Re: [PATCH] mm,do_huge_pmd_numa_page: remove unnecessary TLB flushing code

From: "Huang, Ying" <ying.huang@intel.com>
To: Sean Christopherson <seanjc@google.com>
Cc: Yang Shi <shy828301@gmail.com>, Zi Yan <ziy@nvidia.com>,
	Christian Borntraeger <borntraeger@de.ibm.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linux MM <linux-mm@kvack.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Dan Carpenter <dan.carpenter@oracle.com>,
	Mel Gorman <mgorman@suse.de>,
	Gerald Schaefer <gerald.schaefer@linux.ibm.com>,
	Heiko Carstens <hca@linux.ibm.com>,
	Hugh Dickins <hughd@google.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	Michal Hocko <mhocko@suse.com>, Vasily Gorbik <gor@linux.ibm.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	kvm list <kvm@vger.kernel.org>
Subject: Re: [PATCH] mm,do_huge_pmd_numa_page: remove unnecessary TLB flushing code
Date: Thu, 22 Jul 2021 08:26:34 +0800	[thread overview]
Message-ID: <87lf5z9osl.fsf@yhuang6-desk2.ccr.corp.intel.com> (raw)
In-Reply-To: <YPhAEcHOCZ5yII/T@google.com> (Sean Christopherson's message of "Wed, 21 Jul 2021 15:41:05 +0000")

Sean Christopherson <seanjc@google.com> writes:
>> 
>> Thanks, I think you are correct. By looking into commit 7066f0f933a1
>> ("mm: thp: fix mmu_notifier in migrate_misplaced_transhuge_page()"),
>> the tlb flush and mmu notifier invalidate were needed since the old
>> numa fault implementation didn't change PTE to migration entry so it
>> may cause data corruption due to the writes from GPU secondary MMU.
>> 
>> The refactor does use the generic migration code which converts PTE to
>> migration entry before copying data to the new page.
>
> That's my understanding as well, based on this blurb from commit 7066f0f933a1.
>
>     The standard PAGE_SIZEd migrate_misplaced_page is less accelerated and
>     uses the generic migrate_pages which transitions the pte from
>     numa/protnone to a migration entry in try_to_unmap_one() and flushes TLBs
>     and all mmu notifiers there before copying the page.
>
> That analysis/justification for removing the invalidate_range() call should be
> captured in the changelog.  Confirmation from Andrea would be a nice bonus.

When we flush CPU TLB for a page that may be shared with device/VM TLB,
we will call MMU notifiers for the page to flush the device/VM TLB.
Right?  So when we replaced CPU TLB flushing in do_huge_pmd_numa_page()
with that in try_to_migrate_one(), we will replace the MMU notifiers
calling too.  Do you agree?

Best Regards,
Huang, Ying