ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
/*
|
|
|
|
* arch/arm/common/bL_switcher.c -- big.LITTLE cluster switcher core driver
|
|
|
|
*
|
|
|
|
* Created by: Nicolas Pitre, March 2012
|
|
|
|
* Copyright: (C) 2012-2013 Linaro Limited
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
|
|
* published by the Free Software Foundation.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/interrupt.h>
|
|
|
|
#include <linux/cpu_pm.h>
|
2012-10-26 00:36:17 -06:00
|
|
|
#include <linux/cpu.h>
|
2012-05-16 08:55:54 -06:00
|
|
|
#include <linux/cpumask.h>
|
2012-10-26 00:36:17 -06:00
|
|
|
#include <linux/kthread.h>
|
|
|
|
#include <linux/wait.h>
|
2012-05-16 08:55:54 -06:00
|
|
|
#include <linux/clockchips.h>
|
|
|
|
#include <linux/hrtimer.h>
|
|
|
|
#include <linux/tick.h>
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/irqchip/arm-gic.h>
|
|
|
|
|
|
|
|
#include <asm/smp_plat.h>
|
|
|
|
#include <asm/suspend.h>
|
|
|
|
#include <asm/mcpm.h>
|
|
|
|
#include <asm/bL_switcher.h>
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Use our own MPIDR accessors as the generic ones in asm/cputype.h have
|
|
|
|
* __attribute_const__ and we don't want the compiler to assume any
|
|
|
|
* constness here as the value _does_ change along some code paths.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int read_mpidr(void)
|
|
|
|
{
|
|
|
|
unsigned int id;
|
|
|
|
asm volatile ("mrc p15, 0, %0, c0, c0, 5" : "=r" (id));
|
|
|
|
return id & MPIDR_HWID_BITMASK;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* bL switcher core code.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void bL_do_switch(void *_unused)
|
|
|
|
{
|
|
|
|
unsigned mpidr, cpuid, clusterid, ob_cluster, ib_cluster;
|
|
|
|
|
|
|
|
pr_debug("%s\n", __func__);
|
|
|
|
|
|
|
|
mpidr = read_mpidr();
|
|
|
|
cpuid = MPIDR_AFFINITY_LEVEL(mpidr, 0);
|
|
|
|
clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
|
|
|
|
ob_cluster = clusterid;
|
|
|
|
ib_cluster = clusterid ^ 1;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Our state has been saved at this point. Let's release our
|
|
|
|
* inbound CPU.
|
|
|
|
*/
|
|
|
|
mcpm_set_entry_vector(cpuid, ib_cluster, cpu_resume);
|
|
|
|
sev();
|
|
|
|
|
|
|
|
/*
|
|
|
|
* From this point, we must assume that our counterpart CPU might
|
|
|
|
* have taken over in its parallel world already, as if execution
|
|
|
|
* just returned from cpu_suspend(). It is therefore important to
|
|
|
|
* be very careful not to make any change the other guy is not
|
|
|
|
* expecting. This is why we need stack isolation.
|
|
|
|
*
|
|
|
|
* Fancy under cover tasks could be performed here. For now
|
|
|
|
* we have none.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* Let's put ourself down. */
|
|
|
|
mcpm_cpu_power_down();
|
|
|
|
|
|
|
|
/* should never get here */
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2012-11-27 13:55:33 -07:00
|
|
|
* Stack isolation. To ensure 'current' remains valid, we just use another
|
|
|
|
* piece of our thread's stack space which should be fairly lightly used.
|
|
|
|
* The selected area starts just above the thread_info structure located
|
|
|
|
* at the very bottom of the stack, aligned to a cache line, and indexed
|
|
|
|
* with the cluster number.
