KVM: x86: enable dirty log gradually in small chunks

mainline inclusion
from mainline-v5.10
commit: 3c9bd400
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I66COX
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=linux-5.10.y&id=3c9bd4006bfc2dccda1823db61b3f470ef91cfaa

--------------------------------

It could take kvm->mmu_lock for an extended period of time when
enabling dirty log for the first time. The main cost is to clear
all the D-bits of last level SPTEs. This situation can benefit from
manual dirty log protect as well, which can reduce the mmu_lock
time taken. The sequence is like this:

1. Initialize all the bits of the dirty bitmap to 1 when enabling
   dirty log for the first time
2. Only write protect the huge pages
3. KVM_GET_DIRTY_LOG returns the dirty bitmap info
4. KVM_CLEAR_DIRTY_LOG will clear D-bit for each of the leaf level
   SPTEs gradually in small chunks

Under the Intel(R) Xeon(R) Gold 6152 CPU @ 2.10GHz environment,
I did some tests with a 128G windows VM and counted the time taken
of memory_global_dirty_log_start, here is the numbers:

VM Size        Before    After optimization
128G           460ms     10ms
Signed-off-by: NJay Zhou <jianjay.zhou@huawei.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
[Remove test code because the test code is too different.]
Signed-off-by: zhengchuan<zhengchuan@huawei.com>

Documentation/virtual/kvm/api.txt

@@ -4630,8 +4630,13 @@ capability does not enable write permissions of this MSR for the guest.
 Architectures: all
 Parameters: args[0] whether feature should be enabled or not
 
-With this capability enabled, KVM_GET_DIRTY_LOG will not automatically
-clear and write-protect all pages that are returned as dirty.
+Valid flags are::
+
+  #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE   (1 << 0)
+  #define KVM_DIRTY_LOG_INITIALLY_SET           (1 << 1)
+
+With KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE set, KVM_GET_DIRTY_LOG will not
+automatically clear and write-protect all pages that are returned as dirty.
 Rather, userspace will have to do this operation separately using
 KVM_CLEAR_DIRTY_LOG.
 
@@ -4642,12 +4647,19 @@ than requiring to sync a full memslot; this ensures that KVM does not
 take spinlocks for an extended period of time.  Second, in some cases a
 large amount of time can pass between a call to KVM_GET_DIRTY_LOG and
 userspace actually using the data in the page.  Pages can be modified
-during this time, which is inefficint for both the guest and userspace:
+during this time, which is inefficient for both the guest and userspace:
 the guest will incur a higher penalty due to write protection faults,
 while userspace can see false reports of dirty pages.  Manual reprotection
 helps reducing this time, improving guest performance and reducing the
 number of dirty log false positives.
 
+With KVM_DIRTY_LOG_INITIALLY_SET set, all the bits of the dirty bitmap
+will be initialized to 1 when created.  This also improves performance because
+dirty logging can be enabled gradually in small chunks on the first call
+to KVM_CLEAR_DIRTY_LOG.  KVM_DIRTY_LOG_INITIALLY_SET depends on
+KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (it is also only available on
+x86 for now).
+
 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name
 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make
 it hard or impossible to use it correctly.  The availability of

arch/x86/include/asm/kvm_host.h

@@ -49,6 +49,9 @@
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
+#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
+					KVM_DIRTY_LOG_INITIALLY_SET)
+
 /* x86-specific vcpu->requests bit members */
 #define KVM_REQ_MIGRATE_TIMER		KVM_ARCH_REQ(0)
 #define KVM_REQ_REPORT_TPR_ACCESS	KVM_ARCH_REQ(1)
@@ -1205,7 +1208,8 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
-				      struct kvm_memory_slot *memslot);
+				      struct kvm_memory_slot *memslot,
+				      int start_level);
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot);
 void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,

arch/x86/kvm/mmu.c

@@ -5719,13 +5719,14 @@ static bool slot_rmap_write_protect(struct kvm *kvm,
 }
 
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
-				      struct kvm_memory_slot *memslot)
+				      struct kvm_memory_slot *memslot,
+				      int start_level)
 {
 	bool flush;
 
 	spin_lock(&kvm->mmu_lock);
-	flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect,
-				      false);
+	flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect,
+				  start_level, PT_MAX_HUGEPAGE_LEVEL, false);
 	spin_unlock(&kvm->mmu_lock);
 
