On 10/22/2025 12:41 AM, Michał Winiarski wrote:
> Add debugfs handlers for migration state and handle bitstream
> .read()/.write() to convert from bitstream to/from migration data
> packets.
> As descriptor/trailer are handled at this layer - add handling for both
> save and restore side.
>
> Signed-off-by: Michał Winiarski <[email protected]>
> ---
> drivers/gpu/drm/xe/xe_sriov_migration_data.c | 336 ++++++++++++++++++
> drivers/gpu/drm/xe/xe_sriov_migration_data.h | 5 +
> drivers/gpu/drm/xe/xe_sriov_pf_control.c | 5 +
> drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c | 35 ++
> drivers/gpu/drm/xe/xe_sriov_pf_migration.c | 54 +++
> .../gpu/drm/xe/xe_sriov_pf_migration_types.h | 9 +
> 6 files changed, 444 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> b/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> index b04f9be3b7fed..4cd6c6fc9ba18 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> +++ b/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> @@ -6,6 +6,44 @@
> #include "xe_bo.h"
> #include "xe_device.h"
> #include "xe_sriov_migration_data.h"
> +#include "xe_sriov_pf_helpers.h"
> +#include "xe_sriov_pf_migration.h"
> +#include "xe_sriov_printk.h"
> +
> +static struct mutex *pf_migration_mutex(struct xe_device *xe, unsigned int
> vfid)
> +{
> + xe_assert(xe, IS_SRIOV_PF(xe));
> + xe_assert(xe, vfid <= xe_sriov_pf_get_totalvfs(xe));
other helpers have sep line here
> + return &xe->sriov.pf.vfs[vfid].migration.lock;
> +}
> +
> +static struct xe_sriov_migration_data **pf_pick_pending(struct xe_device
> *xe, unsigned int vfid)
> +{
> + xe_assert(xe, IS_SRIOV_PF(xe));
> + xe_assert(xe, vfid <= xe_sriov_pf_get_totalvfs(xe));
> + lockdep_assert_held(pf_migration_mutex(xe, vfid));
> +
> + return &xe->sriov.pf.vfs[vfid].migration.pending;
> +}
> +
> +static struct xe_sriov_migration_data **
> +pf_pick_descriptor(struct xe_device *xe, unsigned int vfid)
> +{
> + xe_assert(xe, IS_SRIOV_PF(xe));
> + xe_assert(xe, vfid <= xe_sriov_pf_get_totalvfs(xe));
> + lockdep_assert_held(pf_migration_mutex(xe, vfid));
> +
> + return &xe->sriov.pf.vfs[vfid].migration.descriptor;
> +}
> +
> +static struct xe_sriov_migration_data **pf_pick_trailer(struct xe_device
> *xe, unsigned int vfid)
> +{
> + xe_assert(xe, IS_SRIOV_PF(xe));
> + xe_assert(xe, vfid <= xe_sriov_pf_get_totalvfs(xe));
> + lockdep_assert_held(pf_migration_mutex(xe, vfid));
> +
> + return &xe->sriov.pf.vfs[vfid].migration.trailer;
> +}
>
> static bool data_needs_bo(struct xe_sriov_migration_data *data)
> {
> @@ -43,6 +81,9 @@ xe_sriov_migration_data_alloc(struct xe_device *xe)
> */
> void xe_sriov_migration_data_free(struct xe_sriov_migration_data *data)
> {
> + if (IS_ERR_OR_NULL(data))
> + return;
> +
> if (data_needs_bo(data))
> xe_bo_unpin_map_no_vm(data->bo);
> else
> @@ -125,3 +166,298 @@ int xe_sriov_migration_data_init_from_hdr(struct
> xe_sriov_migration_data *data)
>
> return mig_data_init(data);
> }
> +
> +static ssize_t vf_mig_data_hdr_read(struct xe_sriov_migration_data *data,
> + char __user *buf, size_t len)
> +{
> + loff_t offset = sizeof(data->hdr) - data->hdr_remaining;
> +
> + if (!data->hdr_remaining)
> + return -EINVAL;
> +
> + if (len > data->hdr_remaining)
> + len = data->hdr_remaining;
> +
> + if (copy_to_user(buf, (void *)&data->hdr + offset, len))
> + return -EFAULT;
> +
> + data->hdr_remaining -= len;
> +
> + return len;
> +}
> +
> +static ssize_t vf_mig_data_read(struct xe_sriov_migration_data *data,
> + char __user *buf, size_t len)
> +{
> + if (len > data->remaining)
> + len = data->remaining;
> +
> + if (copy_to_user(buf, data->vaddr + (data->size - data->remaining),
> len))
> + return -EFAULT;
> +
> + data->remaining -= len;
> +
> + return len;
> +}
> +
> +static ssize_t __vf_mig_data_read_single(struct xe_sriov_migration_data
> **data,
> + unsigned int vfid, char __user *buf,
> size_t len)
> +{
> + ssize_t copied = 0;
> +
> + if ((*data)->hdr_remaining)
> + copied = vf_mig_data_hdr_read(*data, buf, len);
> + else
> + copied = vf_mig_data_read(*data, buf, len);
> +
> + if ((*data)->remaining == 0 && (*data)->hdr_remaining == 0) {
> + xe_sriov_migration_data_free(*data);
> + *data = NULL;
> + }
> +
> + return copied;
> +}
> +
> +static struct xe_sriov_migration_data **vf_mig_pick_data(struct xe_device
> *xe, unsigned int vfid)
> +{
> + struct xe_sriov_migration_data **data;
> +
> + data = pf_pick_descriptor(xe, vfid);
> + if (*data)
> + return data;
> +
> + data = pf_pick_pending(xe, vfid);
> + if (!*data)
> + *data = xe_sriov_pf_migration_save_consume(xe, vfid);
> + if (*data)
> + return data;
> +
> + data = pf_pick_trailer(xe, vfid);
> + if (*data)
> + return data;
> +
> + return ERR_PTR(-ENODATA);
> +}
> +
> +static ssize_t vf_mig_data_read_single(struct xe_device *xe, unsigned int
> vfid,
> + char __user *buf, size_t len)
> +{
> + struct xe_sriov_migration_data **data = vf_mig_pick_data(xe, vfid);
> +
> + if (IS_ERR_OR_NULL(data))
vf_mig_pick_data() seems to never return NULL, so maybe just IS_ERR() ?
> + return PTR_ERR(data);
> +
> + return __vf_mig_data_read_single(data, vfid, buf, len);
> +}
> +
> +/**
> + * xe_sriov_migration_data_read() - Read migration data from the device.
> + * @xe: the &xe_device
> + * @vfid: the VF identifier
> + * @buf: start address of userspace buffer
> + * @len: requested read size from userspace
> + *
> + * Return: number of bytes that has been successfully read,
> + * 0 if no more migration data is available,
> + * -errno on failure.