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
*/
|
2012-11-27 13:55:33 -07:00
|
|
|
#define STACK_SIZE 512
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
|
|
|
|
static int bL_switchpoint(unsigned long _arg)
|
|
|
|
{
|
|
|
|
unsigned int mpidr = read_mpidr();
|
|
|
|
unsigned int clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
|
2012-11-27 13:55:33 -07:00
|
|
|
void *stack = current_thread_info() + 1;
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
stack = PTR_ALIGN(stack, L1_CACHE_BYTES);
|
2012-11-27 13:55:33 -07:00
|
|
|
stack += clusterid * STACK_SIZE + STACK_SIZE;
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
call_with_stack(bL_do_switch, (void *)_arg, stack);
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Generic switcher interface
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* bL_switch_to - Switch to a specific cluster for the current CPU
|
|
|
|
* @new_cluster_id: the ID of the cluster to switch to.
|
|
|
|
*
|
|
|
|
* This function must be called on the CPU to be switched.
|
|
|
|
* Returns 0 on success, else a negative status code.
|
|
|
|
*/
|
|
|
|
static int bL_switch_to(unsigned int new_cluster_id)
|
|
|
|
{
|
|
|
|
unsigned int mpidr, cpuid, clusterid, ob_cluster, ib_cluster, this_cpu;
|
2012-05-16 08:55:54 -06:00
|
|
|
struct tick_device *tdev;
|
|
|
|
enum clock_event_mode tdev_mode;
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
int ret;
|
|
|
|
|
|
|
|
mpidr = read_mpidr();
|
|
|
|
cpuid = MPIDR_AFFINITY_LEVEL(mpidr, 0);
|
|
|
|
clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
|
|
|
|
ob_cluster = clusterid;
|
|
|
|
ib_cluster = clusterid ^ 1;
|
|
|
|
|
|
|
|
if (new_cluster_id == clusterid)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
pr_debug("before switch: CPU %d in cluster %d\n", cpuid, clusterid);
|
|
|
|
|
|
|
|
/* Close the gate for our entry vectors */
|
|
|
|
mcpm_set_entry_vector(cpuid, ob_cluster, NULL);
|
|
|
|
mcpm_set_entry_vector(cpuid, ib_cluster, NULL);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Let's wake up the inbound CPU now in case it requires some delay
|
|
|
|
* to come online, but leave it gated in our entry vector code.
|
|
|
|
*/
|
|
|
|
ret = mcpm_cpu_power_up(cpuid, ib_cluster);
|
|
|
|
if (ret) {
|
|
|
|
pr_err("%s: mcpm_cpu_power_up() returned %d\n", __func__, ret);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* From this point we are entering the switch critical zone
|
|
|
|
* and can't take any interrupts anymore.
|
|
|
|
*/
|
|
|
|
local_irq_disable();
|
|
|
|
local_fiq_disable();
|
|
|
|
|
|
|
|
this_cpu = smp_processor_id();
|
|
|
|
|
|
|
|
/* redirect GIC's SGIs to our counterpart */
|
|
|
|
gic_migrate_target(cpuid + ib_cluster*4);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Raise a SGI on the inbound CPU to make sure it doesn't stall
|
|
|
|
* in a possible WFI, such as in mcpm_power_down().
