Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "Much x86 work was pushed out to 5.12, but ARM more than made up for it.

  ARM:
   - PSCI relay at EL2 when "protected KVM" is enabled
   - New exception injection code
   - Simplification of AArch32 system register handling
   - Fix PMU accesses when no PMU is enabled
   - Expose CSV3 on non-Meltdown hosts
   - Cache hierarchy discovery fixes
   - PV steal-time cleanups
   - Allow function pointers at EL2
   - Various host EL2 entry cleanups
   - Simplification of the EL2 vector allocation

  s390:
   - memcg accouting for s390 specific parts of kvm and gmap
   - selftest for diag318
   - new kvm_stat for when async_pf falls back to sync

  x86:
   - Tracepoints for the new pagetable code from 5.10
   - Catch VFIO and KVM irqfd events before userspace
   - Reporting dirty pages to userspace with a ring buffer
   - SEV-ES host support
   - Nested VMX support for wait-for-SIPI activity state
   - New feature flag (AVX512 FP16)
   - New system ioctl to report Hyper-V-compatible paravirtualization features

  Generic:
   - Selftest improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (171 commits)
  KVM: SVM: fix 32-bit compilation
  KVM: SVM: Add AP_JUMP_TABLE support in prep for AP booting
  KVM: SVM: Provide support to launch and run an SEV-ES guest
  KVM: SVM: Provide an updated VMRUN invocation for SEV-ES guests
  KVM: SVM: Provide support for SEV-ES vCPU loading
  KVM: SVM: Provide support for SEV-ES vCPU creation/loading
  KVM: SVM: Update ASID allocation to support SEV-ES guests
  KVM: SVM: Set the encryption mask for the SVM host save area
  KVM: SVM: Add NMI support for an SEV-ES guest
  KVM: SVM: Guest FPU state save/restore not needed for SEV-ES guest
  KVM: SVM: Do not report support for SMM for an SEV-ES guest
  KVM: x86: Update __get_sregs() / __set_sregs() to support SEV-ES
  KVM: SVM: Add support for CR8 write traps for an SEV-ES guest
  KVM: SVM: Add support for CR4 write traps for an SEV-ES guest
  KVM: SVM: Add support for CR0 write traps for an SEV-ES guest
  KVM: SVM: Add support for EFER write traps for an SEV-ES guest
  KVM: SVM: Support string IO operations for an SEV-ES guest
  KVM: SVM: Support MMIO for an SEV-ES guest
  KVM: SVM: Create trace events for VMGEXIT MSR protocol processing
  KVM: SVM: Create trace events for VMGEXIT processing
  ...

