Skip to contentSkip to conversation

drm/xe/vf: Post-migration recovery of GGTT nodes and CTB

PATCH Superseded Tomasz Lis 1 participant 5 messages Mar 28, 2025

Subsystems (2)

v5 of 14 Superseded Latest is v14 →

lore
Share & tools
lore

Tomasz Lis

author
#0 lore raw

v5 cover drm/xe/vf: Post-migration recovery of GGTT nodes and CTB

To support VF Migration, it is necessary to do fixups to any non-virtualized resources. These fixups need to be applied within VM, on the KMD working with VF.

This series adds two fixup functions to the recovery worker:
* for fixing drm_mm nodes which represent GGTT allocations
* for fixing content of outgoing CTB buffer

v2: Fixed missing include, made checkpatch happy
v3: Moved some functs to xe_ggtt.c; moved shift computation to just
after querying; improved documentation; switched some warns to asserts; skipping fixups when GGTT shift eq 0; iterating through tiles rather than gts; fixes in log messages
v4: Updated kerneldocs, removed unused funct, properly allocate
balloning nodes if non existent, removed inline keywords, enums for offsets in CTB messages, less error messages, if return unused then made functs void
v5: Removed drm_mm change, but added VF init modifications. These then
allowed to re-use ballooning functions during ggtt node fixing.

Tomasz Lis (4):
drm/xe/vf: Divide ballooning into allocation and insertion drm/xe/sriov: Shifting GGTT area post migration drm/xe/guc: Introduce enum with offsets for multi-LRC register H2G drm/xe/vf: Fixup CTB send buffer messages after migration

 drivers/gpu/drm/xe/abi/guc_actions_abi.h  |   7 +
 drivers/gpu/drm/xe/xe_ggtt.c              |  40 +++++-
 drivers/gpu/drm/xe/xe_ggtt.h              |   3 +
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c       | 148 +++++++++++++++++++---
 drivers/gpu/drm/xe/xe_gt_sriov_vf.h       |   1 +
 drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h |   2 +
 drivers/gpu/drm/xe/xe_guc_ct.c            | 142 +++++++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_ct.h            |   2 +
 drivers/gpu/drm/xe/xe_guc_submit.c        |   4 +
 drivers/gpu/drm/xe/xe_sriov_vf.c          |  42 ++++++
 10 files changed, 369 insertions(+), 22 deletions(-)
Signature · 1 line
2.25.1
author
#1 lore raw

PATCH v5 1/4 drm/xe/vf: Divide ballooning into allocation and insertion

The balloon nodes used to fill areas of GGTT inaccessible for a specific VF, were allocaten and inserted into GGTT within one function. This disallowed re-using the insertion part during VF migration recovery.

This patch separates allocation (init/fini functs) from the insertion of balloons (balloon/deballoon functs). Locks are also moved to ensure calls from post-migration recovery worker will not cause a deadlock.

---
 drivers/gpu/drm/xe/xe_ggtt.c        |  9 +---
 drivers/gpu/drm/xe/xe_ggtt.h        |  2 +
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 64 ++++++++++++++++++++++-------
 3 files changed, 52 insertions(+), 23 deletions(-)
drivers/gpu/drm/xe/xe_ggtt.c +1 -8
index 5fcb2b4c2c13..2d7456e37ef4 100644
@@ -452,9 +452,7 @@ int xe_ggtt_node_insert_balloon(struct xe_ggtt_node *node, u64 start, u64 end)
 	node->base.start = start;
 	node->base.size = end - start;
 
-	mutex_lock(&ggtt->lock);
 	err = drm_mm_reserve_node(&ggtt->mm, &node->base);
-	mutex_unlock(&ggtt->lock);
 
 	if (xe_gt_WARN(ggtt->tile->primary_gt, err,
 		       "Failed to balloon GGTT %#llx-%#llx (%pe)\n",
@@ -477,16 +475,11 @@ void xe_ggtt_node_remove_balloon(struct xe_ggtt_node *node)
 		return;
 
 	if (!drm_mm_node_allocated(&node->base))
-		goto free_node;
+		return;
 
 	xe_ggtt_dump_node(node->ggtt, &node->base, "remove-balloon");
 
-	mutex_lock(&node->ggtt->lock);
 	drm_mm_remove_node(&node->base);
-	mutex_unlock(&node->ggtt->lock);
-
-free_node:
-	xe_ggtt_node_fini(node);
 }
 
