Re: [RFC] iomap: use huge zero folio in iomap_dio_zero

["Pankaj Raghav (Samsung)" <kernel@xxxxxxxxxxxxxxxx>]

On Wed, May 15, 2024 at 07:03:20PM +0100, Matthew Wilcox wrote:
> On Wed, May 15, 2024 at 03:59:43PM +0000, Pankaj Raghav (Samsung) wrote:
> >  static int __init iomap_init(void)
> >  {
> > +       void            *addr = kzalloc(16 * PAGE_SIZE, GFP_KERNEL);
> 
> Don't use XFS coding style outside XFS.
> 
> kzalloc() does not guarantee page alignment much less alignment to
> a folio.  It happens to work today, but that is an implementation
> artefact.
> 
> > +
> > +       if (!addr)
> > +               return -ENOMEM;
> > +
> > +       zero_fsb_folio = virt_to_folio(addr);
> 
> We also don't guarantee that calling kzalloc() gives you a virtual
> address that can be converted to a folio.  You need to allocate a folio
> to be sure that you get a folio.
> 
> Of course, you don't actually need a folio.  You don't need any of the
> folio metadata and can just use raw pages.
> 
> > +       /*
> > +        * The zero folio used is 64k.
> > +        */
> > +       WARN_ON_ONCE(len > (16 * PAGE_SIZE));
> 
> PAGE_SIZE is not necessarily 4KiB.
> 
> > +       bio = iomap_dio_alloc_bio(iter, dio, BIO_MAX_VECS,
> > +                                 REQ_OP_WRITE | REQ_SYNC | REQ_IDLE);
> 
> The point was that we now only need one biovec, not MAX.
> 

Thanks for the comments. I think it all makes sense:

diff --git a/fs/internal.h b/fs/internal.h
index 7ca738904e34..e152b77a77e4 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -35,6 +35,14 @@ static inline void bdev_cache_init(void)
 int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
                get_block_t *get_block, const struct iomap *iomap);
 
+/*
+ * iomap/buffered-io.c
+ */
+
+#define ZERO_FSB_SIZE (65536)
+#define ZERO_FSB_ORDER (get_order(ZERO_FSB_SIZE))
+extern struct page *zero_fs_block;
+
 /*
  * char_dev.c
  */
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 4e8e41c8b3c0..36d2f7edd310 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -42,6 +42,7 @@ struct iomap_folio_state {
 };
 
 static struct bio_set iomap_ioend_bioset;
+struct page *zero_fs_block;
 
 static inline bool ifs_is_fully_uptodate(struct folio *folio,
                struct iomap_folio_state *ifs)
@@ -1985,8 +1986,13 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);
 
+
 static int __init iomap_init(void)
 {
+       zero_fs_block = alloc_pages(GFP_KERNEL | __GFP_ZERO, ZERO_FSB_ORDER);
+       if (!zero_fs_block)
+               return -ENOMEM;
+
        return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
                           offsetof(struct iomap_ioend, io_bio),
                           BIOSET_NEED_BVECS);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index f3b43d223a46..50c2bca8a347 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -236,17 +236,22 @@ static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
                loff_t pos, unsigned len)
 {
        struct inode *inode = file_inode(dio->iocb->ki_filp);
-       struct page *page = ZERO_PAGE(0);
        struct bio *bio;
 
+       /*
+        * Max block size supported is 64k
+        */
+       WARN_ON_ONCE(len > ZERO_FSB_SIZE);
+
        bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE);
        fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
                                  GFP_KERNEL);
+
        bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos);
        bio->bi_private = dio;
        bio->bi_end_io = iomap_dio_bio_end_io;
 
-       __bio_add_page(bio, page, len, 0);
+       __bio_add_page(bio, zero_fs_block, len, 0);
        iomap_dio_submit_bio(iter, dio, bio, pos);
 }