linux-kernel - Re: [PATCH 2/2] mm: shmem: improve the tmpfs large folio read performance

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: <1cb50014-8678-40de-bca3-8a33555ec70e@huawei.com>
Date: Wed, 16 Oct 2024 20:36:34 +0800
From: Kefeng Wang <wangkefeng.wang@...wei.com>
To: Baolin Wang <baolin.wang@...ux.alibaba.com>, <akpm@...ux-foundation.org>,
	<hughd@...gle.com>
CC: <willy@...radead.org>, <david@...hat.com>, <linux-mm@...ck.org>,
	<linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 2/2] mm: shmem: improve the tmpfs large folio read
 performance



On 2024/10/16 18:09, Baolin Wang wrote:
> The tmpfs has already supported the PMD-sized large folios, but the tmpfs
> read operation still performs copying at the PAGE SIZE granularity, which
> is unreasonable. This patch changes to copy data at the folio granularity,
> which can improve the read performance, as well as changing to use folio
> related functions.
> 
> Use 'fio bs=64k' to read a 1G tmpfs file populated with 2M THPs, and I can
> see about 20% performance improvement, and no regression with bs=4k.
> Before the patch:
> READ: bw=10.0GiB/s
> 
> After the patch:
> READ: bw=12.0GiB/s
> 
> Signed-off-by: Baolin Wang <baolin.wang@...ux.alibaba.com>
> ---
>   mm/shmem.c | 22 ++++++++++++----------
>   1 file changed, 12 insertions(+), 10 deletions(-)
> 
> diff --git a/mm/shmem.c b/mm/shmem.c
> index edab02a26aac..7e79b6a96da0 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -3108,13 +3108,12 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   	ssize_t retval = 0;
>   
>   	index = iocb->ki_pos >> PAGE_SHIFT;
> -	offset = iocb->ki_pos & ~PAGE_MASK;
>   
>   	for (;;) {
>   		struct folio *folio = NULL;
> -		struct page *page = NULL;
>   		unsigned long nr, ret;
>   		loff_t end_offset, i_size = i_size_read(inode);
> +		size_t fsize;
>   
>   		if (unlikely(iocb->ki_pos >= i_size))
>   			break;
> @@ -3128,8 +3127,9 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   		if (folio) {
>   			folio_unlock(folio);
>   
> -			page = folio_file_page(folio, index);
> -			if (PageHWPoison(page)) {
> +			if (folio_test_hwpoison(folio) ||
> +			    (folio_test_large(folio) &&
> +			     folio_test_has_hwpoisoned(folio))) {
>   				folio_put(folio);
>   				error = -EIO;
>   				break;
> @@ -3147,7 +3147,12 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   			break;
>   		}
>   		end_offset = min_t(loff_t, i_size, iocb->ki_pos + to->count);
> -		nr = min_t(loff_t, end_offset - iocb->ki_pos, PAGE_SIZE - offset);
> +		if (folio)
> +			fsize = folio_size(folio);
> +		else
> +			fsize = PAGE_SIZE;
> +		offset = iocb->ki_pos & (fsize - 1);
> +		nr = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset);
>   
>   		if (folio) {
>   			/*
> @@ -3156,7 +3161,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   			 * before reading the page on the kernel side.
>   			 */

We'd better to update all the comment from page to folio.

>   			if (mapping_writably_mapped(mapping))
> -				flush_dcache_page(page);
> +				flush_dcache_folio(folio);
>   			/*
>   			 * Mark the page accessed if we read the beginning.
>   			 */
> @@ -3166,9 +3171,8 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   			 * Ok, we have the page, and it's up-to-date, so
>   			 * now we can copy it to user space...
>   			 */
> -			ret = copy_page_to_iter(page, offset, nr, to);
> +			ret = copy_folio_to_iter(folio, offset, nr, to);
>   			folio_put(folio);
> -
>   		} else if (user_backed_iter(to)) {
>   			/*
>   			 * Copy to user tends to be so well optimized, but
> @@ -3186,8 +3190,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   		}
>   
>   		retval += ret;
> -		offset += ret;
> -		offset &= ~PAGE_MASK;
>   		iocb->ki_pos += ret;
>   		index = iocb->ki_pos >> PAGE_SHIFT;
>