Commit 48a1b10a authored by Yinghai Lu's avatar Yinghai Lu Committed by Ingo Molnar
Browse files

x86, sparseirq: move irq_desc according to smp_affinity, v7 



Impact: improve NUMA handling by migrating irq_desc on smp_affinity changes

if CONFIG_NUMA_MIGRATE_IRQ_DESC is set:

-  make irq_desc to go with affinity aka irq_desc moving etc
-  call move_irq_desc in irq_complete_move()
-  legacy irq_desc is not moved, because they are allocated via static array

for logical apic mode, need to add move_desc_in_progress_in_same_domain,
otherwise it will not be moved ==> also could need two phases to get
irq_desc moved.

Signed-off-by: default avatarYinghai Lu <yinghai@kernel.org>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
parent 13bd41bc

arch/x86/Kconfig

+9 −0
Original line number Diff line number Diff line
@@ -248,6 +248,15 @@ config SPARSE_IRQ 


	  If you don't know what to do here, say Y.



config NUMA_MIGRATE_IRQ_DESC

	bool "Move irq desc when changing irq smp_affinity"

	depends on SPARSE_IRQ && SMP

	default n

	help

	  This enables moving irq_desc to cpu/node that irq will use handled.



	  If you don't know what to do here, say N.



config X86_FIND_SMP_CONFIG

	def_bool y

	depends on X86_MPPARSE || X86_VOYAGER

arch/x86/kernel/io_apic.c

+141 −1
Original line number Diff line number Diff line
@@ -141,6 +141,9 @@ struct irq_cfg { 
	unsigned move_cleanup_count;

	u8 vector;

	u8 move_in_progress : 1;

#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC

	u8 move_desc_pending : 1;

#endif

};



/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -223,6 +226,121 @@ void arch_init_chip_data(struct irq_desc *desc, int cpu) 
	}

}



#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC



static void

init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)

{

	struct irq_pin_list *old_entry, *head, *tail, *entry;



	cfg->irq_2_pin = NULL;

	old_entry = old_cfg->irq_2_pin;

	if (!old_entry)

		return;



	entry = get_one_free_irq_2_pin(cpu);

	if (!entry)

		return;



	entry->apic	= old_entry->apic;

	entry->pin	= old_entry->pin;

	head		= entry;

	tail		= entry;

	old_entry	= old_entry->next;

	while (old_entry) {

		entry = get_one_free_irq_2_pin(cpu);

		if (!entry) {

			entry = head;

			while (entry) {

				head = entry->next;

				kfree(entry);

				entry = head;

			}

			/* still use the old one */

			return;

		}

		entry->apic	= old_entry->apic;

		entry->pin	= old_entry->pin;

		tail->next	= entry;

		tail		= entry;

		old_entry	= old_entry->next;

	}



	tail->next = NULL;

	cfg->irq_2_pin = head;

}



static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)

{

	struct irq_pin_list *entry, *next;



	if (old_cfg->irq_2_pin == cfg->irq_2_pin)

		return;



	entry = old_cfg->irq_2_pin;



	while (entry) {

		next = entry->next;

		kfree(entry);

		entry = next;

	}

	old_cfg->irq_2_pin = NULL;

}



void arch_init_copy_chip_data(struct irq_desc *old_desc,

				 struct irq_desc *desc, int cpu)

{

	struct irq_cfg *cfg;

	struct irq_cfg *old_cfg;



	cfg = get_one_free_irq_cfg(cpu);



	if (!cfg)

		return;



	desc->chip_data = cfg;



	old_cfg = old_desc->chip_data;



	memcpy(cfg, old_cfg, sizeof(struct irq_cfg));



	init_copy_irq_2_pin(old_cfg, cfg, cpu);

}



static void free_irq_cfg(struct irq_cfg *old_cfg)

{

	kfree(old_cfg);

}



void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)

{

	struct irq_cfg *old_cfg, *cfg;



	old_cfg = old_desc->chip_data;

	cfg = desc->chip_data;



	if (old_cfg == cfg)

		return;



	if (old_cfg) {

		free_irq_2_pin(old_cfg, cfg);

		free_irq_cfg(old_cfg);

		old_desc->chip_data = NULL;

	}

}



static void set_extra_move_desc(struct irq_desc *desc, cpumask_t mask)

