On 10/11/2025 9:38 PM, Michał Winiarski wrote:
> Connect the helpers to allow save and restore of GGTT migration data in
> stop_copy / resume device state.
>
> Signed-off-by: Michał Winiarski <[email protected]>
> ---
> drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c | 13 ++
> .../gpu/drm/xe/xe_gt_sriov_pf_control_types.h | 1 +
> drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c | 119 ++++++++++++++++++
> drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h | 4 +
> 4 files changed, 137 insertions(+)
>
> 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 f73a3bf40037c..a74f6feca4830 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
> @@ -188,6 +188,7 @@ static const char *control_bit_to_string(enum
> xe_gt_sriov_control_bits bit)
> CASE2STR(MIGRATION_DATA_WIP);
> CASE2STR(SAVE_WIP);
> CASE2STR(SAVE_DATA_GUC);
> + CASE2STR(SAVE_DATA_GGTT);
> CASE2STR(SAVE_FAILED);
> CASE2STR(SAVED);
> CASE2STR(RESTORE_WIP);
> @@ -803,6 +804,7 @@ void xe_gt_sriov_pf_control_vf_data_eof(struct xe_gt *gt,
> unsigned int vfid)
>
> static void pf_exit_vf_save_wip(struct xe_gt *gt, unsigned int vfid)
> {
> + pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_DATA_GGTT);
> pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_DATA_GUC);
> pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WIP);
> }
> @@ -843,6 +845,13 @@ static bool pf_handle_vf_save_wip(struct xe_gt *gt,
> unsigned int vfid)
> return true;
> }
>
> + if (pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_DATA_GGTT)) {
> + ret = xe_gt_sriov_pf_migration_ggtt_save(gt, vfid);
> + if (ret)
> + goto err;
> + return true;
> + }
> +
> xe_gt_sriov_pf_control_vf_data_eof(gt, vfid);
> pf_exit_vf_save_wip(gt, vfid);
> pf_enter_vf_saved(gt, vfid);
> @@ -862,6 +871,8 @@ static bool pf_enter_vf_save_wip(struct xe_gt *gt,
> unsigned int vfid)
> pf_enter_vf_wip(gt, vfid);
> if (xe_gt_sriov_pf_migration_guc_size(gt, vfid) > 0)
> pf_enter_vf_state(gt, vfid,
> XE_GT_SRIOV_STATE_SAVE_DATA_GUC);
> + if (xe_gt_sriov_pf_migration_ggtt_size(gt, vfid) > 0)
> + pf_enter_vf_state(gt, vfid,
> XE_GT_SRIOV_STATE_SAVE_DATA_GGTT);
> pf_queue_vf(gt, vfid);
> return true;
> }
> @@ -970,6 +981,8 @@ static int pf_handle_vf_restore_data(struct xe_gt *gt,
> unsigned int vfid,
> struct xe_sriov_pf_migration_data *data)
> {
> switch (data->type) {
> + case XE_SRIOV_MIG_DATA_GGTT:
> + return xe_gt_sriov_pf_migration_ggtt_restore(gt, vfid, data);
> case XE_SRIOV_MIG_DATA_GUC:
> return xe_gt_sriov_pf_migration_guc_restore(gt, vfid, data);
> default:
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
> b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
> index b9787c425d9f6..c94ff0258306a 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
> @@ -72,6 +72,7 @@ enum xe_gt_sriov_control_bits {
>
> XE_GT_SRIOV_STATE_SAVE_WIP,
> XE_GT_SRIOV_STATE_SAVE_DATA_GUC,
> + XE_GT_SRIOV_STATE_SAVE_DATA_GGTT,
> XE_GT_SRIOV_STATE_SAVE_FAILED,
> XE_GT_SRIOV_STATE_SAVED,
>
> 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 0c10284f0b09a..92ecf47e71bc7 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
> @@ -7,6 +7,7 @@
>
> #include "abi/guc_actions_sriov_abi.h"
> #include "xe_bo.h"
> +#include "xe_gt_sriov_pf_config.h"
> #include "xe_gt_sriov_pf_control.h"
> #include "xe_gt_sriov_pf_helpers.h"
> #include "xe_gt_sriov_pf_migration.h"
> @@ -37,6 +38,117 @@ static void pf_dump_mig_data(struct xe_gt *gt, unsigned
> int vfid,
> }
> }
>
> +static int pf_save_vf_ggtt_mig_data(struct xe_gt *gt, unsigned int vfid)
> +{
> + struct xe_sriov_pf_migration_data *data;
> + size_t size;
> + int ret;
> +
> + size = xe_gt_sriov_pf_config_get_ggtt(gt, vfid);
> + if (size == 0)
> + return 0;
> + size = size / XE_PAGE_SIZE * sizeof(u64);
maybe it would be better to avoid reusing the var and have two:
u64 alloc_size = xe_gt_sriov_pf_config_get_ggtt(...);
u64 pte_size = xe_ggtt_pte_size(alloc_size);
> +
> + data = xe_sriov_pf_migration_data_alloc(gt_to_xe(gt));
> + if (!data)
> + return -ENOMEM;
> +
> + ret = xe_sriov_pf_migration_data_init(data, gt->tile->id, gt->info.id,
> + XE_SRIOV_MIG_DATA_GGTT, 0, size);
> + if (ret)
> + goto fail;
> +
> + ret = xe_gt_sriov_pf_config_ggtt_save(gt, vfid, data->vaddr, size);
> + if (ret)
> + goto fail;
> +
> + pf_dump_mig_data(gt, vfid, data);
> +
> + ret = xe_gt_sriov_pf_migration_ring_produce(gt, vfid, data);
> + if (ret)
> + goto fail;
> +
> + return 0;
> +
> +fail:
> + xe_sriov_pf_migration_data_free(data);
> + xe_gt_sriov_err(gt, "Unable to save VF%u GGTT data (%d)\n", vfid, ret);
use %pe for errors
> + return ret;
> +}
> +
> +static int pf_restore_vf_ggtt_mig_data(struct xe_gt *gt, unsigned int vfid,
> + struct xe_sriov_pf_migration_data *data)
> +{
> + size_t size;
> + int ret;
> +
> + size = xe_gt_sriov_pf_config_get_ggtt(gt, vfid) / XE_PAGE_SIZE *
> sizeof(u64);
> + if (size != data->hdr.size)
> + return -EINVAL;
do we need this ?
