[PATCH v7 15/16] virt: geniezone: Add memory pin/unpin support

[Yi-De Wu <yi-de.wu@mediatek.com>]

From: "Jerry Wang" <ze-yu.wang@mediatek.com>

Protected VM's memory cannot be swapped out because the memory pages are
protected from host access.

Once host accesses to those protected pages, the hardware exception is
triggered and may crash the host. So, we have to make those protected
pages be ineligible for swapping or merging by the host kernel to avoid
host access. To do so, we pin the page when it is assigned (donated) to
VM and unpin when VM relinquish the pages or is destroyed. Besides, the
protected VM’s memory requires hypervisor to clear the content before
returning to host, but VMM may free those memory before clearing, it
will result in those memory pages are reclaimed and reused before
totally clearing. Using pin/unpin can also avoid the above problems.

The implementation is described as follows.
- Use rb_tree to store pinned memory pages.
- Pin the page when handling page fault.
- Unpin the pages when VM relinquish the pages or is destroyed.

Signed-off-by: Jerry Wang <ze-yu.wang@mediatek.com>
Signed-off-by: Yingshiuan Pan <yingshiuan.pan@mediatek.com>
Signed-off-by: Yi-De Wu <yi-de.wu@mediatek.com>
Signed-off-by: Liju Chen <liju-clr.chen@mediatek.com>
---
 drivers/virt/geniezone/gzvm_mmu.c | 60 ++++++++++++++++++++++++++++++-
 drivers/virt/geniezone/gzvm_vm.c  | 18 ++++++++++
 include/linux/gzvm_drv.h          | 10 ++++++
 3 files changed, 87 insertions(+), 1 deletion(-)

diff --git a/drivers/virt/geniezone/gzvm_mmu.c b/drivers/virt/geniezone/gzvm_mmu.c
index 77104df4afe5..0acef342e1f0 100644
--- a/drivers/virt/geniezone/gzvm_mmu.c
+++ b/drivers/virt/geniezone/gzvm_mmu.c
@@ -107,8 +107,59 @@ int gzvm_gfn_to_pfn_memslot(struct gzvm_memslot *memslot, u64 gfn,
 	return 0;
 }
 
+static int cmp_ppages(struct rb_node *node, const struct rb_node *parent)
+{
+	struct gzvm_pinned_page *a = container_of(node,
+						  struct gzvm_pinned_page,
+						  node);
+	struct gzvm_pinned_page *b = container_of(parent,
+						  struct gzvm_pinned_page,
+						  node);
+
+	if (a->ipa < b->ipa)
+		return -1;
+	if (a->ipa > b->ipa)
+		return 1;
+	return 0;
+}
+
+static int gzvm_insert_ppage(struct gzvm *vm, struct gzvm_pinned_page *ppage)
+{
+	if (rb_find_add(&ppage->node, &vm->pinned_pages, cmp_ppages))
+		return -EEXIST;
+	return 0;
+}
+
+static int pin_one_page(struct gzvm *vm, unsigned long hva, u64 gpa)
+{
+	unsigned int flags = FOLL_HWPOISON | FOLL_LONGTERM | FOLL_WRITE;
+	struct gzvm_pinned_page *ppage = NULL;
+	struct mm_struct *mm = current->mm;
+	struct page *page = NULL;
+
+	ppage = kmalloc(sizeof(*ppage), GFP_KERNEL_ACCOUNT);
+	if (!ppage)
+		return -ENOMEM;
+
+	mmap_read_lock(mm);
+	pin_user_pages(hva, 1, flags, &page);
+	mmap_read_unlock(mm);
+
+	if (!page) {
+		kfree(ppage);
+		return -EFAULT;
+	}
+
+	ppage->page = page;
+	ppage->ipa = gpa;
+	gzvm_insert_ppage(vm, ppage);
+
+	return 0;
+}
+
 static int handle_block_demand_page(struct gzvm *vm, int memslot_id, u64 gfn)
 {
+	unsigned long hva;
 	u64 pfn, __gfn;
 	int ret, i;
 
