From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:41 +0800
Subject: drm/i915/gvt: Add 64K huge gtt support
Git-commit: eb3a353014d2c2402e572ab7bef86bf5e328160f
Patch-mainline: v4.19-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166

Finally, this add the first huge gtt support for GVTg - 64K pages. Since
64K page and 4K page cannot be mixed on the same page table, so we always
split a 64K entry into small 4K page. And when unshadow guest 64K entry,
we need ensure all the shadowed entries in shadow page table also get
cleared.

For page table which has 64K gtt entry, only PTE#0, PTE#16, PTE#32, ...
PTE#496 are used. Unused PTEs update should be ignored.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c |   86 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 80 insertions(+), 6 deletions(-)

--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -978,9 +978,12 @@ static int ppgtt_invalidate_spt(struct i
 			ppgtt_invalidate_pte(spt, &e);
 			break;
 		case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+			/* We don't setup 64K shadow entry so far. */
+			WARN(1, "suspicious 64K gtt entry\n");
+			continue;
 		case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
 		case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-			WARN(1, "GVT doesn't support 64K/2M/1GB page\n");
+			WARN(1, "GVT doesn't support 2M/1GB page\n");
 			continue;
 		case GTT_TYPE_PPGTT_PML4_ENTRY:
 		case GTT_TYPE_PPGTT_PDP_ENTRY:
@@ -1075,9 +1078,44 @@ static inline void ppgtt_generate_shadow
 	se->type = ge->type;
 	se->val64 = ge->val64;
 
+	/* Because we always split 64KB pages, so clear IPS in shadow PDE. */
+	if (se->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+		ops->clear_ips(se);
+
 	ops->set_pfn(se, s->shadow_page.mfn);
 }
 
+static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
+	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
+	struct intel_gvt_gtt_entry *se)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	struct intel_gvt_gtt_entry entry = *se;
+	unsigned long start_gfn;
+	dma_addr_t dma_addr;
+	int i, ret;
+
+	gvt_vdbg_mm("Split 64K gtt entry, index %lu\n", index);
+
+	GEM_BUG_ON(index % GTT_64K_PTE_STRIDE);
+
+	start_gfn = ops->get_pfn(se);
+
+	entry.type = GTT_TYPE_PPGTT_PTE_4K_ENTRY;
+	ops->set_64k_splited(&entry);
+
+	for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
+						start_gfn + i, &dma_addr);
+		if (ret)
+			return ret;
+
+		ops->set_pfn(&entry, dma_addr >> PAGE_SHIFT);
+		ppgtt_set_shadow_entry(spt, &entry, index + i);
+	}
+	return 0;
+}
+
 static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
 	struct intel_gvt_gtt_entry *ge)
@@ -1098,9 +1136,16 @@ static int ppgtt_populate_shadow_entry(s
 		gvt_vdbg_mm("shadow 4K gtt entry\n");
 		break;
 	case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+		gvt_vdbg_mm("shadow 64K gtt entry\n");
+		/*
+		 * The layout of 64K page is special, the page size is
+		 * controlled by uper PDE. To be simple, we always split
+		 * 64K page to smaller 4K pages in shadow PT.
+		 */
+		return split_64KB_gtt_entry(vgpu, spt, index, &se);
 	case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
 	case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-		gvt_vgpu_err("GVT doesn't support 64K/2M/1GB entry\n");
+		gvt_vgpu_err("GVT doesn't support 2M/1GB entry\n");
 		return -EINVAL;
 	default:
 		GEM_BUG_ON(1);
@@ -1190,8 +1235,12 @@ static int ppgtt_handle_guest_entry_remo
 		ret = ppgtt_invalidate_spt(s);
 		if (ret)
 			goto fail;
-	} else
+	} else {
+		/* We don't setup 64K shadow entry so far. */
+		WARN(se->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY,
+		     "suspicious 64K entry\n");
 		ppgtt_invalidate_pte(spt, se);
+	}
 
 	return 0;
 fail:
@@ -1414,7 +1463,7 @@ static int ppgtt_handle_guest_write_page
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_gvt_gtt_entry old_se;
 	int new_present;
-	int ret;
+	int i, ret;
 
 	new_present = ops->test_present(we);
 
@@ -1436,8 +1485,21 @@ static int ppgtt_handle_guest_write_page
 		goto fail;
 
 	if (!new_present) {
-		ops->set_pfn(&old_se, vgpu->gtt.scratch_pt[type].page_mfn);
-		ppgtt_set_shadow_entry(spt, &old_se, index);
+		/* For 64KB splited entries, we need clear them all. */
+		if (ops->test_64k_splited(&old_se) &&
+		    !(index % GTT_64K_PTE_STRIDE)) {
+			gvt_vdbg_mm("remove splited 64K shadow entries\n");
+			for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+				ops->clear_64k_splited(&old_se);
+				ops->set_pfn(&old_se,
+					vgpu->gtt.scratch_pt[type].page_mfn);
+				ppgtt_set_shadow_entry(spt, &old_se, index + i);
+			}
+		} else {
+			ops->set_pfn(&old_se,
+				     vgpu->gtt.scratch_pt[type].page_mfn);
+			ppgtt_set_shadow_entry(spt, &old_se, index);
+		}
 	}
 
 	return 0;
@@ -1519,6 +1581,18 @@ static int ppgtt_handle_guest_write_page
 
 	ppgtt_get_guest_entry(spt, &we, index);
 
+	/*
+	 * For page table which has 64K gtt entry, only PTE#0, PTE#16,
+	 * PTE#32, ... PTE#496 are used. Unused PTEs update should be
+	 * ignored.
+	 */
+	if (we.type == GTT_TYPE_PPGTT_PTE_64K_ENTRY &&
+	    (index % GTT_64K_PTE_STRIDE)) {
+		gvt_vdbg_mm("Ignore write to unused PTE entry, index %lu\n",
+			    index);
+		return 0;
+	}
+
 	if (bytes == info->gtt_entry_size) {
 		ret = ppgtt_handle_guest_write_page_table(spt, &we, index);
 		if (ret)