 	/*

arch/x86/kvm/vmx.c

@@ -13918,7 +13918,8 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
 static void vmx_slot_enable_log_dirty(struct kvm *kvm,
 				     struct kvm_memory_slot *slot)
 {
-	kvm_mmu_slot_leaf_clear_dirty(kvm, slot);
+        if (!kvm_dirty_log_manual_protect_and_init_set(kvm))
+                kvm_mmu_slot_leaf_clear_dirty(kvm, slot);
 	kvm_mmu_slot_largepage_remove_write_access(kvm, slot);
 }
 

arch/x86/kvm/x86.c

@@ -9368,7 +9368,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 {
 	/* Still write protect RO slot */
 	if (new->flags & KVM_MEM_READONLY) {
-		kvm_mmu_slot_remove_write_access(kvm, new);
+		kvm_mmu_slot_remove_write_access(kvm, new, PT_PAGE_TABLE_LEVEL);
 		return;
 	}
 
@@ -9403,10 +9403,23 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 	 * See the comments in fast_page_fault().
 	 */
 	if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
-		if (kvm_x86_ops->slot_enable_log_dirty)
+		if (kvm_x86_ops->slot_enable_log_dirty) {
 			kvm_x86_ops->slot_enable_log_dirty(kvm, new);
-		else
-			kvm_mmu_slot_remove_write_access(kvm, new);
+		} else {
+			int level =
+				kvm_dirty_log_manual_protect_and_init_set(kvm) ?
+				PT_DIRECTORY_LEVEL : PT_PAGE_TABLE_LEVEL;
+
+			/*
+			 * If we're with initial-all-set, we don't need
+			 * to write protect any small page because
+			 * they're reported as dirty already.  However
+			 * we still need to write-protect huge pages
+			 * so that the page split can happen lazily on
+			 * the first write to the huge page.
+			 */
+			kvm_mmu_slot_remove_write_access(kvm, new, level);
+		}
 	} else {
 		if (kvm_x86_ops->slot_disable_log_dirty)
 			kvm_x86_ops->slot_disable_log_dirty(kvm, new);

include/linux/kvm_host.h

@@ -339,6 +339,10 @@ static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *mem
 	return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap);
 }
 
+#ifndef KVM_DIRTY_LOG_MANUAL_CAPS
+#define KVM_DIRTY_LOG_MANUAL_CAPS KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE
+#endif
+
 struct kvm_s390_adapter_int {
 	u64 ind_addr;
 	u64 summary_addr;
@@ -472,7 +476,7 @@ struct kvm {
 #endif
 	long tlbs_dirty;
 	struct list_head devices;
-	bool manual_dirty_log_protect;
+	u64 manual_dirty_log_protect;
 	struct dentry *debugfs_dentry;
 	struct kvm_stat_data **debugfs_stat_data;
 	struct srcu_struct srcu;
@@ -506,6 +510,11 @@ struct kvm {
 #define vcpu_err(vcpu, fmt, ...)					\
 	kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
 
+static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm)
+{
+	return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET);
+}
+
 static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
 {
 	return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,

include/uapi/linux/kvm.h

@@ -1589,4 +1589,7 @@ struct kvm_hyperv_eventfd {
 #define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
 #define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
 
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
+
 #endif /* __LINUX_KVM_H */

virt/kvm/kvm_main.c

@@ -839,7 +839,7 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
  * Allocation size is twice as large as the actual dirty bitmap size.
  * See x86's kvm_vm_ioctl_get_dirty_log() why this is needed.
  */
-static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
+static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
 	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
 
@@ -1066,8 +1066,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	/* Allocate page dirty bitmap if needed */
 	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
-		if (kvm_create_dirty_bitmap(&new) < 0)
+		if (kvm_alloc_dirty_bitmap(&new) < 0)
 			goto out_free;
+
+		if (kvm_dirty_log_manual_protect_and_init_set(kvm))
+			bitmap_set(new.dirty_bitmap, 0, new.npages);
 	}
 
 	slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
@@ -3125,14 +3128,15 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_IOEVENTFD_ANY_LENGTH:
 	case KVM_CAP_CHECK_EXTENSION_VM:
 	case KVM_CAP_ENABLE_CAP_VM:
-#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
-	case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2:
-#endif
 		return 1;
 #ifdef CONFIG_KVM_MMIO
 	case KVM_CAP_COALESCED_MMIO:
 		return KVM_COALESCED_MMIO_PAGE_OFFSET;
 #endif
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+	case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2:
+		return KVM_DIRTY_LOG_MANUAL_CAPS;
+#endif
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
@@ -3158,11 +3162,17 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 {
 	switch (cap->cap) {
 #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
-        case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2:
-                if (cap->flags || (cap->args[0] & ~1))
+        case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: {
+                u64 allowed_options = KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE;
+
+                if (cap->args[0] & KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE)
+                        allowed_options = KVM_DIRTY_LOG_MANUAL_CAPS;
+
+                if (cap->flags || (cap->args[0] & ~allowed_options))
                         return -EINVAL;
                 kvm->manual_dirty_log_protect = cap->args[0];
                 return 0;
+        }
 #endif
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);