diff mbox series

[v21,5/6] block: Convert bio_iov_iter_get_pages to use iov_iter_extract_pages

Message ID 20230522205744.2825689-6-dhowells@redhat.com (mailing list archive)
State New
Headers show
Series block: Use page pinning | expand

Commit Message

David Howells May 22, 2023, 8:57 p.m. UTC 
This will pin pages or leave them unaltered rather than getting a ref on
them as appropriate to the iterator.

The pages need to be pinned for DIO rather than having refs taken on them to
prevent VM copy-on-write from malfunctioning during a concurrent fork() (the
result of the I/O could otherwise end up being affected by/visible to the
child process).

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: Jens Axboe <axboe@kernel.dk>
cc: Jan Kara <jack@suse.cz>
cc: Matthew Wilcox <willy@infradead.org>
cc: Logan Gunthorpe <logang@deltatee.com>
cc: linux-block@vger.kernel.org
---

Notes:
    ver #10)
     - Drop bio_set_cleanup_mode(), open coding it instead.
    
    ver #8)
     - Split the patch up a bit [hch].
     - We should only be using pinned/non-pinned pages and not ref'd pages,
       so adjust the comments appropriately.
    
    ver #7)
     - Don't treat BIO_PAGE_REFFED/PINNED as being the same as FOLL_GET/PIN.
    
    ver #5)
     - Transcribe the FOLL_* flags returned by iov_iter_extract_pages() to
       BIO_* flags and got rid of bi_cleanup_mode.
     - Replaced BIO_NO_PAGE_REF to BIO_PAGE_REFFED in the preceding patch.

 block/bio.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

Comments

Jan Kara May 23, 2023, 8:15 a.m. UTC | #1 
On Mon 22-05-23 21:57:43, David Howells wrote:
> This will pin pages or leave them unaltered rather than getting a ref on
> them as appropriate to the iterator.
> 
> The pages need to be pinned for DIO rather than having refs taken on them to
> prevent VM copy-on-write from malfunctioning during a concurrent fork() (the
> result of the I/O could otherwise end up being affected by/visible to the
> child process).
> 
> Signed-off-by: David Howells <dhowells@redhat.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: John Hubbard <jhubbard@nvidia.com>
> cc: Al Viro <viro@zeniv.linux.org.uk>
> cc: Jens Axboe <axboe@kernel.dk>
> cc: Jan Kara <jack@suse.cz>
> cc: Matthew Wilcox <willy@infradead.org>
> cc: Logan Gunthorpe <logang@deltatee.com>
> cc: linux-block@vger.kernel.org
> ---

