovamtfgyxc>
Date: Mon, 27 Oct 2025 13:47:19 +0100
From: Michał Winiarski <michal.winiarski@...el.com>
To: Michal Wajdeczko <michal.wajdeczko@...el.com>
CC: Alex Williamson <alex.williamson@...hat.com>, Lucas De Marchi
<lucas.demarchi@...el.com>, Thomas Hellström
<thomas.hellstrom@...ux.intel.com>, Rodrigo Vivi <rodrigo.vivi@...el.com>,
Jason Gunthorpe <jgg@...pe.ca>, Yishai Hadas <yishaih@...dia.com>, Kevin Tian
<kevin.tian@...el.com>, <intel-xe@...ts.freedesktop.org>,
<linux-kernel@...r.kernel.org>, <kvm@...r.kernel.org>, Matthew Brost
<matthew.brost@...el.com>, <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>, "Lukasz
Laguna" <lukasz.laguna@...el.com>
Subject: Re: [PATCH v2 05/26] drm/xe/pf: Add helpers for migration data
allocation / free
On Thu, Oct 23, 2025 at 12:18:09AM +0200, Michal Wajdeczko wrote:
>
>
> On 10/22/2025 12:41 AM, Michał Winiarski wrote:
> > Now that it's possible to free the packets - connect the restore
> > handling logic with the ring.
> > The helpers will also be used in upcoming changes that will start producing
> > migration data packets.
> >
> > Signed-off-by: Michał Winiarski <michal.winiarski@...el.com>
> > ---
> > drivers/gpu/drm/xe/Makefile | 1 +
> > drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c | 7 +
> > drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c | 29 +++-
> > drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h | 1 +
> > drivers/gpu/drm/xe/xe_sriov_migration_data.c | 127 ++++++++++++++++++
> > drivers/gpu/drm/xe/xe_sriov_migration_data.h | 31 +++++
> > 6 files changed, 195 insertions(+), 1 deletion(-)
> > create mode 100644 drivers/gpu/drm/xe/xe_sriov_migration_data.c
> > create mode 100644 drivers/gpu/drm/xe/xe_sriov_migration_data.h
> >
> > diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
> > index 89e5b26c27975..3d72db9e528e4 100644
> > --- a/drivers/gpu/drm/xe/Makefile
> > +++ b/drivers/gpu/drm/xe/Makefile
> > @@ -173,6 +173,7 @@ xe-$(CONFIG_PCI_IOV) += \
> > xe_lmtt_2l.o \
> > xe_lmtt_ml.o \
> > xe_pci_sriov.o \
> > + xe_sriov_migration_data.o \
> > xe_sriov_pf.o \
> > xe_sriov_pf_control.o \
> > xe_sriov_pf_debugfs.o \
> > diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
> > index cad73fdaee93c..dd9bc9c99f78c 100644
> > --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
> > +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
> > @@ -18,6 +18,7 @@
> > #include "xe_gt_sriov_printk.h"
> > #include "xe_guc_ct.h"
> > #include "xe_sriov.h"
> > +#include "xe_sriov_migration_data.h"
> > #include "xe_sriov_pf_control.h"
> > #include "xe_sriov_pf_migration.h"
> > #include "xe_sriov_pf_service.h"
> > @@ -851,6 +852,8 @@ int xe_gt_sriov_pf_control_resume_vf(struct xe_gt *gt, unsigned int vfid)
> > static void pf_exit_vf_save_wip(struct xe_gt *gt, unsigned int vfid)
> > {
> > if (pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WIP)) {
> > + xe_gt_sriov_pf_migration_ring_free(gt, vfid);
> > +
> > pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_PROCESS_DATA);
> > pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WAIT_DATA);
> > pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_DATA_DONE);
> > @@ -1045,6 +1048,8 @@ int xe_gt_sriov_pf_control_finish_save_vf(struct xe_gt *gt, unsigned int vfid)
> > static void pf_exit_vf_restore_wip(struct xe_gt *gt, unsigned int vfid)
> > {
> > if (pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WIP)) {
> > + xe_gt_sriov_pf_migration_ring_free(gt, vfid);
> > +
> > pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_PROCESS_DATA);
> > pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WAIT_DATA);
> > pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_DATA_DONE);
> > @@ -1078,6 +1083,8 @@ pf_handle_vf_restore_data(struct xe_gt *gt, unsigned int vfid)
> >
> > xe_gt_sriov_notice(gt, "Skipping VF%u unknown data type: %d\n", vfid, data->type);
> >
> > + xe_sriov_migration_data_free(data);
> > +
> > return 0;
> > }
> >
> > diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
> > index b6ffd982d6007..8ba72165759b3 100644
> > --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
> > +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
> > @@ -14,6 +14,7 @@
> > #include "xe_guc.h"
> > #include "xe_guc_ct.h"
> > #include "xe_sriov.h"
> > +#include "xe_sriov_migration_data.h"
> > #include "xe_sriov_pf_migration.h"
> >
> > #define XE_GT_SRIOV_PF_MIGRATION_RING_SIZE 5
> > @@ -418,6 +419,25 @@ bool xe_gt_sriov_pf_migration_ring_full(struct xe_gt *gt, unsigned int vfid)
> > return ptr_ring_full(&pf_pick_gt_migration(gt, vfid)->ring);
> > }
> >
> > +/**
> > + * xe_gt_sriov_pf_migration_ring_free() - Consume and free all data in migration ring
> > + * @gt: the &xe_gt
> > + * @vfid: the VF identifier
> > + */
> > +void xe_gt_sriov_pf_migration_ring_free(struct xe_gt *gt, unsigned int vfid)
> > +{
> > + struct xe_gt_sriov_migration_data *migration = pf_pick_gt_migration(gt, vfid);
> > + struct xe_sriov_migration_data *data;
> > +
> > + if (ptr_ring_empty(&migration->ring))
> > + return;
> > +
> > + xe_gt_sriov_notice(gt, "VF%u unprocessed migration data left in the ring!\n", vfid);
> > +
> > + while ((data = ptr_ring_consume(&migration->ring)))
> > + xe_sriov_migration_data_free(data);
> > +}
> > +
> > /**
> > * xe_gt_sriov_pf_migration_save_produce() - Add VF save data packet to migration ring.
