summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorMiao Xie <miaox@cn.fujitsu.com>2010-05-24 14:32:08 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-05-25 08:06:57 -0700
commitc0ff7453bb5c7c98e0885fb94279f2571946f280 (patch)
tree8bb2b169a5145f0496575dbd2f48bb4b1c83f819 /include
parent708c1bbc9d0c3e57f40501794d9b0eed29d10fce (diff)
cpuset,mm: fix no node to alloc memory when changing cpuset's mems
Before applying this patch, cpuset updates task->mems_allowed and mempolicy by setting all new bits in the nodemask first, and clearing all old unallowed bits later. But in the way, the allocator may find that there is no node to alloc memory. The reason is that cpuset rebinds the task's mempolicy, it cleans the nodes which the allocater can alloc pages on, for example: (mpol: mempolicy) task1 task1's mpol task2 alloc page 1 alloc on node0? NO 1 1 change mems from 1 to 0 1 rebind task1's mpol 0-1 set new bits 0 clear disallowed bits alloc on node1? NO 0 ... can't alloc page goto oom This patch fixes this problem by expanding the nodes range first(set newly allowed bits) and shrink it lazily(clear newly disallowed bits). So we use a variable to tell the write-side task that read-side task is reading nodemask, and the write-side task clears newly disallowed nodes after read-side task ends the current memory allocation. [akpm@linux-foundation.org: fix spello] Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Paul Menage <menage@google.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/cpuset.h43
-rw-r--r--include/linux/sched.h1
2 files changed, 44 insertions, 0 deletions
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index a73454aec333..20b51cab6593 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -86,9 +86,44 @@ extern void rebuild_sched_domains(void);
extern void cpuset_print_task_mems_allowed(struct task_struct *p);
+/*
+ * reading current mems_allowed and mempolicy in the fastpath must protected
+ * by get_mems_allowed()
+ */
+static inline void get_mems_allowed(void)
+{
+ current->mems_allowed_change_disable++;
+
+ /*
+ * ensure that reading mems_allowed and mempolicy happens after the
+ * update of ->mems_allowed_change_disable.
+ *
+ * the write-side task finds ->mems_allowed_change_disable is not 0,
+ * and knows the read-side task is reading mems_allowed or mempolicy,
+ * so it will clear old bits lazily.
+ */
+ smp_mb();
+}
+
+static inline void put_mems_allowed(void)
+{
+ /*
+ * ensure that reading mems_allowed and mempolicy before reducing
+ * mems_allowed_change_disable.
+ *
+ * the write-side task will know that the read-side task is still
+ * reading mems_allowed or mempolicy, don't clears old bits in the
+ * nodemask.
+ */
+ smp_mb();
+ --ACCESS_ONCE(current->mems_allowed_change_disable);
+}
+
static inline void set_mems_allowed(nodemask_t nodemask)
{
+ task_lock(current);
current->mems_allowed = nodemask;
+ task_unlock(current);
}
#else /* !CONFIG_CPUSETS */
@@ -187,6 +222,14 @@ static inline void set_mems_allowed(nodemask_t nodemask)
{
}
+static inline void get_mems_allowed(void)
+{
+}
+
+static inline void put_mems_allowed(void)
+{
+}
+
#endif /* !CONFIG_CPUSETS */
#endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b55e988988b5..415b8f8a3f45 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1421,6 +1421,7 @@ struct task_struct {
#endif
#ifdef CONFIG_CPUSETS
nodemask_t mems_allowed; /* Protected by alloc_lock */
+ int mems_allowed_change_disable;
int cpuset_mem_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS