On Thu, Oct 23, 2025 at 12:49:52AM +0200, Michal Wajdeczko wrote:
>
>
> On 10/22/2025 12:41 AM, Michał Winiarski wrote:
> > The descriptor reuses the KLV format used by GuC and contains metadata
> > that can be used to quickly fail migration when source is incompatible
> > with destination.
> >
> > Signed-off-by: Michał Winiarski <[email protected]>
> > ---
> > drivers/gpu/drm/xe/xe_sriov_migration_data.c | 79 +++++++++++++++++++-
> > drivers/gpu/drm/xe/xe_sriov_migration_data.h | 2 +
> > drivers/gpu/drm/xe/xe_sriov_pf_migration.c | 6 ++
> > 3 files changed, 86 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> > b/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> > index 4cd6c6fc9ba18..b58508c0c30f1 100644
> > --- a/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> > +++ b/drivers/gpu/drm/xe/xe_sriov_migration_data.c
> > @@ -5,6 +5,7 @@
> >
> > #include "xe_bo.h"
> > #include "xe_device.h"
> > +#include "xe_guc_klv_helpers.h"
> > #include "xe_sriov_migration_data.h"
> > #include "xe_sriov_pf_helpers.h"
> > #include "xe_sriov_pf_migration.h"
> > @@ -383,11 +384,18 @@ ssize_t xe_sriov_migration_data_write(struct
> > xe_device *xe, unsigned int vfid,
> > return produced;
> > }
> >
> > -#define MIGRATION_DESCRIPTOR_DWORDS 0
> > +#define MIGRATION_KLV_DEVICE_DEVID_KEY 0xf001u
> > +#define MIGRATION_KLV_DEVICE_DEVID_LEN 1u
> > +#define MIGRATION_KLV_DEVICE_REVID_KEY 0xf002u
> > +#define MIGRATION_KLV_DEVICE_REVID_LEN 1u
> > +
> > +#define MIGRATION_DESCRIPTOR_DWORDS (GUC_KLV_LEN_MIN +
> > MIGRATION_KLV_DEVICE_DEVID_LEN + \
> > + GUC_KLV_LEN_MIN +
> > MIGRATION_KLV_DEVICE_REVID_LEN)
> > 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;
> > + u32 *klvs;
> > int ret;
> >
> > data = xe_sriov_migration_data_alloc(xe);
> > @@ -401,11 +409,80 @@ static size_t pf_descriptor_init(struct xe_device
> > *xe, unsigned int vfid)
> > return ret;
> > }
> >
> > + klvs = data->vaddr;
> > + *klvs++ = PREP_GUC_KLV_CONST(MIGRATION_KLV_DEVICE_DEVID_KEY,
> > + MIGRATION_KLV_DEVICE_DEVID_LEN);
> > + *klvs++ = xe->info.devid;
> > + *klvs++ = PREP_GUC_KLV_CONST(MIGRATION_KLV_DEVICE_REVID_KEY,
> > + MIGRATION_KLV_DEVICE_REVID_LEN);
> > + *klvs++ = xe->info.revid;
> > +
>
> maybe add assert that written KLVs match descriptor size?
I'll track len written and verify with an assert.
>
> > *desc = data;
> >
> > return 0;
> > }
> >
> > +/**
> > + * xe_sriov_migration_data_process_descriptor() - Process migration data
> > descriptor.
> > + * @xe: the &xe_device
> > + * @vfid: the VF identifier
> > + * @data: the &struct xe_sriov_pf_migration_data containing the descriptor
> > + *
> > + * The descriptor uses the same KLV format as GuC, and contains metadata
> > used for
> > + * checking migration data compatibility.
> > + *
> > + * Return: 0 on success, -errno on failure.
> > + */
> > +int xe_sriov_migration_data_process_descriptor(struct xe_device *xe,
> > unsigned int vfid,
> > + struct xe_sriov_migration_data
> > *data)
> > +{
> > + u32 num_dwords = data->size / sizeof(u32);
> > + u32 *klvs = data->vaddr;
> > +
> > + xe_assert(xe, data->type == XE_SRIOV_MIGRATION_DATA_TYPE_DESCRIPTOR);
> > + if (data->size % sizeof(u32) != 0)
>
> no need to compare against 0
Ok.
>
> if (data->size % sizeof(u32))
>
> > + return -EINVAL;
>
> for other errors we warn(), ok to be silent here?
Let's add:
xe_sriov_warn(xe, "Aborting migration, descriptor not in KLV format
(size=%llu)\n",
data->size);
>
> > +
> > + while (num_dwords >= GUC_KLV_LEN_MIN) {
> > + u32 key = FIELD_GET(GUC_KLV_0_KEY, klvs[0]);
> > + u32 len = FIELD_GET(GUC_KLV_0_LEN, klvs[0]);
> > +
> > + klvs += GUC_KLV_LEN_MIN;
> > + num_dwords -= GUC_KLV_LEN_MIN;
> > +
>
> you should check len vs num_dwords here
Ok.
>
> > + switch (key) {
> > + case MIGRATION_KLV_DEVICE_DEVID_KEY:
> > + if (*klvs != xe->info.devid) {
> > + xe_sriov_warn(xe,
> > + "Aborting migration, devid
> > mismatch %#04x!=%#04x\n",
>
> likely %#06x, as you need to count also "0x"
Ok.
>
> > + *klvs, xe->info.devid);
> > + return -ENODEV;
> > + }
> > + break;
> > + case MIGRATION_KLV_DEVICE_REVID_KEY:
> > + if (*klvs != xe->info.revid) {
> > + xe_sriov_warn(xe,
> > + "Aborting migration, revid
> > mismatch %#04x!=%#04x\n",
> > + *klvs, xe->info.revid);
> > + return -ENODEV;
> > + }
> > + break;
> > + default:
> > + xe_sriov_dbg(xe,
> > + "Unknown migration descriptor key %#06x -
> > skipping\n", key);
>
> also print len? and some initial hexdump to help with debug?
I'll replace it with:
xe_sriov_dbg(xe,
"Skipping unknown migration descriptor key %#06x
(len=%#06x)\n",
key, len);
print_hex_dump_bytes("desc: ", DUMP_PREFIX_OFFSET, klvs,
min(SZ_64, len * sizeof(u32)));
>
> > + break;
> > + }
> > +
> > + if (len > num_dwords)
> > + return -EINVAL;
>
> this check should be earlier
Ok.
Thanks,
-Michał
>
> > +
> > + klvs += len;
> > + num_dwords -= len;
> > + }
> > +
> > + 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);
> > diff --git a/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> > b/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> > index 5cde6e9439677..e7f3b332124bc 100644
> > --- a/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> > +++ b/drivers/gpu/drm/xe/xe_sriov_migration_data.h
> > @@ -31,6 +31,8 @@ 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_process_descriptor(struct xe_device *xe,
> > unsigned int vfid,
> > + struct xe_sriov_migration_data
> > *data);
> > 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_migration.c
> > b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> > index 029e14f1ffa74..0b4b237780102 100644
> > --- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> > +++ b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> > @@ -176,9 +176,15 @@ xe_sriov_pf_migration_save_consume(struct xe_device
> > *xe, unsigned int vfid)
> > static int pf_handle_descriptor(struct xe_device *xe, unsigned int vfid,
> > struct xe_sriov_migration_data *data)
> > {
> > + int ret;
> > +
> > if (data->tile != 0 || data->gt != 0)
> > return -EINVAL;
> >
> > + ret = xe_sriov_migration_data_process_descriptor(xe, vfid, data);
> > + if (ret)
> > + return ret;
> > +
> > xe_sriov_migration_data_free(data);
> >
> > return 0;
>
>
>
>
