diff mbox series

[v8,3/5] block: introduce folio awareness and add a bigger size from folio

Message ID 20240711050750.17792-4-kundan.kumar@samsung.com (mailing list archive)
State New, archived
Headers show
Series block: add larger order folio instead of pages | expand

Commit Message

Kundan Kumar July 11, 2024, 5:07 a.m. UTC 
Add a bigger size from folio to bio and skip merge processing for pages.

Fetch the offset of page within a folio. Depending on the size of folio
and folio_offset, fetch a larger length. This length may consist of
multiple contiguous pages if folio is multiorder.

Using the length calculate number of pages which will be added to bio and
increment the loop counter to skip those pages.

Using a helper function check if pages are contiguous and belong to same
folio, this is done as a COW may happen and change contiguous mapping of
pages of folio.

This technique helps to avoid overhead of merging pages which belong to
same large order folio.

Also folio-lize the functions bio_iov_add_page() and
bio_iov_add_zone_append_page()

Signed-off-by: Kundan Kumar <kundan.kumar@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 block/bio.c | 77 ++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 61 insertions(+), 16 deletions(-)

Comments

Anuj gupta July 25, 2024, 8:56 p.m. UTC | #1 
On Thu, Jul 11, 2024 at 10:50 AM Kundan Kumar <kundan.kumar@samsung.com> wrote:
>
> Using a helper function check if pages are contiguous and belong to same
> folio, this is done as a COW may happen and change contiguous mapping of
> pages of folio.
>
You can consider removing this part in the commit description, as the same
comment is present below in the code as well.

>  #define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
>
>  /**
> @@ -1298,9 +1329,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>         unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
>         struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
>         struct page **pages = (struct page **)bv;
> -       ssize_t size, left;
> -       unsigned len, i = 0;
> -       size_t offset;
> +       ssize_t size;
> +       unsigned int i = 0, num_pages;
> +       size_t offset, folio_offset, left, len;
>         int ret = 0;
>
>         /*
> @@ -1342,15 +1373,29 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
>
>         for (left = size, i = 0; left > 0; left -= len, i++) {
Can we do a i+=num_pages here, given that you are incrementing i by 1 here
and by (num_pages-1) at the end of the loop. This way you can get rid of
the increment that you are doing at the end of the loop.

>                 struct page *page = pages[i];
> +               struct folio *folio = page_folio(page);
> +
> +               folio_offset = ((size_t)folio_page_idx(folio, page) <<
> +                               PAGE_SHIFT) + offset;
> +
> +               len = min_t(size_t, (folio_size(folio) - folio_offset), left);
> +
> +               num_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
> +
> +               if (num_pages > 1)
> +                       len = get_contig_folio_len(&num_pages, pages, i,
> +                                                  folio, left, offset);
>
> -               len = min_t(size_t, PAGE_SIZE - offset, left);
>                 if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
> -                       ret = bio_iov_add_zone_append_page(bio, page, len,
> -                                       offset);
> +                       ret = bio_iov_add_zone_append_folio(bio, folio, len,
> +                                       folio_offset);
>                         if (ret)
>                                 break;
>                 } else
> -                       bio_iov_add_page(bio, page, len, offset);
> +                       bio_iov_add_folio(bio, folio, len, folio_offset);
> +
> +               /* Skip the pages which got added */
> +               i = i + (num_pages - 1);
>
>                 offset = 0;
>         }
> --
> 2.25.1
>
--
Anuj Gupta
diff mbox series

Patch

diff --git a/block/bio.c b/block/bio.c
index a7442f4bbfc6..b4df3af3e303 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1245,8 +1245,8 @@  void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 	bio_set_flag(bio, BIO_CLONED);
 }
 
-static int bio_iov_add_page(struct bio *bio, struct page *page,
-		unsigned int len, unsigned int offset)
+static int bio_iov_add_folio(struct bio *bio, struct folio *folio, size_t len,
+			     size_t offset)
 {
 	bool same_page = false;
 
@@ -1255,30 +1255,61 @@  static int bio_iov_add_page(struct bio *bio, struct page *page,
 
 	if (bio->bi_vcnt > 0 &&
 	    bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1],
-				page, len, offset, &same_page)) {
+				folio_page(folio, 0), len, offset,
+				&same_page)) {
 		bio->bi_iter.bi_size += len;
 		if (same_page)
-			bio_release_page(bio, page);
+			bio_release_page(bio, folio_page(folio, 0));
 		return 0;
 	}
-	__bio_add_page(bio, page, len, offset);
+	bio_add_folio_nofail(bio, folio, len, offset);
 	return 0;
 }
 
-static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
-		unsigned int len, unsigned int offset)
+static int bio_iov_add_zone_append_folio(struct bio *bio, struct folio *folio,
+					 size_t len, size_t offset)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	bool same_page = false;
 
-	if (bio_add_hw_page(q, bio, page, len, offset,
+	if (bio_add_hw_folio(q, bio, folio, len, offset,
 			queue_max_zone_append_sectors(q), &same_page) != len)
 		return -EINVAL;
 	if (same_page)
-		bio_release_page(bio, page);
+		bio_release_page(bio, folio_page(folio, 0));
 	return 0;
 }
 
+static unsigned int get_contig_folio_len(unsigned int *num_pages,
+					 struct page **pages, unsigned int i,
+					 struct folio *folio, size_t left,
+					 size_t offset)
+{
+	size_t bytes = left;
+	size_t contig_sz = min_t(size_t, PAGE_SIZE - offset, bytes);
+	unsigned int j;
+
+	/*
+	 * We might COW a single page in the middle of
+	 * a large folio, so we have to check that all
+	 * pages belong to the same folio.
+	 */
+	bytes -= contig_sz;
+	for (j = i + 1; j < i + *num_pages; j++) {
+		size_t next = min_t(size_t, PAGE_SIZE, bytes);
+
+		if (page_folio(pages[j]) != folio ||
+		    pages[j] != pages[j - 1] + 1) {
+			break;
+		}
+		contig_sz += next;
+		bytes -= next;
+	}
+	*num_pages = j - i;
+
+	return contig_sz;
+}
+
 #define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
 
 /**
@@ -1298,9 +1329,9 @@  static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
-	ssize_t size, left;
-	unsigned len, i = 0;
-	size_t offset;
+	ssize_t size;
+	unsigned int i = 0, num_pages;
+	size_t offset, folio_offset, left, len;
 	int ret = 0;
 
 	/*
@@ -1342,15 +1373,29 @@  static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 
 	for (left = size, i = 0; left > 0; left -= len, i++) {
 		struct page *page = pages[i];
+		struct folio *folio = page_folio(page);
+
+		folio_offset = ((size_t)folio_page_idx(folio, page) <<
+				PAGE_SHIFT) + offset;
+
+		len = min_t(size_t, (folio_size(folio) - folio_offset), left);
+
+		num_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+
+		if (num_pages > 1)
+			len = get_contig_folio_len(&num_pages, pages, i,
+						   folio, left, offset);
 
-		len = min_t(size_t, PAGE_SIZE - offset, left);
 		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-			ret = bio_iov_add_zone_append_page(bio, page, len,
-					offset);
+			ret = bio_iov_add_zone_append_folio(bio, folio, len,
+					folio_offset);
 			if (ret)
 				break;
 		} else
-			bio_iov_add_page(bio, page, len, offset);
+			bio_iov_add_folio(bio, folio, len, folio_offset);
+
+		/* Skip the pages which got added */
+		i = i + (num_pages - 1);
 
 		offset = 0;
 	}