> + */
> +ssize_t xe_sriov_migration_data_read(struct xe_device *xe, unsigned int vfid,
> + char __user *buf, size_t len)
> +{
> + ssize_t ret, consumed = 0;
> +
> + xe_assert(xe, IS_SRIOV_PF(xe));
> +
> + scoped_cond_guard(mutex_intr, return -EINTR, pf_migration_mutex(xe,
> vfid)) {
> + while (consumed < len) {
> + ret = vf_mig_data_read_single(xe, vfid, buf, len -
> consumed);
> + if (ret == -ENODATA)
> + break;
> + if (ret < 0)
> + return ret;
> +
> + consumed += ret;
> + buf += ret;
> + }
> + }
> +
> + return consumed;
> +}
> +
> +static ssize_t vf_mig_hdr_write(struct xe_sriov_migration_data *data,
> + const char __user *buf, size_t len)
> +{
> + loff_t offset = sizeof(data->hdr) - data->hdr_remaining;
> + int ret;
> +
> + if (len > data->hdr_remaining)
> + len = data->hdr_remaining;
> +
> + if (copy_from_user((void *)&data->hdr + offset, buf, len))
> + return -EFAULT;
> +
> + data->hdr_remaining -= len;
> +
> + if (!data->hdr_remaining) {
> + ret = xe_sriov_migration_data_init_from_hdr(data);
> + if (ret)
> + return ret;
> + }
> +
> + return len;
> +}
> +
> +static ssize_t vf_mig_data_write(struct xe_sriov_migration_data *data,
> + const char __user *buf, size_t len)
> +{
> + if (len > data->remaining)
> + len = data->remaining;
> +
> + if (copy_from_user(data->vaddr + (data->size - data->remaining), buf,
> len))
> + return -EFAULT;
> +
> + data->remaining -= len;
> +
> + return len;
> +}
> +
> +static ssize_t vf_mig_data_write_single(struct xe_device *xe, unsigned int
> vfid,
> + const char __user *buf, size_t len)
> +{
> + struct xe_sriov_migration_data **data = pf_pick_pending(xe, vfid);
> + int ret;
> + ssize_t copied;
> +
> + if (IS_ERR_OR_NULL(*data)) {
> + *data = xe_sriov_migration_data_alloc(xe);
> + if (!*data)
> + return -ENOMEM;
> + }
> +
> + if ((*data)->hdr_remaining)
> + copied = vf_mig_hdr_write(*data, buf, len);
> + else
> + copied = vf_mig_data_write(*data, buf, len);
> +
> + if ((*data)->hdr_remaining == 0 && (*data)->remaining == 0) {
> + ret = xe_sriov_pf_migration_restore_produce(xe, vfid, *data);
> + if (ret) {
> + xe_sriov_migration_data_free(*data);
> + return ret;
> + }
> +
> + *data = NULL;
> + }
> +
> + return copied;
> +}
> +
> +/**
> + * xe_sriov_migration_data_write() - Write migration data to the device.
> + * @xe: the &xe_device
> + * @vfid: the VF identifier
> + * @buf: start address of userspace buffer
> + * @len: requested write size from userspace
> + *
> + * Return: number of bytes that has been successfully written,
> + * -errno on failure.
> + */
> +ssize_t xe_sriov_migration_data_write(struct xe_device *xe, unsigned int
> vfid,
> + const char __user *buf, size_t len)
> +{
> + ssize_t ret, produced = 0;
> +
> + xe_assert(xe, IS_SRIOV_PF(xe));
> +
> + scoped_cond_guard(mutex_intr, return -EINTR, pf_migration_mutex(xe,
> vfid)) {
> + while (produced < len) {
> + ret = vf_mig_data_write_single(xe, vfid, buf, len -
> produced);
> + if (ret < 0)
> + return ret;
> +
> + produced += ret;
> + buf += ret;
> + }
> + }
> +
> + return produced;
> +}
> +
> +#define MIGRATION_DESCRIPTOR_DWORDS 0
> +static size_t pf_descriptor_init(struct xe_device *xe, unsigned int vfid)
> +{
> + struct xe_sriov_migration_data **desc = pf_pick_descriptor(xe, vfid);
> + struct xe_sriov_migration_data *data;