 /**
drivers/gpu/drm/xe/xe_ggtt.h +2 -0
index 27e7d67de004..fddb68f309d9 100644
@@ -18,6 +18,8 @@ void xe_ggtt_node_fini(struct xe_ggtt_node *node);
 int xe_ggtt_node_insert_balloon(struct xe_ggtt_node *node,
 				u64 start, u64 size);
 void xe_ggtt_node_remove_balloon(struct xe_ggtt_node *node);
+int xe_gt_sriov_vf_balloon_ggtt(struct xe_gt *gt);
+void xe_gt_sriov_vf_deballoon_ggtt(struct xe_gt *gt);
 
 int xe_ggtt_node_insert(struct xe_ggtt_node *node, u32 size, u32 align);
 int xe_ggtt_node_insert_locked(struct xe_ggtt_node *node,
drivers/gpu/drm/xe/xe_gt_sriov_vf.c +49 -15

124 lines not on this page · raw message

Signature · 1 line
2.25.1
author
#2 lore raw

PATCH v5 2/4 drm/xe/sriov: Shifting GGTT area post migration

In reply to Tomasz Lis

We have only one GGTT for all IOV functions, with each VF having assigned a range of addresses for its use. After migration, a VF can receive a different range of addresses than it had initially.

This implements shifting GGTT addresses within drm_mm nodes, so that VMAs stay valid after migration. This will make the driver use new addresses when accessing GGTT from the moment the shifting ends.

By taking the ggtt->lock for the period of VMA fixups, this change also adds constraint on that mutex. Any locks used during the recovery cannot ever wait for hardware response - because after migration, the hardware will not do anything until fixups are finished.

v2: Moved some functs to xe_ggtt.c; moved shift computation to just
after querying; improved documentation; switched some warns to asserts; skipping fixups when GGTT shift eq 0; iterating through tiles (Michal)
v3: Updated kerneldocs, removed unused funct, properly allocate
balloning nodes if non existent
v4: Re-used ballooning functions from VF init, used bool in place of
standard error codes

---
 drivers/gpu/drm/xe/xe_ggtt.c              | 33 +++++++++
 drivers/gpu/drm/xe/xe_ggtt.h              |  1 +
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c       | 84 +++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_gt_sriov_vf.h       |  1 +
 drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h |  2 +
 drivers/gpu/drm/xe/xe_sriov_vf.c          | 17 +++++
 6 files changed, 138 insertions(+)
drivers/gpu/drm/xe/xe_ggtt.c +33 -0
index 2d7456e37ef4..e9e6088104d9 100644
@@ -482,6 +482,39 @@ void xe_ggtt_node_remove_balloon(struct xe_ggtt_node *node)
 	drm_mm_remove_node(&node->base);
 }
 
+/**
+ * xe_ggtt_node_shift_nodes - Shift GGTT nodes to adjust for a change in usable address range.
+ * @ggtt: the &xe_ggtt struct instance
+ * @shift: change to the location of area provisioned for current VF
+ */
+void xe_ggtt_node_shift_nodes(struct xe_ggtt *ggtt, s64 shift)
+{
+	struct drm_mm_node *node, *tmpn;
+	LIST_HEAD(temp_list_head);
+	int err;
+
+	lockdep_assert_held(&ggtt->lock);
+
+	/*
+	 * Move nodes, from range previously assigned to this VF, to a temp list.
+	 */
+	drm_mm_for_each_node_safe(node, tmpn, &ggtt->mm) {
+		drm_mm_remove_node(node);
+		list_add(&node->node_list, &temp_list_head);
+	}
+
+	/*
+	 * Now the GGTT VM contains no nodes. We can re-add all VF nodes with
+	 * shifted offsets.
+	 */
+	list_for_each_entry_safe(node, tmpn, &temp_list_head, node_list) {
+		list_del(&node->node_list);
+		node->start += shift;
+		err = drm_mm_reserve_node(&ggtt->mm, node);
+		xe_tile_assert(ggtt->tile, !err);
+	}
+}
+
 /**
  * xe_ggtt_node_insert_locked - Locked version to insert a &xe_ggtt_node into the GGTT
  * @node: the &xe_ggtt_node to be inserted
drivers/gpu/drm/xe/xe_ggtt.h +1 -0
index fddb68f309d9..557906413761 100644
@@ -18,6 +18,7 @@ void xe_ggtt_node_fini(struct xe_ggtt_node *node);
 int xe_ggtt_node_insert_balloon(struct xe_ggtt_node *node,
 				u64 start, u64 size);
 void xe_ggtt_node_remove_balloon(struct xe_ggtt_node *node);
+void xe_ggtt_node_shift_nodes(struct xe_ggtt *ggtt, s64 shift);
 int xe_gt_sriov_vf_balloon_ggtt(struct xe_gt *gt);
 void xe_gt_sriov_vf_deballoon_ggtt(struct xe_gt *gt);
 
