[PATCH v17 12/14] block: Add BIO_PAGE_PINNED and associated infrastructure

[David Howells]

Add BIO_PAGE_PINNED to indicate that the pages in a bio are pinned
(FOLL_PIN) and that the pin will need removing.

Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: John Hubbard <jhubbard@xxxxxxxxxx>
cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
cc: Jens Axboe <axboe@xxxxxxxxx>
cc: Jan Kara <jack@xxxxxxx>
cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
cc: linux-block@xxxxxxxxxxxxxxx
---

Notes:
    ver #10)
     - Drop bio_set_cleanup_mode(), open coding it instead.
    
    ver #9)
     - Only consider pinning in bio_set_cleanup_mode().  Ref'ing pages in
       struct bio is going away.
     - page_put_unpin() is removed; call unpin_user_page() and put_page()
       directly.
     - Use bio_release_page() in __bio_release_pages().
     - BIO_PAGE_PINNED and BIO_PAGE_REFFED can't both be set, so use if-else
       when testing both of them.
    
    ver #8)
     - Move the infrastructure to clean up pinned pages to this patch [hch].
     - Put BIO_PAGE_PINNED before BIO_PAGE_REFFED as the latter should
       probably be removed at some point.  FOLL_PIN can then be renumbered
       first.

 block/bio.c               |  6 +++---
 block/blk.h               | 12 ++++++++++++
 include/linux/bio.h       |  3 ++-
 include/linux/blk_types.h |  1 +
 4 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 4ff96a0e4091..51ae957cc4b6 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1168,7 +1168,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 	bio_for_each_segment_all(bvec, bio, iter_all) {
 		if (mark_dirty && !PageCompound(bvec->bv_page))
 			set_page_dirty_lock(bvec->bv_page);
-		put_page(bvec->bv_page);
+		bio_release_page(bio, bvec->bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1488,8 +1488,8 @@ void bio_set_pages_dirty(struct bio *bio)
  * the BIO and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
- * here on.  It will run one put_page() against each page and will run one
- * bio_put() against the BIO.
+ * here on.  It will unpin each page and will run one bio_put() against the
+ * BIO.
  */
 
 static void bio_dirty_fn(struct work_struct *work);
diff --git a/block/blk.h b/block/blk.h
index cc4e8873dfde..d65d96994a94 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -432,6 +432,18 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page);
 
+/*
+ * Clean up a page appropriately, where the page may be pinned, may have a
+ * ref taken on it or neither.
+ */
+static inline void bio_release_page(struct bio *bio, struct page *page)
+{
+	if (bio_flagged(bio, BIO_PAGE_PINNED))
+		unpin_user_page(page);
+	else if (bio_flagged(bio, BIO_PAGE_REFFED))
+		put_page(page);
+}
+
 struct request_queue *blk_alloc_queue(int node_id);
 
 int disk_scan_partitions(struct gendisk *disk, fmode_t mode);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b537d03377f0..d8c30c791a9a 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -488,7 +488,8 @@ void zero_fill_bio(struct bio *bio);
 
 static inline void bio_release_pages(struct bio *bio, bool mark_dirty)
 {
-	if (bio_flagged(bio, BIO_PAGE_REFFED))
+	if (bio_flagged(bio, BIO_PAGE_REFFED) ||
+	    bio_flagged(bio, BIO_PAGE_PINNED))
 		__bio_release_pages(bio, mark_dirty);
 }
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 7daa261f4f98..a0e339ff3d09 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -318,6 +318,7 @@ struct bio {
  * bio flags
  */
 enum {
+	BIO_PAGE_PINNED,	/* Unpin pages in bio_release_pages() */
 	BIO_PAGE_REFFED,	/* put pages in bio_release_pages() */
 	BIO_CLONED,		/* doesn't own data */
 	BIO_BOUNCED,		/* bio is a bounce bio */