Revision 3e1a0699095803e53072699a4a1485af7744601d authored by Joe Thornber on 03 March 2014, 16:03:26 UTC, committed by Mike Snitzer on 05 March 2014, 20:26:58 UTC
Ideally a thin pool would never run out of data space; the low water
mark would trigger userland to extend the pool before we completely run
out of space.  However, many small random IOs to unprovisioned space can
consume data space at an alarming rate.  Adjust your low water mark if
you're frequently seeing "out-of-data-space" mode.

Before this fix, if data space ran out the pool would be put in
PM_READ_ONLY mode which also aborted the pool's current metadata
transaction (data loss for any changes in the transaction).  This had a
side-effect of needlessly compromising data consistency.  And retry of
queued unserviceable bios, once the data pool was resized, could
initiate changes to potentially inconsistent pool metadata.

Now when the pool's data space is exhausted transition to a new pool
mode (PM_OUT_OF_DATA_SPACE) that allows metadata to be changed but data
may not be allocated.  This allows users to remove thin volumes or
discard data to recover data space.

The pool is no longer put in PM_READ_ONLY mode in response to the pool
running out of data space.  And PM_READ_ONLY mode no longer aborts the
pool's current metadata transaction.  Also, set_pool_mode() will now
notify userspace when the pool mode is changed.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
1 parent 07f2b6e
Raw File
cpuidle-pseries.c
/*
 *  cpuidle-pseries - idle state cpuidle driver.
 *  Adapted from drivers/idle/intel_idle.c and
 *  drivers/acpi/processor_idle.c
 *
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
#include <linux/cpuidle.h>
#include <linux/cpu.h>
#include <linux/notifier.h>

#include <asm/paca.h>
#include <asm/reg.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/plpar_wrappers.h>

struct cpuidle_driver pseries_idle_driver = {
	.name             = "pseries_idle",
	.owner            = THIS_MODULE,
};

static int max_idle_state;
static struct cpuidle_state *cpuidle_state_table;

static inline void idle_loop_prolog(unsigned long *in_purr)
{
	*in_purr = mfspr(SPRN_PURR);
	/*
	 * Indicate to the HV that we are idle. Now would be
	 * a good time to find other work to dispatch.
	 */
	get_lppaca()->idle = 1;
}

static inline void idle_loop_epilog(unsigned long in_purr)
{
	u64 wait_cycles;

	wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
	wait_cycles += mfspr(SPRN_PURR) - in_purr;
	get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
	get_lppaca()->idle = 0;
}

static int snooze_loop(struct cpuidle_device *dev,
			struct cpuidle_driver *drv,
			int index)
{
	unsigned long in_purr;

	idle_loop_prolog(&in_purr);
	local_irq_enable();
	set_thread_flag(TIF_POLLING_NRFLAG);

	while (!need_resched()) {
		HMT_low();
		HMT_very_low();
	}

	HMT_medium();
	clear_thread_flag(TIF_POLLING_NRFLAG);
	smp_mb();

	idle_loop_epilog(in_purr);

	return index;
}

static void check_and_cede_processor(void)
{
	/*
	 * Ensure our interrupt state is properly tracked,
	 * also checks if no interrupt has occurred while we
	 * were soft-disabled
	 */
	if (prep_irq_for_idle()) {
		cede_processor();
#ifdef CONFIG_TRACE_IRQFLAGS
		/* Ensure that H_CEDE returns with IRQs on */
		if (WARN_ON(!(mfmsr() & MSR_EE)))
			__hard_irq_enable();
#endif
	}
}

static int dedicated_cede_loop(struct cpuidle_device *dev,
				struct cpuidle_driver *drv,
				int index)
{
	unsigned long in_purr;

	idle_loop_prolog(&in_purr);
	get_lppaca()->donate_dedicated_cpu = 1;

	HMT_medium();
	check_and_cede_processor();

	get_lppaca()->donate_dedicated_cpu = 0;

	idle_loop_epilog(in_purr);

	return index;
}

static int shared_cede_loop(struct cpuidle_device *dev,
			struct cpuidle_driver *drv,
			int index)
{
	unsigned long in_purr;

	idle_loop_prolog(&in_purr);

	/*
	 * 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.
	 */
	check_and_cede_processor();

	idle_loop_epilog(in_purr);

	return index;
}

/*
 * States for dedicated partition case.
 */
static struct cpuidle_state dedicated_states[] = {
	{ /* 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 = 10,
		.target_residency = 100,
		.enter = &dedicated_cede_loop },
};

/*
 * States for shared partition case.
 */
static struct cpuidle_state shared_states[] = {
	{ /* Shared Cede */
		.name = "Shared Cede",
		.desc = "Shared Cede",
		.flags = CPUIDLE_FLAG_TIME_VALID,
		.exit_latency = 0,
		.target_residency = 0,
		.enter = &shared_cede_loop },
};

static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n,
			unsigned long action, void *hcpu)
{
	int hotcpu = (unsigned long)hcpu;
	struct cpuidle_device *dev =
				per_cpu(cpuidle_devices, hotcpu);

	if (dev && cpuidle_get_driver()) {
		switch (action) {
		case CPU_ONLINE:
		case CPU_ONLINE_FROZEN:
			cpuidle_pause_and_lock();
			cpuidle_enable_device(dev);
			cpuidle_resume_and_unlock();
			break;

		case CPU_DEAD:
		case CPU_DEAD_FROZEN:
			cpuidle_pause_and_lock();
			cpuidle_disable_device(dev);
			cpuidle_resume_and_unlock();
			break;

		default:
			return NOTIFY_DONE;
		}
	}
	return NOTIFY_OK;
}

static struct notifier_block setup_hotplug_notifier = {
	.notifier_call = pseries_cpuidle_add_cpu_notifier,
};

/*
 * pseries_cpuidle_driver_init()
 */
static int pseries_cpuidle_driver_init(void)
{
	int idle_state;
	struct cpuidle_driver *drv = &pseries_idle_driver;

	drv->state_count = 0;

	for (idle_state = 0; idle_state < max_idle_state; ++idle_state) {
		/* Is the state not enabled? */
		if (cpuidle_state_table[idle_state].enter == NULL)
			continue;

		drv->states[drv->state_count] =	/* structure copy */
			cpuidle_state_table[idle_state];

		drv->state_count += 1;
	}

	return 0;
}

/*
 * pseries_idle_probe()
 * Choose state table for shared versus dedicated partition
 */
static int pseries_idle_probe(void)
{

	if (cpuidle_disable != IDLE_NO_OVERRIDE)
		return -ENODEV;

	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
		if (lppaca_shared_proc(get_lppaca())) {
			cpuidle_state_table = shared_states;
			max_idle_state = ARRAY_SIZE(shared_states);
		} else {
			cpuidle_state_table = dedicated_states;
			max_idle_state = ARRAY_SIZE(dedicated_states);
		}
	} else
		return -ENODEV;

	return 0;
}

static int __init pseries_processor_idle_init(void)
{
	int retval;

	retval = pseries_idle_probe();
	if (retval)
		return retval;

	pseries_cpuidle_driver_init();
	retval = cpuidle_register(&pseries_idle_driver, NULL);
	if (retval) {
		printk(KERN_DEBUG "Registration of pseries driver failed.\n");
		return retval;
	}

	register_cpu_notifier(&setup_hotplug_notifier);
	printk(KERN_DEBUG "pseries_idle_driver registered\n");
	return 0;
}

device_initcall(pseries_processor_idle_init);
back to top