Re: [PATCH v3 11/11] KVM: MMU: apply page track notifier

[Xiao Guangrong <guangrong.xiao@linux.intel.com>]

On 02/19/2016 07:56 PM, Paolo Bonzini wrote:
>
>
> On 14/02/2016 12:31, Xiao Guangrong wrote:
>> Register the notifier to receive write track event so that we can update
>> our shadow page table
>>
>> It makes kvm_mmu_pte_write() be the callback of the notifier, no function
>> is changed
>>
>> Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
>> ---
>>   arch/x86/include/asm/kvm_host.h |  5 +++--
>>   arch/x86/kvm/mmu.c              | 19 +++++++++++++++++--
>>   arch/x86/kvm/x86.c              |  4 ++--
>>   3 files changed, 22 insertions(+), 6 deletions(-)
>>
>> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
>> index 254d103..5246f07 100644
>> --- a/arch/x86/include/asm/kvm_host.h
>> +++ b/arch/x86/include/asm/kvm_host.h
>> @@ -696,6 +696,7 @@ struct kvm_arch {
>>   	 */
>>   	struct list_head active_mmu_pages;
>>   	struct list_head zapped_obsolete_pages;
>> +	struct kvm_page_track_notifier_node mmu_sp_tracker;
>>   	struct kvm_page_track_notifier_head track_notifier_head;
>>
>>   	struct list_head assigned_dev_head;
>> @@ -994,6 +995,8 @@ void kvm_mmu_module_exit(void);
>>   void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
>>   int kvm_mmu_create(struct kvm_vcpu *vcpu);
>>   void kvm_mmu_setup(struct kvm_vcpu *vcpu);
>> +void kvm_mmu_init_vm(struct kvm *kvm);
>> +void kvm_mmu_uninit_vm(struct kvm *kvm);
>>   void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
>>   		u64 dirty_mask, u64 nx_mask, u64 x_mask);
>>
>> @@ -1133,8 +1136,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
>>
>>   void kvm_inject_nmi(struct kvm_vcpu *vcpu);
>>
>> -void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
>> -		       const u8 *new, int bytes);
>>   int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
>>   int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
>>   void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
>> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
>> index f924e6c..57cf30b 100644
>> --- a/arch/x86/kvm/mmu.c
>> +++ b/arch/x86/kvm/mmu.c
>> @@ -4316,8 +4316,8 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
>>   	return spte;
>>   }
>>
>> -void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
>> -		       const u8 *new, int bytes)
>> +static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
>> +			      const u8 *new, int bytes)
>>   {
>>   	gfn_t gfn = gpa >> PAGE_SHIFT;
>>   	struct kvm_mmu_page *sp;
>> @@ -4531,6 +4531,21 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
>>   	init_kvm_mmu(vcpu);
>>   }
>>
>> +void kvm_mmu_init_vm(struct kvm *kvm)
>> +{
>> +	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
>> +
>> +	node->track_write = kvm_mmu_pte_write;
>> +	kvm_page_track_register_notifier(kvm, node);
>> +}
>> +
>> +void kvm_mmu_uninit_vm(struct kvm *kvm)
>> +{
>> +	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
>> +
>> +	kvm_page_track_unregister_notifier(kvm, node);
>> +}
>> +
>>   /* The return value indicates if tlb flush on all vcpus is needed. */
>>   typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
>>
>> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>> index 98019b6..319d572 100644
>> --- a/arch/x86/kvm/x86.c
>> +++ b/arch/x86/kvm/x86.c
>> @@ -4369,7 +4369,6 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
>>   	ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes);
>>   	if (ret < 0)
>>   		return 0;
>> -	kvm_mmu_pte_write(vcpu, gpa, val, bytes);
>>   	kvm_page_track_write(vcpu, gpa, val, bytes);
>>   	return 1;
>>   }
>> @@ -4628,7 +4627,6 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
>>   		return X86EMUL_CMPXCHG_FAILED;
>>
>>   	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
>> -	kvm_mmu_pte_write(vcpu, gpa, new, bytes);
>>   	kvm_page_track_write(vcpu, gpa, new, bytes);
>>
>>   	return X86EMUL_CONTINUE;
>> @@ -7751,6 +7749,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
>>   	INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
>>
>>   	kvm_page_track_init(kvm);
>> +	kvm_mmu_init_vm(kvm);
>>
>>   	return 0;
>>   }
>> @@ -7878,6 +7877,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
>>   	kfree(kvm->arch.vioapic);
>>   	kvm_free_vcpus(kvm);
>>   	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
>> +	kvm_mmu_uninit_vm(kvm);
>
> This function is not necessary, since the VM is disappearing anyway and
> the page tracker is not going to be called.

I think it is still necessary, as we are using srcu to protect the notifier, so
we should wait all the callers of notifier callbacks gone, i.e, synchronize_srcu()
is needed anyway.