@@ -131,6 +182,11 @@ static int handle_block_demand_page(struct gzvm *vm, int memslot_id, u64 gfn)
 			goto err_unlock;
 		}
 		vm->demand_page_buffer[i] = pfn;
+
+		hva = gzvm_gfn_to_hva_memslot(&vm->memslot[memslot_id], __gfn);
+		ret = pin_one_page(vm, hva, PFN_PHYS(__gfn));
+		if (ret)
+			goto err_unlock;
 	}
 
 	ret = gzvm_arch_map_guest_block(vm->vm_id, memslot_id, start_gfn,
@@ -148,6 +204,7 @@ static int handle_block_demand_page(struct gzvm *vm, int memslot_id, u64 gfn)
 
 static int handle_single_demand_page(struct gzvm *vm, int memslot_id, u64 gfn)
 {
+	unsigned long hva;
 	int ret;
 	u64 pfn;
 
@@ -159,7 +216,8 @@ static int handle_single_demand_page(struct gzvm *vm, int memslot_id, u64 gfn)
 	if (unlikely(ret))
 		return -EFAULT;
 
-	return 0;
+	hva = gzvm_gfn_to_hva_memslot(&vm->memslot[memslot_id], gfn);
+	return pin_one_page(vm, hva, PFN_PHYS(gfn));
 }
 
 /**
diff --git a/drivers/virt/geniezone/gzvm_vm.c b/drivers/virt/geniezone/gzvm_vm.c
index 485d1e2097aa..a7d43bedfad0 100644
--- a/drivers/virt/geniezone/gzvm_vm.c
+++ b/drivers/virt/geniezone/gzvm_vm.c
@@ -292,6 +292,21 @@ static long gzvm_vm_ioctl(struct file *filp, unsigned int ioctl,
 	return ret;
 }
 
+static void gzvm_destroy_ppage(struct gzvm *gzvm)
+{
+	struct gzvm_pinned_page *ppage;
+	struct rb_node *node;
+
+	node = rb_first(&gzvm->pinned_pages);
+	while (node) {
+		ppage = rb_entry(node, struct gzvm_pinned_page, node);
+		unpin_user_pages_dirty_lock(&ppage->page, 1, true);
+		node = rb_next(node);
+		rb_erase(&ppage->node, &gzvm->pinned_pages);
+		kfree(ppage);
+	}
+}
+
 static void gzvm_destroy_vm(struct gzvm *gzvm)
 {
 	size_t allocated_size;
@@ -315,6 +330,8 @@ static void gzvm_destroy_vm(struct gzvm *gzvm)
 
 	mutex_unlock(&gzvm->lock);
 
+	gzvm_destroy_ppage(gzvm);
+
 	kfree(gzvm);
 }
 
@@ -390,6 +407,7 @@ static struct gzvm *gzvm_create_vm(unsigned long vm_type)
 	gzvm->vm_id = ret;
 	gzvm->mm = current->mm;
 	mutex_init(&gzvm->lock);
+	gzvm->pinned_pages = RB_ROOT;
 
 	ret = gzvm_vm_irqfd_init(gzvm);
 	if (ret) {
diff --git a/include/linux/gzvm_drv.h b/include/linux/gzvm_drv.h
index 0a8b21e1ed1a..bb470a9f92e4 100644
--- a/include/linux/gzvm_drv.h
+++ b/include/linux/gzvm_drv.h
@@ -12,6 +12,7 @@
 #include <linux/mutex.h>
 #include <linux/gzvm.h>
 #include <linux/srcu.h>
+#include <linux/rbtree.h>
 
 /*
  * For the normal physical address, the highest 12 bits should be zero, so we
@@ -82,6 +83,12 @@ struct gzvm_vcpu {
 	struct gzvm_vcpu_hwstate *hwstate;
 };
 
+struct gzvm_pinned_page {
+	struct rb_node node;
+	struct page *page;
+	u64 ipa;
+};
+
 struct gzvm {
 	struct gzvm_vcpu *vcpus[GZVM_MAX_VCPUS];
 	/* userspace tied to this vm */
@@ -121,6 +128,9 @@ struct gzvm {
 	 * at the same time
 	 */
 	struct mutex  demand_paging_lock;
+
+	/* Use rb-tree to record pin/unpin page */
+	struct rb_root pinned_pages;
 };
 
 long gzvm_dev_ioctl_check_extension(struct gzvm *gzvm, unsigned long args);
-- 
2.18.0