Re: [PATCH v5 3/3] squashfs: implement readahead

[Hsin-Yi Wang <hsinyi@chromium.org>]

On Wed, Jun 8, 2022 at 3:29 AM Fabio M. De Francesco
<fmdefrancesco@gmail.com> wrote:
>
> On lunedì 6 giugno 2022 17:03:05 CEST Hsin-Yi Wang wrote:
> > Implement readahead callback for squashfs. It will read datablocks
> > which cover pages in readahead request. For a few cases it will
> > not mark page as uptodate, including:
> > - file end is 0.
> > - zero filled blocks.
> > - current batch of pages isn't in the same datablock.
> > - decompressor error.
> > Otherwise pages will be marked as uptodate. The unhandled pages will be
> > updated by readpage later.
> >
> > Suggested-by: Matthew Wilcox <willy@infradead.org>
> > Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
> > Reported-by: Matthew Wilcox <willy@infradead.org>
> > Reported-by: Phillip Lougher <phillip@squashfs.org.uk>
> > Reported-by: Xiongwei Song <Xiongwei.Song@windriver.com>
> > Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
> > Reported-by: Andrew Morton <akpm@linux-foundation.org>
> > ---
> > v4->v5:
> > - Handle short file cases reported by Marek and Matthew.
> > - Fix checkpatch error reported by Andrew.
> >
> > v4: https://lore.kernel.org/lkml/20220601103922.1338320-4-hsinyi@chromium.org/
> > v3: https://lore.kernel.org/lkml/20220523065909.883444-4-hsinyi@chromium.org/
> > v2: https://lore.kernel.org/lkml/20220517082650.2005840-4-hsinyi@chromium.org/
> > v1: https://lore.kernel.org/lkml/20220516105100.1412740-3-hsinyi@chromium.org/
> > ---
> >  fs/squashfs/file.c | 124 ++++++++++++++++++++++++++++++++++++++++++++-
> >  1 file changed, 123 insertions(+), 1 deletion(-)
> >
> > diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
> > index a8e495d8eb86..fbd096cd15f4 100644
> > --- a/fs/squashfs/file.c
> > +++ b/fs/squashfs/file.c
> > @@ -39,6 +39,7 @@
> >  #include "squashfs_fs_sb.h"
> >  #include "squashfs_fs_i.h"
> >  #include "squashfs.h"
> > +#include "page_actor.h"
> >
> >  /*
> >   * Locate cache slot in range [offset, index] for specified inode.  If
> > @@ -495,7 +496,128 @@ static int squashfs_read_folio(struct file *file,
> struct folio *folio)
> >       return 0;
> >  }
> >
> > +static void squashfs_readahead(struct readahead_control *ractl)
> > +{
> > +     struct inode *inode = ractl->mapping->host;
> > +     struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
> > +     size_t mask = (1UL << msblk->block_log) - 1;
> > +     unsigned short shift = msblk->block_log - PAGE_SHIFT;
> > +     loff_t start = readahead_pos(ractl) & ~mask;
> > +     size_t len = readahead_length(ractl) + readahead_pos(ractl) -
> start;
> > +     struct squashfs_page_actor *actor;
> > +     unsigned int nr_pages = 0;
> > +     struct page **pages;
> > +     int i, file_end = i_size_read(inode) >> msblk->block_log;
> > +     unsigned int max_pages = 1UL << shift;
> > +
> > +     readahead_expand(ractl, start, (len | mask) + 1);
> > +
> > +     if (file_end == 0)
> > +             return;
> > +
> > +     pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL);
> > +     if (!pages)
> > +             return;
> > +
> > +     actor = squashfs_page_actor_init_special(pages, max_pages, 0);
> > +     if (!actor)
> > +             goto out;
> > +
> > +     for (;;) {
> > +             pgoff_t index;
> > +             int res, bsize;
> > +             u64 block = 0;
> > +             unsigned int expected;
> > +
> > +             nr_pages = __readahead_batch(ractl, pages, max_pages);
> > +             if (!nr_pages)
> > +                     break;
> > +
> > +             if (readahead_pos(ractl) >= i_size_read(inode))
> > +                     goto skip_pages;
> > +
> > +             index = pages[0]->index >> shift;
> > +             if ((pages[nr_pages - 1]->index >> shift) != index)
> > +                     goto skip_pages;
> > +
> > +             expected = index == file_end ?
> > +                        (i_size_read(inode) & (msblk->block_size -
> 1)) :
> > +                         msblk->block_size;
> > +
> > +             bsize = read_blocklist(inode, index, &block);
> > +             if (bsize == 0)
> > +                     goto skip_pages;
> > +
> > +             if (nr_pages < max_pages) {
> > +                     struct squashfs_cache_entry *buffer;
> > +                     unsigned int block_mask = max_pages - 1;
> > +                     int offset = pages[0]->index - (pages[0]-
> >index & ~block_mask);
> > +
> > +                     buffer = squashfs_get_datablock(inode->i_sb,
> block,
> > +
> bsize);
> > +                     if (buffer->error) {
> > +                             squashfs_cache_put(buffer);
> > +                             goto skip_pages;
> > +                     }
> > +
> > +                     expected -= offset * PAGE_SIZE;
> > +                     for (i = 0; i < nr_pages && expected > 0; i+
> +,
> > +                                             expected -=
> PAGE_SIZE, offset++) {
> > +                             int avail = min_t(int, expected,
> PAGE_SIZE);
> > +
> > +                             squashfs_fill_page(pages[i],
> buffer,
> > +                                             offset *
> PAGE_SIZE, avail);
> > +                             unlock_page(pages[i]);
> > +                     }
> > +
> > +                     squashfs_cache_put(buffer);
> > +                     continue;
> > +             }
> > +
> > +             res = squashfs_read_data(inode->i_sb, block, bsize,
> NULL,
> > +                                      actor);
> > +
> > +             if (res == expected) {
> > +                     int bytes;
> > +
> > +                     /* Last page may have trailing bytes not
> filled */
> > +                     bytes = res % PAGE_SIZE;
> > +                     if (bytes) {
> > +                             void *pageaddr;
> > +
> > +                             pageaddr =
> kmap_atomic(pages[nr_pages - 1]);
> > +                             memset(pageaddr + bytes, 0,
> PAGE_SIZE - bytes);
> > +                             kunmap_atomic(pageaddr);
> > +                     }
>
> Hi Hsin-Yi,
>
> kmap_atomic() shouldn't be used in new code, unless there are special
> reasons that I am not able to spot here.
>
> Why not use kmap_local_page(), preferably via memzero_page?

