drm/xe/pf: Add minimalistic migration descriptor

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.

Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patch.msgid.link/20251112132220.516975-9-michal.winiarski@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>

Author: mwiniars

drivers/gpu/drm/xe/xe_sriov_packet.c

@@ -5,6 +5,7 @@
 
 #include "xe_bo.h"
 #include "xe_device.h"
+#include "xe_guc_klv_helpers.h"
 #include "xe_printk.h"
 #include "xe_sriov_packet.h"
 #include "xe_sriov_packet_types.h"
@@ -350,11 +351,19 @@ ssize_t xe_sriov_packet_write_single(struct xe_device *xe, unsigned int vfid,
 	return copied;
 }
 
-#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_packet **desc = pf_pick_descriptor(xe, vfid);
 	struct xe_sriov_packet *data;
+	unsigned int len = 0;
+	u32 *klvs;
 	int ret;
 
 	data = xe_sriov_packet_alloc(xe);
@@ -368,11 +377,92 @@ static size_t pf_descriptor_init(struct xe_device *xe, unsigned int vfid)
 		return ret;
 	}
 
+	klvs = data->vaddr;
+	klvs[len++] = PREP_GUC_KLV_CONST(MIGRATION_KLV_DEVICE_DEVID_KEY,
+					 MIGRATION_KLV_DEVICE_DEVID_LEN);
+	klvs[len++] = xe->info.devid;
+	klvs[len++] = PREP_GUC_KLV_CONST(MIGRATION_KLV_DEVICE_REVID_KEY,
+					 MIGRATION_KLV_DEVICE_REVID_LEN);
+	klvs[len++] = xe->info.revid;
+
+	xe_assert(xe, len == MIGRATION_DESCRIPTOR_DWORDS);
+
 	*desc = data;
 
 	return 0;
 }
 
+/**
+ * xe_sriov_packet_process_descriptor() - Process migration data descriptor packet.
+ * @xe: the &xe_device
+ * @vfid: the VF identifier
+ * @data: the &xe_sriov_packet 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_packet_process_descriptor(struct xe_device *xe, unsigned int vfid,
+				       struct xe_sriov_packet *data)
+{
+	u32 num_dwords = data->hdr.size / sizeof(u32);
+	u32 *klvs = data->vaddr;
+
+	xe_assert(xe, data->hdr.type == XE_SRIOV_PACKET_TYPE_DESCRIPTOR);
+
+	if (data->hdr.size % sizeof(u32)) {
+		xe_sriov_warn(xe, "Aborting migration, descriptor not in KLV format (size=%llu)\n",
+			      data->hdr.size);
+		return -EINVAL;
+	}
+
+	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;
+
+		if (len > num_dwords) {
+			xe_sriov_warn(xe, "Aborting migration, truncated KLV %#x, len %u\n",
+				      key, len);
+			return -EINVAL;
+		}
+
+		switch (key) {
+		case MIGRATION_KLV_DEVICE_DEVID_KEY:
+			if (*klvs != xe->info.devid) {
+				xe_sriov_warn(xe,
+					      "Aborting migration, devid mismatch %#06x!=%#06x\n",
+					      *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 %#06x!=%#06x\n",
+					      *klvs, xe->info.revid);
+				return -ENODEV;
+			}
+			break;
+		default:
+			xe_sriov_dbg(xe,
+				     "Skipping unknown migration KLV %#x, len=%u\n",
+				     key, len);
+			print_hex_dump_bytes("desc: ", DUMP_PREFIX_OFFSET, klvs,
+					     min(SZ_64, len * sizeof(u32)));
+			break;
+		}
+
+		klvs += len;
+		num_dwords -= len;
+	}
+
+	return 0;
+}
+
 static void pf_pending_init(struct xe_device *xe, unsigned int vfid)
 {
 	struct xe_sriov_packet **data = pf_pick_pending(xe, vfid);

drivers/gpu/drm/xe/xe_sriov_packet.h

@@ -24,5 +24,7 @@ ssize_t xe_sriov_packet_read_single(struct xe_device *xe, unsigned int vfid,
 ssize_t xe_sriov_packet_write_single(struct xe_device *xe, unsigned int vfid,
 				     const char __user *buf, size_t len);
 int xe_sriov_packet_save_init(struct xe_device *xe, unsigned int vfid);
+int xe_sriov_packet_process_descriptor(struct xe_device *xe, unsigned int vfid,
+				       struct xe_sriov_packet *data);
 
 #endif

drivers/gpu/drm/xe/xe_sriov_pf_migration.c

@@ -177,9 +177,15 @@ 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_packet *data)
 {
+	int ret;
+
 	if (data->hdr.tile_id != 0 || data->hdr.gt_id != 0)
 		return -EINVAL;
 
+	ret = xe_sriov_packet_process_descriptor(xe, vfid, data);
+	if (ret)
+		return ret;
+
 	xe_sriov_packet_free(data);
 
 	return 0;