[PATCH 05/10] KVM: Create architecture independent ROE skeleton

[Ahmed Abd El Mawgood]

This patch introduces a hypercall that can assist against subset of kernel
rootkits, it works by place readonly protection in shadow PTE. The end
result protection is also kept in a bitmap for each kvm_memory_slot and is
used as reference when updating SPTEs. The whole goal is to protect the
guest kernel static data from modification if attacker is running from
guest ring 0, for this reason there is no hypercall to revert effect of
Memory ROE hypercall. This patch doesn't implement integrity check on guest
TLB so obvious attack on the current implementation will involve guest
virtual address -> guest physical address remapping, but there are plans to
fix that. For this patch to work on a given arch/ one would need to
implement 2 function that are architecture specific:
kvm_roe_arch_commit_protection() and kvm_roe_arch_is_userspace(). Also it
would need to have kvm_roe invoked using the appropriate hypercall
mechanism.

Signed-off-by: Ahmed Abd El Mawgood <ahmedsoliman@xxxxxxxxxxx>
---
 include/kvm/roe.h             |  16 ++++
 include/linux/kvm_host.h      |   1 +
 include/uapi/linux/kvm_para.h |   4 +
 virt/kvm/kvm_main.c           |  19 +++--
 virt/kvm/roe.c                | 136 ++++++++++++++++++++++++++++++++++
 virt/kvm/roe_generic.h        |  19 +++++
 6 files changed, 190 insertions(+), 5 deletions(-)
 create mode 100644 include/kvm/roe.h
 create mode 100644 virt/kvm/roe.c
 create mode 100644 virt/kvm/roe_generic.h

diff --git a/include/kvm/roe.h b/include/kvm/roe.h
new file mode 100644
index 0000000000..6a86866623
--- /dev/null
+++ b/include/kvm/roe.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __KVM_ROE_H__
+#define __KVM_ROE_H__
+/*
+ * KVM Read Only Enforcement
+ * Copyright (c) 2018 Ahmed Abd El Mawgood
+ *
+ * Author Ahmed Abd El Mawgood <ahmedsoliman@xxxxxxxxxxx>
+ *
+ */
+void kvm_roe_arch_commit_protection(struct kvm *kvm,
+		struct kvm_memory_slot *slot);
+int kvm_roe(struct kvm_vcpu *vcpu, u64 a0, u64 a1, u64 a2, u64 a3);
+bool kvm_roe_arch_is_userspace(struct kvm_vcpu *vcpu);
+#endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c926698040..0baea5afcd 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -297,6 +297,7 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
 struct kvm_memory_slot {
 	gfn_t base_gfn;
 	unsigned long npages;
+	unsigned long *roe_bitmap;
 	unsigned long *dirty_bitmap;
 	struct kvm_arch_memory_slot arch;
 	unsigned long userspace_addr;
diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h
index 6c0ce49931..e6004e0750 100644
--- a/include/uapi/linux/kvm_para.h
+++ b/include/uapi/linux/kvm_para.h
@@ -28,7 +28,11 @@
 #define KVM_HC_MIPS_CONSOLE_OUTPUT	8
 #define KVM_HC_CLOCK_PAIRING		9
 #define KVM_HC_SEND_IPI		10
+#define KVM_HC_ROE			11
 
+/* ROE Functionality parameters */
+#define ROE_VERSION			0
+#define ROE_MPROTECT			1
 /*
  * hypercalls use architecture specific
  */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 039c1ef9a7..814ee0fd35 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -61,6 +61,7 @@
 #include "coalesced_mmio.h"
 #include "async_pf.h"
 #include "vfio.h"
+#include "roe_generic.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
@@ -552,9 +553,10 @@ static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			      struct kvm_memory_slot *dont,
 			      enum kvm_mr_change change)
 {
-	if (change == KVM_MR_DELETE)
+	if (change == KVM_MR_DELETE) {
+		kvm_roe_free(free);
 		kvm_destroy_dirty_bitmap(free);
-
+	}
 	kvm_arch_free_memslot(kvm, free, dont);
 
 	free->npages = 0;
@@ -1020,6 +1022,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if (kvm_create_dirty_bitmap(&new) < 0)
 			goto out_free;
 	}
+	if (kvm_roe_init(&new) < 0)
+		goto out_free;
 
 	slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 	if (!slots)
@@ -1273,13 +1277,18 @@ static bool memslot_is_readonly(struct kvm_memory_slot *slot)
 	return slot->flags & KVM_MEM_READONLY;
 }
 
+static bool gfn_is_readonly(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return gfn_is_full_roe(slot, gfn) || memslot_is_readonly(slot);
+}
+
 static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
 				       gfn_t *nr_pages, bool write)
 {
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return KVM_HVA_ERR_BAD;
 
-	if (memslot_is_readonly(slot) && write)
+	if (gfn_is_readonly(slot, gfn) && write)
 		return KVM_HVA_ERR_RO_BAD;
 
 	if (nr_pages)
@@ -1327,7 +1336,7 @@ unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
 	unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false);
 
 	if (!kvm_is_error_hva(hva) && writable)
-		*writable = !memslot_is_readonly(slot);
+		*writable = !gfn_is_readonly(slot, gfn);
 
 	return hva;
 }
@@ -1565,7 +1574,7 @@ kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
 	}
 
