From: Konstantin Khlebnikov <khlebnikov@openvz.org>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Hugh Dickins <hughd@google.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [patch] mm: shmem: use new radix tree iterator
Date: Sat, 02 Feb 2013 12:25:44 +0400 [thread overview]
Message-ID: <510CCD88.30200@openvz.org> (raw)
In-Reply-To: <1359699238-7327-1-git-send-email-hannes@cmpxchg.org>
Johannes Weiner wrote:
> In shmem_find_get_pages_and_swap, use the faster radix tree iterator
> construct from 78c1d78 "radix-tree: introduce bit-optimized iterator".
>
> Signed-off-by: Johannes Weiner<hannes@cmpxchg.org>
Hmm, ACK. shmem_unuse_inode() also can be redone in this way.
I did something similar year ago: https://lkml.org/lkml/2012/2/10/388
As result we can rid of radix_tree_locate_item() and shmem_find_get_pages_and_swap()
> ---
> mm/shmem.c | 25 ++++++++++++-------------
> 1 file changed, 12 insertions(+), 13 deletions(-)
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index a368a1c..c5dc8ae 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -336,19 +336,19 @@ static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
> pgoff_t start, unsigned int nr_pages,
> struct page **pages, pgoff_t *indices)
> {
> - unsigned int i;
> - unsigned int ret;
> - unsigned int nr_found;
> + void **slot;
> + unsigned int ret = 0;
> + struct radix_tree_iter iter;
> +
> + if (!nr_pages)
> + return 0;
>
> rcu_read_lock();
> restart:
> - nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
> - (void ***)pages, indices, start, nr_pages);
> - ret = 0;
> - for (i = 0; i< nr_found; i++) {
> + radix_tree_for_each_slot(slot,&mapping->page_tree,&iter, start) {
> struct page *page;
> repeat:
> - page = radix_tree_deref_slot((void **)pages[i]);
> + page = radix_tree_deref_slot(slot);
> if (unlikely(!page))
> continue;
> if (radix_tree_exception(page)) {
> @@ -365,17 +365,16 @@ static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
> goto repeat;
>
> /* Has the page moved? */
> - if (unlikely(page != *((void **)pages[i]))) {
> + if (unlikely(page != *slot)) {
> page_cache_release(page);
> goto repeat;
> }
> export:
> - indices[ret] = indices[i];
> + indices[ret] = iter.index;
> pages[ret] = page;
> - ret++;
> + if (++ret == nr_pages)
> + break;
> }
> - if (unlikely(!ret&& nr_found))
> - goto restart;
> rcu_read_unlock();
> return ret;
> }
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2013-02-02 8:25 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-02-01 6:13 [patch] mm: shmem: use new radix tree iterator Johannes Weiner
2013-02-02 8:25 ` Konstantin Khlebnikov [this message]
2013-02-04 3:32 ` Hugh Dickins
2013-02-04 13:29 ` Konstantin Khlebnikov
2013-02-05 18:23 ` Johannes Weiner
2013-02-04 2:01 ` Hugh Dickins
2013-02-20 12:16 ` Ric Mason
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=510CCD88.30200@openvz.org \
--to=khlebnikov@openvz.org \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).