linux-kernel - Re: [PATCH v3 1/2] mm: Abstract THP allocation

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: <170988b0-db8a-4612-a70c-b20ea2d4c020@huawei.com>
Date: Wed, 11 Sep 2024 18:52:43 +0800
From: Kefeng Wang <wangkefeng.wang@...wei.com>
To: Dev Jain <dev.jain@....com>, <akpm@...ux-foundation.org>,
	<david@...hat.com>, <willy@...radead.org>, <kirill.shutemov@...ux.intel.com>
CC: <ryan.roberts@....com>, <anshuman.khandual@....com>,
	<catalin.marinas@....com>, <cl@...two.org>, <vbabka@...e.cz>,
	<mhocko@...e.com>, <apopple@...dia.com>, <dave.hansen@...ux.intel.com>,
	<will@...nel.org>, <baohua@...nel.org>, <jack@...e.cz>,
	<mark.rutland@....com>, <hughd@...gle.com>, <aneesh.kumar@...nel.org>,
	<yang@...amperecomputing.com>, <peterx@...hat.com>, <ioworker0@...il.com>,
	<jglisse@...gle.com>, <ziy@...dia.com>,
	<linux-arm-kernel@...ts.infradead.org>, <linux-kernel@...r.kernel.org>,
	<linux-mm@...ck.org>
Subject: Re: [PATCH v3 1/2] mm: Abstract THP allocation



On 2024/9/11 14:55, Dev Jain wrote:
> In preparation for the second patch, abstract away the THP allocation
> logic present in the create_huge_pmd() path, which corresponds to the
> faulting case when no page is present.
> 
> There should be no functional change as a result of applying
> this patch.
> 
> Signed-off-by: Dev Jain <dev.jain@....com>
> ---
>   mm/huge_memory.c | 110 +++++++++++++++++++++++++++++------------------
>   1 file changed, 67 insertions(+), 43 deletions(-)
> 
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 67c86a5d64a6..b96a1ff2bf40 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -943,47 +943,88 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
>   }
>   EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
>   
> -static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
> -			struct page *page, gfp_t gfp)
> +static struct folio *pmd_thp_fault_alloc(gfp_t gfp, struct vm_area_struct *vma,
> +					 unsigned long haddr, unsigned long addr)
>   {
> -	struct vm_area_struct *vma = vmf->vma;
> -	struct folio *folio = page_folio(page);
> -	pgtable_t pgtable;
> -	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
> -	vm_fault_t ret = 0;
> +	const int order = HPAGE_PMD_ORDER;

Maybe move vma_thp_gfp_mask() into this function too.

> +	struct folio *folio = vma_alloc_folio(gfp, order, vma, haddr, true);
>   
> -	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
> +	if (unlikely(!folio)) {
> +		count_vm_event(THP_FAULT_FALLBACK);
> +		count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
> +		goto out;
> +	}
>   
> +	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
>   	if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
>   		folio_put(folio);
>   		count_vm_event(THP_FAULT_FALLBACK);
>   		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
> -		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK);
> -		count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
> -		return VM_FAULT_FALLBACK;
> +		count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
> +		count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
> +		goto out;

We need to return NULL here as folio not set to null,

>   	}
>   	folio_throttle_swaprate(folio, gfp);
>   
> -	pgtable = pte_alloc_one(vma->vm_mm);
> -	if (unlikely(!pgtable)) {
> -		ret = VM_FAULT_OOM;
> -		goto release;
> -	}
> -
> -	folio_zero_user(folio, vmf->address);
> +	folio_zero_user(folio, addr);
>   	/*
>   	 * The memory barrier inside __folio_mark_uptodate makes sure that
>   	 * folio_zero_user writes become visible before the set_pmd_at()
>   	 * write.
>   	 */
>   	__folio_mark_uptodate(folio);
> +out:
> +	return folio;
> +}
> +