Received-SPF: pass (google.com: domain of linux-kernel+bounces-63498-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Message-ID: <487c0bec-4229-4add-bec4-1711f0b9bbee@suse.de>
Date: Tue, 13 Feb 2024 13:20:50 +0100
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [RFC v2 02/14] filemap: align the index to mapping_min_order in
 the page cache
Content-Language: en-US
To: "Pankaj Raghav (Samsung)" <kernel@pankajraghav.com>,
 linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org
Cc: mcgrof@kernel.org, gost.dev@samsung.com, akpm@linux-foundation.org,
 kbusch@kernel.org, djwong@kernel.org, chandan.babu@oracle.com,
 p.raghav@samsung.com, linux-kernel@vger.kernel.org, willy@infradead.org,
 linux-mm@kvack.org, david@fromorbit.com
References: <20240213093713.1753368-1-kernel@pankajraghav.com>
 <20240213093713.1753368-3-kernel@pankajraghav.com>
From: Hannes Reinecke <hare@suse.de>
In-Reply-To: <20240213093713.1753368-3-kernel@pankajraghav.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit

On 2/13/24 10:37, Pankaj Raghav (Samsung) wrote:
> From: Luis Chamberlain <mcgrof@kernel.org>
> 
> Supporting mapping_min_order implies that we guarantee each folio in the
> page cache has at least an order of mapping_min_order. So when adding new
> folios to the page cache we must ensure the index used is aligned to the
> mapping_min_order as the page cache requires the index to be aligned to
> the order of the folio.
> 
> A higher order folio than min_order by definition is a multiple of the
> min_order. If an index is aligned to an order higher than a min_order, it
> will also be aligned to the min order.
> 
> This effectively introduces no new functional changes when min order is
> not set other than a few rounding computations that should result in the
> same value.
> 
> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
> Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
> ---
>   mm/filemap.c | 34 ++++++++++++++++++++++++++--------
>   1 file changed, 26 insertions(+), 8 deletions(-)
> 
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 750e779c23db..323a8e169581 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -2479,14 +2479,16 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
>   {
>   	struct file *filp = iocb->ki_filp;
>   	struct address_space *mapping = filp->f_mapping;
> +	unsigned int min_nrpages = mapping_min_folio_nrpages(mapping);
>   	struct file_ra_state *ra = &filp->f_ra;
> -	pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
> +	pgoff_t index = round_down(iocb->ki_pos >> PAGE_SHIFT, min_nrpages);
>   	pgoff_t last_index;
>   	struct folio *folio;
>   	int err = 0;
>   
>   	/* "last_index" is the index of the page beyond the end of the read */
>   	last_index = DIV_ROUND_UP(iocb->ki_pos + count, PAGE_SIZE);
> +	last_index = round_up(last_index, min_nrpages);

Huh? 'last_index' is unset here; sure you mean 'iocb->ki_pos + count' ?

And what's the rationale to replace 'DIV_ROUND_UP' with 'round_up' ?

>   retry:
>   	if (fatal_signal_pending(current))
>   		return -EINTR;
> @@ -2502,8 +2504,7 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
>   	if (!folio_batch_count(fbatch)) {
>   		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
>   			return -EAGAIN;
> -		err = filemap_create_folio(filp, mapping,
> -				iocb->ki_pos >> PAGE_SHIFT, fbatch);
> +		err = filemap_create_folio(filp, mapping, index, fbatch);
>   		if (err == AOP_TRUNCATED_PAGE)
>   			goto retry;
>   		return err;
> @@ -3095,7 +3096,10 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
>   	struct file *file = vmf->vma->vm_file;
>   	struct file_ra_state *ra = &file->f_ra;
>   	struct address_space *mapping = file->f_mapping;
> -	DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
> +	unsigned int min_order = mapping_min_folio_order(mapping);
> +	unsigned int min_nrpages = mapping_min_folio_nrpages(file->f_mapping);
> +	pgoff_t index = round_down(vmf->pgoff, min_nrpages);
> +	DEFINE_READAHEAD(ractl, file, ra, mapping, index);
>   	struct file *fpin = NULL;
>   	unsigned long vm_flags = vmf->vma->vm_flags;
>   	unsigned int mmap_miss;
> @@ -3147,10 +3151,11 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
>   	 */
>   	fpin = maybe_unlock_mmap_for_io(vmf, fpin);
>   	ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
> +	ra->start = round_down(ra->start, min_nrpages);
>   	ra->size = ra->ra_pages;
>   	ra->async_size = ra->ra_pages / 4;
>   	ractl._index = ra->start;
> -	page_cache_ra_order(&ractl, ra, 0);
> +	page_cache_ra_order(&ractl, ra, min_order);
>   	return fpin;
>   }
>   
> @@ -3164,7 +3169,9 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
>   {
>   	struct file *file = vmf->vma->vm_file;
>   	struct file_ra_state *ra = &file->f_ra;
> -	DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff);
> +	unsigned int min_nrpages = mapping_min_folio_nrpages(file->f_mapping);
> +	pgoff_t index = round_down(vmf->pgoff, min_nrpages);
> +	DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, index);
>   	struct file *fpin = NULL;
>   	unsigned int mmap_miss;
>   
> @@ -3212,13 +3219,17 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
>   	struct file *file = vmf->vma->vm_file;
>   	struct file *fpin = NULL;
>   	struct address_space *mapping = file->f_mapping;
> +	unsigned int min_order = mapping_min_folio_order(mapping);
> +	unsigned int nrpages = 1UL << min_order;
>   	struct inode *inode = mapping->host;
> -	pgoff_t max_idx, index = vmf->pgoff;
> +	pgoff_t max_idx, index = round_down(vmf->pgoff, nrpages);
>   	struct folio *folio;
>   	vm_fault_t ret = 0;
>   	bool mapping_locked = false;
>   
>   	max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
> +	max_idx = round_up(max_idx, nrpages);
> +

Same here.
(And the additional whitespace can probably go ...)

>   	if (unlikely(index >= max_idx))
>   		return VM_FAULT_SIGBUS;
>   
> @@ -3317,13 +3328,17 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
>   	 * We must recheck i_size under page lock.
>   	 */
>   	max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
> +	max_idx = round_up(max_idx, nrpages);
> +

See above.

>   	if (unlikely(index >= max_idx)) {
>   		folio_unlock(folio);
>   		folio_put(folio);
>   		return VM_FAULT_SIGBUS;
>   	}
>   
> -	vmf->page = folio_file_page(folio, index);
> +	VM_BUG_ON_FOLIO(folio_order(folio) < min_order, folio);
> +
> +	vmf->page = folio_file_page(folio, vmf->pgoff);
>   	return ret | VM_FAULT_LOCKED;
>   
>   page_not_uptodate:
> @@ -3658,6 +3673,9 @@ static struct folio *do_read_cache_folio(struct address_space *mapping,
>   {
>   	struct folio *folio;
>   	int err;
> +	unsigned int min_nrpages = mapping_min_folio_nrpages(mapping);
> +
> +	index = round_down(index, min_nrpages);
>   
>   	if (!filler)
>   		filler = mapping->a_ops->read_folio;

Cheers,

Hannes