1
0
Fork 0
alistair23-linux/include/linux/preempt.h

181 lines
4.7 KiB
C
Raw Normal View History

#ifndef __LINUX_PREEMPT_H
#define __LINUX_PREEMPT_H
/*
* include/linux/preempt.h - macros for accessing and manipulating
* preempt_count (used for kernel preemption, interrupt count, etc.)
*/
#include <linux/linkage.h>
#include <linux/list.h>
2013-08-14 06:55:31 -06:00
/*
* We use the MSB mostly because its available; see <linux/preempt_mask.h> for
* the other bits -- can't include that header due to inclusion hell.
*/
#define PREEMPT_NEED_RESCHED 0x80000000
#include <asm/preempt.h>
2013-08-14 06:55:31 -06:00
#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
extern void add_preempt_count(int val);
extern void sub_preempt_count(int val);
#else
# define add_preempt_count(val) do { *preempt_count_ptr() += (val); } while (0)
# define sub_preempt_count(val) do { *preempt_count_ptr() -= (val); } while (0)
#endif
#define inc_preempt_count() add_preempt_count(1)
#define dec_preempt_count() sub_preempt_count(1)
#ifdef CONFIG_PREEMPT
asmlinkage void preempt_schedule(void);
#define preempt_check_resched() \
do { \
2013-08-14 06:55:31 -06:00
if (unlikely(!*preempt_count_ptr())) \
preempt_schedule(); \
} while (0)
tracing/context-tracking: Add preempt_schedule_context() for tracing Dave Jones hit the following bug report: =============================== [ INFO: suspicious RCU usage. ] 3.10.0-rc2+ #1 Not tainted ------------------------------- include/linux/rcupdate.h:771 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 1, debug_locks = 0 RCU used illegally from extended quiescent state! 2 locks held by cc1/63645: #0: (&rq->lock){-.-.-.}, at: [<ffffffff816b39fd>] __schedule+0xed/0x9b0 #1: (rcu_read_lock){.+.+..}, at: [<ffffffff8109d645>] cpuacct_charge+0x5/0x1f0 CPU: 1 PID: 63645 Comm: cc1 Not tainted 3.10.0-rc2+ #1 [loadavg: 40.57 27.55 13.39 25/277 64369] Hardware name: Gigabyte Technology Co., Ltd. GA-MA78GM-S2H/GA-MA78GM-S2H, BIOS F12a 04/23/2010 0000000000000000 ffff88010f78fcf8 ffffffff816ae383 ffff88010f78fd28 ffffffff810b698d ffff88011c092548 000000000023d073 ffff88011c092500 0000000000000001 ffff88010f78fd60 ffffffff8109d7c5 ffffffff8109d645 Call Trace: [<ffffffff816ae383>] dump_stack+0x19/0x1b [<ffffffff810b698d>] lockdep_rcu_suspicious+0xfd/0x130 [<ffffffff8109d7c5>] cpuacct_charge+0x185/0x1f0 [<ffffffff8109d645>] ? cpuacct_charge+0x5/0x1f0 [<ffffffff8108dffc>] update_curr+0xec/0x240 [<ffffffff8108f528>] put_prev_task_fair+0x228/0x480 [<ffffffff816b3a71>] __schedule+0x161/0x9b0 [<ffffffff816b4721>] preempt_schedule+0x51/0x80 [<ffffffff816b4800>] ? __cond_resched_softirq+0x60/0x60 [<ffffffff816b6824>] ? retint_careful+0x12/0x2e [<ffffffff810ff3cc>] ftrace_ops_control_func+0x1dc/0x210 [<ffffffff816be280>] ftrace_call+0x5/0x2f [<ffffffff816b681d>] ? retint_careful+0xb/0x2e [<ffffffff816b4805>] ? schedule_user+0x5/0x70 [<ffffffff816b4805>] ? schedule_user+0x5/0x70 [<ffffffff816b6824>] ? retint_careful+0x12/0x2e ------------[ cut here ]------------ What happened was that the function tracer traced the schedule_user() code that tells RCU that the system is coming back from userspace, and to add the CPU back to the RCU monitoring. Because the function tracer does a preempt_disable/enable_notrace() calls the preempt_enable_notrace() checks the NEED_RESCHED flag. If it is set, then preempt_schedule() is called. But this is called before the user_exit() function can inform the kernel that the CPU is no longer in user mode and needs to be accounted for by RCU. The fix is to create a new preempt_schedule_context() that checks if the kernel is still in user mode and if so to switch it to kernel mode before calling schedule. It also switches back to user mode coming back from schedule in need be. The only user of this currently is the preempt_enable_notrace(), which is only used by the tracing subsystem. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1369423420.6828.226.camel@gandalf.local.home Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-05-24 13:23:40 -06:00
