From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Trinabh Gupta <trinabh@linux.vnet.ibm.com>
Cc: linuxppc-dev@ozlabs.org, linux-pm@lists.linux-foundation.org,
linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH V1 5/7] cpuidle: (POWER) cpuidle driver for pSeries
Date: Fri, 17 Jun 2011 14:36:38 +1000 [thread overview]
Message-ID: <1308285398.32158.12.camel@pasglop> (raw)
In-Reply-To: <20110607163012.6848.19268.stgit@tringupt.in.ibm.com>
On Tue, 2011-06-07 at 22:00 +0530, Trinabh Gupta wrote:
> +static int snooze_loop(struct cpuidle_device *dev,
> + struct cpuidle_driver *drv,
> + int index)
> +{
> + unsigned long in_purr, out_purr;
> + ktime_t kt_before, kt_after;
> + s64 usec_delta;
> +
> + /*
> + * Indicate to the HV that we are idle. Now would be
> + * a good time to find other work to dispatch.
> + */
> + get_lppaca()->idle = 1;
> + get_lppaca()->donate_dedicated_cpu = 1;
> + in_purr = mfspr(SPRN_PURR);
> +
> + kt_before = ktime_get_real();
Don't you want to timestamp before you tell the HV that you are idle ?
Or is the above stuff only polled by phyp when partition interrupts are
enabled ?
> + local_irq_enable();
> + set_thread_flag(TIF_POLLING_NRFLAG);
> + while (!need_resched()) {
> + ppc64_runlatch_off();
> + HMT_low();
> + HMT_very_low();
> + }
> + HMT_medium();
> + clear_thread_flag(TIF_POLLING_NRFLAG);
> + smp_mb();
> + local_irq_disable();
> +
> + kt_after = ktime_get_real();
> + usec_delta = ktime_to_us(ktime_sub(kt_after, kt_before));
> +
> + out_purr = mfspr(SPRN_PURR);
> + get_lppaca()->wait_state_cycles += out_purr - in_purr;
> + get_lppaca()->donate_dedicated_cpu = 0;
> + get_lppaca()->idle = 0;
> +
> + dev->last_residency = (int)usec_delta;
> +
> + return index;
> +}
> +
> +static int dedicated_cede_loop(struct cpuidle_device *dev,
> + struct cpuidle_driver *drv,
> + int index)
> +{
> + unsigned long in_purr, out_purr;
> + ktime_t kt_before, kt_after;
> + s64 usec_delta;
> +
> + /*
> + * Indicate to the HV that we are idle. Now would be
> + * a good time to find other work to dispatch.
> + */
> + get_lppaca()->idle = 1;
> + get_lppaca()->donate_dedicated_cpu = 1;
> + in_purr = mfspr(SPRN_PURR);
> +
> + kt_before = ktime_get_real();
There's a bit too much code duplication for my taste here between the
two functions. Not sure if it can be helped, maybe with some inlines
for the prolog/epilogue ... Looks like stuff that's easy to "fix" in one
place and forget the other...
> + ppc64_runlatch_off();
> + HMT_medium();
> + cede_processor();
> +
> + kt_after = ktime_get_real();
> + usec_delta = ktime_to_us(ktime_sub(kt_after, kt_before));
> +
> + out_purr = mfspr(SPRN_PURR);
> + get_lppaca()->wait_state_cycles += out_purr - in_purr;
> + get_lppaca()->donate_dedicated_cpu = 0;
> + get_lppaca()->idle = 0;
> +
> + dev->last_residency = (int)usec_delta;
> +
> + return index;
> +}
> +
> +static int shared_cede_loop(struct cpuidle_device *dev,
> + struct cpuidle_driver *drv,
> + int index)
> +{
> + unsigned long in_purr, out_purr;
> + ktime_t kt_before, kt_after;
> + s64 usec_delta;
> +
> + /*
> + * Indicate to the HV that we are idle. Now would be
> + * a good time to find other work to dispatch.
> + */
> + get_lppaca()->idle = 1;
> + get_lppaca()->donate_dedicated_cpu = 1;
> + in_purr = mfspr(SPRN_PURR);
> +
> + kt_before = ktime_get_real();
> + /*
> + * Yield the processor to the hypervisor. We return if
> + * an external interrupt occurs (which are driven prior
> + * to returning here) or if a prod occurs from another
> + * processor. When returning here, external interrupts
> + * are enabled.