|
|
|
|
*/
|
|
|
|
arch_send_wakeup_ipi_mask(cpumask_of(this_cpu));
|
|
|
|
|
2012-05-16 08:55:54 -06:00
|
|
|
tdev = tick_get_device(this_cpu);
|
|
|
|
if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu)))
|
|
|
|
tdev = NULL;
|
|
|
|
if (tdev) {
|
|
|
|
tdev_mode = tdev->evtdev->mode;
|
|
|
|
clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
|
|
|
|
}
|
|
|
|
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
ret = cpu_pm_enter();
|
|
|
|
|
|
|
|
/* we can not tolerate errors at this point */
|
|
|
|
if (ret)
|
|
|
|
panic("%s: cpu_pm_enter() returned %d\n", __func__, ret);
|
|
|
|
|
|
|
|
/* Flip the cluster in the CPU logical map for this CPU. */
|
|
|
|
cpu_logical_map(this_cpu) ^= (1 << 8);
|
|
|
|
|
|
|
|
/* Let's do the actual CPU switch. */
|
|
|
|
ret = cpu_suspend(0, bL_switchpoint);
|
|
|
|
if (ret > 0)
|
|
|
|
panic("%s: cpu_suspend() returned %d\n", __func__, ret);
|
|
|
|
|
|
|
|
/* We are executing on the inbound CPU at this point */
|
|
|
|
mpidr = read_mpidr();
|
|
|
|
cpuid = MPIDR_AFFINITY_LEVEL(mpidr, 0);
|
|
|
|
clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
|
|
|
|
pr_debug("after switch: CPU %d in cluster %d\n", cpuid, clusterid);
|
|
|
|
BUG_ON(clusterid != ib_cluster);
|
|
|
|
|
|
|
|
mcpm_cpu_powered_up();
|
|
|
|
|
|
|
|
ret = cpu_pm_exit();
|
|
|
|
|
2012-05-16 08:55:54 -06:00
|
|
|
if (tdev) {
|
|
|
|
clockevents_set_mode(tdev->evtdev, tdev_mode);
|
|
|
|
clockevents_program_event(tdev->evtdev,
|
|
|
|
tdev->evtdev->next_event, 1);
|
|
|
|
}
|
|
|
|
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
local_fiq_enable();
|
|
|
|
local_irq_enable();
|
|
|
|
|
|
|
|
if (ret)
|
|
|
|
pr_err("%s exiting with error %d\n", __func__, ret);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2012-10-26 00:36:17 -06:00
|
|
|
struct bL_thread {
|
|
|
|
struct task_struct *task;
|
|
|
|
wait_queue_head_t wq;
|
|
|
|
int wanted_cluster;
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
};
|
|
|
|
|
2012-10-26 00:36:17 -06:00
|
|
|
static struct bL_thread bL_threads[NR_CPUS];
|
|
|
|
|
|
|
|
static int bL_switcher_thread(void *arg)
|
|
|
|
{
|
|
|
|
struct bL_thread *t = arg;
|
|
|
|
struct sched_param param = { .sched_priority = 1 };
|
|
|
|
int cluster;
|
|
|
|
|
|
|
|
sched_setscheduler_nocheck(current, SCHED_FIFO, ¶m);
|
|
|
|
|
|
|
|
do {
|
|
|
|
if (signal_pending(current))
|
|
|
|
flush_signals(current);
|
|
|
|
wait_event_interruptible(t->wq,
|
|
|
|
t->wanted_cluster != -1 ||
|
|
|
|
kthread_should_stop());
|
|
|
|
cluster = xchg(&t->wanted_cluster, -1);
|
|
|
|
if (cluster != -1)
|
|
|
|
bL_switch_to(cluster);
|
|
|
|
} while (!kthread_should_stop());
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct task_struct * __init bL_switcher_thread_create(int cpu, void *arg)
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
{
|
2012-10-26 00:36:17 -06:00
|
|
|
struct task_struct *task;
|
|
|
|
|
|
|
|
task = kthread_create_on_node(bL_switcher_thread, arg,
|
|
|
|
cpu_to_node(cpu), "kswitcher_%d", cpu);
|
|
|
|
if (!IS_ERR(task)) {
|
|
|
|
kthread_bind(task, cpu);
|
|
|
|
wake_up_process(task);
|
|
|
|
} else
|
|
|
|
pr_err("%s failed for CPU %d\n", __func__, cpu);
|
|
|
|
return task;
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* bL_switch_request - Switch to a specific cluster for the given CPU
|
|
|
|
*
|
|
|
|
* @cpu: the CPU to switch
|
|
|
|
* @new_cluster_id: the ID of the cluster to switch to.
|
|
|
|
*
|
2012-10-26 00:36:17 -06:00
|
|
|
* This function causes a cluster switch on the given CPU by waking up
|
|
|
|
* the appropriate switcher thread. This function may or may not return
|
|
|
|
* before the switch has occurred.