 	/* Do not map writable pfn in the readonly memslot. */
-	if (writable && memslot_is_readonly(slot)) {
+	if (writable && gfn_is_readonly(slot, gfn)) {
 		*writable = false;
 		writable = NULL;
 	}
diff --git a/virt/kvm/roe.c b/virt/kvm/roe.c
new file mode 100644
index 0000000000..3f6eb6ede2
--- /dev/null
+++ b/virt/kvm/roe.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * KVM Read Only Enforcement
+ * Copyright (c) 2018 Ahmed Abd El Mawgood
+ *
+ * Author: Ahmed Abd El Mawgood <ahmedsoliman@xxxxxxxxxxx>
+ *
+ */
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/kvm_para.h>
+#include <kvm/roe.h>
+
+int kvm_roe_init(struct kvm_memory_slot *slot)
+{
+	slot->roe_bitmap = kvzalloc(BITS_TO_LONGS(slot->npages) *
+			sizeof(unsigned long), GFP_KERNEL);
+	if (!slot->roe_bitmap)
+		return -ENOMEM;
+	return 0;
+
+}
+
+void kvm_roe_free(struct kvm_memory_slot *slot)
+{
+	kvfree(slot->roe_bitmap);
+}
+
+static void kvm_roe_protect_slot(struct kvm *kvm, struct kvm_memory_slot *slot,
+		gfn_t gfn, u64 npages)
+{
+	int i;
+
+	for (i = gfn - slot->base_gfn; i < gfn + npages - slot->base_gfn; i++)
+		set_bit(i, slot->roe_bitmap);
+	kvm_roe_arch_commit_protection(kvm, slot);
+}
+
+
+static int __kvm_roe_protect_range(struct kvm *kvm, gpa_t gpa, u64 npages)
+{
+	struct kvm_memory_slot *slot;
+	gfn_t gfn = gpa >> PAGE_SHIFT;
+	int count = 0;
+
+	while (npages != 0) {
+		slot = gfn_to_memslot(kvm, gfn);
+		if (!slot) {
+			gfn += 1;
+			npages -= 1;
+			continue;
+		}
+		if (gfn + npages > slot->base_gfn + slot->npages) {
+			u64 _npages = slot->base_gfn + slot->npages - gfn;
+
+			kvm_roe_protect_slot(kvm, slot, gfn, _npages);
+			gfn += _npages;
+			count += _npages;
+			npages -= _npages;
+		} else {
+			kvm_roe_protect_slot(kvm, slot, gfn, npages);
+			count += npages;
+			npages = 0;
+		}
+	}
+	if (count == 0)
+		return -EINVAL;
+	return count;
+}
+
+static int kvm_roe_protect_range(struct kvm *kvm, gpa_t gpa, u64 npages)
+{
+	int r;
+
+	mutex_lock(&kvm->slots_lock);
+	r = __kvm_roe_protect_range(kvm, gpa, npages);
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
+
+static int kvm_roe_full_protect_range(struct kvm_vcpu *vcpu, u64 gva,
+		u64 npages)
+{
+	struct kvm *kvm = vcpu->kvm;
+	gpa_t gpa;
+	u64 hva;
+	u64 count = 0;
+	int i;
+	int status;
+
+	if (gva & ~PAGE_MASK)
+		return -EINVAL;
+	// We need to make sure that there will be no overflow
+	if ((npages << PAGE_SHIFT) >> PAGE_SHIFT != npages || npages == 0)
+		return -EINVAL;
+	for (i = 0; i < npages; i++) {
+		gpa = kvm_mmu_gva_to_gpa_system(vcpu, gva + (i << PAGE_SHIFT),
+				NULL);
+		hva = gfn_to_hva(kvm, gpa >> PAGE_SHIFT);
+		if (kvm_is_error_hva(hva))
+			continue;
+		if (!access_ok(VERIFY_WRITE, hva, 1 << PAGE_SHIFT))
+			continue;
+		status =  kvm_roe_protect_range(vcpu->kvm, gpa, 1);
+		if (status > 0)
+			count += status;
+	}
+	if (count == 0)
+		return -EINVAL;
+	return count;
+}
+
+int kvm_roe(struct kvm_vcpu *vcpu, u64 a0, u64 a1, u64 a2, u64 a3)
+{
+	int ret;
+	/*
+	 * First we need to make sure that we are running from something that
+	 * isn't usermode
+	 */
+	if (kvm_roe_arch_is_userspace(vcpu))
+		return -KVM_ENOSYS;
+	switch (a0) {
+	case ROE_VERSION:
+		ret = 1; //current version
+		break;
+	case ROE_MPROTECT:
+		ret = kvm_roe_full_protect_range(vcpu, a1, a2);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_roe);
diff --git a/virt/kvm/roe_generic.h b/virt/kvm/roe_generic.h
new file mode 100644
index 0000000000..36e5b52c5b
--- /dev/null
+++ b/virt/kvm/roe_generic.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __KVM_ROE_GENERIC_H__
+#define __KVM_ROE_GENERIC_H__
+/*
+ * KVM Read Only Enforcement
+ * Copyright (c) 2018 Ahmed Abd El Mawgood
+ *
+ * Author Ahmed Abd El Mawgood <ahmedsoliman@xxxxxxxxxxx>
+ *
+ */
+
+void kvm_roe_free(struct kvm_memory_slot *slot);
+int kvm_roe_init(struct kvm_memory_slot *slot);
+static inline bool gfn_is_full_roe(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return test_bit(gfn - slot->base_gfn, slot->roe_bitmap);
+}
+#endif
-- 
2.19.2