KVM: page track: add the framework of guest page tracking

The array, gfn_track[mode][gfn], is introduced in memory slot for every
guest page, this is the tracking count for the gust page on different
modes. If the page is tracked then the count is increased, the page is
not tracked after the count reaches zero

We use 'unsigned short' as the tracking count which should be enough as
shadow page table only can use 2^14 (2^3 for level, 2^1 for cr4_pae, 2^2
for quadrant, 2^3 for access, 2^1 for nxe, 2^1 for cr0_wp, 2^1 for
smep_andnot_wp, 2^1 for smap_andnot_wp, and 2^1 for smm) at most, there
is enough room for other trackers

Two callbacks, kvm_page_track_create_memslot() and
kvm_page_track_free_memslot() are implemented in this patch, they are
internally used to initialize and reclaim the memory of the array

Currently, only write track mode is supported
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -32,6 +32,7 @@
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
 #include <asm/asm.h>
+#include <asm/kvm_page_track.h>
 
 #define KVM_MAX_VCPUS 255
 #define KVM_SOFT_MAX_VCPUS 160
@@ -214,6 +215,14 @@ struct kvm_mmu_memory_cache {
 	void *objects[KVM_NR_MEM_OBJS];
 };
 
+/*
+ * the pages used as guest page table on soft mmu are tracked by
+ * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used
+ * by indirect shadow page can not be more than 15 bits.
+ *
+ * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access,
+ * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
+ */
 union kvm_mmu_page_role {
 	unsigned word;
 	struct {
@@ -650,6 +659,7 @@ struct kvm_lpage_info {
 struct kvm_arch_memory_slot {
 	struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
 	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
+	unsigned short *gfn_track[KVM_PAGE_TRACK_MAX];
 };
 
 /*

arch/x86/include/asm/kvm_page_track.h

+#ifndef _ASM_X86_KVM_PAGE_TRACK_H
+#define _ASM_X86_KVM_PAGE_TRACK_H
+
+enum kvm_page_track_mode {
+	KVM_PAGE_TRACK_WRITE,
+	KVM_PAGE_TRACK_MAX,
+};
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
+				 struct kvm_memory_slot *dont);
+int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
+				  unsigned long npages);
+#endif

arch/x86/kvm/Makefile

@@ -13,9 +13,10 @@ kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
-			   hyperv.o
+			   hyperv.o page_track.o
 
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= assigned-dev.o iommu.o
+
 kvm-intel-y		+= vmx.o pmu_intel.o
 kvm-amd-y		+= svm.o pmu_amd.o
 

arch/x86/kvm/page_track.c

+/*
+ * Support KVM gust page tracking
+ *
+ * This feature allows us to track page access in guest. Currently, only
+ * write access is tracked.
+ *
+ * Copyright(C) 2015 Intel Corporation.
+ *
+ * Author:
+ *   Xiao Guangrong <guangrong.xiao@linux.intel.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_page_track.h>
+
+#include "mmu.h"
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
+				 struct kvm_memory_slot *dont)
+{
+	int i;
+
+	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++)
+		if (!dont || free->arch.gfn_track[i] !=
+		      dont->arch.gfn_track[i]) {
+			kvfree(free->arch.gfn_track[i]);
+			free->arch.gfn_track[i] = NULL;
+		}
+}
+
+int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
+				  unsigned long npages)
+{
+	int  i;
+
+	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
+		slot->arch.gfn_track[i] = kvm_kvzalloc(npages *
+					    sizeof(*slot->arch.gfn_track[i]));
+		if (!slot->arch.gfn_track[i])
+			goto track_free;
+	}
+
+	return 0;
+
+track_free:
+	kvm_page_track_free_memslot(slot, NULL);
+	return -ENOMEM;
+}

arch/x86/kvm/x86.c

@@ -7871,6 +7871,8 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			free->arch.lpage_info[i - 1] = NULL;
 		}
 	}
+
+	kvm_page_track_free_memslot(free, dont);
 }
 
 int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
@@ -7919,6 +7921,9 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 		}
 	}
 
+	if (kvm_page_track_create_memslot(slot, npages))
+		goto out_free;
+
 	return 0;
 
 out_free: