Re: [RFC PATCH v2 15/20] context-tracking: Introduce work deferral infrastructure

[Frederic Weisbecker <frederic@kernel.org>]

Le Thu, Jul 20, 2023 at 05:30:51PM +0100, Valentin Schneider a écrit :
> +enum ctx_state {
> +	/* Following are values */
> +	CONTEXT_DISABLED	= -1,	/* returned by ct_state() if unknown */
> +	CONTEXT_KERNEL		= 0,
> +	CONTEXT_IDLE		= 1,
> +	CONTEXT_USER		= 2,
> +	CONTEXT_GUEST		= 3,
> +	CONTEXT_MAX             = 4,
> +};
> +
> +/*
> + * We cram three different things within the same atomic variable:
> + *
> + *                CONTEXT_STATE_END                        RCU_DYNTICKS_END
> + *                         |       CONTEXT_WORK_END                |
> + *                         |               |                       |
> + *                         v               v                       v
> + *         [ context_state ][ context work ][ RCU dynticks counter ]
> + *         ^                ^               ^
> + *         |                |               |
> + *         |        CONTEXT_WORK_START      |
> + * CONTEXT_STATE_START              RCU_DYNTICKS_START

Should the layout be displayed in reverse? Well at least I always picture
bitmaps in reverse, that's probably due to the direction of the shift arrows.
Not sure what is the usual way to picture it though...

> + */
> +
> +#define CT_STATE_SIZE (sizeof(((struct context_tracking *)0)->state) * BITS_PER_BYTE)
> +
> +#define CONTEXT_STATE_START 0
> +#define CONTEXT_STATE_END   (bits_per(CONTEXT_MAX - 1) - 1)

Since you have non overlapping *_START symbols, perhaps the *_END
are superfluous?

> +
> +#define RCU_DYNTICKS_BITS  (IS_ENABLED(CONFIG_CONTEXT_TRACKING_WORK) ? 16 : 31)
> +#define RCU_DYNTICKS_START (CT_STATE_SIZE - RCU_DYNTICKS_BITS)
> +#define RCU_DYNTICKS_END   (CT_STATE_SIZE - 1)
> +#define RCU_DYNTICKS_IDX   BIT(RCU_DYNTICKS_START)

Might be the right time to standardize and fix our naming:

CT_STATE_START,
CT_STATE_KERNEL,
CT_STATE_USER,
...
CT_WORK_START,
CT_WORK_*,
...
CT_RCU_DYNTICKS_START,
CT_RCU_DYNTICKS_IDX

> +bool ct_set_cpu_work(unsigned int cpu, unsigned int work)
> +{
> +	struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
> +	unsigned int old;
> +	bool ret = false;
> +
> +	preempt_disable();
> +
> +	old = atomic_read(&ct->state);
> +	/*
> +	 * Try setting the work until either
> +	 * - the target CPU no longer accepts any more deferred work
> +	 * - the work has been set
> +	 *
> +	 * NOTE: CONTEXT_GUEST intersects with CONTEXT_USER and CONTEXT_IDLE
> +	 * as they are regular integers rather than bits, but that doesn't
> +	 * matter here: if any of the context state bit is set, the CPU isn't
> +	 * in kernel context.
> +	 */
> +	while ((old & (CONTEXT_GUEST | CONTEXT_USER | CONTEXT_IDLE)) && !ret)

That may still miss a recent entry to userspace due to the first plain read, ending
with an undesired interrupt.

You need at least one cmpxchg. Well, of course that stays racy by nature because
between the cmpxchg() returning CONTEXT_KERNEL and the actual IPI raised and
received, the remote CPU may have gone to userspace already. But still it limits
a little the window.

Thanks.

> +		ret = atomic_try_cmpxchg(&ct->state, &old, old | (work << CONTEXT_WORK_START));
> +
> +	preempt_enable();
> +	return ret;
> +}
> +#else
> +static __always_inline void ct_work_flush(unsigned long work) { }
> +static __always_inline void ct_work_clear(struct context_tracking *ct) { }
> +#endif
> +
>  /*
>   * Record entry into an extended quiescent state.  This is only to be
>   * called when not already in an extended quiescent state, that is,
> @@ -88,7 +133,8 @@ static noinstr void ct_kernel_exit_state(int offset)
>  	 * next idle sojourn.
>  	 */
>  	rcu_dynticks_task_trace_enter();  // Before ->dynticks update!
> -	seq = ct_state_inc(offset);
> +	seq = ct_state_inc_clear_work(offset);
> +
>  	// RCU is no longer watching.  Better be in extended quiescent state!
>  	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & RCU_DYNTICKS_IDX));
>  }
> @@ -100,7 +146,7 @@ static noinstr void ct_kernel_exit_state(int offset)
>   */
>  static noinstr void ct_kernel_enter_state(int offset)
>  {
> -	int seq;
> +	unsigned long seq;
>  
>  	/*
>  	 * CPUs seeing atomic_add_return() must see prior idle sojourns,
> @@ -108,6 +154,7 @@ static noinstr void ct_kernel_enter_state(int offset)
>  	 * critical section.
>  	 */
>  	seq = ct_state_inc(offset);
> +	ct_work_flush(seq);
>  	// RCU is now watching.  Better not be in an extended quiescent state!
>  	rcu_dynticks_task_trace_exit();  // After ->dynticks update!
>  	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & RCU_DYNTICKS_IDX));
> diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
> index bae8f11070bef..fdb266f2d774b 100644
> --- a/kernel/time/Kconfig
> +++ b/kernel/time/Kconfig
> @@ -181,6 +181,11 @@ config CONTEXT_TRACKING_USER_FORCE
>  	  Say N otherwise, this option brings an overhead that you
>  	  don't want in production.
>  
> +config CONTEXT_TRACKING_WORK
> +	bool
> +	depends on HAVE_CONTEXT_TRACKING_WORK && CONTEXT_TRACKING_USER
> +	default y
> +
>  config NO_HZ
>  	bool "Old Idle dynticks config"
>  	help
> -- 
> 2.31.1
>