Re: [PATCH v5 11/13] KVM: Zap existing KVM mappings when pages changed in the private fd

[Michael Roth]

On Thu, Mar 10, 2022 at 10:09:09PM +0800, Chao Peng wrote:
> KVM gets notified when memory pages changed in the memory backing store.
> When userspace allocates the memory with fallocate() or frees memory
> with fallocate(FALLOC_FL_PUNCH_HOLE), memory backing store calls into
> KVM fallocate/invalidate callbacks respectively. To ensure KVM never
> maps both the private and shared variants of a GPA into the guest, in
> the fallocate callback, we should zap the existing shared mapping and
> in the invalidate callback we should zap the existing private mapping.
> 
> In the callbacks, KVM firstly converts the offset range into the
> gfn_range and then calls existing kvm_unmap_gfn_range() which will zap
> the shared or private mapping. Both callbacks pass in a memslot
> reference but we need 'kvm' so add a reference in memslot structure.
> 
> Signed-off-by: Yu Zhang <yu.c.zhang@xxxxxxxxxxxxxxx>
> Signed-off-by: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
> ---
>  include/linux/kvm_host.h |  3 ++-
>  virt/kvm/kvm_main.c      | 36 ++++++++++++++++++++++++++++++++++++
>  2 files changed, 38 insertions(+), 1 deletion(-)
> 
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 9b175aeca63f..186b9b981a65 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -236,7 +236,7 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
>  int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
>  #endif
>  
> -#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
> +#if defined(KVM_ARCH_WANT_MMU_NOTIFIER) || defined(CONFIG_MEMFILE_NOTIFIER)
>  struct kvm_gfn_range {
>  	struct kvm_memory_slot *slot;
>  	gfn_t start;
> @@ -568,6 +568,7 @@ struct kvm_memory_slot {
>  	loff_t private_offset;
>  	struct memfile_pfn_ops *pfn_ops;
>  	struct memfile_notifier notifier;
> +	struct kvm *kvm;
>  };
>  
>  static inline bool kvm_slot_is_private(const struct kvm_memory_slot *slot)
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 67349421eae3..52319f49d58a 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -841,8 +841,43 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
>  #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
>  
>  #ifdef CONFIG_MEMFILE_NOTIFIER
> +static void kvm_memfile_notifier_handler(struct memfile_notifier *notifier,
> +					 pgoff_t start, pgoff_t end)
> +{
> +	int idx;
> +	struct kvm_memory_slot *slot = container_of(notifier,
> +						    struct kvm_memory_slot,
> +						    notifier);
> +	struct kvm_gfn_range gfn_range = {
> +		.slot		= slot,
> +		.start		= start - (slot->private_offset >> PAGE_SHIFT),
> +		.end		= end - (slot->private_offset >> PAGE_SHIFT),
> +		.may_block 	= true,
> +	};
> +	struct kvm *kvm = slot->kvm;
> +
> +	gfn_range.start = max(gfn_range.start, slot->base_gfn);
> +	gfn_range.end = min(gfn_range.end, slot->base_gfn + slot->npages);
> +
> +	if (gfn_range.start >= gfn_range.end)
> +		return;
> +
> +	idx = srcu_read_lock(&kvm->srcu);
> +	KVM_MMU_LOCK(kvm);
> +	kvm_unmap_gfn_range(kvm, &gfn_range);
> +	kvm_flush_remote_tlbs(kvm);
> +	KVM_MMU_UNLOCK(kvm);
> +	srcu_read_unlock(&kvm->srcu, idx);

Should this also invalidate gfn_to_pfn_cache mappings? Otherwise it seems
possible the kernel might end up inadvertantly writing to now-private guest
memory via a now-stale gfn_to_pfn_cache entry.