diff mbox series

[v4,9/9] iomap: Copy larger chunks from userspace

Message ID 20230710130253.3484695-10-willy@infradead.org (mailing list archive)
State New, archived
Headers show
Series Create large folios in iomap buffered write path | expand

Commit Message

Matthew Wilcox July 10, 2023, 1:02 p.m. UTC 
If we have a large folio, we can copy in larger chunks than PAGE_SIZE.
Start at the maximum page cache size and shrink by half every time we
hit the "we are short on memory" problem.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/iomap/buffered-io.c | 32 +++++++++++++++++---------------
 1 file changed, 17 insertions(+), 15 deletions(-)

Comments

Darrick J. Wong July 13, 2023, 4:58 a.m. UTC | #1 
On Mon, Jul 10, 2023 at 02:02:53PM +0100, Matthew Wilcox (Oracle) wrote:
> If we have a large folio, we can copy in larger chunks than PAGE_SIZE.
> Start at the maximum page cache size and shrink by half every time we
> hit the "we are short on memory" problem.
> 
> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
> Reviewed-by: Christoph Hellwig <hch@lst.de>

Looks good!
Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

> ---
>  fs/iomap/buffered-io.c | 32 +++++++++++++++++---------------
>  1 file changed, 17 insertions(+), 15 deletions(-)
> 
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 2d3e90f4d16e..f21f1f641c4a 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -769,6 +769,7 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
>  static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
>  {
>  	loff_t length = iomap_length(iter);
> +	size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
>  	loff_t pos = iter->pos;
>  	ssize_t written = 0;
>  	long status = 0;
> @@ -777,15 +778,12 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
>  
>  	do {
>  		struct folio *folio;
> -		struct page *page;
> -		unsigned long offset;	/* Offset into pagecache page */
> -		unsigned long bytes;	/* Bytes to write to page */
> +		size_t offset;		/* Offset into folio */
> +		size_t bytes;		/* Bytes to write to folio */
>  		size_t copied;		/* Bytes copied from user */
>  
> -		offset = offset_in_page(pos);
> -		bytes = min_t(unsigned long, PAGE_SIZE - offset,
> -						iov_iter_count(i));
> -again:
> +		offset = pos & (chunk - 1);
> +		bytes = min(chunk - offset, iov_iter_count(i));
>  		status = balance_dirty_pages_ratelimited_flags(mapping,
>  							       bdp_flags);
>  		if (unlikely(status))
> @@ -815,12 +813,14 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
>  		if (iter->iomap.flags & IOMAP_F_STALE)
>  			break;
>  
> -		page = folio_file_page(folio, pos >> PAGE_SHIFT);
> -		if (mapping_writably_mapped(mapping))
> -			flush_dcache_page(page);
> +		offset = offset_in_folio(folio, pos);
> +		if (bytes > folio_size(folio) - offset)
> +			bytes = folio_size(folio) - offset;
>  
> -		copied = copy_page_from_iter_atomic(page, offset, bytes, i);
> +		if (mapping_writably_mapped(mapping))
> +			flush_dcache_folio(folio);
>  
> +		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
>  		status = iomap_write_end(iter, pos, bytes, copied, folio);
>  
>  		if (unlikely(copied != status))
> @@ -836,11 +836,13 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
>  			 */
>  			if (copied)
>  				bytes = copied;
> -			goto again;
> +			if (chunk > PAGE_SIZE)
> +				chunk /= 2;
> +		} else {
> +			pos += status;
> +			written += status;
> +			length -= status;
>  		}
> -		pos += status;
> -		written += status;
> -		length -= status;
>  	} while (iov_iter_count(i) && length);
>  
>  	if (status == -EAGAIN) {
> -- 
> 2.39.2
>
diff mbox series

Patch

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 2d3e90f4d16e..f21f1f641c4a 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -769,6 +769,7 @@  static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 {
 	loff_t length = iomap_length(iter);
+	size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
 	loff_t pos = iter->pos;
 	ssize_t written = 0;
 	long status = 0;
@@ -777,15 +778,12 @@  static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 
 	do {
 		struct folio *folio;
-		struct page *page;
-		unsigned long offset;	/* Offset into pagecache page */
-		unsigned long bytes;	/* Bytes to write to page */
+		size_t offset;		/* Offset into folio */
+		size_t bytes;		/* Bytes to write to folio */
 		size_t copied;		/* Bytes copied from user */
 
-		offset = offset_in_page(pos);
-		bytes = min_t(unsigned long, PAGE_SIZE - offset,
-						iov_iter_count(i));
-again:
+		offset = pos & (chunk - 1);
+		bytes = min(chunk - offset, iov_iter_count(i));
 		status = balance_dirty_pages_ratelimited_flags(mapping,
 							       bdp_flags);
 		if (unlikely(status))
@@ -815,12 +813,14 @@  static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		if (iter->iomap.flags & IOMAP_F_STALE)
 			break;
 
-		page = folio_file_page(folio, pos >> PAGE_SHIFT);
-		if (mapping_writably_mapped(mapping))
-			flush_dcache_page(page);
+		offset = offset_in_folio(folio, pos);
+		if (bytes > folio_size(folio) - offset)
+			bytes = folio_size(folio) - offset;
 
-		copied = copy_page_from_iter_atomic(page, offset, bytes, i);
+		if (mapping_writably_mapped(mapping))
+			flush_dcache_folio(folio);
 
+		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
 		status = iomap_write_end(iter, pos, bytes, copied, folio);
 
 		if (unlikely(copied != status))
@@ -836,11 +836,13 @@  static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 			 */
 			if (copied)
 				bytes = copied;
-			goto again;
+			if (chunk > PAGE_SIZE)
+				chunk /= 2;
+		} else {
+			pos += status;
+			written += status;
+			length -= status;
 		}
-		pos += status;
-		written += status;
-		length -= status;
 	} while (iov_iter_count(i) && length);
 
 	if (status == -EAGAIN) {