Received-SPF: pass (google.com: domain of linux-kernel+bounces-148745-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Message-ID: <2062c2d1-4ebb-4a40-89f9-3083e6912301@redhat.com>
Date: Wed, 17 Apr 2024 17:02:19 +0200
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH 1/1] mm/vmscan: avoid split PMD-mapped THP during
 shrink_folio_list()
To: Lance Yang <ioworker0@gmail.com>, akpm@linux-foundation.org
Cc: willy@infradead.org, maskray@google.com, ziy@nvidia.com,
 ryan.roberts@arm.com, 21cnbao@gmail.com, mhocko@suse.com,
 fengwei.yin@intel.com, zokeefe@google.com, shy828301@gmail.com,
 xiehuan09@gmail.com, wangkefeng.wang@huawei.com, songmuchun@bytedance.com,
 peterx@redhat.com, minchan@kernel.org, linux-mm@kvack.org,
 linux-kernel@vger.kernel.org
References: <20240417141111.77855-1-ioworker0@gmail.com>
From: David Hildenbrand <david@redhat.com>
Content-Language: en-US
Autocrypt: addr=david@redhat.com; keydata=
 xsFNBFXLn5EBEAC+zYvAFJxCBY9Tr1xZgcESmxVNI/0ffzE/ZQOiHJl6mGkmA1R7/uUpiCjJ
 dBrn+lhhOYjjNefFQou6478faXE6o2AhmebqT4KiQoUQFV4R7y1KMEKoSyy8hQaK1umALTdL
 QZLQMzNE74ap+GDK0wnacPQFpcG1AE9RMq3aeErY5tujekBS32jfC/7AnH7I0v1v1TbbK3Gp
 XNeiN4QroO+5qaSr0ID2sz5jtBLRb15RMre27E1ImpaIv2Jw8NJgW0k/D1RyKCwaTsgRdwuK
 Kx/Y91XuSBdz0uOyU/S8kM1+ag0wvsGlpBVxRR/xw/E8M7TEwuCZQArqqTCmkG6HGcXFT0V9
 PXFNNgV5jXMQRwU0O/ztJIQqsE5LsUomE//bLwzj9IVsaQpKDqW6TAPjcdBDPLHvriq7kGjt
 WhVhdl0qEYB8lkBEU7V2Yb+SYhmhpDrti9Fq1EsmhiHSkxJcGREoMK/63r9WLZYI3+4W2rAc
 UucZa4OT27U5ZISjNg3Ev0rxU5UH2/pT4wJCfxwocmqaRr6UYmrtZmND89X0KigoFD/XSeVv
 jwBRNjPAubK9/k5NoRrYqztM9W6sJqrH8+UWZ1Idd/DdmogJh0gNC0+N42Za9yBRURfIdKSb
 B3JfpUqcWwE7vUaYrHG1nw54pLUoPG6sAA7Mehl3nd4pZUALHwARAQABzSREYXZpZCBIaWxk
 ZW5icmFuZCA8ZGF2aWRAcmVkaGF0LmNvbT7CwZgEEwEIAEICGwMGCwkIBwMCBhUIAgkKCwQW
 AgMBAh4BAheAAhkBFiEEG9nKrXNcTDpGDfzKTd4Q9wD/g1oFAl8Ox4kFCRKpKXgACgkQTd4Q
 9wD/g1oHcA//a6Tj7SBNjFNM1iNhWUo1lxAja0lpSodSnB2g4FCZ4R61SBR4l/psBL73xktp
 rDHrx4aSpwkRP6Epu6mLvhlfjmkRG4OynJ5HG1gfv7RJJfnUdUM1z5kdS8JBrOhMJS2c/gPf
 wv1TGRq2XdMPnfY2o0CxRqpcLkx4vBODvJGl2mQyJF/gPepdDfcT8/PY9BJ7FL6Hrq1gnAo4
 3Iv9qV0JiT2wmZciNyYQhmA1V6dyTRiQ4YAc31zOo2IM+xisPzeSHgw3ONY/XhYvfZ9r7W1l
