block: convert bio_map_user_iov to use iov_iter_extract_pages

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 visible to/affected by
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
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20230522205744.2825689-7-dhowells@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-map.c b/block/blk-map.c
index 33d9f6e89ba6214daf4fc998ea53330a294ec89e..3551c3ff17cf636925aae47a91bc461a195e720b 100644 (file)
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -281,22 +281,21 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 
        if (blk_queue_pci_p2pdma(rq->q))
                extraction_flags |= ITER_ALLOW_P2PDMA;
+       if (iov_iter_extract_will_pin(iter))
+               bio_set_flag(bio, BIO_PAGE_PINNED);
 
-       bio_set_flag(bio, BIO_PAGE_REFFED);
        while (iov_iter_count(iter)) {
-               struct page **pages, *stack_pages[UIO_FASTIOV];
+               struct page *stack_pages[UIO_FASTIOV];
+               struct page **pages = stack_pages;
                ssize_t bytes;
                size_t offs;
                int npages;
 
-               if (nr_vecs <= ARRAY_SIZE(stack_pages)) {
-                       pages = stack_pages;
-                       bytes = iov_iter_get_pages(iter, pages, LONG_MAX,
-                                                  nr_vecs, &offs, extraction_flags);
-               } else {
-                       bytes = iov_iter_get_pages_alloc(iter, &pages,
-                                               LONG_MAX, &offs, extraction_flags);
-               }
+               if (nr_vecs > ARRAY_SIZE(stack_pages))
+                       pages = NULL;
+
+               bytes = iov_iter_extract_pages(iter, &pages, LONG_MAX,
+                                              nr_vecs, extraction_flags, &offs);
                if (unlikely(bytes <= 0)) {
                        ret = bytes ? bytes : -EFAULT;
                        goto out_unmap;
@@ -318,7 +317,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
                                if (!bio_add_hw_page(rq->q, bio, page, n, offs,
                                                     max_sectors, &same_page)) {
                                        if (same_page)
-                                               put_page(page);
+                                               bio_release_page(bio, page);
                                        break;
                                }
 
@@ -330,7 +329,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
                 * release the pages we didn't map into the bio, if any
                 */
                while (j < npages)
-                       put_page(pages[j++]);
+                       bio_release_page(bio, pages[j++]);
                if (pages != stack_pages)
                        kvfree(pages);
                /* couldn't stuff something into bio? */