> > * @gt: the &xe_gt
> > @@ -543,11 +563,18 @@ xe_gt_sriov_pf_migration_save_consume(struct xe_gt *gt, unsigned int vfid)
> > return ERR_PTR(-EAGAIN);
> > }
> >
> > +static void pf_mig_data_destroy(void *ptr)
> > +{
> > + struct xe_sriov_migration_data *data = ptr;
> > +
> > + xe_sriov_migration_data_free(data);
> > +}
> > +
> > static void action_ring_cleanup(struct drm_device *dev, void *arg)
> > {
> > struct ptr_ring *r = arg;
> >
> > - ptr_ring_cleanup(r, NULL);
> > + ptr_ring_cleanup(r, pf_mig_data_destroy);
> > }
> >
> > /**
> > diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
> > index 9e67f18ded205..1ed2248f0a17e 100644
> > --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
> > +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
> > @@ -17,6 +17,7 @@ int xe_gt_sriov_pf_migration_restore_guc_state(struct xe_gt *gt, unsigned int vf
> >
> > bool xe_gt_sriov_pf_migration_ring_empty(struct xe_gt *gt, unsigned int vfid);
> > bool xe_gt_sriov_pf_migration_ring_full(struct xe_gt *gt, unsigned int vfid);
> > +void xe_gt_sriov_pf_migration_ring_free(struct xe_gt *gt, unsigned int vfid);
> >
> > int xe_gt_sriov_pf_migration_save_produce(struct xe_gt *gt, unsigned int vfid,
> > struct xe_sriov_migration_data *data);
> > diff --git a/drivers/gpu/drm/xe/xe_sriov_migration_data.c b/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> > new file mode 100644
> > index 0000000000000..b04f9be3b7fed
> > --- /dev/null
> > +++ b/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> > @@ -0,0 +1,127 @@
> > +// SPDX-License-Identifier: MIT
> > +/*
> > + * Copyright © 2025 Intel Corporation
> > + */
> > +
> > +#include "xe_bo.h"
> > +#include "xe_device.h"
> > +#include "xe_sriov_migration_data.h"
> > +
> > +static bool data_needs_bo(struct xe_sriov_migration_data *data)
> > +{
> > + return data->type == XE_SRIOV_MIGRATION_DATA_TYPE_VRAM;
> > +}
> > +
> > +/**
> > + * xe_sriov_migration_data() - Allocate migration data packet
> > + * @xe: the &xe_device
> > + *
> > + * Only allocates the "outer" structure, without initializing the migration
> > + * data backing storage.
> > + *
> > + * Return: Pointer to &xe_sriov_migration_data on success,
> > + * NULL in case of error.
> > + */
> > +struct xe_sriov_migration_data *
>
> no line split
Ok.
>
> > +xe_sriov_migration_data_alloc(struct xe_device *xe)
> > +{
> > + struct xe_sriov_migration_data *data;
> > +
> > + data = kzalloc(sizeof(*data), GFP_KERNEL);
> > + if (!data)
> > + return NULL;
> > +
> > + data->xe = xe;
> > + data->hdr_remaining = sizeof(data->hdr);
> > +
> > + return data;
> > +}
> > +
> > +/**
> > + * xe_sriov_migration_data_free() - Free migration data packet.
> > + * @data: the &xe_sriov_migration_data packet
> > + */
> > +void xe_sriov_migration_data_free(struct xe_sriov_migration_data *data)
> > +{
> > + if (data_needs_bo(data))
> > + xe_bo_unpin_map_no_vm(data->bo);
> > + else
> > + kvfree(data->buff);
> > +
> > + kfree(data);
> > +}
> > +
> > +static int mig_data_init(struct xe_sriov_migration_data *data)
> > +{
> > + struct xe_gt *gt = xe_device_get_gt(data->xe, data->gt);
> > +
> > + if (data->size == 0)
> > + return 0;
> > +
> > + if (data_needs_bo(data)) {
>
> struct xe_bo *bo;
> then
> bo = ...
