Re: [PATCH v1 2/5] userfaultfd: introduce access-likely mode for common operations

From: Nadav Amit <namit@vmware.com>
To: Peter Xu <peterx@redhat.com>
Cc: Linux MM <linux-mm@kvack.org>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Hugh Dickins <hughd@google.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Axel Rasmussen <axelrasmussen@google.com>,
	David Hildenbrand <david@redhat.com>,
	Mike Rapoport <rppt@linux.ibm.com>,
	Dave Hansen <dave.hansen@linux.intel.com>
Subject: Re: [PATCH v1 2/5] userfaultfd: introduce access-likely mode for common operations
Date: Tue, 28 Jun 2022 21:15:16 +0000	[thread overview]
Message-ID: <CB85D7FA-1009-45B3-985C-0E17CAFADB0E@vmware.com> (raw)
In-Reply-To: <YrtupSKdW/YPkluy@xz-m1.local>

On Jun 28, 2022, at 2:12 PM, Peter Xu <peterx@redhat.com> wrote:

> ⚠ External Email
> 
> On Tue, Jun 28, 2022 at 09:03:02PM +0000, Nadav Amit wrote:
>>> Both shmem & hugetlb support private mappings for all three modes, afaict.
>> 
>> Sorry, let me more clear. I meant private (!VM_SHARED) file-backed memory.
> 
> I normally use "file-backed" to stand for "shmem + hugetlb" in any uffd
> context.
> 
> If you meant anything outside shmem/hugetlb for uffd (e.g. on xfs), then we
> never support them anyway, do we?
> 
> Hmm.. What am I ultimately missing?

You are not missing anything. We just have communication problems.

I meant - we do not support uffd+xfs today, but maybe one day we will. I do
not know/think of any implications WRITE_HINT should have in such case, but
it would be useful to have the option to decide how to handle something like
that in the future (and not bind ourselves to certain behavior now).