[PATCH v7 2/2] drm/i915/gvt: Fix guest i915 48bit full ppgtt blocking issue

[Zhenyu Wang]

From: Tina Zhang <tina.zhang at intel.com>

Guest i915 48bit full ppgtt functionality was blocking by an issue, which
would lead to gpu hardware hang. Guest i915 driver may update the ppgtt
table just before this workload is going to be submitted to the hardware
by device model. This case wasn't handled well by device model before, due
to the small time window between removing old ppgtt entry and adding the
new one. Errors occur when the workload is executed by hardware during
that small time window. This patch is to remove this time window by adding
the new ppgtt entry first and then remove the old one.

Changes in v2:
- Move VGT_CAPS_FULL_PPGTT introduction to patch 2/4. (Joonas)

Changes since v2:
- Divide the whole patch set into two separate patch series, with one
  patch in i915 side to check guest i915 full ppgtt capability and enable
  it when this capability is supported by the device model, and the other
  one in gvt side which fixs the blocking issue and enables the device
  model to provide the capability to guest. And this patch focuses on gvt
  side. (Joonas)
- Change the title from "reorder the shadow ppgtt update process by adding
  entry first" to "Fix guest i915 full ppgtt blocking issue". (Tina)

Changes since v3:
- Rebase to the latest branch.

Changes since v4:
- Tested by Tina Zhang.

Changes since v5:
- Rebase to the latest branch.

Signed-off-by: Tina Zhang <tina.zhang at intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw at linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c  | 45 +++++++++++++++++++++++++----------------
 drivers/gpu/drm/i915/gvt/vgpu.c |  1 +
 2 files changed, 29 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 6166e34d892b..27bda426d42e 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -979,29 +979,26 @@ static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
 }
 
 static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_guest_page *gpt,
-		unsigned long index)
+		struct intel_gvt_gtt_entry *se, unsigned long index)
 {
 	struct intel_vgpu_ppgtt_spt *spt = guest_page_to_ppgtt_spt(gpt);
 	struct intel_vgpu_shadow_page *sp = &spt->shadow_page;
 	struct intel_vgpu *vgpu = spt->vgpu;
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
-	struct intel_gvt_gtt_entry e;
 	int ret;
 
-	ppgtt_get_shadow_entry(spt, &e, index);
-
-	trace_gpt_change(spt->vgpu->id, "remove", spt, sp->type, e.val64,
+	trace_gpt_change(spt->vgpu->id, "remove", spt, sp->type, se->val64,
 			 index);
 
-	if (!ops->test_present(&e))
+	if (!ops->test_present(se))
 		return 0;
 
-	if (ops->get_pfn(&e) == vgpu->gtt.scratch_pt[sp->type].page_mfn)
+	if (ops->get_pfn(se) == vgpu->gtt.scratch_pt[sp->type].page_mfn)
 		return 0;
 
-	if (gtt_type_is_pt(get_next_pt_type(e.type))) {
+	if (gtt_type_is_pt(get_next_pt_type(se->type))) {
 		struct intel_vgpu_ppgtt_spt *s =
-			ppgtt_find_shadow_page(vgpu, ops->get_pfn(&e));
+			ppgtt_find_shadow_page(vgpu, ops->get_pfn(se));
 		if (!s) {
 			gvt_vgpu_err("fail to find guest page\n");
 			ret = -ENXIO;
@@ -1011,12 +1008,10 @@ static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_guest_page *gpt,
 		if (ret)
 			goto fail;
 	}
-	ops->set_pfn(&e, vgpu->gtt.scratch_pt[sp->type].page_mfn);
-	ppgtt_set_shadow_entry(spt, &e, index);
 	return 0;
 fail:
 	gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
-			spt, e.val64, e.type);
+			spt, se->val64, se->type);
 	return ret;
 }
 
@@ -1236,22 +1231,37 @@ static int ppgtt_handle_guest_write_page_table(
 {
 	struct intel_vgpu_ppgtt_spt *spt = guest_page_to_ppgtt_spt(gpt);
 	struct intel_vgpu *vgpu = spt->vgpu;
+	int type = spt->shadow_page.type;
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	struct intel_gvt_gtt_entry se;
 
 	int ret;
 	int new_present;
 
 	new_present = ops->test_present(we);
 
-	ret = ppgtt_handle_guest_entry_removal(gpt, index);
-	if (ret)
-		goto fail;
+	/*
+	 * Adding the new entry first and then removing the old one, that can
+	 * guarantee the ppgtt table is validated during the window between
+	 * adding and removal.
+	 */
+	ppgtt_get_shadow_entry(spt, &se, index);
 
 	if (new_present) {
 		ret = ppgtt_handle_guest_entry_add(gpt, we, index);
 		if (ret)
 			goto fail;
 	}
+
+	ret = ppgtt_handle_guest_entry_removal(gpt, &se, index);
+	if (ret)
+		goto fail;
+
+	if (!new_present) {
+		ops->set_pfn(&se, vgpu->gtt.scratch_pt[type].page_mfn);
+		ppgtt_set_shadow_entry(spt, &se, index);
+	}
+
 	return 0;
 fail:
 	gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d.\n",
@@ -1323,7 +1333,7 @@ static int ppgtt_handle_guest_write_page_table_bytes(void *gp,
 	struct intel_vgpu *vgpu = spt->vgpu;
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	const struct intel_gvt_device_info *info = &vgpu->gvt->device_info;
-	struct intel_gvt_gtt_entry we;
+	struct intel_gvt_gtt_entry we, se;
 	unsigned long index;
 	int ret;
 
@@ -1339,7 +1349,8 @@ static int ppgtt_handle_guest_write_page_table_bytes(void *gp,
 			return ret;
 	} else {
 		if (!test_bit(index, spt->post_shadow_bitmap)) {
-			ret = ppgtt_handle_guest_entry_removal(gpt, index);
+			ppgtt_get_shadow_entry(spt, &se, index);
+			ret = ppgtt_handle_guest_entry_removal(gpt, &se, index);
 			if (ret)
 				return ret;
 		}
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 90c14e6e3ea0..73f47c12bb9f 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -43,6 +43,7 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu)
 	vgpu_vreg(vgpu, vgtif_reg(version_minor)) = 0;
 	vgpu_vreg(vgpu, vgtif_reg(display_ready)) = 0;
 	vgpu_vreg(vgpu, vgtif_reg(vgt_id)) = vgpu->id;
+	vgpu_vreg(vgpu, vgtif_reg(vgt_caps)) = VGT_CAPS_FULL_PPGTT_48BIT;
 	vgpu_vreg(vgpu, vgtif_reg(avail_rs.mappable_gmadr.base)) =
 		vgpu_aperture_gmadr_base(vgpu);
 	vgpu_vreg(vgpu, vgtif_reg(avail_rs.mappable_gmadr.size)) =
-- 
2.11.0