linux-kernel - Re: [PATCH v2 1/3] mm: shmem: simplify the suitable huge orders validation for tmpfs

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: <cf919805-9fb1-4d7a-83bc-60225151cd63@arm.com>
Date: Mon, 15 Jul 2024 14:30:36 +0100
From: Ryan Roberts <ryan.roberts@....com>
To: Baolin Wang <baolin.wang@...ux.alibaba.com>, akpm@...ux-foundation.org,
 hughd@...gle.com
Cc: willy@...radead.org, david@...hat.com, 21cnbao@...il.com, ziy@...dia.com,
 ioworker0@...il.com, linux-mm@...ck.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 1/3] mm: shmem: simplify the suitable huge orders
 validation for tmpfs

On 13/07/2024 14:24, Baolin Wang wrote:
> Move the suitable huge orders validation into shmem_suitable_orders() for
> tmpfs, which can reuse some code to simplify the logic.
> 
> In addition, we don't have special handling for the error code -E2BIG when
> checking for conflicts with PMD sized THP in the pagecache for tmpfs, instead,
> it will just fallback to order-0 allocations like this patch does, so this
> simplification will not add functional changes.
> 
> Signed-off-by: Baolin Wang <baolin.wang@...ux.alibaba.com>

Reviewed-by: Ryan Roberts <ryan.roberts@....com>

> ---
>  mm/shmem.c | 39 +++++++++++++++------------------------
>  1 file changed, 15 insertions(+), 24 deletions(-)
> 
> diff --git a/mm/shmem.c b/mm/shmem.c
> index f24dfbd387ba..db7e9808830f 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1685,19 +1685,29 @@ static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault
>  					   struct address_space *mapping, pgoff_t index,
>  					   unsigned long orders)
>  {
> -	struct vm_area_struct *vma = vmf->vma;
> +	struct vm_area_struct *vma = vmf ? vmf->vma : NULL;
>  	unsigned long pages;
>  	int order;
>  
> -	orders = thp_vma_suitable_orders(vma, vmf->address, orders);
> -	if (!orders)
> -		return 0;
> +	if (vma) {
> +		orders = thp_vma_suitable_orders(vma, vmf->address, orders);
> +		if (!orders)
> +			return 0;
> +	}
>  
>  	/* Find the highest order that can add into the page cache */
>  	order = highest_order(orders);
>  	while (orders) {
>  		pages = 1UL << order;
>  		index = round_down(index, pages);
> +		/*
> +		 * Check for conflict before waiting on a huge allocation.
> +		 * Conflict might be that a huge page has just been allocated
> +		 * and added to page cache by a racing thread, or that there
> +		 * is already at least one small page in the huge extent.
> +		 * Be careful to retry when appropriate, but not forever!
> +		 * Elsewhere -EEXIST would be the right code, but not here.
> +		 */
>  		if (!xa_find(&mapping->i_pages, &index,
>  			     index + pages - 1, XA_PRESENT))
>  			break;
> @@ -1735,7 +1745,6 @@ static struct folio *shmem_alloc_and_add_folio(struct vm_fault *vmf,
>  {
>  	struct address_space *mapping = inode->i_mapping;
>  	struct shmem_inode_info *info = SHMEM_I(inode);
> -	struct vm_area_struct *vma = vmf ? vmf->vma : NULL;
>  	unsigned long suitable_orders = 0;
>  	struct folio *folio = NULL;
>  	long pages;
> @@ -1745,26 +1754,8 @@ static struct folio *shmem_alloc_and_add_folio(struct vm_fault *vmf,
>  		orders = 0;
>  
>  	if (orders > 0) {
> -		if (vma && vma_is_anon_shmem(vma)) {
> -			suitable_orders = shmem_suitable_orders(inode, vmf,
> +		suitable_orders = shmem_suitable_orders(inode, vmf,
>  							mapping, index, orders);
> -		} else if (orders & BIT(HPAGE_PMD_ORDER)) {
> -			pages = HPAGE_PMD_NR;
> -			suitable_orders = BIT(HPAGE_PMD_ORDER);
> -			index = round_down(index, HPAGE_PMD_NR);
> -
> -			/*
> -			 * Check for conflict before waiting on a huge allocation.
> -			 * Conflict might be that a huge page has just been allocated
> -			 * and added to page cache by a racing thread, or that there
> -			 * is already at least one small page in the huge extent.
> -			 * Be careful to retry when appropriate, but not forever!
> -			 * Elsewhere -EEXIST would be the right code, but not here.
> -			 */
> -			if (xa_find(&mapping->i_pages, &index,
> -				    index + HPAGE_PMD_NR - 1, XA_PRESENT))
> -				return ERR_PTR(-E2BIG);
> -		}
>  
>  		order = highest_order(suitable_orders);
>  		while (suitable_orders) {