kernel-ark/include/linux/cpuset.h
John Stultz db751fe3ea cpuset: Fix potential deadlock w/ set_mems_allowed
After adding lockdep support to seqlock/seqcount structures,
I started seeing the following warning:

[    1.070907] ======================================================
[    1.072015] [ INFO: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected ]
[    1.073181] 3.11.0+ #67 Not tainted
[    1.073801] ------------------------------------------------------
[    1.074882] kworker/u4:2/708 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
[    1.076088]  (&p->mems_allowed_seq){+.+...}, at: [<ffffffff81187d7f>] new_slab+0x5f/0x280
[    1.077572]
[    1.077572] and this task is already holding:
[    1.078593]  (&(&q->__queue_lock)->rlock){..-...}, at: [<ffffffff81339f03>] blk_execute_rq_nowait+0x53/0xf0
[    1.080042] which would create a new lock dependency:
[    1.080042]  (&(&q->__queue_lock)->rlock){..-...} -> (&p->mems_allowed_seq){+.+...}
[    1.080042]
[    1.080042] but this new dependency connects a SOFTIRQ-irq-safe lock:
[    1.080042]  (&(&q->__queue_lock)->rlock){..-...}
[    1.080042] ... which became SOFTIRQ-irq-safe at:
[    1.080042]   [<ffffffff810ec179>] __lock_acquire+0x5b9/0x1db0
[    1.080042]   [<ffffffff810edfe5>] lock_acquire+0x95/0x130
[    1.080042]   [<ffffffff818968a1>] _raw_spin_lock+0x41/0x80
[    1.080042]   [<ffffffff81560c9e>] scsi_device_unbusy+0x7e/0xd0
[    1.080042]   [<ffffffff8155a612>] scsi_finish_command+0x32/0xf0
[    1.080042]   [<ffffffff81560e91>] scsi_softirq_done+0xa1/0x130
[    1.080042]   [<ffffffff8133b0f3>] blk_done_softirq+0x73/0x90
[    1.080042]   [<ffffffff81095dc0>] __do_softirq+0x110/0x2f0
[    1.080042]   [<ffffffff81095fcd>] run_ksoftirqd+0x2d/0x60
[    1.080042]   [<ffffffff810bc506>] smpboot_thread_fn+0x156/0x1e0
[    1.080042]   [<ffffffff810b3916>] kthread+0xd6/0xe0
[    1.080042]   [<ffffffff818980ac>] ret_from_fork+0x7c/0xb0
[    1.080042]
[    1.080042] to a SOFTIRQ-irq-unsafe lock:
[    1.080042]  (&p->mems_allowed_seq){+.+...}
[    1.080042] ... which became SOFTIRQ-irq-unsafe at:
[    1.080042] ...  [<ffffffff810ec1d3>] __lock_acquire+0x613/0x1db0
[    1.080042]   [<ffffffff810edfe5>] lock_acquire+0x95/0x130
[    1.080042]   [<ffffffff810b3df2>] kthreadd+0x82/0x180
[    1.080042]   [<ffffffff818980ac>] ret_from_fork+0x7c/0xb0
[    1.080042]
[    1.080042] other info that might help us debug this:
[    1.080042]
[    1.080042]  Possible interrupt unsafe locking scenario:
[    1.080042]
[    1.080042]        CPU0                    CPU1
[    1.080042]        ----                    ----
[    1.080042]   lock(&p->mems_allowed_seq);
[    1.080042]                                local_irq_disable();
[    1.080042]                                lock(&(&q->__queue_lock)->rlock);
[    1.080042]                                lock(&p->mems_allowed_seq);
[    1.080042]   <Interrupt>
[    1.080042]     lock(&(&q->__queue_lock)->rlock);
[    1.080042]
[    1.080042]  *** DEADLOCK ***

The issue stems from the kthreadd() function calling set_mems_allowed
with irqs enabled. While its possibly unlikely for the actual deadlock
to trigger, a fix is fairly simple: disable irqs before taking the
mems_allowed_seq lock.

Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/1381186321-4906-4-git-send-email-john.stultz@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-06 12:40:27 +01:00

241 lines
5.7 KiB
C

#ifndef _LINUX_CPUSET_H
#define _LINUX_CPUSET_H
/*
* cpuset interface
*
* Copyright (C) 2003 BULL SA
* Copyright (C) 2004-2006 Silicon Graphics, Inc.
*
*/
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <linux/nodemask.h>
#include <linux/mm.h>
#ifdef CONFIG_CPUSETS
extern int number_of_cpusets; /* How many cpusets are defined in system? */
extern int cpuset_init(void);
extern void cpuset_init_smp(void);
extern void cpuset_update_active_cpus(bool cpu_online);
extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
#define cpuset_current_mems_allowed (current->mems_allowed)
void cpuset_init_current_mems_allowed(void);
int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask);
extern int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask);
extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask);
static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
{
return number_of_cpusets <= 1 ||
__cpuset_node_allowed_softwall(node, gfp_mask);
}
static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
{
return number_of_cpusets <= 1 ||
__cpuset_node_allowed_hardwall(node, gfp_mask);
}
static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
{
return cpuset_node_allowed_softwall(zone_to_nid(z), gfp_mask);
}
static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
{
return cpuset_node_allowed_hardwall(zone_to_nid(z), gfp_mask);
}
extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
const struct task_struct *tsk2);
#define cpuset_memory_pressure_bump() \
do { \
if (cpuset_memory_pressure_enabled) \
__cpuset_memory_pressure_bump(); \
} while (0)
extern int cpuset_memory_pressure_enabled;
extern void __cpuset_memory_pressure_bump(void);
extern void cpuset_task_status_allowed(struct seq_file *m,
struct task_struct *task);
extern int proc_cpuset_show(struct seq_file *, void *);
extern int cpuset_mem_spread_node(void);
extern int cpuset_slab_spread_node(void);
static inline int cpuset_do_page_mem_spread(void)
{
return current->flags & PF_SPREAD_PAGE;
}
static inline int cpuset_do_slab_mem_spread(void)
{
return current->flags & PF_SPREAD_SLAB;
}
extern int current_cpuset_is_being_rebound(void);
extern void rebuild_sched_domains(void);
extern void cpuset_print_task_mems_allowed(struct task_struct *p);
/*
* get_mems_allowed is required when making decisions involving mems_allowed
* such as during page allocation. mems_allowed can be updated in parallel
* and depending on the new value an operation can fail potentially causing
* process failure. A retry loop with get_mems_allowed and put_mems_allowed
* prevents these artificial failures.
*/
static inline unsigned int get_mems_allowed(void)
{
return read_seqcount_begin(&current->mems_allowed_seq);
}
/*
* If this returns false, the operation that took place after get_mems_allowed
* may have failed. It is up to the caller to retry the operation if
* appropriate.
*/
static inline bool put_mems_allowed(unsigned int seq)
{
return !read_seqcount_retry(&current->mems_allowed_seq, seq);
}
static inline void set_mems_allowed(nodemask_t nodemask)
{
unsigned long flags;
task_lock(current);
local_irq_save(flags);
write_seqcount_begin(&current->mems_allowed_seq);
current->mems_allowed = nodemask;
write_seqcount_end(&current->mems_allowed_seq);
local_irq_restore(flags);
task_unlock(current);
}
#else /* !CONFIG_CPUSETS */
static inline int cpuset_init(void) { return 0; }
static inline void cpuset_init_smp(void) {}
static inline void cpuset_update_active_cpus(bool cpu_online)
{
partition_sched_domains(1, NULL, NULL);
}
static inline void cpuset_cpus_allowed(struct task_struct *p,
struct cpumask *mask)
{
cpumask_copy(mask, cpu_possible_mask);
}
static inline void cpuset_cpus_allowed_fallback(struct task_struct *p)
{
}
static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
{
return node_possible_map;
}
#define cpuset_current_mems_allowed (node_states[N_MEMORY])
static inline void cpuset_init_current_mems_allowed(void) {}
static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
{
return 1;
}
static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
{
return 1;
}
static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
{
return 1;
}
static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
{
return 1;
}
static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
{
return 1;
}
static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
const struct task_struct *tsk2)
{
return 1;
}
static inline void cpuset_memory_pressure_bump(void) {}
static inline void cpuset_task_status_allowed(struct seq_file *m,
struct task_struct *task)
{
}
static inline int cpuset_mem_spread_node(void)
{
return 0;
}
static inline int cpuset_slab_spread_node(void)
{
return 0;
}
static inline int cpuset_do_page_mem_spread(void)
{
return 0;
}
static inline int cpuset_do_slab_mem_spread(void)
{
return 0;
}
static inline int current_cpuset_is_being_rebound(void)
{
return 0;
}
static inline void rebuild_sched_domains(void)
{
partition_sched_domains(1, NULL, NULL);
}
static inline void cpuset_print_task_mems_allowed(struct task_struct *p)
{
}
static inline void set_mems_allowed(nodemask_t nodemask)
{
}
static inline unsigned int get_mems_allowed(void)
{
return 0;
}
static inline bool put_mems_allowed(unsigned int seq)
{
return true;
}
#endif /* !CONFIG_CPUSETS */
#endif /* _LINUX_CPUSET_H */