On Tue, 10 Dec 2019 13:43:02 -0700 Jens Axboe <axboe@xxxxxxxxx> wrote:
> If RWF_UNCACHED is set for io_uring (or pwritev2(2)), we'll drop the
> cache instantiated for buffered writes. If new pages aren't
> instantiated, we leave them alone. This provides similar semantics to
> reads with RWF_UNCACHED set.
>
Wouid be nice to see a description of the proposed userspace API(s)
for exploiting this feature.
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -285,6 +285,7 @@ enum positive_aop_returns {
> #define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct
> * helper code (eg buffer layer)
> * to clear GFP_FS from alloc */
> +#define AOP_FLAG_UNCACHED 0x0004
>
> /*
> * oh the beauties of C type declarations.
> @@ -3106,6 +3107,10 @@ extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *);
> extern ssize_t generic_perform_write(struct file *, struct iov_iter *,
> struct kiocb *);
>
> +struct pagevec;
> +extern void write_drop_cached_pages(struct pagevec *pvec,
> + struct address_space *mapping);
> +
> ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
> rwf_t flags);
> ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
> diff --git a/mm/filemap.c b/mm/filemap.c
> index fe37bd2b2630..2e36129ebe38 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -3287,10 +3287,12 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
> pgoff_t index, unsigned flags)
> {
> struct page *page;
> - int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT;
> + int fgp_flags = FGP_LOCK|FGP_WRITE;
>
> if (flags & AOP_FLAG_NOFS)
> fgp_flags |= FGP_NOFS;
> + if (!(flags & AOP_FLAG_UNCACHED))
> + fgp_flags |= FGP_CREAT;
>
> page = pagecache_get_page(mapping, index, fgp_flags,
> mapping_gfp_mask(mapping));
> @@ -3301,21 +3303,65 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
> }
> EXPORT_SYMBOL(grab_cache_page_write_begin);
>
> +/*
> + * Start writeback on the pages in pgs[], and then try and remove those pages
> + * from the page cached. Used with RWF_UNCACHED.
> + */
> +void write_drop_cached_pages(struct pagevec *pvec,
> + struct address_space *mapping)
> +{
> + loff_t start, end;
> + int i;
> +
> + end = 0;
> + start = LLONG_MAX;
> + for (i = 0; i < pagevec_count(pvec); i++) {
> + loff_t off = page_offset(pvec->pages[i]);
> + if (off < start)
> + start = off;
> + if (off > end)
> + end = off;
> + }
> +
> + __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE);
> +
> + for (i = 0; i < pagevec_count(pvec); i++) {
> + struct page *page = pvec->pages[i];
> +
> + lock_page(page);
> + if (page->mapping == mapping) {
> + wait_on_page_writeback(page);
> + if (!page_has_private(page) ||
> + try_to_release_page(page, 0))
> + remove_mapping(mapping, page);
> + }
> + unlock_page(page);
> + }
This is kinda invalidate_inode_pages2_range(), only much less so? Why
doesn't this code need to do all the things which
invalidate_inode_pages2_range() does? What happens if these pages are
mmapped, faulted in? Not faulted in?
> + pagevec_release(pvec);
> +}
