[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <54210DA5.4040606@huawei.com>
Date: Tue, 23 Sep 2014 14:05:25 +0800
From: Zefan Li <lizefan@...wei.com>
To: Tejun Heo <tj@...nel.org>
CC: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
Tetsuo Handa <penguin-kernel@...ove.SAKURA.ne.jp>,
Miao Xie <miaox@...fujitsu.com>,
LKML <linux-kernel@...r.kernel.org>,
Cgroups <cgroups@...r.kernel.org>,
Kees Cook <keescook@...omium.org>
Subject: [PATCH v2 3/3] cpuset: PF_SPREAD_PAGE and PF_SPREAD_SLAB should be
atomic flags
When we change cpuset.memory_spread_{page,slab}, cpuset will flip
PF_SPREAD_{PAGE,SLAB} bit of tsk->flags for each task in that cpuset.
This should be done using atomic bitops, but currently we don't,
which is broken.
Tetsuo reported a hard-to-reproduce kernel crash on RHEL6, which happend
when one thread tried to clear PF_USED_MATH while at the same time another
thread tried to flip PF_SPREAD_PAGE/PF_SPREAD_SLAB. They both operate on
the same task.
Here's the full report:
https://lkml.org/lkml/2014/9/19/230
To fix this, we make PF_SPREAD_PAGE and PF_SPARED_SLAB atomic flags.
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Ingo Molnar <mingo@...nel.org>
Cc: Miao Xie <miaox@...fujitsu.com>
Cc: Kees Cook <keescook@...omium.org>
Fixes: 950592f7b991 ("cpusets: update tasks' page/slab spread flags in time")
Cc: <stable@...r.kernel.org> # 2.6.31+
Reported-by: Tetsuo Handa <penguin-kernel@...ove.SAKURA.ne.jp>
Signed-off-by: Zefan Li <lizefan@...wei.com>
---
include/linux/cpuset.h | 4 ++--
include/linux/sched.h | 6 ++++--
kernel/cpuset.c | 9 +++++----
3 files changed, 11 insertions(+), 8 deletions(-)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 0d4e067..2f073db 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -94,12 +94,12 @@ extern int cpuset_slab_spread_node(void);
static inline int cpuset_do_page_mem_spread(void)
{
- return current->flags & PF_SPREAD_PAGE;
+ return task_spread_page(current);
}
static inline int cpuset_do_slab_mem_spread(void)
{
- return current->flags & PF_SPREAD_SLAB;
+ return task_spread_slab(current);
}
extern int current_cpuset_is_being_rebound(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 04a2ae2..ee634d1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1903,8 +1903,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
#define PF_KTHREAD 0x00200000 /* I am a kernel thread */
#define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */
#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */
-#define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */
-#define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */
#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
@@ -1958,6 +1956,8 @@ static inline void memalloc_noio_restore(unsigned int flags)
/* Per-process atomic flags. */
#define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */
+#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */
+#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */
#define TASK_PFA_BITOPS(name, func) \
static inline bool task_##func(struct task_struct *p) \
@@ -1970,6 +1970,8 @@ static inline void task_clear_##func(struct task_struct *p) \
{ clear_bit(PFA_##name, &p->atomic_flags); }
TASK_PFA_BITOPS(NO_NEW_PRIVS, no_new_privs)
+TASK_PFA_BITOPS(SPREAD_PAGE, spread_page)
+TASK_PFA_BITOPS(SPREAD_SLAB, spread_slab)
/*
* task->jobctl flags
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index a37f4ed..1f107c7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -365,13 +365,14 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs,
struct task_struct *tsk)
{
if (is_spread_page(cs))
- tsk->flags |= PF_SPREAD_PAGE;
+ task_set_spread_page(tsk);
else
- tsk->flags &= ~PF_SPREAD_PAGE;
+ task_clear_spread_page(tsk);
+
if (is_spread_slab(cs))
- tsk->flags |= PF_SPREAD_SLAB;
+ task_set_spread_slab(tsk);
else
- tsk->flags &= ~PF_SPREAD_SLAB;
+ task_clear_spread_slab(tsk);
}
/*
--
1.8.0.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists