Re: [PATCH v3 01/12] mm/khugepaged: record SCAN_PMD_MAPPED when scan_pmd() finds THP

[Peter Xu <peterx@redhat.com>]

Hi, Zach,

On Tue, Apr 26, 2022 at 07:44:01AM -0700, Zach O'Keefe wrote:
> When scanning an anon pmd to see if it's eligible for collapse, return
> SCAN_PMD_MAPPED if the pmd already maps a THP.  Note that
> SCAN_PMD_MAPPED is different from SCAN_PAGE_COMPOUND used in the
> file-collapse path, since the latter might identify pte-mapped compound
> pages.  This is required by MADV_COLLAPSE which necessarily needs to
> know what hugepage-aligned/sized regions are already pmd-mapped.
> 
> Signed-off-by: Zach O'Keefe <zokeefe@google.com>
> Reported-by: kernel test robot <lkp@intel.com>

IIUC we don't need to attach this reported-by if this is not a bugfix.  I
think you can simply fix all issues reported by the test bot and only
attach the line if the patch is fixing the problem that the bot was
reporting explicitly.

> ---
>  include/trace/events/huge_memory.h |  3 ++-
>  mm/internal.h                      |  1 +
>  mm/khugepaged.c                    | 30 ++++++++++++++++++++++++++----
>  mm/rmap.c                          | 15 +++++++++++++--
>  4 files changed, 42 insertions(+), 7 deletions(-)
> 
> diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
> index d651f3437367..9faa678e0a5b 100644
> --- a/include/trace/events/huge_memory.h
> +++ b/include/trace/events/huge_memory.h
> @@ -33,7 +33,8 @@
>  	EM( SCAN_ALLOC_HUGE_PAGE_FAIL,	"alloc_huge_page_failed")	\
>  	EM( SCAN_CGROUP_CHARGE_FAIL,	"ccgroup_charge_failed")	\
>  	EM( SCAN_TRUNCATED,		"truncated")			\
> -	EMe(SCAN_PAGE_HAS_PRIVATE,	"page_has_private")		\
> +	EM( SCAN_PAGE_HAS_PRIVATE,	"page_has_private")		\
> +	EMe(SCAN_PMD_MAPPED,		"page_pmd_mapped")		\

Nit: IMHO it can be put even in the middle so we don't need to touch the
EMe() every time. :)

Apart from that, it does sound proper to me to put SCAN_PMD_MAPPED to be
right after SCAN_PMD_NULL anyway.

>  
>  #undef EM
>  #undef EMe
> diff --git a/mm/internal.h b/mm/internal.h
> index 0667abd57634..51ae9f71a2a3 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -172,6 +172,7 @@ extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason
>  /*
>   * in mm/rmap.c:
>   */
> +pmd_t *mm_find_pmd_raw(struct mm_struct *mm, unsigned long address);
>  extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
>  
>  /*
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index ba8dbd1825da..2933b13fc975 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -51,6 +51,7 @@ enum scan_result {
>  	SCAN_CGROUP_CHARGE_FAIL,
>  	SCAN_TRUNCATED,
>  	SCAN_PAGE_HAS_PRIVATE,
> +	SCAN_PMD_MAPPED,
>  };
>  
>  #define CREATE_TRACE_POINTS
> @@ -987,6 +988,29 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
>  	return 0;
>  }
>  
> +static int find_pmd_or_thp_or_none(struct mm_struct *mm,
> +				   unsigned long address,
> +				   pmd_t **pmd)
> +{
> +	pmd_t pmde;
> +
> +	*pmd = mm_find_pmd_raw(mm, address);
> +	if (!*pmd)
> +		return SCAN_PMD_NULL;
> +
> +	pmde = pmd_read_atomic(*pmd);
> +
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> +	/* See comments in pmd_none_or_trans_huge_or_clear_bad() */
> +	barrier();
> +#endif
> +	if (!pmd_present(pmde) || pmd_none(pmde))

Could we drop the pmd_none() check?  I assume !pmd_present() should have
covered that case already?

> +		return SCAN_PMD_NULL;
> +	if (pmd_trans_huge(pmde))
> +		return SCAN_PMD_MAPPED;
> +	return SCAN_SUCCEED;
> +}
> +
>  /*
>   * Bring missing pages in from swap, to complete THP collapse.
>   * Only done if khugepaged_scan_pmd believes it is worthwhile.
> @@ -1238,11 +1262,9 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
>  
>  	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
>  
> -	pmd = mm_find_pmd(mm, address);
> -	if (!pmd) {
> -		result = SCAN_PMD_NULL;
> +	result = find_pmd_or_thp_or_none(mm, address, &pmd);
> +	if (result != SCAN_SUCCEED)
>  		goto out;
> -	}
>  
>  	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
>  	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
> diff --git a/mm/rmap.c b/mm/rmap.c
> index 61e63db5dc6f..49817f35e65c 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -759,13 +759,12 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
>  	return vma_address(page, vma);
>  }
>  
> -pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
> +pmd_t *mm_find_pmd_raw(struct mm_struct *mm, unsigned long address)
>  {
>  	pgd_t *pgd;
>  	p4d_t *p4d;
>  	pud_t *pud;
>  	pmd_t *pmd = NULL;
> -	pmd_t pmde;
>  
>  	pgd = pgd_offset(mm, address);
>  	if (!pgd_present(*pgd))
> @@ -780,6 +779,18 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
>  		goto out;
>  
>  	pmd = pmd_offset(pud, address);
> +out:
> +	return pmd;
> +}
> +
> +pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
> +{
> +	pmd_t pmde;
> +	pmd_t *pmd;
> +
> +	pmd = mm_find_pmd_raw(mm, address);
> +	if (!pmd)
> +		goto out;
>  	/*
>  	 * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at()
>  	 * without holding anon_vma lock for write.  So when looking for a
> -- 
> 2.36.0.rc2.479.g8af0fa9b8e-goog
> 

-- 
Peter Xu