#ifdef CONFIG_CONTEXT_TRACKING
void preempt_schedule_context(void);
#define preempt_check_resched_context() \
do { \
2013-08-14 06:55:31 -06:00
if (unlikely(!*preempt_count_ptr())) \
tracing/context-tracking: Add preempt_schedule_context() for tracing Dave Jones hit the following bug report: =============================== [ INFO: suspicious RCU usage. ] 3.10.0-rc2+ #1 Not tainted ------------------------------- include/linux/rcupdate.h:771 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 1, debug_locks = 0 RCU used illegally from extended quiescent state! 2 locks held by cc1/63645: #0: (&rq->lock){-.-.-.}, at: [<ffffffff816b39fd>] __schedule+0xed/0x9b0 #1: (rcu_read_lock){.+.+..}, at: [<ffffffff8109d645>] cpuacct_charge+0x5/0x1f0 CPU: 1 PID: 63645 Comm: cc1 Not tainted 3.10.0-rc2+ #1 [loadavg: 40.57 27.55 13.39 25/277 64369] Hardware name: Gigabyte Technology Co., Ltd. GA-MA78GM-S2H/GA-MA78GM-S2H, BIOS F12a 04/23/2010 0000000000000000 ffff88010f78fcf8 ffffffff816ae383 ffff88010f78fd28 ffffffff810b698d ffff88011c092548 000000000023d073 ffff88011c092500 0000000000000001 ffff88010f78fd60 ffffffff8109d7c5 ffffffff8109d645 Call Trace: [<ffffffff816ae383>] dump_stack+0x19/0x1b [<ffffffff810b698d>] lockdep_rcu_suspicious+0xfd/0x130 [<ffffffff8109d7c5>] cpuacct_charge+0x185/0x1f0 [<ffffffff8109d645>] ? cpuacct_charge+0x5/0x1f0 [<ffffffff8108dffc>] update_curr+0xec/0x240 [<ffffffff8108f528>] put_prev_task_fair+0x228/0x480 [<ffffffff816b3a71>] __schedule+0x161/0x9b0 [<ffffffff816b4721>] preempt_schedule+0x51/0x80 [<ffffffff816b4800>] ? __cond_resched_softirq+0x60/0x60 [<ffffffff816b6824>] ? retint_careful+0x12/0x2e [<ffffffff810ff3cc>] ftrace_ops_control_func+0x1dc/0x210 [<ffffffff816be280>] ftrace_call+0x5/0x2f [<ffffffff816b681d>] ? retint_careful+0xb/0x2e [<ffffffff816b4805>] ? schedule_user+0x5/0x70 [<ffffffff816b4805>] ? schedule_user+0x5/0x70 [<ffffffff816b6824>] ? retint_careful+0x12/0x2e ------------[ cut here ]------------ What happened was that the function tracer traced the schedule_user() code that tells RCU that the system is coming back from userspace, and to add the CPU back to the RCU monitoring. Because the function tracer does a preempt_disable/enable_notrace() calls the preempt_enable_notrace() checks the NEED_RESCHED flag. If it is set, then preempt_schedule() is called. But this is called before the user_exit() function can inform the kernel that the CPU is no longer in user mode and needs to be accounted for by RCU. The fix is to create a new preempt_schedule_context() that checks if the kernel is still in user mode and if so to switch it to kernel mode before calling schedule. It also switches back to user mode coming back from schedule in need be. The only user of this currently is the preempt_enable_notrace(), which is only used by the tracing subsystem. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1369423420.6828.226.camel@gandalf.local.home Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-05-24 13:23:40 -06:00
preempt_schedule_context(); \
} while (0)
#else
#define preempt_check_resched_context() preempt_check_resched()
#endif /* CONFIG_CONTEXT_TRACKING */
#else /* !CONFIG_PREEMPT */
#define preempt_check_resched() do { } while (0)