Right, these can be replaced with kmap_local_page(pages[nr_pages - 1],
bytes, PAGE_SIZE - bytes);

Thanks for the suggestion.
>
> Thanks,
>
> Fabio
>
> > +
> > +                     for (i = 0; i < nr_pages; i++) {
> > +                             flush_dcache_page(pages[i]);
> > +                             SetPageUptodate(pages[i]);
> > +                     }
> > +             }
> > +
> > +             for (i = 0; i < nr_pages; i++) {
> > +                     unlock_page(pages[i]);
> > +                     put_page(pages[i]);
> > +             }
> > +     }
> > +
> > +     kfree(actor);
> > +     kfree(pages);
> > +     return;
> > +
> > +skip_pages:
> > +     for (i = 0; i < nr_pages; i++) {
> > +             unlock_page(pages[i]);
> > +             put_page(pages[i]);
> > +     }
> > +
> > +     kfree(actor);
> > +out:
> > +     kfree(pages);
> > +}
> >
> >  const struct address_space_operations squashfs_aops = {
> > -     .read_folio = squashfs_read_folio
> > +     .read_folio = squashfs_read_folio,
> > +     .readahead = squashfs_readahead
> >  };
> > --
> > 2.36.1.255.ge46751e96f-goog
> >
> >
> >
>
>
>
>