3 files changed, 346 insertions, 27 deletions

diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
new file mode 100644
index 000000000000..9d01299563ee
--- /dev/null
+++ b/virt/kvm/dirty_ring.c
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * KVM dirty ring implementation
+ *
+ * Copyright 2019 Red Hat, Inc.
+ */
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/vmalloc.h>
+#include <linux/kvm_dirty_ring.h>
+#include <trace/events/kvm.h>
+
+int __weak kvm_cpu_dirty_log_size(void)
+{
+	return 0;
+}
+
+u32 kvm_dirty_ring_get_rsvd_entries(void)
+{
+	return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
+}
+
+static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring)
+{
+	return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index);
+}
+
+bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+{
+	return kvm_dirty_ring_used(ring) >= ring->soft_limit;
+}
+
+static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring)
+{
+	return kvm_dirty_ring_used(ring) >= ring->size;
+}
+
+struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+
+	WARN_ON_ONCE(vcpu->kvm != kvm);
+
+	return &vcpu->dirty_ring;
+}
+
+static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
+{
+	struct kvm_memory_slot *memslot;
+	int as_id, id;
+
+	as_id = slot >> 16;
+	id = (u16)slot;
+
+	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+		return;
+
+	memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id);
+
+	if (!memslot || (offset + __fls(mask)) >= memslot->npages)
+		return;
+
+	spin_lock(&kvm->mmu_lock);
+	kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask);
+	spin_unlock(&kvm->mmu_lock);
+}
+
+int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size)
+{
+	ring->dirty_gfns = vmalloc(size);
+	if (!ring->dirty_gfns)
+		return -ENOMEM;
+	memset(ring->dirty_gfns, 0, size);
+
+	ring->size = size / sizeof(struct kvm_dirty_gfn);
+	ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries();
+	ring->dirty_index = 0;
+	ring->reset_index = 0;
+	ring->index = index;
+
+	return 0;
+}
+
+static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn)
+{
+	gfn->flags = 0;
+}
+
+static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn)
+{
+	gfn->flags = KVM_DIRTY_GFN_F_DIRTY;
+}
+
+static inline bool kvm_dirty_gfn_invalid(struct kvm_dirty_gfn *gfn)
+{
+	return gfn->flags == 0;
+}
+
+static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn)
+{
+	return gfn->flags & KVM_DIRTY_GFN_F_RESET;
+}
+
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
+{
+	u32 cur_slot, next_slot;
+	u64 cur_offset, next_offset;
+	unsigned long mask;
+	int count = 0;
+	struct kvm_dirty_gfn *entry;
+	bool first_round = true;
+
+	/* This is only needed to make compilers happy */
+	cur_slot = cur_offset = mask = 0;
+
+	while (true) {
+		entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)];
+
+		if (!kvm_dirty_gfn_harvested(entry))
+			break;
+
+		next_slot = READ_ONCE(entry->slot);
+		next_offset = READ_ONCE(entry->offset);
+
+		/* Update the flags to reflect that this GFN is reset */
+		kvm_dirty_gfn_set_invalid(entry);
+
+		ring->reset_index++;
+		count++;
+		/*
+		 * Try to coalesce the reset operations when the guest is
+		 * scanning pages in the same slot.
+		 */
+		if (!first_round && next_slot == cur_slot) {
+			s64 delta = next_offset - cur_offset;
+
+			if (delta >= 0 && delta < BITS_PER_LONG) {
+				mask |= 1ull << delta;
+				continue;
+			}
+
+			/* Backwards visit, careful about overflows!  */
+			if (delta > -BITS_PER_LONG && delta < 0 &&
+			    (mask << -delta >> -delta) == mask) {
+				cur_offset = next_offset;
+				mask = (mask << -delta) | 1;
+				continue;
+			}
+		}
+		kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+		cur_slot = next_slot;
+		cur_offset = next_offset;
+		mask = 1;
+		first_round = false;
+	}
+
+	kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+
+	trace_kvm_dirty_ring_reset(ring);
+
+	return count;
+}
+
+void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
+{
+	struct kvm_dirty_gfn *entry;
+
+	/* It should never get full */
+	WARN_ON_ONCE(kvm_dirty_ring_full(ring));
+
+	entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)];
+
+	entry->slot = slot;
+	entry->offset = offset;
+	/*
+	 * Make sure the data is filled in before we publish this to
+	 * the userspace program.  There's no paired kernel-side reader.
+	 */
+	smp_wmb();
+	kvm_dirty_gfn_set_dirtied(entry);
+	ring->dirty_index++;
+	trace_kvm_dirty_ring_push(ring, slot, offset);
+}
+
+struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset)
+{
+	return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE);
+}
+
+void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
+{
+	vfree(ring->dirty_gfns);
+	ring->dirty_gfns = NULL;
+}
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index c2323c27a28b..e996989cd580 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -191,8 +191,12 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 	struct kvm *kvm = irqfd->kvm;
 	unsigned seq;
 	int idx;
+	int ret = 0;
 
 	if (flags & EPOLLIN) {
+		u64 cnt;
+		eventfd_ctx_do_read(irqfd->eventfd, &cnt);
+
 		idx = srcu_read_lock(&kvm->irq_srcu);
 		do {
 			seq = read_seqcount_begin(&irqfd->irq_entry_sc);
@@ -204,6 +208,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 					      false) == -EWOULDBLOCK)
 			schedule_work(&irqfd->inject);
 		srcu_read_unlock(&kvm->irq_srcu, idx);
+		ret = 1;
 	}
 
 	if (flags & EPOLLHUP) {
@@ -227,7 +232,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 		spin_unlock_irqrestore(&kvm->irqfds.lock, iflags);
 	}
 
-	return 0;
+	return ret;
 }
 
 static void
@@ -236,7 +241,7 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(pt, struct kvm_kernel_irqfd, pt);
-	add_wait_queue(wqh, &irqfd->wait);
+	add_wait_queue_priority(wqh, &irqfd->wait);
 }
 
 /* Must be called under irqfds.lock */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f69357a29688..5f260488e999 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -63,6 +63,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
 
+#include <linux/kvm_dirty_ring.h>
+
 /* Worst case buffer size needed for holding an integer. */
 #define ITOA_MAX_LEN 12
 
@@ -415,6 +417,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 
 void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	kvm_dirty_ring_free(&vcpu->dirty_ring);
 	kvm_arch_vcpu_destroy(vcpu);
 