> + */
> + cede_processor();
> +
> + kt_after = ktime_get_real();
> +
> + usec_delta = ktime_to_us(ktime_sub(kt_after, kt_before));
> +
> + out_purr = mfspr(SPRN_PURR);
> + get_lppaca()->wait_state_cycles += out_purr - in_purr;
> + get_lppaca()->donate_dedicated_cpu = 0;
> + get_lppaca()->idle = 0;
> +
> + dev->last_residency = (int)usec_delta;
> +
> + return index;
> +}
> +
> +/*
> + * States for dedicated partition case.
> + */
> +static struct cpuidle_state dedicated_states[MAX_IDLE_STATE_COUNT] = {
> + { /* Snooze */
> + .name = "snooze",
> + .desc = "snooze",
> + .flags = CPUIDLE_FLAG_TIME_VALID,
> + .exit_latency = 0,
> + .target_residency = 0,
> + .enter = &snooze_loop },
> + { /* CEDE */
> + .name = "CEDE",
> + .desc = "CEDE",
> + .flags = CPUIDLE_FLAG_TIME_VALID,
> + .exit_latency = 1,
> + .target_residency = 10,
> + .enter = &dedicated_cede_loop },
> +};
> +
> +/*
> + * States for shared partition case.
> + */
> +static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = {
> + { /* Shared Cede */
> + .name = "Shared Cede",
> + .desc = "Shared Cede",
> + .flags = CPUIDLE_FLAG_TIME_VALID,
> + .exit_latency = 0,
> + .target_residency = 0,
> + .enter = &shared_cede_loop },
> +};
> +
> +int pseries_notify_cpuidle_add_cpu(int cpu)
> +{
> + struct cpuidle_device *dev =
> + per_cpu_ptr(pseries_idle_cpuidle_devices, cpu);
> + if (dev && cpuidle_get_driver()) {
> + cpuidle_disable_device(dev);
> + cpuidle_enable_device(dev);
> + }
> + return 0;
> +}
> +
> +/*
> + * pseries_idle_cpuidle_driver_init()
> + */
> +static int pseries_idle_cpuidle_driver_init(void)
> +{
> + int cstate;
> + struct cpuidle_driver *drv = &pseries_idle_driver;
> +
> + drv->state_count = 0;
> +
> + for (cstate = 0; cstate < MAX_IDLE_STATE_COUNT; ++cstate) {
> +
> + if (cstate > max_cstate)
> + break;
> +
> + /* is the state not enabled? */
> + if (cpuidle_state_table[cstate].enter == NULL)
> + continue;
> +
> + drv->states[drv->state_count] = /* structure copy */
> + cpuidle_state_table[cstate];
> +
> + if (cpuidle_state_table == dedicated_states)
> + drv->states[drv->state_count].target_residency =
> + __get_cpu_var(smt_snooze_delay);
> +
> + drv->state_count += 1;
> + }
> +
> + return 0;
> +}
> +
> +/* pseries_idle_devices_uninit(void)
> + * unregister cpuidle devices and de-allocate memory
> + */
> +static void pseries_idle_devices_uninit(void)
> +{
> + int i;
> + struct cpuidle_device *dev;
> +
> + for_each_possible_cpu(i) {
> + dev = per_cpu_ptr(pseries_idle_cpuidle_devices, i);
> + cpuidle_unregister_device(dev);
> + }
> +
> + free_percpu(pseries_idle_cpuidle_devices);
> + return;
> +}
> +
> +/* pseries_idle_devices_init()
> + * allocate, initialize and register cpuidle device
> + */
> +static int pseries_idle_devices_init(void)
> +{
> + int i;
> + struct cpuidle_driver *drv = &pseries_idle_driver;
> + struct cpuidle_device *dev;
> +
> + pseries_idle_cpuidle_devices = alloc_percpu(struct cpuidle_device);
> + if (pseries_idle_cpuidle_devices == NULL)
> + return -ENOMEM;
> +
> + for_each_possible_cpu(i) {
> + dev = per_cpu_ptr(pseries_idle_cpuidle_devices, i);
> + dev->state_count = drv->state_count;
> + dev->cpu = i;
> + if (cpuidle_register_device(dev)) {
> + printk(KERN_DEBUG "cpuidle_register_device %d failed!\n",
> + i);
> + return -EIO;
> + }
> + }
> +
> + return 0;
> +}
> +
> +/*
> + * pseries_idle_probe()
> + * Choose state table for shared versus dedicated partition
> + */
> +static int pseries_idle_probe(void)
> +{
> + if (max_cstate == 0) {
> + printk(KERN_DEBUG "pseries processor idle disabled.\n");
> + return -EPERM;
> + }
> +
> + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) {
> + printk(KERN_DEBUG "Using default idle\n");
> + return -ENODEV;
> + }
> +
> + if (get_lppaca()->shared_proc)