drivers/gpu/drm/xe/xe_gt_sriov_vf.c +84 -0

96 lines not on this page · raw message

drivers/gpu/drm/xe/xe_gt_sriov_vf.h +1 -0
index ba6c5d74e326..26d3140bba91 100644
@@ -18,6 +18,7 @@ int xe_gt_sriov_vf_query_config(struct xe_gt *gt);
 int xe_gt_sriov_vf_connect(struct xe_gt *gt);
 int xe_gt_sriov_vf_query_runtime(struct xe_gt *gt);
 int xe_gt_sriov_vf_prepare_ggtt(struct xe_gt *gt);
+bool xe_gt_sriov_vf_fixup_ggtt_nodes(struct xe_gt *gt);
 int xe_gt_sriov_vf_notify_resfix_done(struct xe_gt *gt);
 void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt);
 
drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h +2 -0
index a57f13b5afcd..5ccbdf8d08b6 100644
@@ -40,6 +40,8 @@ struct xe_gt_sriov_vf_selfconfig {
 	u64 ggtt_base;
 	/** @ggtt_size: assigned size of the GGTT region. */
 	u64 ggtt_size;
+	/** @ggtt_shift: difference in ggtt_base on last migration */
+	s64 ggtt_shift;
 	/** @lmem_size: assigned size of the LMEM. */
 	u64 lmem_size;
 	/** @num_ctxs: assigned number of GuC submission context IDs. */
drivers/gpu/drm/xe/xe_sriov_vf.c +17 -0
index c1275e64aa9c..2eb6b8d8a217 100644
@@ -7,6 +7,7 @@
 
 #include "xe_assert.h"
 #include "xe_device.h"
+#include "xe_gt.h"
 #include "xe_gt_sriov_printk.h"
 #include "xe_gt_sriov_vf.h"
 #include "xe_pm.h"
@@ -170,6 +171,20 @@ static bool vf_post_migration_imminent(struct xe_device *xe)
 	work_pending(&xe->sriov.vf.migration.worker);
 }
 
+static bool vf_post_migration_fixup_ggtt_nodes(struct xe_device *xe)
+{
+	struct xe_tile *tile;
+	unsigned int id;
+	bool need_fixups = false;
+
+	for_each_tile(tile, xe, id) {
+		struct xe_gt *gt = tile->primary_gt;
+
+		need_fixups |= xe_gt_sriov_vf_fixup_ggtt_nodes(gt);
+	}
+	return need_fixups;
+}
+
 /*
  * Notify all GuCs about resource fixups apply finished.
  */
@@ -191,6 +206,7 @@ static void vf_post_migration_notify_resfix_done(struct xe_device *xe)
 
 static void vf_post_migration_recovery(struct xe_device *xe)
 {
+	bool need_fixups;
 	int err;
 
 	drm_dbg(&xe->drm, "migration recovery in progress\n");
@@ -201,6 +217,7 @@ static void vf_post_migration_recovery(struct xe_device *xe)
 	if (unlikely(err))
 		goto fail;
 
+	need_fixups = vf_post_migration_fixup_ggtt_nodes(xe);
 	/* FIXME: add the recovery steps */
 	vf_post_migration_notify_resfix_done(xe);
 	xe_pm_runtime_put(xe);
Signature · 1 line
2.25.1
author
#3 lore raw

PATCH v5 3/4 drm/xe/guc: Introduce enum with offsets for multi-LRC register H2G

In reply to Tomasz Lis

Some GuC messages are constructed with incrementing dword counter rather than referencing specific DWORDs, as described in GuC interface specification.

