Re: [PATCH 2/3] rcu: Create rcu_sync infrastructure

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

On Wed, Oct 02, 2013 at 04:56:57PM +0200, Peter Zijlstra wrote:
> From: Oleg Nesterov <oleg@redhat.com>
> 
> It is functionally equivalent to
> 
>         struct xxx_struct {
>                 atomic_t counter;
>         };
> 
>         static inline bool xxx_is_idle(struct xxx_struct *xxx)
>         {
>                 return atomic_read(&xxx->counter) == 0;
>         }
> 
>         static inline void xxx_enter(struct xxx_struct *xxx)
>         {
>                 atomic_inc(&xxx->counter);
>                 synchronize_sched();
>         }
> 
>         static inline void xxx_enter(struct xxx_struct *xxx)
>         {
>                 synchronize_sched();
>                 atomic_dec(&xxx->counter);
>         }
> 
> except: it records the state and synchronize_sched() is only called by
> xxx_enter() and only if necessary.

Could you please make the "xxx_" above match the prefix below?

One comment below for the code's self-defense.

							Thanx, Paul

> Signed-off-by: Peter Zijlstra <peterz@infradead.org>
> Link: http://lkml.kernel.org/r/20130929183634.GA15563@redhat.com
> ---
>  include/linux/rcusync.h |   64 ++++++++++++++++++++++++++++
>  kernel/Makefile         |    3 -
>  kernel/rcusync.c        |  108 ++++++++++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 174 insertions(+), 1 deletion(-)
> 
> --- /dev/null
> +++ b/include/linux/rcusync.h
> @@ -0,0 +1,64 @@
> +#ifndef _LINUX_RCUSYNC_H_
> +#define _LINUX_RCUSYNC_H_
> +
> +#include <linux/wait.h>
> +#include <linux/rcupdate.h>
> +
> +struct rcu_sync_struct {
> +	int			gp_state;
> +	int			gp_count;
> +	wait_queue_head_t	gp_wait;
> +
> +	int			cb_state;
> +	struct rcu_head		cb_head;
> +
> +	void (*sync)(void);
> +	void (*call)(struct rcu_head *, void (*)(struct rcu_head *));
> +};
> +
> +#define ___RCU_SYNC_INIT(name)						\
> +	.gp_state = 0,							\
> +	.gp_count = 0,							\
> +	.gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait),		\
> +	.cb_state = 0
> +
> +#define __RCU_SCHED_SYNC_INIT(name) {					\
> +	___RCU_SYNC_INIT(name),						\
> +	.sync = synchronize_sched,					\
> +	.call = call_rcu_sched,						\
> +}
> +
> +#define __RCU_BH_SYNC_INIT(name) {					\
> +	___RCU_SYNC_INIT(name),						\
> +	.sync = synchronize_rcu_bh,					\
> +	.call = call_rcu_bh,						\
> +}
> +
> +#define __RCU_SYNC_INIT(name) {						\
> +	___RCU_SYNC_INIT(name),						\
> +	.sync = synchronize_rcu,					\
> +	.call = call_rcu,						\
> +}
> +
> +#define DEFINE_RCU_SCHED_SYNC(name)					\
> +	struct rcu_sync_struct name = __RCU_SCHED_SYNC_INIT(name)
> +
> +#define DEFINE_RCU_BH_SYNC(name)					\
> +	struct rcu_sync_struct name = __RCU_BH_SYNC_INIT(name)
> +
> +#define DEFINE_RCU_SYNC(name)						\
> +	struct rcu_sync_struct name = __RCU_SYNC_INIT(name)
> +
> +static inline bool rcu_sync_is_idle(struct rcu_sync_struct *rss)
> +{

It would be nice to validate that we are in the corresponding type of
RCU read-side critical section, but I would hate to pay a function call
through a pointer for this if !PROVE_RCU.  But even more, I would hate
rare bugs due to someone forgetting an rcu_read_lock().

How about the something like the following, where ->read_side_check()
gets rcu_read_lock_held(), rcu_read_lock_bh_held(), or
rcu_read_lock_sched_held(), as appropriate?

#ifdef CONFIG_PROVE_RCU
#define rcu_sync_is_idle_check(rss) BUG_ON(!rss->read_side_check())
#else
#define rcu_sync_is_idle_check(rss) do { } while (0)
#endif

	rcu_sync_is_idle_check(rss);

