Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Wed, 9 Jun 2021 13:25:44 +0300
From:   "Kirill A. Shutemov" <kirill@shutemov.name>
To:     Hugh Dickins <hughd@google.com>
Cc:     linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 03/10] mm/thp: try_to_unmap() use TTU_SYNC for safe
 splitting (fwd)
Message-ID: <20210609102544.lua6zb6j5g4gpsxx@box.shutemov.name>
References: <6b2b6683-d9a7-b7d0-a3e5-425b96338d63@google.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <6b2b6683-d9a7-b7d0-a3e5-425b96338d63@google.com>
Precedence: bulk

On Tue, Jun 08, 2021 at 09:12:20PM -0700, Hugh Dickins wrote:
> 
> 
> ---------- Forwarded message ----------
> Date: Tue, 8 Jun 2021 21:10:19 -0700 (PDT)
> From: Hugh Dickins <hughd@google.com>
> To: Andrew Morton <akpm@linux-foundation.org>
> Cc: Hugh Dickins <hughd@google.com>,
>     Kirill A. Shutemov <kirill.shutemov@linux.intel.com>,
>     Yang Shi <shy828301@gmail.com>, Wang Yugui <wangyugui@e16-tech.com>,
>     Matthew Wilcox <willy@infradead.org>,
>     Naoya Horiguchi <naoya.horiguchi@nec.com>,
>     Alistair Popple <apopple@nvidia.com>, Ralph Campbell <rcampbell@nvidia.com>,
>     Zi Yan <ziy@nvidia.com>, Miaohe Lin <linmiaohe@huawei.com>,
>     Minchan Kim <minchan@kernel.org>, Jue Wang <juew@google.com>,
>     Peter Xu <peterx@redhat.com>, Jan Kara <jack@suse.cz>,
>     Shakeel Butt <shakeelb@google.com>, Oscar Salvador <osalvador@suse.de>
> Subject: [PATCH v2 03/10] mm/thp: try_to_unmap() use TTU_SYNC for safe splitting
> 
> Stressing huge tmpfs often crashed on unmap_page()'s VM_BUG_ON_PAGE
> (!unmap_success): with dump_page() showing mapcount:1, but then its
> raw struct page output showing _mapcount ffffffff i.e. mapcount 0.
> 
> And even if that particular VM_BUG_ON_PAGE(!unmap_success) is removed,
> it is immediately followed by a VM_BUG_ON_PAGE(compound_mapcount(head)),
> and further down an IS_ENABLED(CONFIG_DEBUG_VM) total_mapcount BUG():
> all indicative of some mapcount difficulty in development here perhaps.
> But the !CONFIG_DEBUG_VM path handles the failures correctly and silently.
> 
> I believe the problem is that once a racing unmap has cleared pte or pmd,
> try_to_unmap_one() may skip taking the page table lock, and emerge from
> try_to_unmap() before the racing task has reached decrementing mapcount.
> 
> Instead of abandoning the unsafe VM_BUG_ON_PAGE(), and the ones that
> follow, use PVMW_SYNC in try_to_unmap_one() in this case: adding TTU_SYNC
> to the options, and passing that from unmap_page().
> 
> When CONFIG_DEBUG_VM, or for non-debug too?  Consensus is to do the same
> for both: the slight overhead added should rarely matter, except perhaps
> if splitting sparsely-populated multiply-mapped shmem.  Once confident
> that bugs are fixed, TTU_SYNC here can be removed, and the race tolerated.
> 
> Fixes: fec89c109f3a ("thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers")
> Signed-off-by: Hugh Dickins <hughd@google.com>
> Cc: <stable@vger.kernel.org>

Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>

-- 
 Kirill A. Shutemov