tracing/context-tracking: Add preempt_schedule_context() for tracing Dave Jones hit the following bug report: =============================== [ INFO: suspicious RCU usage. ] 3.10.0-rc2+ #1 Not tainted ------------------------------- include/linux/rcupdate.h:771 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 1, debug_locks = 0 RCU used illegally from extended quiescent state! 2 locks held by cc1/63645: #0: (&rq->lock){-.-.-.}, at: [<ffffffff816b39fd>] __schedule+0xed/0x9b0 #1: (rcu_read_lock){.+.+..}, at: [<ffffffff8109d645>] cpuacct_charge+0x5/0x1f0 CPU: 1 PID: 63645 Comm: cc1 Not tainted 3.10.0-rc2+ #1 [loadavg: 40.57 27.55 13.39 25/277 64369] Hardware name: Gigabyte Technology Co., Ltd. GA-MA78GM-S2H/GA-MA78GM-S2H, BIOS F12a 04/23/2010 0000000000000000 ffff88010f78fcf8 ffffffff816ae383 ffff88010f78fd28 ffffffff810b698d ffff88011c092548 000000000023d073 ffff88011c092500 0000000000000001 ffff88010f78fd60 ffffffff8109d7c5 ffffffff8109d645 Call Trace: [<ffffffff816ae383>] dump_stack+0x19/0x1b [<ffffffff810b698d>] lockdep_rcu_suspicious+0xfd/0x130 [<ffffffff8109d7c5>] cpuacct_charge+0x185/0x1f0 [<ffffffff8109d645>] ? cpuacct_charge+0x5/0x1f0 [<ffffffff8108dffc>] update_curr+0xec/0x240 [<ffffffff8108f528>] put_prev_task_fair+0x228/0x480 [<ffffffff816b3a71>] __schedule+0x161/0x9b0 [<ffffffff816b4721>] preempt_schedule+0x51/0x80 [<ffffffff816b4800>] ? __cond_resched_softirq+0x60/0x60 [<ffffffff816b6824>] ? retint_careful+0x12/0x2e [<ffffffff810ff3cc>] ftrace_ops_control_func+0x1dc/0x210 [<ffffffff816be280>] ftrace_call+0x5/0x2f [<ffffffff816b681d>] ? retint_careful+0xb/0x2e [<ffffffff816b4805>] ? schedule_user+0x5/0x70 [<ffffffff816b4805>] ? schedule_user+0x5/0x70 [<ffffffff816b6824>] ? retint_careful+0x12/0x2e ------------[ cut here ]------------ What happened was that the function tracer traced the schedule_user() code that tells RCU that the system is coming back from userspace, and to add the CPU back to the RCU monitoring. Because the function tracer does a preempt_disable/enable_notrace() calls the preempt_enable_notrace() checks the NEED_RESCHED flag. If it is set, then preempt_schedule() is called. But this is called before the user_exit() function can inform the kernel that the CPU is no longer in user mode and needs to be accounted for by RCU. The fix is to create a new preempt_schedule_context() that checks if the kernel is still in user mode and if so to switch it to kernel mode before calling schedule. It also switches back to user mode coming back from schedule in need be. The only user of this currently is the preempt_enable_notrace(), which is only used by the tracing subsystem. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1369423420.6828.226.camel@gandalf.local.home Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-05-24 13:23:40 -06:00
#define preempt_check_resched_context() do { } while (0)
#endif /* CONFIG_PREEMPT */
#ifdef CONFIG_PREEMPT_COUNT
#define preempt_disable() \
do { \
inc_preempt_count(); \
barrier(); \
} while (0)
#define sched_preempt_enable_no_resched() \
do { \
barrier(); \
dec_preempt_count(); \
} while (0)
#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
#define preempt_enable() \
do { \
preempt_enable_no_resched(); \
preempt_check_resched(); \
} while (0)
/* For debugging and tracer internals only! */
#define add_preempt_count_notrace(val) \
do { *preempt_count_ptr() += (val); } while (0)
#define sub_preempt_count_notrace(val) \
do { *preempt_count_ptr() -= (val); } while (0)
#define inc_preempt_count_notrace() add_preempt_count_notrace(1)
#define dec_preempt_count_notrace() sub_preempt_count_notrace(1)