 	/*
@@ -1362,7 +1365,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	/* Allocate/free page dirty bitmap as needed */
 	if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
 		new.dirty_bitmap = NULL;
-	else if (!new.dirty_bitmap) {
+	else if (!new.dirty_bitmap && !kvm->dirty_ring_size) {
 		r = kvm_alloc_dirty_bitmap(&new);
 		if (r)
 			return r;
@@ -1423,6 +1426,10 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 	unsigned long n;
 	unsigned long any = 0;
 
+	/* Dirty ring tracking is exclusive to dirty log tracking */
+	if (kvm->dirty_ring_size)
+		return -ENXIO;
+
 	*memslot = NULL;
 	*is_dirty = 0;
 
@@ -1484,6 +1491,10 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
+	/* Dirty ring tracking is exclusive to dirty log tracking */
+	if (kvm->dirty_ring_size)
+		return -ENXIO;
+
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
@@ -1592,6 +1603,10 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
+	/* Dirty ring tracking is exclusive to dirty log tracking */
+	if (kvm->dirty_ring_size)
+		return -ENXIO;
+
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
@@ -2196,7 +2211,8 @@ int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_map);
 
-static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
+static void __kvm_unmap_gfn(struct kvm *kvm,
+			struct kvm_memory_slot *memslot,
 			struct kvm_host_map *map,
 			struct gfn_to_pfn_cache *cache,
 			bool dirty, bool atomic)
@@ -2221,7 +2237,7 @@ static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
 #endif
 
 	if (dirty)
-		mark_page_dirty_in_slot(memslot, map->gfn);
+		mark_page_dirty_in_slot(kvm, memslot, map->gfn);
 
 	if (cache)
 		cache->dirty |= dirty;
@@ -2235,7 +2251,7 @@ static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
 int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, 
 		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
 {
-	__kvm_unmap_gfn(gfn_to_memslot(vcpu->kvm, map->gfn), map,
+	__kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map,
 			cache, dirty, atomic);
 	return 0;
 }
@@ -2243,8 +2259,8 @@ EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
 
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
 {
-	__kvm_unmap_gfn(kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), map, NULL,
-			dirty, false);
+	__kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn),
+			map, NULL, dirty, false);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
@@ -2418,7 +2434,8 @@ int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa,
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic);
 
-static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,
+static int __kvm_write_guest_page(struct kvm *kvm,
+				  struct kvm_memory_slot *memslot, gfn_t gfn,
 			          const void *data, int offset, int len)
 {
 	int r;
@@ -2430,7 +2447,7 @@ static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,
 	r = __copy_to_user((void __user *)addr + offset, data, len);
 	if (r)
 		return -EFAULT;
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(kvm, memslot, gfn);
 	return 0;
 }
 
@@ -2439,7 +2456,7 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn,
 {
 	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
 
-	return __kvm_write_guest_page(slot, gfn, data, offset, len);
+	return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest_page);
 
@@ -2448,7 +2465,7 @@ int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
 {
 	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 
-	return __kvm_write_guest_page(slot, gfn, data, offset, len);
+	return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page);
 
@@ -2567,7 +2584,7 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
 	if (r)
 		return -EFAULT;
-	mark_page_dirty_in_slot(ghc->memslot, gpa >> PAGE_SHIFT);
+	mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT);
 
 	return 0;
 }
@@ -2616,23 +2633,16 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 }
 EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
 
-int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
-{
-	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
-
-	return kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
-}
-EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
-
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 {
+	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int seg;
 	int offset = offset_in_page(gpa);
 	int ret;
 
 	while ((seg = next_segment(len, offset)) != 0) {
-		ret = kvm_clear_guest_page(kvm, gfn, offset, seg);
+		ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
 		if (ret < 0)
 			return ret;
 		offset = 0;
@@ -2643,12 +2653,19 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn)
+void mark_page_dirty_in_slot(struct kvm *kvm,
+			     struct kvm_memory_slot *memslot,
+		 	     gfn_t gfn)
 {
-	if (memslot && memslot->dirty_bitmap) {
+	if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
+		u32 slot = (memslot->as_id << 16) | memslot->id;
 
-		set_bit_le(rel_gfn, memslot->dirty_bitmap);
+		if (kvm->dirty_ring_size)
+			kvm_dirty_ring_push(kvm_dirty_ring_get(kvm),
+					    slot, rel_gfn);
+		else
+			set_bit_le(rel_gfn, memslot->dirty_bitmap);
 	}
 }
 EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot);
@@ -2658,7 +2675,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 	struct kvm_memory_slot *memslot;
 
 	memslot = gfn_to_memslot(kvm, gfn);
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(kvm, memslot, gfn);
 }
 EXPORT_SYMBOL_GPL(mark_page_dirty);
 
