The following patch series includes a bunch of clean-ups for the
pseries cpuidle backend driver. This includes,
moving the driver from arch/powerpc/platforms/pseries to
driver/cpuidle, refactoring of the code, making it a non-module,
removing smt-snooze-delay update and dead code around it.
After a number of attempts to consolidate the backend cpuidle driver
for pSeries and powernv platforms, it seems best to have separate
idle drivers for both the platforms as any kind of code duplication
seizes to exist beyond snooze loop and a hot plug notifier.
Also going further, with addition of device tree parsing to setup
idle states and related changes just for powernv platform, it is
best to keep these drivers separate without adding complexity
and thus improving readabilty for both the platform drivers.
The clean-up undertaken here was posted earlier as part of
generic powerpc cpuidle driver clean-up.
V1 -> http://lkml.org/lkml/2013/7/23/143
V2 -> https://lkml.org/lkml/2013/7/30/872
V3 -> http://comments.gmane.org/gmane.linux.ports.ppc.embedded/63093
V4 -> https://lkml.org/lkml/2013/8/22/25
V5 -> http://lkml.org/lkml/2013/8/22/184
V6 -> https://lkml.org/lkml/2013/8/27/432
V7 -> https://lkml.org/lkml/2013/10/29/216
V8 -> https://lkml.org/lkml/2013/11/11/29
Deepthi Dharwar (5):
pseries/cpuidle: Move processor_idle.c to drivers/cpuidle.
pseries/cpuidle: Use cpuidle_register() for initialisation.
pseries/cpuidle: Make cpuidle-pseries backend driver a non-module.
pseries/cpuidle: Remove MAX_IDLE_STATE macro.
pseries/cpuidle: smt-snooze-delay cleanup.
Preeti U Murthy (1):
pseries/cpuidle: Remove redundant call to ppc64_runlatch_off() in cpu idle routines
arch/powerpc/include/asm/processor.h | 7
arch/powerpc/kernel/sysfs.c | 2
arch/powerpc/platforms/pseries/Kconfig | 9 -
arch/powerpc/platforms/pseries/Makefile | 1
arch/powerpc/platforms/pseries/processor_idle.c | 364 -----------------------
drivers/cpuidle/Kconfig | 5
drivers/cpuidle/Kconfig.powerpc | 11 +
drivers/cpuidle/Makefile | 4
drivers/cpuidle/cpuidle-pseries.c | 267 +++++++++++++++++
9 files changed, 287 insertions(+), 383 deletions(-)
delete mode 100644 arch/powerpc/platforms/pseries/processor_idle.c
create mode 100644 drivers/cpuidle/Kconfig.powerpc
create mode 100644 drivers/cpuidle/cpuidle-pseries.c
-- Deepthi
From: Preeti U Murthy <[email protected]>
Commit fbd7740fdfdf9475f(powerpc: Simplify pSeries idle loop) switched pseries
cpu idle handling from complete idle loops to ppc_md.powersave functions.
Earlier to this switch, ppc64_runlatch_off() had to be called in each of the
idle routines. But after the switch, this call is handled in arch_cpu_idle(),
just before the call to ppc_md.powersave, where platform specific idle
routines are called.
As a consequence, the call to ppc64_runlatch_off() got duplicated in the
arch_cpu_idle() routine as well as in the some of the idle routines in
pseries and commit fbd7740fdfdf9475f missed to get rid of these redundant
calls. These calls were carried over subsequent enhancements to the pseries
cpuidle routines.
Although multiple calls to ppc64_runlatch_off() is harmless, there is still some
overhead due to it. Besides that, these calls could also make way for a
misunderstanding that it is *necessary* to call ppc64_runlatch_off() multiple
times, when that is not the case. Hence this patch takes care of eliminating
this redundancy.
Signed-off-by: Preeti U Murthy <[email protected]>
Reviewed-by: Srivatsa S. Bhat <[email protected]>
Signed-off-by: Deepthi Dharwar <[email protected]>
---
arch/powerpc/platforms/pseries/processor_idle.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
index a166e38..09e4f56 100644
--- a/arch/powerpc/platforms/pseries/processor_idle.c
+++ b/arch/powerpc/platforms/pseries/processor_idle.c
@@ -17,7 +17,6 @@
#include <asm/reg.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
-#include <asm/runlatch.h>
#include <asm/plpar_wrappers.h>
struct cpuidle_driver pseries_idle_driver = {
@@ -63,7 +62,6 @@ static int snooze_loop(struct cpuidle_device *dev,
set_thread_flag(TIF_POLLING_NRFLAG);
while ((!need_resched()) && cpu_online(cpu)) {
- ppc64_runlatch_off();
HMT_low();
HMT_very_low();
}
@@ -103,7 +101,6 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
idle_loop_prolog(&in_purr);
get_lppaca()->donate_dedicated_cpu = 1;
- ppc64_runlatch_off();
HMT_medium();
check_and_cede_processor();
Move the file from arch specific pseries/processor_idle.c
to drivers/cpuidle/cpuidle-pseries.c
Make the relevant Makefile and Kconfig changes.
