block: set FOLL_PCI_P2PDMA in __bio_iov_iter_get_pages()

When a bio's queue supports PCI P2PDMA, set FOLL_PCI_P2PDMA for
iov_iter_get_pages_flags(). This allows PCI P2PDMA pages to be passed
from userspace and enables the O_DIRECT path in iomap based filesystems
and direct to block devices.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20221021174116.7200-7-logang@deltatee.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/bio.c b/block/bio.c
index c7a1242..aa1de6a 100644 (file)
--- a/block/bio.c
+++ b/block/bio.c
@@ -1197,6 +1197,7 @@ 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;
+       unsigned int gup_flags = 0;
        ssize_t size, left;
        unsigned len, i = 0;
        size_t offset, trim;
@@ -1210,6 +1211,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
        BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
        pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
 
+       if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue))
+               gup_flags |= FOLL_PCI_P2PDMA;
+
        /*
         * Each segment in the iov is required to be a block size multiple.
         * However, we may not be able to get the entire segment if it spans
@@ -1217,8 +1221,9 @@ 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_pages2(iter, pages, UINT_MAX - bio->bi_iter.bi_size,
-                                 nr_pages, &offset);
+       size = iov_iter_get_pages(iter, pages,
+                                 UINT_MAX - bio->bi_iter.bi_size,
+                                 nr_pages, &offset, gup_flags);
        if (unlikely(size <= 0))
                return size ? size : -EFAULT;