This change introduces the definitions of DWORD numbers for parameters which will need to be referenced in a CTB parser to be added in a following patch. To ensure correctness of these DWORDs, verification in form of asserts was added to the message construction code.

---
 drivers/gpu/drm/xe/abi/guc_actions_abi.h | 7 +++++++
 drivers/gpu/drm/xe/xe_guc_submit.c       | 4 ++++
 2 files changed, 11 insertions(+)
drivers/gpu/drm/xe/abi/guc_actions_abi.h +7 -0
index 448afb86e05c..86bd4b092c7c 100644
@@ -161,6 +161,13 @@ enum xe_guc_preempt_options {
 	XE_GUC_PREEMPT_OPTION_DROP_SUBMIT_Q = 0x8,
 };
 
+enum xe_guc_register_context_multi_lrc_param_offsets {
+	XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_WQ_DESC = 5,
+	XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_WQ_BASE = 7,
+	XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_N_CHILDREN = 10,
+	XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_HWLRCA = 11
+};
+
 enum xe_guc_report_status {
 	XE_GUC_REPORT_STATUS_UNKNOWN = 0x0,
 	XE_GUC_REPORT_STATUS_ACKED = 0x1,
drivers/gpu/drm/xe/xe_guc_submit.c +4 -0
index 31bc2022bfc2..3c8574e2c1f3 100644
@@ -469,12 +469,16 @@ static void __register_mlrc_exec_queue(struct xe_guc *guc,
 	action[len++] = info->context_idx;
 	action[len++] = info->engine_class;
 	action[len++] = info->engine_submit_mask;
+	xe_gt_assert(guc_to_gt(guc), len == XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_WQ_DESC);
 	action[len++] = info->wq_desc_lo;
 	action[len++] = info->wq_desc_hi;
+	xe_gt_assert(guc_to_gt(guc), len == XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_WQ_BASE);
 	action[len++] = info->wq_base_lo;
 	action[len++] = info->wq_base_hi;
 	action[len++] = info->wq_size;
+	xe_gt_assert(guc_to_gt(guc), len == XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_N_CHILDREN);
 	action[len++] = q->width;
+	xe_gt_assert(guc_to_gt(guc), len == XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_HWLRCA);
 	action[len++] = info->hwlrca_lo;
 	action[len++] = info->hwlrca_hi;
 
Signature · 1 line
2.25.1
author
#4 lore raw

PATCH v5 4/4 drm/xe/vf: Fixup CTB send buffer messages after migration

In reply to Tomasz Lis

During post-migration recovery of a VF, it is necessary to update GGTT references included in messages which are going to be sent to GuC. GuC will start consuming messages after VF KMD will inform it about fixups being done; before that, the VF KMD is expected to update any H2G messages which are already in send buffer but were not consumed by GuC.

Only a small subset of messages allowed for VFs have GGTT references in them. This patch adds the functionality to parse the CTB send ring buffer and shift addresses contained within.

While fixing the CTB content, ct->lock is not taken. This means the only barrier taken remains GGTT address lock - which is ok, because only requests with GGTT addresses matter, but it also means tail changes can happen during the CTB fixups execution (which may be ignored as any new messages will not have anything to fix).

The GGTT address locking will be introduced in a future series.

v2: removed storing shift as that's now done in VMA nodes patch;
macros to inlines; warns to asserts; log messages fixes (Michal)
v3: removed inline keywords, enums for offsets in CTB messages,
less error messages, if return unused then made functs void (Michal)
v4: update the cached head before starting fixups
v5: removed/updated comments, wrapped lines, converted assert into
error, enums for offsets to separate patch, reused xe_map_rd

---
 drivers/gpu/drm/xe/xe_guc_ct.c   | 142 +++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_ct.h   |   2 +
 drivers/gpu/drm/xe/xe_sriov_vf.c |  25 ++++++
 3 files changed, 169 insertions(+)
drivers/gpu/drm/xe/xe_guc_ct.c +142 -0
index 686fe664c20d..6c80106e5e8b 100644
@@ -84,6 +84,8 @@ struct g2h_fence {
 	bool done;
 };
 
+#define make_u64(hi, lo) ((u64)((u64)(u32)(hi) << 32 | (u32)(lo)))
+
 static void g2h_fence_init(struct g2h_fence *g2h_fence, u32 *response_buffer)
 {
 	g2h_fence->response_buffer = response_buffer;
@@ -1622,6 +1624,146 @@ static void g2h_worker_func(struct work_struct *w)
 	receive_g2h(ct);
 }
 