> + int ret;
> +
> + data = xe_sriov_migration_data_alloc(xe);
> + if (!data)
> + return -ENOMEM;
> +
> + ret = xe_sriov_migration_data_init(data, 0, 0,
> XE_SRIOV_MIGRATION_DATA_TYPE_DESCRIPTOR,
> + 0, MIGRATION_DESCRIPTOR_DWORDS *
> sizeof(u32));
> + if (ret) {
> + xe_sriov_migration_data_free(data);
> + return ret;
> + }
> +
> + *desc = data;
> +
> + return 0;
> +}
> +
> +static void pf_pending_init(struct xe_device *xe, unsigned int vfid)
> +{
> + struct xe_sriov_migration_data **data = pf_pick_pending(xe, vfid);
> +
> + *data = NULL;
> +}
> +
> +#define MIGRATION_TRAILER_SIZE 0
> +static int pf_trailer_init(struct xe_device *xe, unsigned int vfid)
> +{
> + struct xe_sriov_migration_data **trailer = pf_pick_trailer(xe, vfid);
> + struct xe_sriov_migration_data *data;
> + int ret;
> +
> + data = xe_sriov_migration_data_alloc(xe);
> + if (!data)
> + return -ENOMEM;
> +
> + ret = xe_sriov_migration_data_init(data, 0, 0,
> XE_SRIOV_MIGRATION_DATA_TYPE_TRAILER,
> + 0, MIGRATION_TRAILER_SIZE);
> + if (ret) {
> + xe_sriov_migration_data_free(data);
> + return ret;
> + }
> +
> + *trailer = data;
> +
> + return 0;
> +}
> +
> +/**
> + * xe_sriov_migration_data_save_init() - Initialize the pending save
> migration data.
> + * @xe: the &xe_device
> + * @vfid: the VF identifier
> + *
> + * Return: 0 on success, -errno on failure.
> + */
> +int xe_sriov_migration_data_save_init(struct xe_device *xe, unsigned int
> vfid)
> +{
> + int ret;
> +
> + scoped_cond_guard(mutex_intr, return -EINTR, pf_migration_mutex(xe,
> vfid)) {
> + ret = pf_descriptor_init(xe, vfid);
> + if (ret)
> + return ret;
> +
> + ret = pf_trailer_init(xe, vfid);
> + if (ret)
> + return ret;
> +
> + pf_pending_init(xe, vfid);
> + }
> +
> + return 0;
> +}
> diff --git a/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> b/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> index ef65dccddc035..5cde6e9439677 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> +++ b/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> @@ -27,5 +27,10 @@ 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);
> +ssize_t xe_sriov_migration_data_read(struct xe_device *xe, unsigned int vfid,
> + char __user *buf, size_t len);
> +ssize_t xe_sriov_migration_data_write(struct xe_device *xe, unsigned int
> vfid,
> + const char __user *buf, size_t len);
> +int xe_sriov_migration_data_save_init(struct xe_device *xe, unsigned int
> vfid);
>
> #endif
> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_control.c
> b/drivers/gpu/drm/xe/xe_sriov_pf_control.c
> index 8d8a01faf5291..c2768848daba1 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_control.c
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_control.c
> @@ -5,6 +5,7 @@
>
> #include "xe_device.h"
> #include "xe_gt_sriov_pf_control.h"
> +#include "xe_sriov_migration_data.h"
> #include "xe_sriov_pf_control.h"
> #include "xe_sriov_printk.h"
>
> @@ -165,6 +166,10 @@ int xe_sriov_pf_control_trigger_save_vf(struct xe_device
> *xe, unsigned int vfid)
> unsigned int id;
> int ret;
>
> + ret = xe_sriov_migration_data_save_init(xe, vfid);
> + if (ret)
> + return ret;
> +
> for_each_gt(gt, xe, id) {
> ret = xe_gt_sriov_pf_control_trigger_save_vf(gt, vfid);
> if (ret)
> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> b/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> index e0e6340c49106..a9a28aec22421 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> @@ -9,6 +9,7 @@
> #include "xe_device.h"
> #include "xe_device_types.h"
> #include "xe_pm.h"
> +#include "xe_sriov_migration_data.h"
> #include "xe_sriov_pf.h"
> #include "xe_sriov_pf_control.h"
> #include "xe_sriov_pf_debugfs.h"
> @@ -132,6 +133,7 @@ static void pf_populate_pf(struct xe_device *xe, struct
> dentry *pfdent)
> * /sys/kernel/debug/dri/BDF/
> * ├── sriov
> * │ ├── vf1
> + * │ │ ├── migration_data
> * │ │ ├── pause
> * │ │ ├── reset
> * │ │ ├── resume
> @@ -220,6 +222,38 @@ DEFINE_VF_CONTROL_ATTRIBUTE(reset_vf);
> DEFINE_VF_CONTROL_ATTRIBUTE_RW(save_vf);
> DEFINE_VF_CONTROL_ATTRIBUTE_RW(restore_vf);
>
> +static ssize_t data_write(struct file *file, const char __user *buf, size_t
> count, loff_t *pos)
> +{
> + struct dentry *dent = file_dentry(file)->d_parent;
> + struct xe_device *xe = extract_xe(dent);
> + unsigned int vfid = extract_vfid(dent);
> +
> + if (*pos)
> + return -ESPIPE;
> +
> + return xe_sriov_migration_data_write(xe, vfid, buf, count);
> +}
> +
> +static ssize_t data_read(struct file *file, char __user *buf, size_t count,
> loff_t *ppos)
> +{
> + struct dentry *dent = file_dentry(file)->d_parent;
> + struct xe_device *xe = extract_xe(dent);
> + unsigned int vfid = extract_vfid(dent);
> +
> + if (*ppos)
> + return -ESPIPE;
> +
> + return xe_sriov_migration_data_read(xe, vfid, buf, count);
> +}
> +
> +static const struct file_operations data_vf_fops = {
> + .owner = THIS_MODULE,
> + .open = simple_open,
> + .write = data_write,
> + .read = data_read,
> + .llseek = default_llseek,
> +};
> +
> static void pf_populate_vf(struct xe_device *xe, struct dentry *vfdent)
> {
> debugfs_create_file("pause", 0200, vfdent, xe, &pause_vf_fops);
> @@ -228,6 +262,7 @@ static void pf_populate_vf(struct xe_device *xe, struct
> dentry *vfdent)
> debugfs_create_file("reset", 0200, vfdent, xe, &reset_vf_fops);
> debugfs_create_file("save", 0600, vfdent, xe, &save_vf_fops);
> debugfs_create_file("restore", 0600, vfdent, xe, &restore_vf_fops);
> + debugfs_create_file("migration_data", 0600, vfdent, xe, &data_vf_fops);
> }
>
> static void pf_populate_with_tiles(struct xe_device *xe, struct dentry
> *dent, unsigned int vfid)
> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> index eaf581317bdef..029e14f1ffa74 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> @@ -10,6 +10,7 @@
> #include "xe_gt_sriov_pf_migration.h"
> #include "xe_pm.h"
> #include "xe_sriov.h"
> +#include "xe_sriov_migration_data.h"
> #include "xe_sriov_pf_helpers.h"
> #include "xe_sriov_pf_migration.h"
> #include "xe_sriov_printk.h"
> @@ -53,6 +54,15 @@ static bool pf_check_migration_support(struct xe_device
> *xe)
> return IS_ENABLED(CONFIG_DRM_XE_DEBUG);
> }
>
> +static void pf_migration_cleanup(struct drm_device *dev, void *arg)
> +{
> + struct xe_sriov_pf_migration *migration = arg;
> +
> + xe_sriov_migration_data_free(migration->pending);
> + xe_sriov_migration_data_free(migration->trailer);
> + xe_sriov_migration_data_free(migration->descriptor);
> +}
> +
> /**
> * xe_sriov_pf_migration_init() - Initialize support for SR-IOV VF migration.