> + cpuidle_state_table = shared_states;
> + else
> + cpuidle_state_table = dedicated_states;
> +
> + return 0;
> +}
> +
> +static int __init pseries_processor_idle_init(void)
> +{
> + int retval;
> +
> + retval = pseries_idle_probe();
> + if (retval)
> + return retval;
> +
> + pseries_idle_cpuidle_driver_init();
> + retval = cpuidle_register_driver(&pseries_idle_driver);
> + if (retval) {
> + printk(KERN_DEBUG "Registration of pseries driver failed.\n");
> + return retval;
> + }
> +
> + retval = pseries_idle_devices_init();
> + if (retval) {
> + pseries_idle_devices_uninit();
> + cpuidle_unregister_driver(&pseries_idle_driver);
> + return retval;
> + }
> +
> + printk(KERN_DEBUG "pseries_idle_driver registered\n");
> +
> + return 0;
> +}
> +
> +device_initcall(pseries_processor_idle_init);
> diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
> index e9f6d28..7c60380 100644
> --- a/arch/powerpc/platforms/pseries/pseries.h
> +++ b/arch/powerpc/platforms/pseries/pseries.h
> @@ -56,4 +56,7 @@ extern struct device_node *dlpar_configure_connector(u32);
> extern int dlpar_attach_node(struct device_node *);
> extern int dlpar_detach_node(struct device_node *);
>
> +/* Snooze Delay, pseries_idle */
> +DECLARE_PER_CPU(long, smt_snooze_delay);
> +
> #endif /* _PSERIES_PSERIES_H */
> diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
> index 593acce..6893a0c 100644
> --- a/arch/powerpc/platforms/pseries/setup.c
> +++ b/arch/powerpc/platforms/pseries/setup.c
> @@ -584,9 +584,6 @@ static int __init pSeries_probe(void)
> return 1;
> }
>
> -
> -DECLARE_PER_CPU(long, smt_snooze_delay);
> -
> static void pseries_dedicated_idle_sleep(void)
> {
> unsigned int cpu = smp_processor_id();
> diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
> index fbffd7e..2e46883 100644
> --- a/arch/powerpc/platforms/pseries/smp.c
> +++ b/arch/powerpc/platforms/pseries/smp.c
> @@ -150,6 +150,7 @@ static void __devinit smp_xics_setup_cpu(int cpu)
> set_cpu_current_state(cpu, CPU_STATE_ONLINE);
> set_default_offline_state(cpu);
> #endif
> + pseries_notify_cpuidle_add_cpu(cpu);
> }
>
> static int __devinit smp_pSeries_kick_cpu(int nr)
>
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@lists.ozlabs.org
> https://lists.ozlabs.org/listinfo/linuxppc-dev
next prev parent reply other threads:[~2011-06-17 4:37 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-06-07 16:29 [RFC PATCH V1 0/7] cpuidle: (POWER) cpuidle driver for pSeries Trinabh Gupta
2011-06-07 16:29 ` [RFC PATCH V1 1/7] cpuidle: create bootparam "cpuidle.off=1" Trinabh Gupta
2011-06-17 4:29 ` Benjamin Herrenschmidt
2011-06-21 4:36 ` Trinabh Gupta
2011-06-07 16:29 ` [RFC PATCH V1 2/7] cpuidle: replace xen access to x86 pm_idle and default_idle Trinabh Gupta
2011-06-07 16:29 ` [RFC PATCH V1 3/7] cpuidle: stop using pm_idle Trinabh Gupta
2011-08-03 17:45 ` Len Brown
2011-06-07 16:30 ` [RFC PATCH V1 4/7] cpuidle: (powerpc) Add cpu_idle_wait() to allow switching idle routines Trinabh Gupta
2011-06-17 4:32 ` Benjamin Herrenschmidt
2011-06-21 6:00 ` Trinabh Gupta
2011-06-07 16:30 ` [RFC PATCH V1 5/7] cpuidle: (POWER) cpuidle driver for pSeries Trinabh Gupta
2011-06-17 4:36 ` Benjamin Herrenschmidt [this message]
2011-06-21 9:00 ` Trinabh Gupta
2011-06-07 16:30 ` [RFC PATCH V1 6/7] cpuidle: (POWER) Enable cpuidle and directly call cpuidle_idle_call() " Trinabh Gupta
2011-06-07 16:30 ` [RFC PATCH V1 7/7] cpuidle: (POWER) Handle power_save=off Trinabh Gupta
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1308285398.32158.12.camel@pasglop \
--to=benh@kernel.crashing.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@lists.linux-foundation.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=trinabh@linux.vnet.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).