[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Z+y4E3tcOCOJxCiS@yzhao56-desk.sh.intel.com>
Date: Wed, 2 Apr 2025 12:07:47 +0800
From: Yan Zhao <yan.y.zhao@...el.com>
To: Ackerley Tng <ackerleytng@...gle.com>
CC: <tabba@...gle.com>, <quic_eberman@...cinc.com>, <roypat@...zon.co.uk>,
<jgg@...dia.com>, <peterx@...hat.com>, <david@...hat.com>,
<rientjes@...gle.com>, <fvdl@...gle.com>, <jthoughton@...gle.com>,
<seanjc@...gle.com>, <pbonzini@...hat.com>, <zhiquan1.li@...el.com>,
<fan.du@...el.com>, <jun.miao@...el.com>, <isaku.yamahata@...el.com>,
<muchun.song@...ux.dev>, <mike.kravetz@...cle.com>, <erdemaktas@...gle.com>,
<vannapurve@...gle.com>, <qperret@...gle.com>, <jhubbard@...dia.com>,
<willy@...radead.org>, <shuah@...nel.org>, <brauner@...nel.org>,
<bfoster@...hat.com>, <kent.overstreet@...ux.dev>, <pvorel@...e.cz>,
<rppt@...nel.org>, <richard.weiyang@...il.com>, <anup@...infault.org>,
<haibo1.xu@...el.com>, <ajones@...tanamicro.com>, <vkuznets@...hat.com>,
<maciej.wieczor-retman@...el.com>, <pgonda@...gle.com>,
<oliver.upton@...ux.dev>, <linux-kernel@...r.kernel.org>,
<linux-mm@...ck.org>, <kvm@...r.kernel.org>,
<linux-kselftest@...r.kernel.org>, <linux-fsdevel@...ck.org>,
<rick.p.edgecombe@...el.com>
Subject: Re: [RFC PATCH 27/39] KVM: guest_memfd: Allow mmapping guest_memfd
files
On Tue, Sep 10, 2024 at 11:43:58PM +0000, Ackerley Tng wrote:
> guest_memfd files can always be mmap()ed to userspace, but
> faultability is controlled by an attribute on the inode.
>
> Co-developed-by: Fuad Tabba <tabba@...gle.com>
> Signed-off-by: Fuad Tabba <tabba@...gle.com>
> Co-developed-by: Ackerley Tng <ackerleytng@...gle.com>
> Signed-off-by: Ackerley Tng <ackerleytng@...gle.com>
>
> ---
> virt/kvm/guest_memfd.c | 46 ++++++++++++++++++++++++++++++++++++++++--
> 1 file changed, 44 insertions(+), 2 deletions(-)
>
> diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
> index b603518f7b62..fc2483e35876 100644
> --- a/virt/kvm/guest_memfd.c
> +++ b/virt/kvm/guest_memfd.c
> @@ -781,7 +781,8 @@ static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
> {
Hi Ackerley,
If userspace mmaps a guest_memfd to a VA when a GFN range is shared, it looks
that even after the GFN range has been successfully converted to private,
userspace can still call madvise(mem, size, MADV_REMOVE) on the userspace VA.
This action triggers kvm_gmem_punch_hole() and kvm_gmem_invalidate_begin(),
which can zap the private GFNs in the EPT.
Is this behavior intended for in-place conversion, and could it potentially lead
to private GFN ranges being accidentally zapped from the EPT?
Apologies if I missed any related discussions on this topic.
Thanks
Yan
> struct list_head *gmem_list = &inode->i_mapping->i_private_list;
> pgoff_t start = offset >> PAGE_SHIFT;
> - pgoff_t end = (offset + len) >> PAGE_SHIFT;
> + pgoff_t nr = len >> PAGE_SHIFT;
> + pgoff_t end = start + nr;
> struct kvm_gmem *gmem;
>
> /*
> @@ -790,6 +791,9 @@ static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
> */
> filemap_invalidate_lock(inode->i_mapping);
>
> + /* TODO: Check if even_cows should be 0 or 1 */
> + unmap_mapping_range(inode->i_mapping, start, len, 0);
> +
> list_for_each_entry(gmem, gmem_list, entry)
> kvm_gmem_invalidate_begin(gmem, start, end);
>
Powered by blists - more mailing lists