summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorDaisuke Nishimura <nishimura@mxp.nes.nec.co.jp>2010-11-24 12:57:06 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2010-11-25 06:50:44 +0900
commitb1dd693e5b9348bd68a80e679e03cf9c0973b01b (patch)
tree557c8e0634fba47ea61ed9fbb8742d907c567944 /mm
parent11e7946f196e5fdde20584e3e58c60335ee3b3bc (diff)
downloadop-kernel-dev-b1dd693e5b9348bd68a80e679e03cf9c0973b01b.zip
op-kernel-dev-b1dd693e5b9348bd68a80e679e03cf9c0973b01b.tar.gz
memcg: avoid deadlock between move charge and try_charge()
__mem_cgroup_try_charge() can be called under down_write(&mmap_sem)(e.g. mlock does it). This means it can cause deadlock if it races with move charge: Ex.1) move charge | try charge --------------------------------------+------------------------------ mem_cgroup_can_attach() | down_write(&mmap_sem) mc.moving_task = current | .. mem_cgroup_precharge_mc() | __mem_cgroup_try_charge() mem_cgroup_count_precharge() | prepare_to_wait() down_read(&mmap_sem) | if (mc.moving_task) -> cannot aquire the lock | -> true | schedule() Ex.2) move charge | try charge --------------------------------------+------------------------------ mem_cgroup_can_attach() | mc.moving_task = current | mem_cgroup_precharge_mc() | mem_cgroup_count_precharge() | down_read(&mmap_sem) | .. | up_read(&mmap_sem) | | down_write(&mmap_sem) mem_cgroup_move_task() | .. mem_cgroup_move_charge() | __mem_cgroup_try_charge() down_read(&mmap_sem) | prepare_to_wait() -> cannot aquire the lock | if (mc.moving_task) | -> true | schedule() To avoid this deadlock, we do all the move charge works (both can_attach() and attach()) under one mmap_sem section. And after this patch, we set/clear mc.moving_task outside mc.lock, because we use the lock only to check mc.from/to. Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/memcontrol.c43
1 files changed, 26 insertions, 17 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 62d1880..26218df 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -278,13 +278,14 @@ enum move_type {
/* "mc" and its members are protected by cgroup_mutex */
static struct move_charge_struct {
- spinlock_t lock; /* for from, to, moving_task */
+ spinlock_t lock; /* for from, to */
struct mem_cgroup *from;
struct mem_cgroup *to;
unsigned long precharge;
unsigned long moved_charge;
unsigned long moved_swap;
struct task_struct *moving_task; /* a task moving charges */
+ struct mm_struct *mm;
wait_queue_head_t waitq; /* a waitq for other context */
} mc = {
.lock = __SPIN_LOCK_UNLOCKED(mc.lock),
@@ -4631,7 +4632,7 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
unsigned long precharge;
struct vm_area_struct *vma;
- down_read(&mm->mmap_sem);
+ /* We've already held the mmap_sem */
for (vma = mm->mmap; vma; vma = vma->vm_next) {
struct mm_walk mem_cgroup_count_precharge_walk = {
.pmd_entry = mem_cgroup_count_precharge_pte_range,
@@ -4643,7 +4644,6 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
walk_page_range(vma->vm_start, vma->vm_end,
&mem_cgroup_count_precharge_walk);
}
- up_read(&mm->mmap_sem);
precharge = mc.precharge;
mc.precharge = 0;
@@ -4694,11 +4694,16 @@ static void mem_cgroup_clear_mc(void)
mc.moved_swap = 0;
}
+ if (mc.mm) {
+ up_read(&mc.mm->mmap_sem);
+ mmput(mc.mm);
+ }
spin_lock(&mc.lock);
mc.from = NULL;
mc.to = NULL;
- mc.moving_task = NULL;
spin_unlock(&mc.lock);
+ mc.moving_task = NULL;
+ mc.mm = NULL;
mem_cgroup_end_move(from);
memcg_oom_recover(from);
memcg_oom_recover(to);
@@ -4724,12 +4729,21 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
return 0;
/* We move charges only when we move a owner of the mm */
if (mm->owner == p) {
+ /*
+ * We do all the move charge works under one mmap_sem to
+ * avoid deadlock with down_write(&mmap_sem)
+ * -> try_charge() -> if (mc.moving_task) -> sleep.
+ */
+ down_read(&mm->mmap_sem);
+
VM_BUG_ON(mc.from);
VM_BUG_ON(mc.to);
VM_BUG_ON(mc.precharge);
VM_BUG_ON(mc.moved_charge);
VM_BUG_ON(mc.moved_swap);
VM_BUG_ON(mc.moving_task);
+ VM_BUG_ON(mc.mm);
+
mem_cgroup_start_move(from);
spin_lock(&mc.lock);
mc.from = from;
@@ -4737,14 +4751,16 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
mc.precharge = 0;
mc.moved_charge = 0;
mc.moved_swap = 0;
- mc.moving_task = current;
spin_unlock(&mc.lock);
+ mc.moving_task = current;
+ mc.mm = mm;
ret = mem_cgroup_precharge_mc(mm);
if (ret)
mem_cgroup_clear_mc();
- }
- mmput(mm);
+ /* We call up_read() and mmput() in clear_mc(). */
+ } else
+ mmput(mm);
}
return ret;
}
@@ -4832,7 +4848,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
struct vm_area_struct *vma;
lru_add_drain_all();
- down_read(&mm->mmap_sem);
+ /* We've already held the mmap_sem */
for (vma = mm->mmap; vma; vma = vma->vm_next) {
int ret;
struct mm_walk mem_cgroup_move_charge_walk = {
@@ -4851,7 +4867,6 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
*/
break;
}
- up_read(&mm->mmap_sem);
}
static void mem_cgroup_move_task(struct cgroup_subsys *ss,
@@ -4860,17 +4875,11 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
struct task_struct *p,
bool threadgroup)
{
- struct mm_struct *mm;
-
- if (!mc.to)
+ if (!mc.mm)
/* no need to move charge */
return;
- mm = get_task_mm(p);
- if (mm) {
- mem_cgroup_move_charge(mm);
- mmput(mm);
- }
+ mem_cgroup_move_charge(mc.mm);
mem_cgroup_clear_mc();
}
#else /* !CONFIG_MMU */
OpenPOWER on IntegriCloud