there seems to be similar check in xe_ggtt_node_load() called by restore() below
> +
> + pf_dump_mig_data(gt, vfid, data);
> +
> + ret = xe_gt_sriov_pf_config_ggtt_restore(gt, vfid, data->vaddr, size);
> + if (ret)
> + return ret;
> +
> + return 0;
> +}
> +
> +/**
> + * xe_gt_sriov_pf_migration_ggtt_size() - Get the size of VF GGTT migration
> data.
> + * @gt: the &struct xe_gt
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: size in bytes or a negative error code on failure.
> + */
> +ssize_t xe_gt_sriov_pf_migration_ggtt_size(struct xe_gt *gt, unsigned int
> vfid)
> +{
> + if (gt != xe_root_mmio_gt(gt_to_xe(gt)))
> + return 0;
> +
> + return xe_gt_sriov_pf_config_get_ggtt(gt, vfid) / XE_PAGE_SIZE *
> sizeof(u64);
this conversion logic should be done by xe_ggtt layer helper
> +}
> +
> +/**
> + * xe_gt_sriov_pf_migration_ggtt_save() - Save VF GGTT migration data.
> + * @gt: the &struct xe_gt
> + * @vfid: the VF identifier
since there is assert, probably you should also say: "(can't be 0)"
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_gt_sriov_pf_migration_ggtt_save(struct xe_gt *gt, unsigned int vfid)
> +{
> + xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
> + xe_gt_assert(gt, vfid != PFID);
> + xe_gt_assert(gt, vfid <= xe_sriov_pf_get_totalvfs(gt_to_xe(gt)));
> +
> + return pf_save_vf_ggtt_mig_data(gt, vfid);
> +}
> +
> +/**
> + * xe_gt_sriov_pf_migration_ggtt_restore() - Restore VF GGTT migration data.
> + * @gt: the &struct xe_gt
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_gt_sriov_pf_migration_ggtt_restore(struct xe_gt *gt, unsigned int
> vfid,
> + struct xe_sriov_pf_migration_data
> *data)
> +{
> + xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
> + xe_gt_assert(gt, vfid != PFID);
> + xe_gt_assert(gt, vfid <= xe_sriov_pf_get_totalvfs(gt_to_xe(gt)));
> +
> + return pf_restore_vf_ggtt_mig_data(gt, vfid, data);
> +}
> +
> /* Return: number of dwords saved/restored/required or a negative error code
> on failure */
> static int guc_action_vf_save_restore(struct xe_guc *guc, u32 vfid, u32
> opcode,
> u64 addr, u32 ndwords)
> @@ -290,6 +402,13 @@ ssize_t xe_gt_sriov_pf_migration_size(struct xe_gt *gt,
> unsigned int vfid)
> size += sizeof(struct xe_sriov_pf_migration_hdr);
> total += size;
>
> + size = xe_gt_sriov_pf_migration_ggtt_size(gt, vfid);
> + if (size < 0)
> + return size;
> + else if (size > 0)
> + size += sizeof(struct xe_sriov_pf_migration_hdr);
> + total += size;
> +
> return total;
> }
>
> 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 5df64449232bc..5bb8cba2ea0cb 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
> @@ -16,6 +16,10 @@ ssize_t xe_gt_sriov_pf_migration_guc_size(struct xe_gt
> *gt, unsigned int vfid);
> int xe_gt_sriov_pf_migration_guc_save(struct xe_gt *gt, unsigned int vfid);
> int xe_gt_sriov_pf_migration_guc_restore(struct xe_gt *gt, unsigned int vfid,
> struct xe_sriov_pf_migration_data
> *data);
> +ssize_t xe_gt_sriov_pf_migration_ggtt_size(struct xe_gt *gt, unsigned int
> vfid);
> +int xe_gt_sriov_pf_migration_ggtt_save(struct xe_gt *gt, unsigned int vfid);
> +int xe_gt_sriov_pf_migration_ggtt_restore(struct xe_gt *gt, unsigned int
> vfid,
> + struct xe_sriov_pf_migration_data
> *data);
>
> ssize_t xe_gt_sriov_pf_migration_size(struct xe_gt *gt, unsigned int vfid);
>