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
*/
|
2012-10-26 00:36:17 -06:00
|
|
|
int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
{
|
2012-10-26 00:36:17 -06:00
|
|
|
struct bL_thread *t;
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
|
2012-10-26 00:36:17 -06:00
|
|
|
if (cpu >= ARRAY_SIZE(bL_threads)) {
|
|
|
|
pr_err("%s: cpu %d out of bounds\n", __func__, cpu);
|
|
|
|
return -EINVAL;
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
}
|
|
|
|
|
2012-10-26 00:36:17 -06:00
|
|
|
t = &bL_threads[cpu];
|
|
|
|
if (IS_ERR(t->task))
|
|
|
|
return PTR_ERR(t->task);
|
|
|
|
if (!t->task)
|
|
|
|
return -ESRCH;
|
|
|
|
|
|
|
|
t->wanted_cluster = new_cluster_id;
|
|
|
|
wake_up(&t->wq);
|
|
|
|
return 0;
|
ARM: b.L: core switcher code
This is the core code implementing big.LITTLE switcher functionality.
Rationale for this code is available here:
http://lwn.net/Articles/481055/
The main entry point for a switch request is:
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
If the calling CPU is not the wanted one, this wrapper takes care of
sending the request to the appropriate CPU with schedule_work_on().
At the moment the core switch operation is handled by bL_switch_to()
which must be called on the CPU for which a switch is requested.
What this code does:
* Return early if the current cluster is the wanted one.
* Close the gate in the kernel entry vector for both the inbound
and outbound CPUs.
* Wake up the inbound CPU so it can perform its reset sequence in
parallel up to the kernel entry vector gate.
* Migrate all interrupts in the GIC targeting the outbound CPU
interface to the inbound CPU interface, including SGIs. This is
performed by gic_migrate_target() in drivers/irqchip/irq-gic.c.
* Call cpu_pm_enter() which takes care of flushing the VFP state to
RAM and save the CPU interface config from the GIC to RAM.
* Modify the cpu_logical_map to refer to the inbound physical CPU.
* Call cpu_suspend() which saves the CPU state (general purpose
registers, page table address) onto the stack and store the
resulting stack pointer in an array indexed by the updated
cpu_logical_map, then call the provided shutdown function.
This happens in arch/arm/kernel/sleep.S.
At this point, the provided shutdown function executed by the outbound
CPU ungates the inbound CPU. Therefore the inbound CPU:
* Picks up the saved stack pointer in the array indexed by its MPIDR
in arch/arm/kernel/sleep.S.
* The MMU and caches are re-enabled using the saved state on the
provided stack, just like if this was a resume operation from a
suspended state.
* Then cpu_suspend() returns, although this is on the inbound CPU
rather than the outbound CPU which called it initially.
* The function cpu_pm_exit() is called which effect is to restore the
CPU interface state in the GIC using the state previously saved by
the outbound CPU.
* Exit of bL_switch_to() to resume normal kernel execution on the
new CPU.
However, the outbound CPU is potentially still running in parallel while
the inbound CPU is resuming normal kernel execution, hence we need
per CPU stack isolation to execute bL_do_switch(). After the outbound
CPU has ungated the inbound CPU, it calls mcpm_cpu_power_down() to:
* Clean its L1 cache.
* If it is the last CPU still alive in its cluster (last man standing),
it also cleans its L2 cache and disables cache snooping from the other
cluster.
* Power down the CPU (or whole cluster).
Code called from bL_do_switch() might end up referencing 'current' for
some reasons. However, 'current' is derived from the stack pointer.
With any arbitrary stack, the returned value for 'current' and any
dereferenced values through it are just random garbage which may lead to
segmentation faults.
The active page table during the execution of bL_do_switch() is also a
problem. There is no guarantee that the inbound CPU won't destroy the
corresponding task which would free the attached page table while the
outbound CPU is still running and relying on it.
To solve both issues, we borrow some of the task space belonging to
the init/idle task which, by its nature, is lightly used and therefore
is unlikely to clash with our usage. The init task is also never going
away.
