drm/i915/gvt: Add shadow context descriptor updating

The current context logic only updates the descriptor of context when
it's being pinned to graphics memory space. But this cannot satisfy the
requirement of shadow context. The addressing mode of the pinned shadow
context descriptor may be changed according to the guest addressing mode.
And this won't be updated, as the already pinned shadow context has no
chance to update its descriptor. And this will lead to GPU hang issue,
as shadow context is used with wrong descriptor. This patch fixes this
issue by letting the pinned shadow context descriptor update its
addressing mode on demand.

This patch fixes GPU HANG issue which happends after changing the
grub parameter i915.enable_ppgtt form 0x01 to 0x03 or vice versa and
then rebooting the guest.

Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Kechen Lu <kechen.lu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drivers/gpu/drm/i915/gvt/execlist.c

@@ -796,6 +796,8 @@ static void clean_workloads(struct intel_vgpu *vgpu, unsigned long engine_mask)
 			list_del_init(&pos->list);
 			free_workload(pos);
 		}
+
+		clear_bit(engine->id, vgpu->shadow_ctx_desc_updated);
 	}
 }
 

drivers/gpu/drm/i915/gvt/gvt.h

@@ -167,6 +167,7 @@ struct intel_vgpu {
 	atomic_t running_workload_num;
 	DECLARE_BITMAP(tlb_handle_pending, I915_NUM_ENGINES);
 	struct i915_gem_context *shadow_ctx;
+	DECLARE_BITMAP(shadow_ctx_desc_updated, I915_NUM_ENGINES);
 
 #if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT)
 	struct {

drivers/gpu/drm/i915/gvt/scheduler.c

@@ -184,6 +184,23 @@ static int shadow_context_status_change(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
+		struct intel_engine_cs *engine)
+{
+	struct intel_context *ce = &ctx->engine[engine->id];
+	u64 desc = 0;
+
+	desc = ce->lrc_desc;
+
+	/* Update bits 0-11 of the context descriptor which includes flags
+	 * like GEN8_CTX_* cached in desc_template
+	 */
+	desc &= U64_MAX << 12;
+	desc |= ctx->desc_template & ((1ULL << 12) - 1);
+
+	ce->lrc_desc = desc;
+}
+
 /**
  * intel_gvt_scan_and_shadow_workload - audit the workload by scanning and
  * shadow it as well, include ringbuffer,wa_ctx and ctx.
@@ -210,6 +227,10 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 	shadow_ctx->desc_template |= workload->ctx_desc.addressing_mode <<
 				    GEN8_CTX_ADDRESSING_MODE_SHIFT;
 
+	if (!test_and_set_bit(ring_id, vgpu->shadow_ctx_desc_updated))
+		shadow_context_descriptor_update(shadow_ctx,
+					dev_priv->engine[ring_id]);
+
 	rq = i915_gem_request_alloc(dev_priv->engine[ring_id], shadow_ctx);
 	if (IS_ERR(rq)) {
 		gvt_vgpu_err("fail to allocate gem request\n");
@@ -656,5 +677,7 @@ int intel_vgpu_init_gvt_context(struct intel_vgpu *vgpu)
 
 	vgpu->shadow_ctx->engine[RCS].initialised = true;
 
+	bitmap_zero(vgpu->shadow_ctx_desc_updated, I915_NUM_ENGINES);
+
 	return 0;
 }