> +	return !rss->gp_state; /* GP_IDLE */
> +}
> +
> +enum rcu_sync_type { RCU_SYNC, RCU_SCHED_SYNC, RCU_BH_SYNC };
> +
> +extern void rcu_sync_init(struct rcu_sync_struct *, enum rcu_sync_type);
> +extern void rcu_sync_enter(struct rcu_sync_struct *);
> +extern void rcu_sync_exit(struct rcu_sync_struct *);
> +
> +#endif /* _LINUX_RCUSYNC_H_ */
> +
> --- a/kernel/Makefile
> +++ b/kernel/Makefile
> @@ -10,7 +10,8 @@ obj-y     = fork.o exec_domain.o panic.o
>  	    kthread.o wait.o sys_ni.o posix-cpu-timers.o mutex.o \
>  	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
>  	    notifier.o ksysfs.o cred.o reboot.o \
> -	    async.o range.o groups.o lglock.o smpboot.o
> +	    async.o range.o groups.o lglock.o smpboot.o \
> +	    rcusync.o
> 
>  ifdef CONFIG_FUNCTION_TRACER
>  # Do not trace debug files and internal ftrace files
> --- /dev/null
> +++ b/kernel/rcusync.c
> @@ -0,0 +1,108 @@
> +
> +#include <linux/rcusync.h>
> +#include <linux/sched.h>
> +
> +enum { GP_IDLE = 0, GP_PENDING, GP_PASSED };
> +enum { CB_IDLE = 0, CB_PENDING, CB_REPLAY };
> +
> +#define	rss_lock	gp_wait.lock
> +
> +void rcu_sync_init(struct rcu_sync_struct *rss, enum rcu_sync_type type)
> +{
> +	memset(rss, 0, sizeof(*rss));
> +	init_waitqueue_head(&rss->gp_wait);
> +
> +	switch (type) {
> +	case RCU_SYNC:
> +		rss->sync = synchronize_rcu;
> +		rss->call = call_rcu;
> +		break;
> +
> +	case RCU_SCHED_SYNC:
> +		rss->sync = synchronize_sched;
> +		rss->call = call_rcu_sched;
> +		break;
> +
> +	case RCU_BH_SYNC:
> +		rss->sync = synchronize_rcu_bh;
> +		rss->call = call_rcu_bh;
> +		break;
> +	}
> +}
> +
> +void rcu_sync_enter(struct rcu_sync_struct *rss)
> +{
> +	bool need_wait, need_sync;
> +
> +	spin_lock_irq(&rss->rss_lock);
> +	need_wait = rss->gp_count++;
> +	need_sync = rss->gp_state == GP_IDLE;
> +	if (need_sync)
> +		rss->gp_state = GP_PENDING;
> +	spin_unlock_irq(&rss->rss_lock);
> +
> +	BUG_ON(need_wait && need_sync);
> +
> +	if (need_sync) {
> +		rss->sync();
> +		rss->gp_state = GP_PASSED;
> +		wake_up_all(&rss->gp_wait);
> +	} else if (need_wait) {
> +		wait_event(rss->gp_wait, rss->gp_state == GP_PASSED);
> +	} else {
> +		/*
> +		 * Possible when there's a pending CB from a rcu_sync_exit().
> +		 * Nobody has yet been allowed the 'fast' path and thus we can
> +		 * avoid doing any sync(). The callback will get 'dropped'.
> +		 */
> +		BUG_ON(rss->gp_state != GP_PASSED);
> +	}
> +}
> +
> +static void rcu_sync_func(struct rcu_head *rcu)
> +{
> +	struct rcu_sync_struct *rss =
> +		container_of(rcu, struct rcu_sync_struct, cb_head);
> +	unsigned long flags;
> +
> +
> +	BUG_ON(rss->gp_state != GP_PASSED);
> +	BUG_ON(rss->cb_state == CB_IDLE);
> +
> +	spin_lock_irqsave(&rss->rss_lock, flags);
> +	if (rss->gp_count) {
> +		/*
> +		 * A new rcu_sync_begin() has happened; drop the callback.
> +		 */
> +		rss->cb_state = CB_IDLE;
> +	} else if (rss->cb_state == CB_REPLAY) {
> +		/*
> +		 * A new rcu_sync_exit() has happened; requeue the callback
> +		 * to catch a later GP.
> +		 */
> +		rss->cb_state = CB_PENDING;
> +		rss->call(&rss->cb_head, rcu_sync_func);
> +	} else {
> +		/*
> +		 * We're at least a GP after rcu_sync_exit(); eveybody will now
> +		 * have observed the write side critical section. Let 'em rip!.
> +		 */
> +		rss->cb_state = CB_IDLE;
> +		rss->gp_state = GP_IDLE;
> +	}
> +	spin_unlock_irqrestore(&rss->rss_lock, flags);
> +}
> +
> +void rcu_sync_exit(struct rcu_sync_struct *rss)
> +{
> +	spin_lock_irq(&rss->rss_lock);
> +	if (!--rss->gp_count) {
> +		if (rss->cb_state == CB_IDLE) {
> +			rss->cb_state = CB_PENDING;
> +			rss->call(&rss->cb_head, rcu_sync_func);
> +		} else if (rss->cb_state == CB_PENDING) {
> +			rss->cb_state = CB_REPLAY;
> +		}
> +	}
> +	spin_unlock_irq(&rss->rss_lock);
> +}
> 
>