On Sun, May 04, 2025 at 09:13:44PM +0200, Bernd Schubert wrote:
>
>
> On 4/26/25 02:08, Joanne Koong wrote:
> > Add support for folios larger than one page size for readahead.
> >
> > Signed-off-by: Joanne Koong <joannelkoong@xxxxxxxxx>
> > Reviewed-by: Jeff Layton <jlayton@xxxxxxxxxx>
> > ---
> > fs/fuse/file.c | 36 +++++++++++++++++++++++++++---------
> > 1 file changed, 27 insertions(+), 9 deletions(-)
> >
> > diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> > index 1d38486fae50..9a31f2a516b9 100644
> > --- a/fs/fuse/file.c
> > +++ b/fs/fuse/file.c
> > @@ -876,14 +876,13 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
> > fuse_io_free(ia);
> > }
> >
> > -static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
> > +static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
> > + unsigned int count)
> > {
> > struct fuse_file *ff = file->private_data;
> > struct fuse_mount *fm = ff->fm;
> > struct fuse_args_pages *ap = &ia->ap;
> > loff_t pos = folio_pos(ap->folios[0]);
> > - /* Currently, all folios in FUSE are one page */
> > - size_t count = ap->num_folios << PAGE_SHIFT;
> > ssize_t res;
> > int err;
> >
> > @@ -918,6 +917,7 @@ static void fuse_readahead(struct readahead_control *rac)
> > struct inode *inode = rac->mapping->host;
> > struct fuse_conn *fc = get_fuse_conn(inode);
> > unsigned int max_pages, nr_pages;
> > + struct folio *folio = NULL;
> >
> > if (fuse_is_bad(inode))
> > return;
> > @@ -939,8 +939,8 @@ static void fuse_readahead(struct readahead_control *rac)
> > while (nr_pages) {
> > struct fuse_io_args *ia;
> > struct fuse_args_pages *ap;
> > - struct folio *folio;
> > unsigned cur_pages = min(max_pages, nr_pages);
> > + unsigned int pages = 0;
> >
> > if (fc->num_background >= fc->congestion_threshold &&
> > rac->ra->async_size >= readahead_count(rac))
> > @@ -952,10 +952,12 @@ static void fuse_readahead(struct readahead_control *rac)
> >
> > ia = fuse_io_alloc(NULL, cur_pages);
> > if (!ia)
> > - return;
> > + break;
> > ap = &ia->ap;
> >
> > - while (ap->num_folios < cur_pages) {
> > + while (pages < cur_pages) {
> > + unsigned int folio_pages;
> > +
> > /*
> > * This returns a folio with a ref held on it.
> > * The ref needs to be held until the request is
> > @@ -963,13 +965,29 @@ static void fuse_readahead(struct readahead_control *rac)
> > * fuse_try_move_page()) drops the ref after it's
> > * replaced in the page cache.
> > */
> > - folio = __readahead_folio(rac);
> > + if (!folio)
> > + folio = __readahead_folio(rac);
> > +
> > + folio_pages = folio_nr_pages(folio);
> > + if (folio_pages > cur_pages - pages)
> > + break;
> > +
>
> Hmm, so let's assume this would be a 2MB folio, but fc->max_pages is
> limited to 1MB - we not do read-ahead anymore?
It's hard for me to say without seeing the actual enablement patches,
but filesystems are supposed to call mapping_set_folio_order_range to
constrain the sizes of the folios that the pagecache requests.
--D
> Thanks,
> Bernd
>
>
> > ap->folios[ap->num_folios] = folio;
> > ap->descs[ap->num_folios].length = folio_size(folio);
> > ap->num_folios++;
> > + pages += folio_pages;
> > + folio = NULL;
> > + }
> > + if (!pages) {
> > + fuse_io_free(ia);
> > + break;
> > }
> > - fuse_send_readpages(ia, rac->file);
> > - nr_pages -= cur_pages;
> > + fuse_send_readpages(ia, rac->file, pages << PAGE_SHIFT);
> > + nr_pages -= pages;
> > + }
> > + if (folio) {
> > + folio_end_read(folio, false);
> > + folio_put(folio);
> > }
> > }
> >
>
>
