Re: [PATCH] udmabuf: revert 'Add support for mapping hugepages (v4)'

From: David Hildenbrand <david@redhat.com>
To: "Kasireddy, Vivek" <vivek.kasireddy@intel.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"dri-devel@lists.freedesktop.org"
	<dri-devel@lists.freedesktop.org>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
	Hugh Dickins <hughd@google.com>
Cc: "Hocko, Michal" <mhocko@suse.com>,
	"jmarchan@redhat.com" <jmarchan@redhat.com>,
	"Kim, Dongwon" <dongwon.kim@intel.com>,
	"Chang, Junxiao" <junxiao.chang@intel.com>,
	"muchun.song@linux.dev" <muchun.song@linux.dev>,
	"stable@vger.kernel.org" <stable@vger.kernel.org>,
	James Houghton <jthoughton@google.com>,
	Gerd Hoffmann <kraxel@redhat.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	"kirill.shutemov@linux.intel.com"
	<kirill.shutemov@linux.intel.com>
Subject: Re: [PATCH] udmabuf: revert 'Add support for mapping hugepages (v4)'
Date: Mon, 12 Jun 2023 09:46:22 +0200	[thread overview]
Message-ID: <281caf4f-25da-3a73-554b-4fb252963035@redhat.com> (raw)
In-Reply-To: <IA0PR11MB71851B64A5E7062E3BDD8D2FF854A@IA0PR11MB7185.namprd11.prod.outlook.com>

On 12.06.23 09:10, Kasireddy, Vivek wrote:
> Hi Mike,

Hi Vivek,

> 
> Sorry for the late reply; I just got back from vacation.
> If it is unsafe to directly use the subpages of a hugetlb page, then reverting
> this patch seems like the only option for addressing this issue immediately.
> So, this patch is
> Acked-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
> 
> As far as the use-case is concerned, there are two main users of the udmabuf
> driver: Qemu and CrosVM VMMs. However, it appears Qemu is the only one
> that uses hugetlb pages (when hugetlb=on is set) as the backing store for
> Guest (Linux, Android and Windows) system memory. The main goal is to
> share the pages associated with the Guest allocated framebuffer (FB) with
> the Host GPU driver and other components in a zero-copy way. To that end,
> the guest GPU driver (virtio-gpu) allocates 4k size pages (associated with
> the FB) and pins them before sharing the (guest) physical (or dma) addresses
> (and lengths) with Qemu. Qemu then translates the addresses into file
> offsets and shares these offsets with udmabuf.

Is my understanding correct, that we can effectively long-term pin 
(worse than mlock) 64 MiB per UDMABUF_CREATE, allowing eventually !root 
users

ll /dev/udmabuf
crw-rw---- 1 root kvm 10, 125 12. Jun 08:12 /dev/udmabuf

to bypass there effective MEMLOCK limit, fragmenting physical memory and 
breaking swap?

Regarding the udmabuf_vm_fault(), I assume we're mapping pages we 
obtained from the memfd ourselves into a special VMA (mmap() of the 
udmabuf). I'm not sure how well shmem pages are prepared for getting 
mapped by someone else into an arbitrary VMA (page->index?).

... also, just imagine someone doing FALLOC_FL_PUNCH_HOLE / ftruncate() 
on the memfd. What's mapped into the memfd no longer corresponds to 
what's pinned / mapped into the VMA.

Was linux-mm (and especially shmem maintainers, ccing Hugh) involved in 
the upstreaming of udmabuf?

-- 
Cheers,

David / dhildenb