Looks good. Feel free to add:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> 
> Notes:
>     ver #10)
>      - Drop bio_set_cleanup_mode(), open coding it instead.
>     
>     ver #8)
>      - Split the patch up a bit [hch].
>      - We should only be using pinned/non-pinned pages and not ref'd pages,
>        so adjust the comments appropriately.
>     
>     ver #7)
>      - Don't treat BIO_PAGE_REFFED/PINNED as being the same as FOLL_GET/PIN.
>     
>     ver #5)
>      - Transcribe the FOLL_* flags returned by iov_iter_extract_pages() to
>        BIO_* flags and got rid of bi_cleanup_mode.
>      - Replaced BIO_NO_PAGE_REF to BIO_PAGE_REFFED in the preceding patch.
> 
>  block/bio.c | 23 ++++++++++++-----------
>  1 file changed, 12 insertions(+), 11 deletions(-)
> 
> diff --git a/block/bio.c b/block/bio.c
> index 17bd01ecde36..798cc4cf3bd2 100644
> --- a/block/bio.c
> +++ b/block/bio.c
> @@ -1205,7 +1205,7 @@ static int bio_iov_add_page(struct bio *bio, struct page *page,
>  	}
>  
>  	if (same_page)
> -		put_page(page);
> +		bio_release_page(bio, page);
>  	return 0;
>  }
>  
> @@ -1219,7 +1219,7 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
>  			queue_max_zone_append_sectors(q), &same_page) != len)
>  		return -EINVAL;
>  	if (same_page)
> -		put_page(page);
> +		bio_release_page(bio, page);
>  	return 0;
>  }
>  
> @@ -1230,10 +1230,10 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
>   * @bio: bio to add pages to
>   * @iter: iov iterator describing the region to be mapped
>   *
> - * Pins pages from *iter and appends them to @bio's bvec array. The
> - * pages will have to be released using put_page() when done.
> - * For multi-segment *iter, this function only adds pages from the
> - * next non-empty segment of the iov iterator.
> + * Extracts pages from *iter and appends them to @bio's bvec array.  The pages
> + * will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag.
> + * For a multi-segment *iter, this function only adds pages from the next
> + * non-empty segment of the iov iterator.
>   */
>  static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>  {
> @@ -1265,9 +1265,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>  	 * result to ensure the bio's total size is correct. The remainder of
>  	 * the iov data will be picked up in the next bio iteration.
>  	 */
> -	size = iov_iter_get_pages(iter, pages,
> -				  UINT_MAX - bio->bi_iter.bi_size,
> -				  nr_pages, &offset, extraction_flags);
> +	size = iov_iter_extract_pages(iter, &pages,
> +				      UINT_MAX - bio->bi_iter.bi_size,
> +				      nr_pages, extraction_flags, &offset);
>  	if (unlikely(size <= 0))
>  		return size ? size : -EFAULT;
>  
> @@ -1300,7 +1300,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>  	iov_iter_revert(iter, left);
>  out:
>  	while (i < nr_pages)
> -		put_page(pages[i++]);
> +		bio_release_page(bio, pages[i++]);
>  
>  	return ret;
>  }
> @@ -1335,7 +1335,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>  		return 0;
>  	}
>  
> -	bio_set_flag(bio, BIO_PAGE_REFFED);
> +	if (iov_iter_extract_will_pin(iter))
> +		bio_set_flag(bio, BIO_PAGE_PINNED);
>  	do {
>  		ret = __bio_iov_iter_get_pages(bio, iter);
>  	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
>
diff mbox series

Patch

diff --git a/block/bio.c b/block/bio.c
index 17bd01ecde36..798cc4cf3bd2 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1205,7 +1205,7 @@  static int bio_iov_add_page(struct bio *bio, struct page *page,
 	}
 
 	if (same_page)
-		put_page(page);
+		bio_release_page(bio, page);
 	return 0;
 }
 
@@ -1219,7 +1219,7 @@  static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
 			queue_max_zone_append_sectors(q), &same_page) != len)
 		return -EINVAL;
 	if (same_page)
-		put_page(page);
+		bio_release_page(bio, page);
 	return 0;
 }
 
@@ -1230,10 +1230,10 @@  static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins pages from *iter and appends them to @bio's bvec array. The
- * pages will have to be released using put_page() when done.
- * For multi-segment *iter, this function only adds pages from the
- * next non-empty segment of the iov iterator.
+ * Extracts pages from *iter and appends them to @bio's bvec array.  The pages
+ * will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag.
+ * For a multi-segment *iter, this function only adds pages from the next
+ * non-empty segment of the iov iterator.
  */
 static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
@@ -1265,9 +1265,9 @@  static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	 * result to ensure the bio's total size is correct. The remainder of
 	 * the iov data will be picked up in the next bio iteration.
 	 */
-	size = iov_iter_get_pages(iter, pages,
-				  UINT_MAX - bio->bi_iter.bi_size,
-				  nr_pages, &offset, extraction_flags);
+	size = iov_iter_extract_pages(iter, &pages,
+				      UINT_MAX - bio->bi_iter.bi_size,
+				      nr_pages, extraction_flags, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
 
@@ -1300,7 +1300,7 @@  static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	iov_iter_revert(iter, left);
 out:
 	while (i < nr_pages)
-		put_page(pages[i++]);
+		bio_release_page(bio, pages[i++]);
 
 	return ret;
 }
@@ -1335,7 +1335,8 @@  int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 		return 0;
 	}
 
-	bio_set_flag(bio, BIO_PAGE_REFFED);
+	if (iov_iter_extract_will_pin(iter))
+		bio_set_flag(bio, BIO_PAGE_PINNED);
 	do {
 		ret = __bio_iov_iter_get_pages(bio, iter);
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));