KVM: x86: Add new dirty logging kvm_x86_ops for PML

This patch adds new kvm_x86_ops dirty logging hooks to enable/disable dirty
logging for particular memory slot, and to flush potentially logged dirty GPAs
before reporting slot->dirty_bitmap to userspace.

kvm x86 common code calls these hooks when they are available so PML logic can
be hidden to VMX specific. SVM won't be impacted as these hooks remain NULL
there.

Signed-off-by: Kai Huang <kai.huang@linux.intel.com>
Reviewed-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -802,6 +802,31 @@ struct kvm_x86_ops {
 	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
 
 	void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
+
+	/*
+	 * Arch-specific dirty logging hooks. These hooks are only supposed to
+	 * be valid if the specific arch has hardware-accelerated dirty logging
+	 * mechanism. Currently only for PML on VMX.
+	 *
+	 *  - slot_enable_log_dirty:
+	 *	called when enabling log dirty mode for the slot.
+	 *  - slot_disable_log_dirty:
+	 *	called when disabling log dirty mode for the slot.
+	 *	also called when slot is created with log dirty disabled.
+	 *  - flush_log_dirty:
+	 *	called before reporting dirty_bitmap to userspace.
+	 *  - enable_log_dirty_pt_masked:
+	 *	called when reenabling log dirty for the GFNs in the mask after
+	 *	corresponding bits are cleared in slot->dirty_bitmap.
+	 */
+	void (*slot_enable_log_dirty)(struct kvm *kvm,
+				      struct kvm_memory_slot *slot);
+	void (*slot_disable_log_dirty)(struct kvm *kvm,
+				       struct kvm_memory_slot *slot);
+	void (*flush_log_dirty)(struct kvm *kvm);
+	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
+					   struct kvm_memory_slot *slot,
+					   gfn_t offset, unsigned long mask);
 };
 
 struct kvm_arch_async_pf {

arch/x86/kvm/mmu.c

@@ -1335,7 +1335,11 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 				struct kvm_memory_slot *slot,
 				gfn_t gfn_offset, unsigned long mask)
 {
-	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
+	if (kvm_x86_ops->enable_log_dirty_pt_masked)
+		kvm_x86_ops->enable_log_dirty_pt_masked(kvm, slot, gfn_offset,
+				mask);
+	else
+		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
 static bool rmap_write_protect(struct kvm *kvm, u64 gfn)

arch/x86/kvm/x86.c

@@ -3780,6 +3780,12 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 
 	mutex_lock(&kvm->slots_lock);
 
+	/*
+	 * Flush potentially hardware-cached dirty pages to dirty_bitmap.
+	 */
+	if (kvm_x86_ops->flush_log_dirty)
+		kvm_x86_ops->flush_log_dirty(kvm);
+
 	r = kvm_get_dirty_log_protect(kvm, log, &is_dirty);
 
 	/*
@@ -7533,6 +7539,56 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
+				     struct kvm_memory_slot *new)
+{
+	/* Still write protect RO slot */
+	if (new->flags & KVM_MEM_READONLY) {
+		kvm_mmu_slot_remove_write_access(kvm, new);
+		return;
+	}
+
+	/*
+	 * Call kvm_x86_ops dirty logging hooks when they are valid.
+	 *
+	 * kvm_x86_ops->slot_disable_log_dirty is called when:
+	 *
+	 *  - KVM_MR_CREATE with dirty logging is disabled
+	 *  - KVM_MR_FLAGS_ONLY with dirty logging is disabled in new flag
+	 *
+	 * The reason is, in case of PML, we need to set D-bit for any slots
+	 * with dirty logging disabled in order to eliminate unnecessary GPA
+	 * logging in PML buffer (and potential PML buffer full VMEXT). This
+	 * guarantees leaving PML enabled during guest's lifetime won't have
+	 * any additonal overhead from PML when guest is running with dirty
+	 * logging disabled for memory slots.
+	 *
+	 * kvm_x86_ops->slot_enable_log_dirty is called when switching new slot
+	 * to dirty logging mode.
+	 *
+	 * If kvm_x86_ops dirty logging hooks are invalid, use write protect.
+	 *
+	 * In case of write protect:
+	 *
+	 * Write protect all pages for dirty logging.
+	 *
+	 * All the sptes including the large sptes which point to this
+	 * slot are set to readonly. We can not create any new large
+	 * spte on this slot until the end of the logging.
+	 *
+	 * See the comments in fast_page_fault().
+	 */
+	if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+		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 {
+		if (kvm_x86_ops->slot_disable_log_dirty)
+			kvm_x86_ops->slot_disable_log_dirty(kvm, new);
+	}
+}
+
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
@@ -7562,16 +7618,15 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	new = id_to_memslot(kvm->memslots, mem->slot);
 
 	/*
-	 * Write protect all pages for dirty logging.
+	 * Set up write protection and/or dirty logging for the new slot.
 	 *
-	 * All the sptes including the large sptes which point to this
-	 * slot are set to readonly. We can not create any new large
-	 * spte on this slot until the end of the logging.
-	 *
-	 * See the comments in fast_page_fault().
+	 * For KVM_MR_DELETE and KVM_MR_MOVE, the shadow pages of old slot have
+	 * been zapped so no dirty logging staff is needed for old slot. For
+	 * KVM_MR_FLAGS_ONLY, the old slot is essentially the same one as the
+	 * new and it's also covered when dealing with the new slot.
 	 */
-	if ((change != KVM_MR_DELETE) && (new->flags & KVM_MEM_LOG_DIRTY_PAGES))
-		kvm_mmu_slot_remove_write_access(kvm, new);
+	if (change != KVM_MR_DELETE)
+		kvm_mmu_slot_apply_flags(kvm, new);
 }
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)