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

From: Sean Christopherson <seanjc@google.com>
To: Chao Peng <chao.p.peng@linux.intel.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
	linux-api@vger.kernel.org, qemu-devel@nongnu.org,
	Paolo Bonzini <pbonzini@redhat.com>,
	Jonathan Corbet <corbet@lwn.net>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
	Hugh Dickins <hughd@google.com>, Jeff Layton <jlayton@kernel.org>,
	"J . Bruce Fields" <bfields@fieldses.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Mike Rapoport <rppt@kernel.org>,
	Steven Price <steven.price@arm.com>,
	"Maciej S . Szmigiero" <mail@maciej.szmigiero.name>,
	Vlastimil Babka <vbabka@suse.cz>,
	Vishal Annapurve <vannapurve@google.com>,
	Yu Zhang <yu.c.zhang@linux.intel.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	luto@kernel.org, jun.nakajima@intel.com, dave.hansen@intel.com,
	ak@linux.intel.com, david@redhat.com
Subject: Re: [PATCH v5 11/13] KVM: Zap existing KVM mappings when pages changed in the private fd
Date: Tue, 29 Mar 2022 19:23:04 +0000	[thread overview]
Message-ID: <YkNcmGsOw4MThaym@google.com> (raw)
In-Reply-To: <20220310140911.50924-12-chao.p.peng@linux.intel.com>

On Thu, Mar 10, 2022, Chao Peng wrote:
> 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);

This should check the result of kvm_unmap_gfn_range() and flush only if necessary.

kvm->mmu_notifier_seq needs to be incremented, otherwise KVM will incorrectly
install a SPTE if the mapping is zapped between retrieving the pfn in faultin and
installing it after acquire mmu_lock.

> +	KVM_MMU_UNLOCK(kvm);
> +	srcu_read_unlock(&kvm->srcu, idx);
> +}
> +
> +static struct memfile_notifier_ops kvm_memfile_notifier_ops = {
> +	.invalidate = kvm_memfile_notifier_handler,
> +	.fallocate = kvm_memfile_notifier_handler,
> +};
> +
>  static inline int kvm_memfile_register(struct kvm_memory_slot *slot)
>  {
> +	slot->notifier.ops = &kvm_memfile_notifier_ops;
>  	return memfile_register_notifier(file_inode(slot->private_file),
>  					 &slot->notifier,
>  					 &slot->pfn_ops);
> @@ -1963,6 +1998,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
>  	new->private_file = file;
>  	new->private_offset = mem->flags & KVM_MEM_PRIVATE ?
>  			      region_ext->private_offset : 0;
> +	new->kvm = kvm;
>  
>  	r = kvm_set_memslot(kvm, old, new, change);
>  	if (!r)
> -- 
> 2.17.1
> 