#define preempt_disable_notrace() \
do { \
inc_preempt_count_notrace(); \
barrier(); \
} while (0)
#define preempt_enable_no_resched_notrace() \
do { \
barrier(); \
dec_preempt_count_notrace(); \
} while (0)
/* preempt_check_resched is OK to trace */
#define preempt_enable_notrace() \
do { \
preempt_enable_no_resched_notrace(); \
tracing/context-tracking: Add preempt_schedule_context() for tracing Dave Jones hit the following bug report: =============================== [ INFO: suspicious RCU usage. ] 3.10.0-rc2+ #1 Not tainted ------------------------------- include/linux/rcupdate.h:771 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 1, debug_locks = 0 RCU used illegally from extended quiescent state! 2 locks held by cc1/63645: #0: (&rq->lock){-.-.-.}, at: [<ffffffff816b39fd>] __schedule+0xed/0x9b0 #1: (rcu_read_lock){.+.+..}, at: [<ffffffff8109d645>] cpuacct_charge+0x5/0x1f0 CPU: 1 PID: 63645 Comm: cc1 Not tainted 3.10.0-rc2+ #1 [loadavg: 40.57 27.55 13.39 25/277 64369] Hardware name: Gigabyte Technology Co., Ltd. GA-MA78GM-S2H/GA-MA78GM-S2H, BIOS F12a 04/23/2010 0000000000000000 ffff88010f78fcf8 ffffffff816ae383 ffff88010f78fd28 ffffffff810b698d ffff88011c092548 000000000023d073 ffff88011c092500 0000000000000001 ffff88010f78fd60 ffffffff8109d7c5 ffffffff8109d645 Call Trace: [<ffffffff816ae383>] dump_stack+0x19/0x1b [<ffffffff810b698d>] lockdep_rcu_suspicious+0xfd/0x130 [<ffffffff8109d7c5>] cpuacct_charge+0x185/0x1f0 [<ffffffff8109d645>] ? cpuacct_charge+0x5/0x1f0 [<ffffffff8108dffc>] update_curr+0xec/0x240 [<ffffffff8108f528>] put_prev_task_fair+0x228/0x480 [<ffffffff816b3a71>] __schedule+0x161/0x9b0 [<ffffffff816b4721>] preempt_schedule+0x51/0x80 [<ffffffff816b4800>] ? __cond_resched_softirq+0x60/0x60 [<ffffffff816b6824>] ? retint_careful+0x12/0x2e [<ffffffff810ff3cc>] ftrace_ops_control_func+0x1dc/0x210 [<ffffffff816be280>] ftrace_call+0x5/0x2f [<ffffffff816b681d>] ? retint_careful+0xb/0x2e [<ffffffff816b4805>] ? schedule_user+0x5/0x70 [<ffffffff816b4805>] ? schedule_user+0x5/0x70 [<ffffffff816b6824>] ? retint_careful+0x12/0x2e ------------[ cut here ]------------ What happened was that the function tracer traced the schedule_user() code that tells RCU that the system is coming back from userspace, and to add the CPU back to the RCU monitoring. Because the function tracer does a preempt_disable/enable_notrace() calls the preempt_enable_notrace() checks the NEED_RESCHED flag. If it is set, then preempt_schedule() is called. But this is called before the user_exit() function can inform the kernel that the CPU is no longer in user mode and needs to be accounted for by RCU. The fix is to create a new preempt_schedule_context() that checks if the kernel is still in user mode and if so to switch it to kernel mode before calling schedule. It also switches back to user mode coming back from schedule in need be. The only user of this currently is the preempt_enable_notrace(), which is only used by the tracing subsystem. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1369423420.6828.226.camel@gandalf.local.home Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-05-24 13:23:40 -06:00
preempt_check_resched_context(); \
} while (0)
#else /* !CONFIG_PREEMPT_COUNT */