> * @xe: the &xe_device
> @@ -62,6 +72,7 @@ static bool pf_check_migration_support(struct xe_device *xe)
> int xe_sriov_pf_migration_init(struct xe_device *xe)
> {
> unsigned int n, totalvfs;
> + int err;
>
> xe_assert(xe, IS_SRIOV_PF(xe));
>
> @@ -73,7 +84,15 @@ int xe_sriov_pf_migration_init(struct xe_device *xe)
> for (n = 1; n <= totalvfs; n++) {
> struct xe_sriov_pf_migration *migration = pf_pick_migration(xe,
> n);
>
> + err = drmm_mutex_init(&xe->drm, &migration->lock);
> + if (err)
> + return err;
> +
> init_waitqueue_head(&migration->wq);
> +
> + err = drmm_add_action_or_reset(&xe->drm, pf_migration_cleanup,
> migration);
shouldn't we use devm instead here ?
> + if (err)
> + return err;
> }
>
> return 0;
> @@ -154,6 +173,36 @@ xe_sriov_pf_migration_save_consume(struct xe_device *xe,
> unsigned int vfid)
> return data;
> }
>
> +static int pf_handle_descriptor(struct xe_device *xe, unsigned int vfid,
> + struct xe_sriov_migration_data *data)
> +{
> + if (data->tile != 0 || data->gt != 0)
> + return -EINVAL;
> +
> + xe_sriov_migration_data_free(data);
> +
> + return 0;
> +}
> +
> +static int pf_handle_trailer(struct xe_device *xe, unsigned int vfid,
> + struct xe_sriov_migration_data *data)
> +{
> + struct xe_gt *gt;
> + u8 gt_id;
> +
> + if (data->tile != 0 || data->gt != 0)
> + return -EINVAL;
> + if (data->offset != 0 || data->size != 0 || data->buff || data->bo)
> + return -EINVAL;
> +
> + xe_sriov_migration_data_free(data);
> +
> + for_each_gt(gt, xe, gt_id)
> + xe_gt_sriov_pf_control_restore_data_done(gt, vfid);
> +
> + return 0;
> +}
> +
> /**
> * xe_sriov_pf_migration_restore_produce() - Produce a VF migration data
> packet to the device.
> * @xe: the &xe_device
> @@ -173,6 +222,11 @@ int xe_sriov_pf_migration_restore_produce(struct
> xe_device *xe, unsigned int vfi
>
> xe_assert(xe, IS_SRIOV_PF(xe));
>
> + if (data->type == XE_SRIOV_MIGRATION_DATA_TYPE_DESCRIPTOR)
> + return pf_handle_descriptor(xe, vfid, data);
> + else if (data->type == XE_SRIOV_MIGRATION_DATA_TYPE_TRAILER)
no need for "else" here
> + return pf_handle_trailer(xe, vfid, data);
> +
> gt = xe_device_get_gt(xe, data->gt);
> if (!gt || data->tile != gt->tile->id) {
> xe_sriov_err_ratelimited(xe, "VF%d Invalid GT - tile:%u,
> GT:%u\n",
> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration_types.h
> b/drivers/gpu/drm/xe/xe_sriov_pf_migration_types.h
> index 2a45ee4e3ece8..8468e5eeb6d66 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_migration_types.h
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_migration_types.h
> @@ -7,6 +7,7 @@
> #define _XE_SRIOV_PF_MIGRATION_TYPES_H_
>
> #include <linux/types.h>
> +#include <linux/mutex_types.h>
> #include <linux/wait.h>
>
> /**
> @@ -53,6 +54,14 @@ struct xe_sriov_migration_data {
> struct xe_sriov_pf_migration {
> /** @wq: waitqueue used to avoid busy-waiting for snapshot
> production/consumption */
> wait_queue_head_t wq;
> + /** @lock: Mutex protecting the migration data */
> + struct mutex lock;
> + /** @pending: currently processed data packet of VF resource */
> + struct xe_sriov_migration_data *pending;
> + /** @trailer: data packet used to indicate the end of stream */
> + struct xe_sriov_migration_data *trailer;
> + /** @descriptor: data packet containing the metadata describing the
> device */
> + struct xe_sriov_migration_data *descriptor;
> };
>
> #endif