Right now the logical CPU number is assumed to be equivalent to the
physical CPU number within each cluster. The kernel should also be
booted with only one cluster active. These limitations will be lifted
eventually.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
2012-04-12 00:56:10 -06:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(bL_switch_request);
|
2012-10-26 00:36:17 -06:00
|
|
|
|
2012-11-21 09:53:27 -07:00
|
|
|
/*
|
|
|
|
* Activation and configuration code.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static cpumask_t bL_switcher_removed_logical_cpus;
|
|
|
|
|
|
|
|
static void __init bL_switcher_restore_cpus(void)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for_each_cpu(i, &bL_switcher_removed_logical_cpus)
|
|
|
|
cpu_up(i);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __init bL_switcher_halve_cpus(void)
|
|
|
|
{
|
|
|
|
int cpu, cluster, i, ret;
|
|
|
|
cpumask_t cluster_mask[2], common_mask;
|
|
|
|
|
|
|
|
cpumask_clear(&bL_switcher_removed_logical_cpus);
|
|
|
|
cpumask_clear(&cluster_mask[0]);
|
|
|
|
cpumask_clear(&cluster_mask[1]);
|
|
|
|
|
|
|
|
for_each_online_cpu(i) {
|
|
|
|
cpu = cpu_logical_map(i) & 0xff;
|
|
|
|
cluster = (cpu_logical_map(i) >> 8) & 0xff;
|
|
|
|
if (cluster >= 2) {
|
|
|
|
pr_err("%s: only dual cluster systems are supported\n", __func__);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
cpumask_set_cpu(cpu, &cluster_mask[cluster]);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!cpumask_and(&common_mask, &cluster_mask[0], &cluster_mask[1])) {
|
|
|
|
pr_err("%s: no common set of CPUs\n", __func__);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
for_each_online_cpu(i) {
|
|
|
|
cpu = cpu_logical_map(i) & 0xff;
|
|
|
|
cluster = (cpu_logical_map(i) >> 8) & 0xff;
|
|
|
|
|
|
|
|
if (cpumask_test_cpu(cpu, &common_mask)) {
|
|
|
|
/*
|
|
|
|
* We keep only those logical CPUs which number
|
|
|
|
* is equal to their physical CPU number. This is
|
|
|
|
* not perfect but good enough for now.
|
|
|
|
*/
|
|
|
|
if (cpu == i)
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = cpu_down(i);
|
|
|
|
if (ret) {
|
|
|
|
bL_switcher_restore_cpus();
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
cpumask_set_cpu(i, &bL_switcher_removed_logical_cpus);
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-10-26 00:36:17 -06:00
|
|
|
static int __init bL_switcher_init(void)
|
|
|
|
{
|
2012-11-21 09:53:27 -07:00
|
|
|
int cpu, ret;
|
2012-10-26 00:36:17 -06:00
|
|
|
|
|
|
|
pr_info("big.LITTLE switcher initializing\n");
|
|
|
|
|
2012-11-21 09:53:27 -07:00
|
|
|
if (MAX_NR_CLUSTERS != 2) {
|
|
|
|
pr_err("%s: only dual cluster systems are supported\n", __func__);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
cpu_hotplug_driver_lock();
|
|
|
|
ret = bL_switcher_halve_cpus();
|
|
|
|
if (ret) {
|
|
|
|
cpu_hotplug_driver_unlock();
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2012-10-26 00:36:17 -06:00
|
|
|
for_each_online_cpu(cpu) {
|
|
|
|
struct bL_thread *t = &bL_threads[cpu];
|
|
|
|
init_waitqueue_head(&t->wq);
|
|
|
|
t->wanted_cluster = -1;
|
|
|
|
t->task = bL_switcher_thread_create(cpu, t);
|
|
|
|
}
|
2012-11-21 09:53:27 -07:00
|
|
|
cpu_hotplug_driver_unlock();
|
2012-10-26 00:36:17 -06:00
|
|
|
|
|
|
|
pr_info("big.LITTLE switcher initialized\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
late_initcall(bL_switcher_init);
|