>
> so will not have that long line
Ok.
>
> > + struct xe_bo *bo = xe_bo_create_pin_map_novm(data->xe, gt->tile,
> > + PAGE_ALIGN(data->size),
> > + ttm_bo_type_kernel,
> > + XE_BO_FLAG_SYSTEM | XE_BO_FLAG_PINNED,
> > + false);
> > + if (IS_ERR(bo))
> > + return PTR_ERR(bo);
> > +
> > + data->bo = bo;
> > + data->vaddr = bo->vmap.vaddr;
> > + } else {
> > + void *buff = kvzalloc(data->size, GFP_KERNEL);
> > +
> > + if (!buff)
> > + return -ENOMEM;
> > +
> > + data->buff = buff;
> > + data->vaddr = buff;
> > + }
> > +
> > + return 0;
> > +}
> > +
> > +#define XE_SRIOV_MIGRATION_DATA_SUPPORTED_VERSION 1
> > +/**
> > + * xe_sriov_migration_data_init() - Initialize the migration data header and backing storage.
> > + * @data: the &xe_sriov_migration_data packet
> > + * @tile_id: tile identifier
> > + * @gt_id: GT identifier
> > + * @type: &xe_sriov_migration_data_type
> > + * @offset: offset of data packet payload (within wider resource)
> > + * @size: size of data packet payload
> > + *
> > + * Return: 0 on success or a negative error code on failure.
> > + */
> > +int xe_sriov_migration_data_init(struct xe_sriov_migration_data *data, u8 tile_id, u8 gt_id,
> > + enum xe_sriov_migration_data_type type, loff_t offset, size_t size)
> > +{
> > + data->version = XE_SRIOV_MIGRATION_DATA_SUPPORTED_VERSION;
> > + data->type = type;
> > + data->tile = tile_id;
> > + data->gt = gt_id;
> > + data->offset = offset;
> > + data->size = size;
> > + data->remaining = size;
> > +
> > + return mig_data_init(data);
> > +}
> > +
> > +/**
> > + * xe_sriov_migration_data_init() - Initialize the migration data backing storage based on header.
> > + * @data: the &xe_sriov_migration_data packet
> > + *
> > + * Header data is expected to be filled prior to calling this function.
> > + *
> > + * Return: 0 on success or a negative error code on failure.
> > + */
> > +int xe_sriov_migration_data_init_from_hdr(struct xe_sriov_migration_data *data)
> > +{
> > + if (data->version != XE_SRIOV_MIGRATION_DATA_SUPPORTED_VERSION)
> > + return -EINVAL;
> > +
> > + data->remaining = data->size;
> > +
> > + return mig_data_init(data);
> > +}
> > diff --git a/drivers/gpu/drm/xe/xe_sriov_migration_data.h b/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> > new file mode 100644
> > index 0000000000000..ef65dccddc035
> > --- /dev/null
> > +++ b/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> > @@ -0,0 +1,31 @@
> > +/* SPDX-License-Identifier: MIT */
> > +/*
> > + * Copyright © 2025 Intel Corporation
> > + */
> > +
> > +#ifndef _XE_SRIOV_MIGRATION_DATA_H_
> > +#define _XE_SRIOV_MIGRATION_DATA_H_
> > +
> > +#include <linux/types.h>
> > +
> > +struct xe_device;
> > +
> > +enum xe_sriov_migration_data_type {
> > + /* Skipping 0 to catch uninitialized data */
> > + XE_SRIOV_MIGRATION_DATA_TYPE_DESCRIPTOR = 1,
> > + XE_SRIOV_MIGRATION_DATA_TYPE_TRAILER,
> > + XE_SRIOV_MIGRATION_DATA_TYPE_GGTT,
> > + XE_SRIOV_MIGRATION_DATA_TYPE_MMIO,
> > + XE_SRIOV_MIGRATION_DATA_TYPE_GUC,
> > + XE_SRIOV_MIGRATION_DATA_TYPE_VRAM,
> > +};
> > +
> > +struct xe_sriov_migration_data *
>
> no need for line split here
Ok.
> > +xe_sriov_migration_data_alloc(struct xe_device *xe);
> > +void xe_sriov_migration_data_free(struct xe_sriov_migration_data *snapshot);
> > +
> > +int xe_sriov_migration_data_init(struct xe_sriov_migration_data *data, u8 tile_id, u8 gt_id,
> > + enum xe_sriov_migration_data_type, loff_t offset, size_t size);
> > +int xe_sriov_migration_data_init_from_hdr(struct xe_sriov_migration_data *snapshot);
> > +
> > +#endif
>
> just few nits, otherwise LGTM
>
> Reviewed-by: Michal Wajdeczko <michal.wajdeczko@...el.com>
>
Thanks,
-Michał
Powered by blists - more mailing lists