[PATCH 13/22] x86: mp: Allow running functions on multiple CPUs

[Wolfgang Wallner <wolfgang.wallner@br-automation.com>]

Hi Simon,

-----"Simon Glass" <sjg@chromium.org> schrieb: -----
> Betreff: [PATCH 13/22] x86: mp: Allow running functions on multiple CPUs
> 
> Add a way to run a function on a selection of CPUs. This supports either
> a single CPU, all CPUs, just the main CPU or just the 'APs', in Intel
> terminology.
> 
> It works by writing into a mailbox and then waiting for the CPUs to notice
> it, take action and indicate they are done.
> 
> When SMP is not yet enabled, this just calls the function on the main CPU.
> 
> Signed-off-by: Simon Glass <sjg@chromium.org>
> ---
> 
>  arch/x86/cpu/mp_init.c    | 82 ++++++++++++++++++++++++++++++++++++---
>  arch/x86/include/asm/mp.h | 30 ++++++++++++++
>  2 files changed, 106 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/x86/cpu/mp_init.c b/arch/x86/cpu/mp_init.c
> index 139e9749e74..9f97dc7a9ba 100644
> --- a/arch/x86/cpu/mp_init.c
> +++ b/arch/x86/cpu/mp_init.c
> @@ -50,12 +50,7 @@ struct cpu_map {
>  };
>  
>  struct mp_callback {
> -	/**
> -	 * func() - Function to call on the AP
> -	 *
> -	 * @arg: Argument to pass
> -	 */
> -	void (*func)(void *arg);
> +	mp_run_func func;
>  	void *arg;
>  	int logical_cpu_number;
>  };
> @@ -483,6 +478,50 @@ static void store_callback(struct mp_callback **slot, struct mp_callback *val)
>  	);
>  }

Could you please add a function description for run_ap_work()?

> +static int run_ap_work(struct mp_callback *callback, struct udevice *bsp,
> +		       int num_cpus, uint expire_ms)
> +{
> +	int cur_cpu = bsp->req_seq;
> +	int num_aps = num_cpus - 1; /* number of non-BSPs to get this message */
> +	int cpus_accepted;
> +	ulong start;
> +	int i;
> +
> +	/* Signal to all the APs to run the func. */
> +	for (i = 0; i < num_cpus; i++) {
> +		if (cur_cpu != i)
> +			store_callback(&ap_callbacks[i], callback);
> +	}
> +	mfence();
> +
> +	/* Wait for all the APs to signal back that call has been accepted. */
> +	start = get_timer(0);
> +
> +	do {
> +		mdelay(1);
> +		cpus_accepted = 0;
> +
> +		for (i = 0; i < num_cpus; i++) {
> +			if (cur_cpu == i)
> +				continue;
> +			if (!read_callback(&ap_callbacks[i]))
> +				cpus_accepted++;
> +		}
> +
> +		if (expire_ms && get_timer(start) >= expire_ms) {
> +			log(UCLASS_CPU, LOGL_CRIT,
> +			    "AP call expired; %d/%d CPUs accepted\n",
> +			    cpus_accepted, num_aps);
> +			return -ETIMEDOUT;
> +		}
> +	} while (cpus_accepted != num_aps);
> +
> +	/* Make sure we can see any data written by the APs */
> +	mfence();
> +
> +	return 0;
> +}
> +
>  /**
>   * ap_wait_for_instruction() - Wait for and process requests from the main CPU
>   *
> @@ -539,6 +578,37 @@ static struct mp_flight_record mp_steps[] = {
>  	MP_FR_BLOCK_APS(ap_wait_for_instruction, NULL, NULL, NULL),
>  };
>  
> +int mp_run_on_cpus(int cpu_select, mp_run_func func, void *arg)
> +{
> +	struct mp_callback lcb = {
> +		.func = func,
> +		.arg = arg,
> +		.logical_cpu_number = cpu_select,
> +	};
> +	struct udevice *dev;
> +	int num_cpus;
> +	int ret;
> +
> +	if (!(gd->flags & GD_FLG_SMP_INIT))
> +		return -ENXIO;
> +
> +	ret = get_bsp(&dev, &num_cpus);
> +	if (ret < 0)
> +		return log_msg_ret("bsp", ret);
> +	if (cpu_select == MP_SELECT_ALL || cpu_select == MP_SELECT_BSP ||
> +	    cpu_select == ret) {
> +		/* Run on BSP first */
> +		func(arg);
> +	}
> +
> +	/* Allow up to 1 second for all APs to finish */
> +	ret = run_ap_work(&lcb, dev, num_cpus, 1000 /* ms */);
> +	if (ret)
> +		return log_msg_ret("aps", ret);
> +
> +	return 0;
> +}
> +
>  int mp_init(void)
>  {
>  	int num_aps, num_cpus;
> diff --git a/arch/x86/include/asm/mp.h b/arch/x86/include/asm/mp.h
> index 41b1575f4be..0272b3c0b6a 100644
> --- a/arch/x86/include/asm/mp.h
> +++ b/arch/x86/include/asm/mp.h
> @@ -86,4 +86,34 @@ int mp_init(void);
>  /* Set up additional CPUs */
>  int x86_mp_init(void);
>  
> +/**
> + * mp_run_func() - Function to call on the AP
> + *
> + * @arg: Argument to pass
> + */
> +typedef void (*mp_run_func)(void *arg);
> +
> +#if defined(CONFIG_SMP) && !CONFIG_IS_ENABLED(X86_64)
> +/**
> + * mp_run_on_cpus() - Run a function on one or all CPUs
> + *
> + * This does not return until all CPUs have completed the work
> + *
> + * @cpu_select: CPU to run on, or MP_SELECT_ALL for all, or MP_SELECT_BSP for
> + *	BSP
> + * @func: Function to run
> + * @arg: Argument to pass to the function
> + * @return 0 on success, -ve on error
> + */
> +int mp_run_on_cpus(int cpu_select, mp_run_func func, void *arg);
> +#else
> +static inline int mp_run_on_cpus(int cpu_select, mp_run_func func, void *arg)
> +{
> +	/* There is only one CPU, so just call the function here */
> +	func(arg);
> +
> +	return 0;
> +}
> +#endif
> +
>  #endif /* _X86_MP_H_ */
> -- 
> 2.27.0.rc0.183.gde8f92d652-goog

regards, Wolfgang