spinlocks and preemption points need to be at least compiler barriers In UP and non-preempt respectively, the spinlocks and preemption disable/enable points are stubbed out entirely, because there is no regular code that can ever hit the kind of concurrency they are meant to protect against. However, while there is no regular code that can cause scheduling, we _do_ end up having some exceptional (literally!) code that can do so, and that we need to make sure does not ever get moved into the critical region by the compiler. In particular, get_user() and put_user() is generally implemented as inline asm statements (even if the inline asm may then make a call instruction to call out-of-line), and can obviously cause a page fault and IO as a result. If that inline asm has been scheduled into the middle of a preemption-safe (or spinlock-protected) code region, we obviously lose. Now, admittedly this is *very* unlikely to actually ever happen, and we've not seen examples of actual bugs related to this. But partly exactly because it's so hard to trigger and the resulting bug is so subtle, we should be extra careful to get this right. So make sure that even when preemption is disabled, and we don't have to generate any actual *code* to explicitly tell the system that we are in a preemption-disabled region, we need to at least tell the compiler not to move things around the critical region. This patch grew out of the same discussion that caused commits 79e5f05edcbf ("ARC: Add implicit compiler barrier to raw_local_irq* functions") and 3e2e0d2c222b ("tile: comment assumption about __insn_mtspr for <asm/irqflags.h>") to come about. Note for stable: use discretion when/if applying this. As mentioned, this bug may never have actually bitten anybody, and gcc may never have done the required code motion for it to possibly ever trigger in practice. Cc: stable@vger.kernel.org Cc: Steven Rostedt <srostedt@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-09 11:48:33 -06:00
/*
* Even if we don't have any preemption, we need preempt disable/enable
* to be barriers, so that we don't have things like get_user/put_user
* that can cause faults and scheduling migrate into our preempt-protected
* region.
*/
#define preempt_disable() barrier()
#define sched_preempt_enable_no_resched() barrier()
#define preempt_enable_no_resched() barrier()
#define preempt_enable() barrier()
#define preempt_disable_notrace() barrier()
#define preempt_enable_no_resched_notrace() barrier()
#define preempt_enable_notrace() barrier()
#endif /* CONFIG_PREEMPT_COUNT */
#ifdef CONFIG_PREEMPT_NOTIFIERS
struct preempt_notifier;
/**
* preempt_ops - notifiers called when a task is preempted and rescheduled
* @sched_in: we're about to be rescheduled:
* notifier: struct preempt_notifier for the task being scheduled
* cpu: cpu we're scheduled on
* @sched_out: we've just been preempted
* notifier: struct preempt_notifier for the task being preempted
* next: the task that's kicking us out
*
* Please note that sched_in and out are called under different
* contexts. sched_out is called with rq lock held and irq disabled
* while sched_in is called without rq lock and irq enabled. This
* difference is intentional and depended upon by its users.
*/
struct preempt_ops {
void (*sched_in)(struct preempt_notifier *notifier, int cpu);
void (*sched_out)(struct preempt_notifier *notifier,
struct task_struct *next);
};
/**
* preempt_notifier - key for installing preemption notifiers
* @link: internal use
* @ops: defines the notifier functions to be called
*
* Usually used in conjunction with container_of().
*/
struct preempt_notifier {
struct hlist_node link;
struct preempt_ops *ops;
};
void preempt_notifier_register(struct preempt_notifier *notifier);
void preempt_notifier_unregister(struct preempt_notifier *notifier);
static inline void preempt_notifier_init(struct preempt_notifier *notifier,
struct preempt_ops *ops)
{
INIT_HLIST_NODE(&notifier->link);
notifier->ops = ops;
}
#endif
#endif /* __LINUX_PREEMPT_H */