{

	struct irq_cfg *cfg = desc->chip_data;



	if (!cfg->move_in_progress) {

		/* it means that domain is not changed */

		if (!cpus_intersects(desc->affinity, mask))

			cfg->move_desc_pending = 1;

	}

}

#endif



#else

static struct irq_cfg *irq_cfg(unsigned int irq)

{
@@ -231,9 +349,11 @@ static struct irq_cfg *irq_cfg(unsigned int irq) 


#endif



#ifndef CONFIG_NUMA_MIGRATE_IRQ_DESC

static inline void set_extra_move_desc(struct irq_desc *desc, cpumask_t mask)

{

}

#endif



struct io_apic {

	unsigned int index;
@@ -2346,14 +2466,34 @@ static void irq_complete_move(struct irq_desc **descp) 
	struct irq_cfg *cfg = desc->chip_data;

	unsigned vector, me;



	if (likely(!cfg->move_in_progress))

	if (likely(!cfg->move_in_progress)) {

#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC

		if (likely(!cfg->move_desc_pending))

			return;



		/* domain is not change, but affinity is changed */

		me = smp_processor_id();

		if (cpu_isset(me, desc->affinity)) {

			*descp = desc = move_irq_desc(desc, me);

			/* get the new one */

			cfg = desc->chip_data;

			cfg->move_desc_pending = 0;

		}

#endif

		return;

	}



	vector = ~get_irq_regs()->orig_ax;

	me = smp_processor_id();

	if ((vector == cfg->vector) && cpu_isset(me, cfg->domain)) {

		cpumask_t cleanup_mask;



#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC

		*descp = desc = move_irq_desc(desc, me);

		/* get the new one */

		cfg = desc->chip_data;

#endif



		cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);

		cfg->move_cleanup_count = cpus_weight(cleanup_mask);

		send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);

include/linux/irq.h

+10 −0
Original line number Diff line number Diff line
@@ -227,6 +227,16 @@ extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int cpu); 


#endif



static inline struct irq_desc *

irq_remap_to_desc(unsigned int irq, struct irq_desc *desc)

{

#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC

	return irq_to_desc(irq);

#else

	return desc;

#endif

}



/*

 * Migration helpers for obsolete names, they will go away:

 */

kernel/irq/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -3,3 +3,4 @@ obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o 
obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o

obj-$(CONFIG_PROC_FS) += proc.o

obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o

obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o

kernel/irq/chip.c

+10 −2
Original line number Diff line number Diff line
@@ -353,6 +353,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc) 


	spin_lock(&desc->lock);

	mask_ack_irq(desc, irq);

	desc = irq_remap_to_desc(irq, desc);



	if (unlikely(desc->status & IRQ_INPROGRESS))

		goto out_unlock;
@@ -430,6 +431,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) 
	desc->status &= ~IRQ_INPROGRESS;

out:

	desc->chip->eoi(irq);

	desc = irq_remap_to_desc(irq, desc);



	spin_unlock(&desc->lock);

}
@@ -466,12 +468,14 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc) 
		    !desc->action)) {

		desc->status |= (IRQ_PENDING | IRQ_MASKED);

		mask_ack_irq(desc, irq);

		desc = irq_remap_to_desc(irq, desc);

		goto out_unlock;

	}

	kstat_incr_irqs_this_cpu(irq, desc);



	/* Start handling the irq */

	desc->chip->ack(irq);

	desc = irq_remap_to_desc(irq, desc);



	/* Mark the IRQ currently in progress.*/

	desc->status |= IRQ_INPROGRESS;
@@ -532,8 +536,10 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc) 
	if (!noirqdebug)

		note_interrupt(irq, desc, action_ret);



	if (desc->chip->eoi)

	if (desc->chip->eoi) {

		desc->chip->eoi(irq);

		desc = irq_remap_to_desc(irq, desc);

	}

}



void
@@ -568,8 +574,10 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, 


	/* Uninstall? */

	if (handle == handle_bad_irq) {

		if (desc->chip != &no_irq_chip)

		if (desc->chip != &no_irq_chip) {

			mask_ack_irq(desc, irq);

			desc = irq_remap_to_desc(irq, desc);

		}

		desc->status |= IRQ_DISABLED;

		desc->depth = 1;

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE