From: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
To: linux-mm <linux-mm@kvack.org>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
Paul Menage <menage@google.com>, Li Zefan <lizf@cn.fujitsu.com>,
Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Subject: [RFC][PATCH 8/8] memcg: migrate charge of shmem swap
Date: Thu, 24 Sep 2009 14:50:41 +0900 [thread overview]
Message-ID: <20090924145041.bcf98ab6.nishimura@mxp.nes.nec.co.jp> (raw)
In-Reply-To: <20090924144214.508469d1.nishimura@mxp.nes.nec.co.jp>
This patch enables charge migration of shmem's swap.
To find the shmem's page or swap entry corresponding to a !pte_present pte,
this patch add a function to search them from the inode and the offset.
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
---
include/linux/swap.h | 4 ++++
mm/memcontrol.c | 21 +++++++++++++++++----
mm/shmem.c | 37 +++++++++++++++++++++++++++++++++++++
3 files changed, 58 insertions(+), 4 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4ec9001..e232653 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -278,6 +278,10 @@ extern int kswapd_run(int nid);
/* linux/mm/shmem.c */
extern int shmem_unuse(swp_entry_t entry, struct page *page);
#endif /* CONFIG_MMU */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
+ struct page **pagep, swp_entry_t *ent);
+#endif
extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index fe0902c..1c674b0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3310,10 +3310,23 @@ static int is_target_pte_for_migration(struct vm_area_struct *vma,
if (!pte_present(ptent)) {
if (!do_swap_account)
return 0;
- /* TODO: handle swap of shmes/tmpfs */
- if (pte_none(ptent) || pte_file(ptent))
- return 0;
- else if (is_swap_pte(ptent)) {
+ if (pte_none(ptent) || pte_file(ptent)) {
+ if (!vma->vm_file)
+ return 0;
+ if (mapping_cap_swap_backed(vma->vm_file->f_mapping)) {
+ struct inode *inode;
+ pgoff_t pgoff = 0;
+
+ inode = vma->vm_file->f_path.dentry->d_inode;
+ if (pte_none(ptent))
+ pgoff = linear_page_index(vma, addr);
+ if (pte_file(ptent))
+ pgoff = pte_to_pgoff(ptent);
+
+ mem_cgroup_get_shmem_target(inode, pgoff,
+ &page, &ent);
+ }
+ } else if (is_swap_pte(ptent)) {
ent = pte_to_swp_entry(ptent);
if (is_migration_entry(ent))
return 0;
diff --git a/mm/shmem.c b/mm/shmem.c
index 10b7f37..96bc1b7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2714,3 +2714,40 @@ int shmem_zero_setup(struct vm_area_struct *vma)
vma->vm_ops = &shmem_vm_ops;
return 0;
}
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+/**
+ * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file
+ * @inode: the inode to be searched
+ * @pgoff: the offset to be searched
+ * @pagep: the pointer for the found page to be stored
+ * @ent: the pointer for the found swap entry to be stored
+ *
+ * If a page is found, refcount of it is incremented. Callers should handle
+ * these refcount.
+ */
+void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
+ struct page **pagep, swp_entry_t *ent)
+{
+ swp_entry_t entry = { .val = 0 }, *ptr;
+ struct page *page = NULL;
+ struct shmem_inode_info *info = SHMEM_I(inode);
+
+ if ((pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode))
+ goto out;
+
+ spin_lock(&info->lock);
+ ptr = shmem_swp_entry(info, pgoff, NULL);
+ if (ptr && ptr->val) {
+ entry.val = ptr->val;
+ page = find_get_page(&swapper_space, entry.val);
+ } else
+ page = find_get_page(inode->i_mapping, pgoff);
