linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
To: Linux Containers <containers@lists.osdl.org>,
	Linux MM <linux-mm@kvack.org>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>,
	Pavel Emelyanov <xemul@openvz.org>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	YAMAMOTO Takashi <yamamoto@valinux.co.jp>,
	Hugh Dickins <hugh@veritas.com>,
	"IKEDA, Munehiro" <m-ikeda@ds.jp.nec.com>
Subject: [PATCH 3/4] swapcgroup: implement charge/uncharge
Date: Thu, 22 May 2008 15:20:05 +0900	[thread overview]
Message-ID: <48351095.3040009@mxp.nes.nec.co.jp> (raw)
In-Reply-To: <48350F15.9070007@mxp.nes.nec.co.jp>

This patch implements charge and uncharge of swapcgroup.

- what will be charged ?
  charge the number of swap entries in bytes.

- when to charge/uncharge ?
  charge at get_swap_entry(), and uncharge at swap_entry_free().

- to what group charge the swap entry ?
  To determine to what mem_cgroup the swap entry should be charged,
  I changed the argument of get_swap_entry() from (void) to
  (struct page *). As a result, get_swap_entry() can determine
  to what mem_cgroup it should charge the swap entry
  by referring to page->page_cgroup->mem_cgroup.

- from what group uncharge the swap entry ?
  I added to swap_info_struct a member 'struct swap_cgroup **',
  array of pointer to which swap_cgroup the swap entry is
  charged.


Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>

---
 include/linux/memcontrol.h |   21 +++++++++++++++++++
 include/linux/swap.h       |    4 +-
 mm/memcontrol.c            |   47 ++++++++++++++++++++++++++++++++++++++++++++
 mm/shmem.c                 |    2 +-
 mm/swap_state.c            |    2 +-
 mm/swapfile.c              |   14 ++++++++++++-
 6 files changed, 85 insertions(+), 5 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index fdf3967..a7e6621 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -24,6 +24,7 @@ struct mem_cgroup;
 struct page_cgroup;
 struct page;
 struct mm_struct;
+struct swap_info_struct;
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
@@ -172,5 +173,25 @@ static inline long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
 }
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
+#ifdef CONFIG_CGROUP_SWAP_RES_CTLR
+extern int swap_cgroup_charge(struct page *page,
+			struct swap_info_struct *si,
+			unsigned long offset);
+extern void swap_cgroup_uncharge(struct swap_info_struct *si,
+				unsigned long offset);
+#else /* CONFIG_CGROUP_SWAP_RES_CTLR */
+static inline int swap_cgroup_charge(struct page *page,
+			struct swap_info_struct *si,
+			unsigned long offset)
+{
+	return 0;
+}
+
+static inline void swap_cgroup_uncharge(struct swap_info_struct *si,
+				unsigned long offset)
+{
+}
+#endif /* CONFIG_CGROUP_SWAP_RES_CTLR */
+
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 67de27b..18887f0 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -241,7 +241,7 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t,
 /* linux/mm/swapfile.c */
 extern long total_swap_pages;
 extern void si_swapinfo(struct sysinfo *);
-extern swp_entry_t get_swap_page(void);
+extern swp_entry_t get_swap_page(struct page *);
 extern swp_entry_t get_swap_page_of_type(int);
 extern int swap_duplicate(swp_entry_t);
 extern int valid_swaphandles(swp_entry_t, unsigned long *);
@@ -342,7 +342,7 @@ static inline int remove_exclusive_swap_page(struct page *p)
 	return 0;
 }
 
-static inline swp_entry_t get_swap_page(void)
+static inline swp_entry_t get_swap_page(struct page *page)
 {
 	swp_entry_t entry;
 	entry.val = 0;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a837215..84e803d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1220,3 +1220,50 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.attach = mem_cgroup_move_task,
 	.early_init = 0,
 };
+
+#ifdef CONFIG_CGROUP_SWAP_RES_CTLR
+int swap_cgroup_charge(struct page *page,
+			struct swap_info_struct *si,
+			unsigned long offset)
+{
+	int ret;
+	struct page_cgroup *pc;
+	struct mem_cgroup *mem;
+
+	lock_page_cgroup(page);
+	pc = page_get_page_cgroup(page);
+	if (unlikely(!pc))
+		mem = &init_mem_cgroup;
+	else
+		mem = pc->mem_cgroup;
+	unlock_page_cgroup(page);
+
+	css_get(&mem->css);
+	ret = res_counter_charge(&mem->swap_res, PAGE_SIZE);
+	if (!ret)
+		si->memcg[offset] = mem;
+	else
+		css_put(&mem->css);
+
+	return ret;
+}
+
+void swap_cgroup_uncharge(struct swap_info_struct *si,
+				unsigned long offset)
+{
+	struct mem_cgroup *mem = si->memcg[offset];
+
+	/* "mem" would be NULL:
+	 * 1. when get_swap_page() failed at charging swap_cgroup,
+	 *    and called swap_entry_free().
+	 * 2. when this swap entry had been assigned by
+	 *    get_swap_page_of_type() (via SWSUSP?).
+	 */
+	if (mem) {
+		res_counter_uncharge(&mem->swap_res, PAGE_SIZE);
+		si->memcg[offset] = NULL;
+		css_put(&mem->css);
+	}
+}
+#endif
+
diff --git a/mm/shmem.c b/mm/shmem.c
index 95b056d..69f8909 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1029,7 +1029,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	 * want to check if there's a redundant swappage to be discarded.
 	 */
 	if (wbc->for_reclaim)
-		swap = get_swap_page();
+		swap = get_swap_page(page);
 	else
 		swap.val = 0;
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 676e191..a78d617 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -130,7 +130,7 @@ int add_to_swap(struct page * page, gfp_t gfp_mask)
 	BUG_ON(!PageUptodate(page));
 
