Received-SPF: pass (google.com: domain of linux-kernel+bounces-120495-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Message-ID: <c97ba53f-b11e-42e3-a528-54a83884eec1@suse.cz>
Date: Wed, 27 Mar 2024 09:06:33 +0100
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH 09/10] mm: page_isolation: prepare for hygienic freelists
To: Johannes Weiner <hannes@cmpxchg.org>,
 Andrew Morton <akpm@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>, Zi Yan <ziy@nvidia.com>,
 "Huang, Ying" <ying.huang@intel.com>, David Hildenbrand <david@redhat.com>,
 linux-mm@kvack.org, linux-kernel@vger.kernel.org
References: <20240320180429.678181-1-hannes@cmpxchg.org>
 <20240320180429.678181-10-hannes@cmpxchg.org>
Content-Language: en-US
From: Vlastimil Babka <vbabka@suse.cz>
In-Reply-To: <20240320180429.678181-10-hannes@cmpxchg.org>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit

On 3/20/24 7:02 PM, Johannes Weiner wrote:
> Page isolation currently sets MIGRATE_ISOLATE on a block, then drops
> zone->lock and scans the block for straddling buddies to split
> up. Because this happens non-atomically wrt the page allocator, it's
> possible for allocations to get a buddy whose first block is a regular
> pcp migratetype but whose tail is isolated. This means that in certain
> cases memory can still be allocated after isolation. It will also
> trigger the freelist type hygiene warnings in subsequent patches.
> 
> start_isolate_page_range()
>   isolate_single_pageblock()
>     set_migratetype_isolate(tail)
>       lock zone->lock
>       move_freepages_block(tail) // nop
>       set_pageblock_migratetype(tail)
>       unlock zone->lock
>                                                      __rmqueue_smallest()
>                                                        del_page_from_freelist(head)
>                                                        expand(head, head_mt)
>                                                          WARN(head_mt != tail_mt)
>     start_pfn = ALIGN_DOWN(MAX_ORDER_NR_PAGES)
>     for (pfn = start_pfn, pfn < end_pfn)
>       if (PageBuddy())
>         split_free_page(head)
> 
> Introduce a variant of move_freepages_block() provided by the
> allocator specifically for page isolation; it moves free pages,
> converts the block, and handles the splitting of straddling buddies
> while holding zone->lock.
> 
> The allocator knows that pageblocks and buddies are always naturally
> aligned, which means that buddies can only straddle blocks if they're
> actually >pageblock_order. This means the search-and-split part can be
> simplified compared to what page isolation used to do.
> 
> Also tighten up the page isolation code around the expectations of
> which pages can be large, and how they are freed.
> 
> Based on extensive discussions with and invaluable input from Zi Yan.
> 
> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>

Nice cleanup of hairy code as well!

Reviewed-by: Vlastimil Babka <vbabka@suse.cz>