[PATCH v7 9/9] drm/xe/vf: Rebase exec queue parallel commands during migration recovery

[Tomasz Lis]

Parallel exec queues have an additional command streamer buffer which holds
a GGTT reference to data within context status. The GGTT references have to
be fixed after VF migration.

v2: Properly handle nop entry, verify if parsing goes ok

Signed-off-by: Tomasz Lis <tomasz.lis at intel.com>
Cc: Michal Winiarski <michal.winiarski at intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 43 +++++++++++++++++++++++++++++-
 1 file changed, 42 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 84bc352f6f12..9eb0fd863218 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -693,6 +693,44 @@ static void wq_item_append(struct xe_exec_queue *q)
 	parallel_write(xe, map, wq_desc.tail, q->guc->wqi_tail);
 }
 
+static void wq_items_rebase(struct xe_exec_queue *q)
+{
+	struct xe_guc *guc = exec_queue_to_guc(q);
+	struct xe_device *xe = guc_to_xe(guc);
+	struct iosys_map map = xe_lrc_parallel_map(q->lrc[0]);
+	int i = q->guc->wqi_head;
+
+	/* the ring starts after a header struct */
+	iosys_map_incr(&map, offsetof(struct guc_submit_parallel_scratch, wq[0]));
+
+	while ((i % WQ_SIZE) != (q->guc->wqi_tail % WQ_SIZE)) {
+		u32 len_dw, type, val;
+
+		if (i < 0 || i > 2 * WQ_SIZE)
+			break;
+
+		val = xe_map_rd_ring_u32(xe, &map, i / sizeof(u32) + 0, WQ_SIZE / sizeof(u32));
+		len_dw = FIELD_GET(WQ_LEN_MASK, val);
+		type = FIELD_GET(WQ_TYPE_MASK, val);
+
+		if (len_dw >= WQ_SIZE / sizeof(u32))
+			break;
+
+		if (type == WQ_TYPE_MULTI_LRC) {
+			val = xe_lrc_descriptor(q->lrc[0]);
+			xe_map_wr_ring_u32(xe, &map, i / sizeof(u32) + 1,
+					   WQ_SIZE / sizeof(u32), val);
+		} else if (type != WQ_TYPE_NOOP) {
+			break;
+		}
+
+		i += (len_dw + 1) * sizeof(u32);
+	}
+
+	if (i != q->guc->wqi_tail)
+		xe_gt_err(q->gt, "Exec queue fixups incomplete - wqi parse failed\n");
+}
+
 #define RESUME_PENDING	~0x0ull
 static void submit_exec_queue(struct xe_exec_queue *q)
 {
@@ -2506,7 +2544,10 @@ void xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch)
 	unsigned long index;
 
 	mutex_lock(&guc->submission_state.lock);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
 		xe_exec_queue_contexts_hwsp_rebase(q, scratch);
+		if (xe_exec_queue_is_parallel(q))
+			wq_items_rebase(q);
+	}
 	mutex_unlock(&guc->submission_state.lock);
 }
-- 
2.25.1