@@ -2667,7 +2684,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn)
 	struct kvm_memory_slot *memslot;
 
 	memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
 
@@ -3008,6 +3025,17 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
 
+static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff)
+{
+#if KVM_DIRTY_LOG_PAGE_OFFSET > 0
+	return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) &&
+	    (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET +
+	     kvm->dirty_ring_size / PAGE_SIZE);
+#else
+	return false;
+#endif
+}
+
 static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
 {
 	struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data;
@@ -3023,6 +3051,10 @@ static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
 	else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
 #endif
+	else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff))
+		page = kvm_dirty_ring_get_page(
+		    &vcpu->dirty_ring,
+		    vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET);
 	else
 		return kvm_arch_vcpu_fault(vcpu, vmf);
 	get_page(page);
@@ -3036,6 +3068,14 @@ static const struct vm_operations_struct kvm_vcpu_vm_ops = {
 
 static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	struct kvm_vcpu *vcpu = file->private_data;
+	unsigned long pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+
+	if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) ||
+	     kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) &&
+	    ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED)))
+		return -EINVAL;
+
 	vma->vm_ops = &kvm_vcpu_vm_ops;
 	return 0;
 }
@@ -3129,6 +3169,13 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	if (r)
 		goto vcpu_free_run_page;
 
+	if (kvm->dirty_ring_size) {
+		r = kvm_dirty_ring_alloc(&vcpu->dirty_ring,
+					 id, kvm->dirty_ring_size);
+		if (r)
+			goto arch_vcpu_destroy;
+	}
+
 	mutex_lock(&kvm->lock);
 	if (kvm_get_vcpu_by_id(kvm, id)) {
 		r = -EEXIST;
@@ -3162,6 +3209,8 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 
 unlock_vcpu_destroy:
 	mutex_unlock(&kvm->lock);
+	kvm_dirty_ring_free(&vcpu->dirty_ring);
+arch_vcpu_destroy:
 	kvm_arch_vcpu_destroy(vcpu);
 vcpu_free_run_page:
 	free_page((unsigned long)vcpu->run);
@@ -3634,12 +3683,78 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #endif
 	case KVM_CAP_NR_MEMSLOTS:
 		return KVM_USER_MEM_SLOTS;
+	case KVM_CAP_DIRTY_LOG_RING:
+#if KVM_DIRTY_LOG_PAGE_OFFSET > 0
+		return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
+#else
+		return 0;
+#endif
 	default:
 		break;
 	}
 	return kvm_vm_ioctl_check_extension(kvm, arg);
 }
 
+static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size)
+{
+	int r;
+
+	if (!KVM_DIRTY_LOG_PAGE_OFFSET)
+		return -EINVAL;
+
+	/* the size should be power of 2 */
+	if (!size || (size & (size - 1)))
+		return -EINVAL;
+
+	/* Should be bigger to keep the reserved entries, or a page */
+	if (size < kvm_dirty_ring_get_rsvd_entries() *
+	    sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE)
+		return -EINVAL;
+
+	if (size > KVM_DIRTY_RING_MAX_ENTRIES *
+	    sizeof(struct kvm_dirty_gfn))
+		return -E2BIG;
+
+	/* We only allow it to set once */
+	if (kvm->dirty_ring_size)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+
+	if (kvm->created_vcpus) {
+		/* We don't allow to change this value after vcpu created */
+		r = -EINVAL;
+	} else {
+		kvm->dirty_ring_size = size;
+		r = 0;
+	}
+
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+	int cleared = 0;
+
+	if (!kvm->dirty_ring_size)
+		return -EINVAL;
+
+	mutex_lock(&kvm->slots_lock);
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring);
+
+	mutex_unlock(&kvm->slots_lock);
+
+	if (cleared)
+		kvm_flush_remote_tlbs(kvm);
+
+	return cleared;
+}
+
 int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 						  struct kvm_enable_cap *cap)
 {
@@ -3670,6 +3785,8 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 		kvm->max_halt_poll_ns = cap->args[0];
 		return 0;
 	}
+	case KVM_CAP_DIRTY_LOG_RING:
+		return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);
 	}
@@ -3854,6 +3971,9 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_CHECK_EXTENSION:
 		r = kvm_vm_ioctl_check_extension_generic(kvm, arg);
 		break;
+	case KVM_RESET_DIRTY_RINGS:
+		r = kvm_vm_ioctl_reset_dirty_pages(kvm);
+		break;
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}