+ if (ptr)
+ shmem_swp_unmap(ptr);
+ spin_unlock(&info->lock);
+out:
+ *pagep = page;
+ *ent = entry;
+}
+#endif
--
1.5.6.1
--
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:[~2009-09-24 5:58 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-09-17 2:23 [RFC][EXPERIMENTAL][PATCH 0/8] memcg: migrate charge at task move Daisuke Nishimura
2009-09-17 2:24 ` [PATCH 1/8] memcg: introduce mem_cgroup_cancel_charge() Daisuke Nishimura
2009-09-17 4:12 ` KAMEZAWA Hiroyuki
2009-09-17 2:24 ` [PATCH 2/8] memcg: cleanup mem_cgroup_move_parent() Daisuke Nishimura
2009-09-17 4:15 ` KAMEZAWA Hiroyuki
2009-09-17 2:25 ` [PATCH 3/8] cgroup: introduce cancel_attach() Daisuke Nishimura
2009-09-17 2:26 ` [PATCH 4/8] memcg: add interface to migrate charge Daisuke Nishimura
2009-09-17 4:20 ` KAMEZAWA Hiroyuki
2009-09-17 4:40 ` Daisuke Nishimura
2009-09-17 2:26 ` [PATCH 5/8] memcg: migrate charge of anon Daisuke Nishimura
2009-09-17 4:57 ` KAMEZAWA Hiroyuki
2009-09-17 5:56 ` Daisuke Nishimura
2009-09-17 6:25 ` KAMEZAWA Hiroyuki
2009-09-17 23:52 ` KOSAKI Motohiro
2009-09-17 2:27 ` [PATCH 6/8] memcg: migrate charge of shmem Daisuke Nishimura
2009-09-17 5:02 ` KAMEZAWA Hiroyuki
2009-09-17 2:28 ` [PATCH 7/8] memcg: migrate charge of swap Daisuke Nishimura
2009-09-17 5:25 ` KAMEZAWA Hiroyuki
2009-09-17 6:17 ` Daisuke Nishimura
2009-09-17 6:28 ` KAMEZAWA Hiroyuki
2009-09-17 2:29 ` [PATCH 8/8] memcg: avoid oom during charge migration Daisuke Nishimura
2009-09-17 7:01 ` [RFC][EXPERIMENTAL][PATCH 0/8] memcg: migrate charge at task move Daisuke Nishimura
2009-09-24 5:42 ` [RFC][PATCH 0/8] memcg: migrate charge at task move (24/Sep) Daisuke Nishimura
2009-09-24 5:43 ` [RFC][PATCH 1/8] cgroup: introduce cancel_attach() Daisuke Nishimura
2009-09-24 6:33 ` KAMEZAWA Hiroyuki
2009-09-24 23:39 ` Daisuke Nishimura
2009-09-24 5:44 ` [RFC][PATCH 2/8] memcg: introduce mem_cgroup_cancel_charge() Daisuke Nishimura
2009-09-24 5:46 ` [RFC][PATCH 3/8] memcg: cleanup mem_cgroup_move_parent() Daisuke Nishimura
2009-09-24 6:37 ` KAMEZAWA Hiroyuki
2009-09-24 6:54 ` Daisuke Nishimura
2009-09-24 5:47 ` [RFC][PATCH 4/8] memcg: add interface to migrate charge Daisuke Nishimura
2009-09-24 6:54 ` KAMEZAWA Hiroyuki
2009-09-24 23:39 ` Daisuke Nishimura
2009-09-24 5:48 ` [RFC][PATCH 5/8] memcg: migrate charge of mapped page Daisuke Nishimura
2009-09-24 7:22 ` KAMEZAWA Hiroyuki
2009-09-24 8:00 ` Daisuke Nishimura
2009-09-25 0:28 ` Daisuke Nishimura
2009-09-25 0:49 ` KAMEZAWA Hiroyuki
2009-09-24 5:49 ` [RFC][PATCH 6/8] memcg: avoid oom during charge migration Daisuke Nishimura
2009-09-24 7:34 ` KAMEZAWA Hiroyuki
2009-09-25 1:44 ` Daisuke Nishimura
2009-09-25 1:55 ` KAMEZAWA Hiroyuki
2009-09-25 4:51 ` Daisuke Nishimura
2009-09-25 5:36 ` Daisuke Nishimura
2009-09-25 5:52 ` KAMEZAWA Hiroyuki
2009-09-24 5:49 ` [RFC][PATCH 7/8] memcg: migrate charge of swap Daisuke Nishimura
2009-09-24 5:50 ` Daisuke Nishimura [this message]
2009-09-24 7:41 ` [RFC][PATCH 8/8] memcg: migrate charge of shmem swap KAMEZAWA Hiroyuki
2009-09-25 0:28 ` Daisuke Nishimura
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=20090924145041.bcf98ab6.nishimura@mxp.nes.nec.co.jp \
--to=nishimura@mxp.nes.nec.co.jp \
--cc=balbir@linux.vnet.ibm.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-mm@kvack.org \
--cc=lizf@cn.fujitsu.com \
--cc=menage@google.com \
/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