[PATCH] memcg: add commens for expaing memory barrier (Was Re: Lowoverhead patches for the memory cgroup controller (v5)

[KAMEZAWA Hiroyuki]

On Tue, 23 Jun 2009 09:01:16 +0900
KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> wrote:
> > Do we still need the smp_wmb()?
> > 
> > It's hard to say, because we forgot to document it :(
> > 
> Sorry for lack of documentation.
> 
> pc->mem_cgroup should be visible before SetPageCgroupUsed(). Othrewise,
> A routine believes USED bit will see bad pc->mem_cgroup.
> 
> I'd like to  add a comment later (againt new mmotm.)
> 

Ok, it's now.
==
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>

Add comments for the reason of smp_wmb() in mem_cgroup_commit_charge().

Cc: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
---
 mm/memcontrol.c |    7 +++++++
 1 file changed, 7 insertions(+)

Index: mmotm-2.6.31-Jun25/mm/memcontrol.c
===================================================================
--- mmotm-2.6.31-Jun25.orig/mm/memcontrol.c
+++ mmotm-2.6.31-Jun25/mm/memcontrol.c
@@ -1134,6 +1134,13 @@ static void __mem_cgroup_commit_charge(s
 	}
 
 	pc->mem_cgroup = mem;
+	/*
+ 	 * We access a page_cgroup asynchronously without lock_page_cgroup().
+ 	 * Especially when a page_cgroup is taken from a page, pc->mem_cgroup
+ 	 * is accessed after testing USED bit. To make pc->mem_cgroup visible
+ 	 * before USED bit, we need memory barrier here.
+ 	 * See mem_cgroup_add_lru_list(), etc.
+ 	 */
 	smp_wmb();
 	switch (ctype) {
 	case MEM_CGROUP_CHARGE_TYPE_CACHE:


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/