linux-kernel - Re: [PATCH v8 3/3] mm/vmscan: avoid split lazyfree THP during shrink_folio

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <e7c0aff1-b690-4926-9a34-4e32c9f3faaa@redhat.com>
Date: Mon, 17 Jun 2024 20:04:42 +0200
From: David Hildenbrand <david@...hat.com>
To: Lance Yang <ioworker0@...il.com>, akpm@...ux-foundation.org
Cc: willy@...radead.org, sj@...nel.org, baolin.wang@...ux.alibaba.com,
 maskray@...gle.com, ziy@...dia.com, ryan.roberts@....com, 21cnbao@...il.com,
 mhocko@...e.com, fengwei.yin@...el.com, zokeefe@...gle.com,
 shy828301@...il.com, xiehuan09@...il.com, libang.li@...group.com,
 wangkefeng.wang@...wei.com, songmuchun@...edance.com, peterx@...hat.com,
 minchan@...nel.org, linux-mm@...ck.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v8 3/3] mm/vmscan: avoid split lazyfree THP during
 shrink_folio_list()

Sorry for taking so long to review ... getting there. Mostly nits.

> @@ -497,6 +499,13 @@ static inline void split_huge_pmd_locked(struct vm_area_struct *vma,
>   					 unsigned long address, pmd_t *pmd,
>   					 bool freeze, struct folio *folio) {}
>   
> +static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma,
> +					 unsigned long addr, pmd_t *pmdp,
> +					 struct folio *folio)
> +{
> +	return false;
> +}
> +
>   #define split_huge_pud(__vma, __pmd, __address)	\
>   	do { } while (0)
>   
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index e766d3f3a302..425374ae06ed 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2688,6 +2688,82 @@ static void unmap_folio(struct folio *folio)
>   	try_to_unmap_flush();
>   }
>   
> +static bool __discard_anon_folio_pmd_locked(struct vm_area_struct *vma,
> +					    unsigned long addr, pmd_t *pmdp,
> +					    struct folio *folio)
> +{
> +	VM_WARN_ON_FOLIO(folio_test_swapbacked(folio), folio);
> +	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);

I would drop these (that's exactly what the single caller checks). In 
any case don't place them above the variable declaration ;)

> +
> +	struct mm_struct *mm = vma->vm_mm;
> +	int ref_count, map_count;
> +	pmd_t orig_pmd = *pmdp;
> +	struct page *page;
> +
> +	if (unlikely(!pmd_present(orig_pmd) || !pmd_trans_huge(orig_pmd)))
> +		return false;
> +
> +	page = pmd_page(orig_pmd);
> +	if (unlikely(page_folio(page) != folio))
> +		return false;

I'm curious, how could that happen? And how could it happen that we have 
!pmd_trans_huge() ? Didn't rmap walking code make sure that this PMD 
maps the folio already, and we are holding the PTL?

> +
> +	if (folio_test_dirty(folio) || pmd_dirty(orig_pmd))
> +		return false;
> +
> +	orig_pmd = pmdp_huge_clear_flush(vma, addr, pmdp);
> +
> +	/*
> +	 * Syncing against concurrent GUP-fast:
> +	 * - clear PMD; barrier; read refcount
> +	 * - inc refcount; barrier; read PMD
> +	 */
> +	smp_mb();
> +
> +	ref_count = folio_ref_count(folio);
> +	map_count = folio_mapcount(folio);
> +
> +	/*
> +	 * Order reads for folio refcount and dirty flag
> +	 * (see comments in __remove_mapping()).
> +	 */
> +	smp_rmb();
> +
> +	/*
> +	 * If the folio or its PMD is redirtied at this point, or if there
> +	 * are unexpected references, we will give up to discard this folio
> +	 * and remap it.
> +	 *
> +	 * The only folio refs must be one from isolation plus the rmap(s).
> +	 */
> +	if (folio_test_dirty(folio) || pmd_dirty(orig_pmd) ||
> +	    ref_count != map_count + 1) {
> +		set_pmd_at(mm, addr, pmdp, orig_pmd);
> +		return false;
> +	}
> +
> +	folio_remove_rmap_pmd(folio, page, vma);
> +	zap_deposited_table(mm, pmdp);
> +	add_mm_counter(mm, MM_ANONPAGES, -HPAGE_PMD_NR);
> +	if (vma->vm_flags & VM_LOCKED)
> +		mlock_drain_local();
> +	folio_put(folio);
> +
> +	return true;
> +}
> +
> +bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr,
> +			   pmd_t *pmdp, struct folio *folio)
> +{
> +	VM_WARN_ON_FOLIO(!folio_test_pmd_mappable(folio), folio);
> +	VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);
> +	VM_WARN_ON_ONCE(!IS_ALIGNED(addr, HPAGE_PMD_SIZE));
> +
> +	if (folio_test_anon(folio) && !folio_test_swapbacked(folio))
> +		return __discard_anon_folio_pmd_locked(vma, addr, pmdp, folio);
> +
> +	return false;
> +}
> +
>   static void remap_page(struct folio *folio, unsigned long nr)
>   {
>   	int i = 0;
> diff --git a/mm/rmap.c b/mm/rmap.c
> index dacf24bc82f0..7d97806f74cd 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -1678,16 +1678,23 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
>   			goto walk_abort;
>   		}
>   
> -		if (!pvmw.pte && (flags & TTU_SPLIT_HUGE_PMD)) {
> -			/*
> -			 * We temporarily have to drop the PTL and start once
> -			 * again from that now-PTE-mapped page table.
> -			 */
> -			split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd,
> -					      false, folio);
> -			flags &= ~TTU_SPLIT_HUGE_PMD;
> -			page_vma_mapped_walk_restart(&pvmw);
> -			continue;
> +		if (!pvmw.pte) {
> +			if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd,
> +						  folio))
> +				goto walk_done;
> +
> +			if (flags & TTU_SPLIT_HUGE_PMD) {
> +				/*
> +				 * We temporarily have to drop the PTL and start
> +				 * once again from that now-PTE-mapped page
> +				 * table.

Nit: it's not a PTE-mapped page table.

Maybe

"... restart so we can process the PTE-mapped THP."



>   		}
>   
>   		/* Unexpected PMD-mapped THP? */

Nothing else jumped at me :)

-- 
Cheers,

David / dhildenb