+static u32 xe_map_rd_u32(struct xe_device *xe, struct iosys_map *cmds,
+			     u32 head, u32 pos)
+{
+	return xe_map_rd(xe, cmds, (head + pos) * sizeof(u32), u32);
+}
+
+static void xe_map_fixup_u64(struct xe_device *xe, struct iosys_map *cmds,
+			       u32 head, u32 pos, s64 shift)
+{
+	u32 msg[2];
+	u64 offset;
+
+	xe_map_memcpy_from(xe, msg, cmds, (head + pos) * sizeof(u32),
+			   2 * sizeof(u32));
+	offset = make_u64(msg[1], msg[0]);
+	offset += shift;
+	msg[0] = lower_32_bits(offset);
+	msg[1] = upper_32_bits(offset);
+	xe_map_memcpy_to(xe, cmds, (head + pos) * sizeof(u32), msg, 2 * sizeof(u32));
+}
+
+/*
+ * Shift any GGTT addresses within a single message left within CTB from
+ * before post-migration recovery.
+ * @ct: pointer to CT struct of the target GuC
+ * @cmds: iomap buffer containing CT messages
+ * @head: start of the target message within the buffer
+ * @len: length of the target message
+ * @size: size of the commands buffer
+ * @shift: the address shift to be added to each GGTT reference
+ */
+static void ct_update_addresses_in_message(struct xe_guc_ct *ct,
+					   struct iosys_map *cmds, u32 head,
+					   u32 len, u32 size, s64 shift)
+{
+	struct xe_device *xe = ct_to_xe(ct);
+	u32 action, i, n;
+	u32 msg[1];
+
+	xe_map_memcpy_from(xe, msg, cmds, head * sizeof(u32),
+			   1 * sizeof(u32));
+	action = FIELD_GET(GUC_HXG_REQUEST_MSG_0_ACTION, msg[0]);
+	switch (action) {
+	case XE_GUC_ACTION_REGISTER_CONTEXT:
+	case XE_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC:
+		xe_map_fixup_u64(xe, cmds, head,
+				 XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_WQ_DESC, shift);
+		xe_map_fixup_u64(xe, cmds, head,
+				 XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_WQ_BASE, shift);
+		if (action == XE_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC) {
+			n = xe_map_rd_u32(xe, cmds, head,
+				       XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_N_CHILDREN);
+			for (i = 0; i < n; i++)
+				xe_map_fixup_u64(xe, cmds, head,
+					    XE_GUC_REGISTER_CONTEXT_MULTI_LRC_OFFS_HWLRCA
+					    + 2 * i, shift);
+		} else {
+			xe_map_fixup_u64(xe, cmds, head, 10, shift);
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static int ct_update_addresses_in_buffer(struct xe_guc_ct *ct,
+					 struct guc_ctb *h2g,
+					 s64 shift, u32 *mhead, s32 avail)
+{
+	struct xe_device *xe = ct_to_xe(ct);
+	u32 head = *mhead;
+	u32 size = h2g->info.size;
+	u32 msg[1];
+	u32 len;
+
+	/* Read header */
+	xe_map_memcpy_from(xe, msg, &h2g->cmds, sizeof(u32) * head,
+			   sizeof(u32));
+	len = FIELD_GET(GUC_CTB_MSG_0_NUM_DWORDS, msg[0]) + GUC_CTB_MSG_MIN_LEN;
+
+	if (unlikely(len > (u32)avail)) {
+		xe_gt_err(ct_to_gt(ct), "H2G channel broken on read, avail=%d, len=%d, fixups skipped\n",
+			  avail, len);
+		return 0;
+	}
+
+	head = (head + 1) % size;
+	ct_update_addresses_in_message(ct, &h2g->cmds, head, len - 1, size, shift);
+	*mhead = (head + len - 1) % size;
+
+	return avail - len;
+}
+
+/**
+ * xe_guc_ct_fixup_messages_with_ggtt - Fixup any pending H2G CTB messages by updating
+ * GGTT offsets in their payloads.
+ * @ct: pointer to CT struct of the target GuC
+ * @ggtt_shift: shift to be added to all GGTT addresses within the CTB
+ */
+void xe_guc_ct_fixup_messages_with_ggtt(struct xe_guc_ct *ct, s64 ggtt_shift)
+{
+	struct xe_guc *guc = ct_to_guc(ct);
+	struct xe_gt *gt = guc_to_gt(guc);
+	struct guc_ctb *h2g = &ct->ctbs.h2g;
+	u32 head, tail, size;
+	s32 avail;
+
+	if (unlikely(h2g->info.broken))
+		return;
+
+	h2g->info.head = desc_read(ct_to_xe(ct), h2g, head);
+	head = h2g->info.head;
+	tail = READ_ONCE(h2g->info.tail);
+	size = h2g->info.size;
+
+	if (unlikely(head > size))
+		goto corrupted;
+
+	if (unlikely(tail >= size))
+		goto corrupted;
+
+	avail = tail - head;
+
+	/* beware of buffer wrap case */
+	if (unlikely(avail < 0))
+		avail += size;
+	xe_gt_dbg(gt, "available %d (%u:%u:%u)\n", avail, head, tail, size);
+	xe_gt_assert(gt, avail >= 0);
+
+	while (avail > 0)
+		avail = ct_update_addresses_in_buffer(ct, h2g, ggtt_shift, &head, avail);
+
+	return;
+
+corrupted:
+	xe_gt_err(gt, "Corrupted H2G descriptor head=%u tail=%u size=%u, fixups not applied\n",
+		 head, tail, size);
+	h2g->info.broken = true;
+}
+
 static struct xe_guc_ct_snapshot *guc_ct_snapshot_alloc(struct xe_guc_ct *ct, bool atomic,
 							bool want_ctb)
 {
drivers/gpu/drm/xe/xe_guc_ct.h +2 -0
index 82c4ae458dda..5649bda82823 100644
@@ -22,6 +22,8 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot, struct drm_pr
 void xe_guc_ct_snapshot_free(struct xe_guc_ct_snapshot *snapshot);
 void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool want_ctb);
 