 pNQdc2G+o4Di9NPFHQQhDw3YTRR1opJaTlRDzxYxzU6ZnUUBghxt9cwUWTpfCktkMZiPSDGd
 KgQBjnweV2jw9UOTxjb4LXqDjmSNkjDdQUOU69jGMUXgihvo4zhYcMX8F5gWdRtMR7DzW/YE
 BgVcyxNkMIXoY1aYj6npHYiNQesQlqjU6azjbH70/SXKM5tNRplgW8TNprMDuntdvV9wNkFs
 9TyM02V5aWxFfI42+aivc4KEw69SE9KXwC7FSf5wXzuTot97N9Phj/Z3+jx443jo2NR34XgF
 89cct7wJMjOF7bBefo0fPPZQuIma0Zym71cP61OP/i11ahNye6HGKfxGCOcs5wW9kRQEk8P9
 M/k2wt3mt/fCQnuP/mWutNPt95w9wSsUyATLmtNrwccz63XOwU0EVcufkQEQAOfX3n0g0fZz
 Bgm/S2zF/kxQKCEKP8ID+Vz8sy2GpDvveBq4H2Y34XWsT1zLJdvqPI4af4ZSMxuerWjXbVWb
 T6d4odQIG0fKx4F8NccDqbgHeZRNajXeeJ3R7gAzvWvQNLz4piHrO/B4tf8svmRBL0ZB5P5A
 2uhdwLU3NZuK22zpNn4is87BPWF8HhY0L5fafgDMOqnf4guJVJPYNPhUFzXUbPqOKOkL8ojk
 CXxkOFHAbjstSK5Ca3fKquY3rdX3DNo+EL7FvAiw1mUtS+5GeYE+RMnDCsVFm/C7kY8c2d0G
 NWkB9pJM5+mnIoFNxy7YBcldYATVeOHoY4LyaUWNnAvFYWp08dHWfZo9WCiJMuTfgtH9tc75
 7QanMVdPt6fDK8UUXIBLQ2TWr/sQKE9xtFuEmoQGlE1l6bGaDnnMLcYu+Asp3kDT0w4zYGsx
 5r6XQVRH4+5N6eHZiaeYtFOujp5n+pjBaQK7wUUjDilPQ5QMzIuCL4YjVoylWiBNknvQWBXS
 lQCWmavOT9sttGQXdPCC5ynI+1ymZC1ORZKANLnRAb0NH/UCzcsstw2TAkFnMEbo9Zu9w7Kv
 AxBQXWeXhJI9XQssfrf4Gusdqx8nPEpfOqCtbbwJMATbHyqLt7/oz/5deGuwxgb65pWIzufa
 N7eop7uh+6bezi+rugUI+w6DABEBAAHCwXwEGAEIACYCGwwWIQQb2cqtc1xMOkYN/MpN3hD3
 AP+DWgUCXw7HsgUJEqkpoQAKCRBN3hD3AP+DWrrpD/4qS3dyVRxDcDHIlmguXjC1Q5tZTwNB
 boaBTPHSy/Nksu0eY7x6HfQJ3xajVH32Ms6t1trDQmPx2iP5+7iDsb7OKAb5eOS8h+BEBDeq
 3ecsQDv0fFJOA9ag5O3LLNk+3x3q7e0uo06XMaY7UHS341ozXUUI7wC7iKfoUTv03iO9El5f
 XpNMx/YrIMduZ2+nd9Di7o5+KIwlb2mAB9sTNHdMrXesX8eBL6T9b+MZJk+mZuPxKNVfEQMQ
 a5SxUEADIPQTPNvBewdeI80yeOCrN+Zzwy/Mrx9EPeu59Y5vSJOx/z6OUImD/GhX7Xvkt3kq
 Er5KTrJz3++B6SH9pum9PuoE/k+nntJkNMmQpR4MCBaV/J9gIOPGodDKnjdng+mXliF3Ptu6
 3oxc2RCyGzTlxyMwuc2U5Q7KtUNTdDe8T0uE+9b8BLMVQDDfJjqY0VVqSUwImzTDLX9S4g/8
 kC4HRcclk8hpyhY2jKGluZO0awwTIMgVEzmTyBphDg/Gx7dZU1Xf8HFuE+UZ5UDHDTnwgv7E
 th6RC9+WrhDNspZ9fJjKWRbveQgUFCpe1sa77LAw+XFrKmBHXp9ZVIe90RMe2tRL06BGiRZr
 jPrnvUsUUsjRoRNJjKKA/REq+sAnhkNPPZ/NNMjaZ5b8Tovi8C0tmxiCHaQYqj7G2rgnT0kt
 WNyWQQ==
Organization: Red Hat
In-Reply-To: <20240417141111.77855-1-ioworker0@gmail.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit

On 17.04.24 16:11, Lance Yang wrote:
> When the user no longer requires the pages, they would use madvise(madv_free)
> to mark the pages as lazy free. IMO, they would not typically rewrite to the
> given range.
> 
> At present, a PMD-mapped THP marked as lazyfree during shrink_folio_list()
> is unconditionally split, which may be unnecessary. If the THP is exclusively
> mapped and clean, and the PMD associated with it is also clean, then we can
> attempt to remove the PMD mapping from it. This change will improve the
> efficiency of memory reclamation in this case.
> 
> On an Intel i5 CPU, reclaiming 1GiB of PMD-mapped THPs using
> mem_cgroup_force_empty() results in the following runtimes in seconds
> (shorter is better):
> 
> --------------------------------------------
> |     Old       |      New       |  Change  |
> --------------------------------------------
> |   0.683426    |    0.049197    |  -92.80% |
> --------------------------------------------
> 
> Signed-off-by: Lance Yang <ioworker0@gmail.com>
> ---
>   include/linux/huge_mm.h |  1 +
>   include/linux/rmap.h    |  1 +
>   mm/huge_memory.c        |  2 +-
>   mm/rmap.c               | 81 +++++++++++++++++++++++++++++++++++++++++
>   mm/vmscan.c             |  7 ++++
>   5 files changed, 91 insertions(+), 1 deletion(-)
> 
> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> index 7cd07b83a3d0..02a71c05f68a 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -36,6 +36,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
>   int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
>   		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
>   		    unsigned long cp_flags);
> +inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd);
>   
>   vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
>   vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
> diff --git a/include/linux/rmap.h b/include/linux/rmap.h
> index 0f906dc6d280..8c2f45713351 100644
> --- a/include/linux/rmap.h
> +++ b/include/linux/rmap.h
> @@ -100,6 +100,7 @@ enum ttu_flags {
>   					 * do a final flush if necessary */
>   	TTU_RMAP_LOCKED		= 0x80,	/* do not grab rmap lock:
>   					 * caller holds it */
> +	TTU_LAZYFREE_THP	= 0x100, /* avoid split PMD-mapped THP */
>   };
>   
>   #ifdef CONFIG_MMU
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 58f2c4745d80..309fba9624c2 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1801,7 +1801,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
>   	return ret;
>   }
>   
> -static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
> +inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
>   {
>   	pgtable_t pgtable;
>   
> diff --git a/mm/rmap.c b/mm/rmap.c
> index 2608c40dffad..4994f9e402d4 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -77,6 +77,7 @@
>   #include <linux/mm_inline.h>
>   
>   #include <asm/tlbflush.h>
> +#include <asm/tlb.h>
>   
>   #define CREATE_TRACE_POINTS
>   #include <trace/events/tlb.h>
> @@ -1606,6 +1607,80 @@ void folio_remove_rmap_pmd(struct folio *folio, struct page *page,
>   #endif
>   }
>   
> +static bool __try_to_unmap_lazyfree_thp(struct vm_area_struct *vma,
> +					     unsigned long address,
> +					     struct folio *folio)
> +{
> +	spinlock_t *ptl;
> +	pmd_t *pmdp, orig_pmd;
> +	struct mmu_notifier_range range;
> +	struct mmu_gather tlb;
> +	struct mm_struct *mm = vma->vm_mm;
> +	struct page *page;
> +	bool ret = false;
> +
> +	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
> +	VM_WARN_ON_FOLIO(folio_test_swapbacked(folio), folio);
> +	VM_WARN_ON_FOLIO(!folio_test_pmd_mappable(folio), folio);
> +	VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);
> +
> +	/*
> +	 * If we encounter a PMD-mapped THP that marked as lazyfree, we
> +	 * will try to unmap it without splitting.
> +	 *
> +	 * The folio exclusively mapped should only have two refs:
> +	 * one from the isolation and one from the rmap.
> +	 */
> +	if (folio_entire_mapcount(folio) != 1 || folio_test_dirty(folio) ||
> +	    folio_ref_count(folio) != 2)

folio_mapcount() == 1 is a bit nicer. Bit I assume you can drop that 
completely and only check the refcount?

> +		return false;
> +
> +	pmdp = mm_find_pmd(mm, address);
> +	if (unlikely(!pmdp))
> +		return false;
> +	if (pmd_dirty(*pmdp))
> +		return false;
> +
> +	tlb_gather_mmu(&tlb, mm);
> +	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
> +				address & HPAGE_PMD_MASK,
> +				(address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE);
> +	mmu_notifier_invalidate_range_start(&range);
> +
> +	ptl = pmd_lock(mm, pmdp);
> +	orig_pmd = *pmdp;
> +	if (unlikely(!pmd_present(orig_pmd) || !pmd_trans_huge(orig_pmd)))
> +		goto out;
> +
> +	page = pmd_page(orig_pmd);
> +	if (unlikely(page_folio(page) != folio))
> +		goto out;
> +
> +	orig_pmd = pmdp_huge_get_and_clear(mm, address, pmdp);
> +	tlb_remove_pmd_tlb_entry(&tlb, pmdp, address);

Until this point, the page could have been pinned (including GUP-fast) 
and we might be in trouble if we drop it.

-- 
Cheers,

David / dhildenb