 	for (;;) {
-		entry = get_swap_page();
+		entry = get_swap_page(page);
 		if (!entry.val)
 			return 0;
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 232bf20..682b71e 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -172,7 +172,10 @@ no_page:
 	return 0;
 }
 
-swp_entry_t get_swap_page(void)
+/* get_swap_page() calls this */
+static int swap_entry_free(struct swap_info_struct *, unsigned long);
+
+swp_entry_t get_swap_page(struct page *page)
 {
 	struct swap_info_struct *si;
 	pgoff_t offset;
@@ -201,6 +204,14 @@ swp_entry_t get_swap_page(void)
 		swap_list.next = next;
 		offset = scan_swap_map(si);
 		if (offset) {
+			/*
+			 * This should be the first use of this swap entry.
+			 * So, charge this swap entry here.
+			 */
+			if (swap_cgroup_charge(page, si, offset)) {
+				swap_entry_free(si, offset);
+				goto noswap;
+			}
 			spin_unlock(&swap_lock);
 			return swp_entry(type, offset);
 		}
@@ -285,6 +296,7 @@ static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
 				swap_list.next = p - swap_info;
 			nr_swap_pages++;
 			p->inuse_pages--;
+			swap_cgroup_uncharge(p, offset);
 		}
 	}
 	return count;


--
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>

  parent reply	other threads:[~2008-05-22  6:20 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-05-22  6:13 [PATCH 0/4] swapcgroup(v2) Daisuke Nishimura
2008-05-22  6:17 ` [PATCH 1/4] swapcgroup: add cgroup files Daisuke Nishimura
2008-05-22  6:18 ` [PATCH 2/4] swapcgroup: add member to swap_info_struct for cgroup Daisuke Nishimura
2008-05-22  7:23   ` KAMEZAWA Hiroyuki
2008-05-22  8:46     ` Daisuke Nishimura
2008-05-22  9:35       ` KAMEZAWA Hiroyuki
2008-05-22  6:20 ` Daisuke Nishimura [this message]
2008-05-22  7:37   ` [PATCH 3/4] swapcgroup: implement charge/uncharge KAMEZAWA Hiroyuki
2008-05-23 11:52     ` Daisuke Nishimura
2008-05-26  0:57       ` KAMEZAWA Hiroyuki
2008-05-27 13:42         ` KAMEZAWA Hiroyuki
2008-05-22  6:22 ` [PATCH 4/4] swapcgroup: modify vm_swap_full for cgroup Daisuke Nishimura
2008-05-22  6:45   ` YAMAMOTO Takashi
2008-05-22 12:34     ` Daisuke Nishimura
2008-05-25 23:35       ` YAMAMOTO Takashi
2008-05-22  7:39   ` KAMEZAWA Hiroyuki
2008-05-22  8:00   ` KOSAKI Motohiro
2008-05-22 12:22     ` Daisuke Nishimura
2008-05-22 12:32       ` KOSAKI Motohiro
2008-05-23 12:26         ` Daisuke Nishimura
2008-05-22  7:44 ` [PATCH 0/4] swapcgroup(v2) KAMEZAWA Hiroyuki
2008-05-23  2:10   ` Daisuke Nishimura
2008-05-23  2:42     ` Daisuke Nishimura
2008-05-22 21:27 ` Balbir Singh
2008-05-23  4:27   ` Daisuke Nishimura
2008-05-27  7:31     ` YAMAMOTO Takashi
2008-05-27  7:42       ` Balbir Singh
2008-05-27  8:30         ` Daisuke Nishimura
2008-05-27 13:18           ` Balbir Singh
2008-05-27 13:42             ` Daisuke Nishimura
2008-05-27 13:46               ` Balbir Singh
2008-05-27 14:00                 ` Daisuke Nishimura
2008-05-23  2:26 ` Rik van Riel
2008-05-23  3:10   ` KAMEZAWA Hiroyuki
2008-05-23  3:32     ` Rik van Riel
2008-05-23  3:59     ` Balbir Singh
2008-05-23  4:30       ` KOSAKI Motohiro
2008-05-23  4:51         ` Balbir Singh
2008-05-23  5:23           ` KAMEZAWA Hiroyuki
2008-05-23  5:29           ` David Singleton
2008-05-23  6:00             ` KOSAKI Motohiro
2008-05-23  6:45               ` Balbir Singh

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=48351095.3040009@mxp.nes.nec.co.jp \
    --to=nishimura@mxp.nes.nec.co.jp \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=containers@lists.osdl.org \
    --cc=hugh@veritas.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-mm@kvack.org \
    --cc=m-ikeda@ds.jp.nec.com \
    --cc=xemul@openvz.org \
    --cc=yamamoto@valinux.co.jp \
    /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