+void xe_guc_ct_fixup_messages_with_ggtt(struct xe_guc_ct *ct, s64 ggtt_shift);
+
 static inline bool xe_guc_ct_enabled(struct xe_guc_ct *ct)
 {
 	return ct->state == XE_GUC_CT_STATE_ENABLED;
drivers/gpu/drm/xe/xe_sriov_vf.c +25 -0
index 2eb6b8d8a217..9a1b578fdd03 100644
@@ -10,6 +10,7 @@
 #include "xe_gt.h"
 #include "xe_gt_sriov_printk.h"
 #include "xe_gt_sriov_vf.h"
+#include "xe_guc_ct.h"
 #include "xe_pm.h"
 #include "xe_sriov.h"
 #include "xe_sriov_printk.h"
@@ -158,6 +159,27 @@ static int vf_post_migration_requery_guc(struct xe_device *xe)
 	return ret;
 }
 
+static s32 xe_gt_sriov_vf_ggtt_shift(struct xe_gt *gt)
+{
+	struct xe_gt_sriov_vf_selfconfig *config = &gt->sriov.vf.self_config;
+
+	return config->ggtt_shift;
+}
+
+static void vf_post_migration_fixup_ctb(struct xe_device *xe)
+{
+	struct xe_gt *gt;
+	unsigned int id;
+
+	xe_assert(xe, IS_SRIOV_VF(xe));
+
+	for_each_gt(gt, xe, id) {
+		s32 shift = xe_gt_sriov_vf_ggtt_shift(gt);
+
+		xe_guc_ct_fixup_messages_with_ggtt(&gt->uc.guc.ct, shift);
+	}
+}
+
 /*
  * vf_post_migration_imminent - Check if post-restore recovery is coming.
  * @xe: the &xe_device struct instance
@@ -219,6 +241,9 @@ static void vf_post_migration_recovery(struct xe_device *xe)
 
 	need_fixups = vf_post_migration_fixup_ggtt_nodes(xe);
 	/* FIXME: add the recovery steps */
+	if (need_fixups)
+		vf_post_migration_fixup_ctb(xe);
+
 	vf_post_migration_notify_resfix_done(xe);
 	xe_pm_runtime_put(xe);
 	drm_notice(&xe->drm, "migration recovery ended\n");
Signature · 1 line
2.25.1