[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20091210163331.2565.A69D9226@jp.fujitsu.com>
Date: Thu, 10 Dec 2009 16:34:27 +0900 (JST)
From: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
To: LKML <linux-kernel@...r.kernel.org>
Cc: kosaki.motohiro@...fujitsu.com, linux-mm <linux-mm@...ck.org>,
Rik van Riel <riel@...hat.com>,
Andrea Arcangeli <aarcange@...hat.com>,
Larry Woodman <lwoodman@...hat.com>
Subject: [RFC][PATCH v2 7/8] Try to mark PG_mlocked if wipe_page_reference find VM_LOCKED vma
Both try_to_unmap() and wipe_page_reference() walk each ptes, but
latter doesn't mark PG_mlocked altough find VM_LOCKED vma.
This patch does it.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
Reviewed-by: Rik van Riel <riel@...hat.com>
---
mm/rmap.c | 14 ++++++++++++++
mm/vmscan.c | 2 ++
2 files changed, 16 insertions(+), 0 deletions(-)
diff --git a/mm/rmap.c b/mm/rmap.c
index 5ae7c81..cfda0a0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -376,6 +376,7 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
*
* SWAP_SUCCESS - success
* SWAP_AGAIN - give up to take lock, try later again
+ * SWAP_MLOCK - the page is mlocked
*/
int wipe_page_reference_one(struct page *page,
struct page_reference_context *refctx,
@@ -401,6 +402,7 @@ int wipe_page_reference_one(struct page *page,
if (IS_ERR(pte)) {
if (PTR_ERR(pte) == -EAGAIN) {
ret = SWAP_AGAIN;
+ goto out_mlock;
}
goto out;
}
@@ -430,6 +432,17 @@ int wipe_page_reference_one(struct page *page,
out:
return ret;
+
+out_mlock:
+ if (refctx->is_page_locked &&
+ down_read_trylock(&vma->vm_mm->mmap_sem)) {
+ if (vma->vm_flags & VM_LOCKED) {
+ mlock_vma_page(page);
+ ret = SWAP_MLOCK;
+ }
+ up_read(&vma->vm_mm->mmap_sem);
+ }
+ return ret;
}
static int wipe_page_reference_anon(struct page *page,
@@ -550,6 +563,7 @@ static int wipe_page_reference_file(struct page *page,
*
* SWAP_SUCCESS - success to wipe all ptes
* SWAP_AGAIN - temporary busy, try again later
+ * SWAP_MLOCK - the page is mlocked
*/
int wipe_page_reference(struct page *page,
struct mem_cgroup *memcg,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c235059..4738a12 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -625,6 +625,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
ret = wipe_page_reference(page, sc->mem_cgroup, &refctx);
if (ret == SWAP_AGAIN)
goto keep_locked;
+ else if (ret == SWAP_MLOCK)
+ goto cull_mlocked;
VM_BUG_ON(ret != SWAP_SUCCESS);
/*
--
1.6.5.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists