linux-kernel - Re: [RFC PATCH v2 38/51] KVM: guest_memfd: Split allocator pages for guest

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <558a649d-d419-46e2-adb8-4027e105c1ce@linux.intel.com>
Date: Thu, 5 Jun 2025 13:24:57 +0800
From: Binbin Wu <binbin.wu@...ux.intel.com>
To: Ackerley Tng <ackerleytng@...gle.com>
Cc: kvm@...r.kernel.org, linux-mm@...ck.org, linux-kernel@...r.kernel.org,
 x86@...nel.org, linux-fsdevel@...r.kernel.org, aik@....com,
 ajones@...tanamicro.com, akpm@...ux-foundation.org, amoorthy@...gle.com,
 anthony.yznaga@...cle.com, anup@...infault.org, aou@...s.berkeley.edu,
 bfoster@...hat.com, brauner@...nel.org, catalin.marinas@....com,
 chao.p.peng@...el.com, chenhuacai@...nel.org, dave.hansen@...el.com,
 david@...hat.com, dmatlack@...gle.com, dwmw@...zon.co.uk,
 erdemaktas@...gle.com, fan.du@...el.com, fvdl@...gle.com, graf@...zon.com,
 haibo1.xu@...el.com, hch@...radead.org, hughd@...gle.com,
 ira.weiny@...el.com, isaku.yamahata@...el.com, jack@...e.cz,
 james.morse@....com, jarkko@...nel.org, jgg@...pe.ca, jgowans@...zon.com,
 jhubbard@...dia.com, jroedel@...e.de, jthoughton@...gle.com,
 jun.miao@...el.com, kai.huang@...el.com, keirf@...gle.com,
 kent.overstreet@...ux.dev, kirill.shutemov@...el.com,
 liam.merwick@...cle.com, maciej.wieczor-retman@...el.com,
 mail@...iej.szmigiero.name, maz@...nel.org, mic@...ikod.net,
 michael.roth@....com, mpe@...erman.id.au, muchun.song@...ux.dev,
 nikunj@....com, nsaenz@...zon.es, oliver.upton@...ux.dev,
 palmer@...belt.com, pankaj.gupta@....com, paul.walmsley@...ive.com,
 pbonzini@...hat.com, pdurrant@...zon.co.uk, peterx@...hat.com,
 pgonda@...gle.com, pvorel@...e.cz, qperret@...gle.com,
 quic_cvanscha@...cinc.com, quic_eberman@...cinc.com,
 quic_mnalajal@...cinc.com, quic_pderrin@...cinc.com,
 quic_pheragu@...cinc.com, quic_svaddagi@...cinc.com, quic_tsoni@...cinc.com,
 richard.weiyang@...il.com, rick.p.edgecombe@...el.com, rientjes@...gle.com,
 roypat@...zon.co.uk, rppt@...nel.org, seanjc@...gle.com, shuah@...nel.org,
 steven.price@....com, steven.sistare@...cle.com, suzuki.poulose@....com,
 tabba@...gle.com, thomas.lendacky@....com, usama.arif@...edance.com,
 vannapurve@...gle.com, vbabka@...e.cz, viro@...iv.linux.org.uk,
 vkuznets@...hat.com, wei.w.wang@...el.com, will@...nel.org,
 willy@...radead.org, xiaoyao.li@...el.com, yan.y.zhao@...el.com,
 yilun.xu@...el.com, yuzenghui@...wei.com, zhiquan1.li@...el.com
Subject: Re: [RFC PATCH v2 38/51] KVM: guest_memfd: Split allocator pages for
 guest_memfd use



On 5/15/2025 7:42 AM, Ackerley Tng wrote:
[...]
> +
> +static inline int kvm_gmem_try_split_folio_in_filemap(struct inode *inode,
> +						      struct folio *folio)
> +{
> +	size_t to_nr_pages;
> +	void *priv;
> +
> +	if (!kvm_gmem_has_custom_allocator(inode))
> +		return 0;
> +
> +	priv = kvm_gmem_allocator_private(inode);
> +	to_nr_pages = kvm_gmem_allocator_ops(inode)->nr_pages_in_page(priv);
> +
> +	if (kvm_gmem_has_some_shared(inode, folio->index, to_nr_pages))

What if a huge page whose attribute is shared?

> +		return kvm_gmem_split_folio_in_filemap(inode, folio);
> +
> +	return 0;
> +}
> +
[...]
>   
>   static int kvm_gmem_shareability_setup(struct maple_tree *mt, loff_t size, u64 flags)
> @@ -563,11 +1005,16 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
>   		return folio;
>   
>   	if (kvm_gmem_has_custom_allocator(inode)) {
> -		void *p = kvm_gmem_allocator_private(inode);
> +		size_t nr_pages;
> +		void *p;
>   
> +		p = kvm_gmem_allocator_private(inode);
>   		folio = kvm_gmem_allocator_ops(inode)->alloc_folio(p);
>   		if (IS_ERR(folio))
>   			return folio;
> +
> +		nr_pages = kvm_gmem_allocator_ops(inode)->nr_pages_in_folio(p);
> +		index_floor = round_down(index, nr_pages);
>   	} else {
>   		gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
>   
> @@ -580,10 +1027,11 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
>   			folio_put(folio);
>   			return ERR_PTR(ret);
>   		}
> +
> +		index_floor = index;
>   	}
>   	allocated_size = folio_size(folio);
>   
> -	index_floor = round_down(index, folio_nr_pages(folio));
>   	ret = kvm_gmem_filemap_add_folio(inode->i_mapping, folio, index_floor);
>   	if (ret) {
>   		folio_put(folio);
> @@ -600,6 +1048,13 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
>   		return ERR_PTR(ret);
>   	}
>   
> +	/* Leave just filemap's refcounts on folio. */
> +	folio_put(folio);
> +
> +	ret = kvm_gmem_try_split_folio_in_filemap(inode, folio);

When !CONFIG_KVM_GMEM_SHARED_MEM, kvm_gmem_try_split_folio_in_filemap() is
undefined.

> +	if (ret)
> +		goto err;
> +
>   	spin_lock(&inode->i_lock);
>   	inode->i_blocks += allocated_size / 512;
>   	spin_unlock(&inode->i_lock);
>
[...]