Also, introduce Kconfig.powerpc in drivers/cpuidle
for all powerpc cpuidle drivers.
Signed-off-by: Deepthi Dharwar <[email protected]>
---
arch/powerpc/include/asm/processor.h | 2
arch/powerpc/platforms/pseries/Kconfig | 9 -
arch/powerpc/platforms/pseries/Makefile | 1
arch/powerpc/platforms/pseries/processor_idle.c | 361 -----------------------
drivers/cpuidle/Kconfig | 5
drivers/cpuidle/Kconfig.powerpc | 11 +
drivers/cpuidle/Makefile | 4
drivers/cpuidle/cpuidle-pseries.c | 361 +++++++++++++++++++++++
8 files changed, 382 insertions(+), 372 deletions(-)
delete mode 100644 arch/powerpc/platforms/pseries/processor_idle.c
create mode 100644 drivers/cpuidle/Kconfig.powerpc
create mode 100644 drivers/cpuidle/cpuidle-pseries.c
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index fc14a38..fa98fdf 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -445,7 +445,7 @@ enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
extern int powersave_nap; /* set if nap mode can be used in idle loop */
extern void power7_nap(void);
-#ifdef CONFIG_PSERIES_IDLE
+#ifdef CONFIG_PSERIES_CPUIDLE
extern void update_smt_snooze_delay(int cpu, int residency);
#else
static inline void update_smt_snooze_delay(int cpu, int residency) {}
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 62b4f80..bb59bb0 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -119,12 +119,3 @@ config DTL
which are accessible through a debugfs file.
Say N if you are unsure.
-
-config PSERIES_IDLE
- bool "Cpuidle driver for pSeries platforms"
- depends on CPU_IDLE
- depends on PPC_PSERIES
- default y
- help
- Select this option to enable processor idle state management
- through cpuidle subsystem.
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index fbccac9..0348079 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -21,7 +21,6 @@ obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o
obj-$(CONFIG_CMM) += cmm.o
obj-$(CONFIG_DTL) += dtl.o
obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o
-obj-$(CONFIG_PSERIES_IDLE) += processor_idle.o
obj-$(CONFIG_LPARCFG) += lparcfg.o
ifeq ($(CONFIG_PPC_PSERIES),y)
diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
deleted file mode 100644
index 09e4f56..0000000
--- a/arch/powerpc/platforms/pseries/processor_idle.c
+++ /dev/null
@@ -1,361 +0,0 @@
-/*
- * processor_idle - 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,
-};
-
-#define MAX_IDLE_STATE_COUNT 2
-
-static int max_idle_state = MAX_IDLE_STATE_COUNT - 1;
-static struct cpuidle_device __percpu *pseries_cpuidle_devices;
-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;
- int cpu = dev->cpu;
-
- idle_loop_prolog(&in_purr);
- local_irq_enable();
- set_thread_flag(TIF_POLLING_NRFLAG);
-
- while ((!need_resched()) && cpu_online(cpu)) {
- 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[MAX_IDLE_STATE_COUNT] = {
- { /* Snooze */
- .name = "snooze",
- .desc = "snooze",
- .flags = CPUIDLE_FLAG_TIME_VALID,
- .exit_latency = 0,
- .target_residency = 0,
- .enter = &snooze_loop },
- { /* CEDE */
- .name = "CEDE",
- .desc = "CEDE",
- .flags = CPUIDLE_FLAG_TIME_VALID,
- .exit_latency = 10,
- .target_residency = 100,
- .enter = &dedicated_cede_loop },
-};
-
-/*
- * States for shared partition case.
- */
-static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = {
- { /* Shared Cede */
- .name = "Shared Cede",
- .desc = "Shared Cede",
- .flags = CPUIDLE_FLAG_TIME_VALID,
- .exit_latency = 0,
- .target_residency = 0,
- .enter = &shared_cede_loop },
-};
-
-void update_smt_snooze_delay(int cpu, int residency)
-{
- struct cpuidle_driver *drv = cpuidle_get_driver();
- struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
-
- if (cpuidle_state_table != dedicated_states)
- return;
-
- if (residency < 0) {
- /* Disable the Nap state on that cpu */
- if (dev)
- dev->states_usage[1].disable = 1;
- } else
- if (drv)
- drv->states[1].target_residency = residency;
-}
-
-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_ptr(pseries_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_COUNT; ++idle_state) {
-
- if (idle_state > max_idle_state)
- break;
-
- /* 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_devices_uninit(void)
- * unregister cpuidle devices and de-allocate memory
- */
-static void pseries_idle_devices_uninit(void)
-{
- int i;
- struct cpuidle_device *dev;
-
- for_each_possible_cpu(i) {
- dev = per_cpu_ptr(pseries_cpuidle_devices, i);
- cpuidle_unregister_device(dev);
- }
-
- free_percpu(pseries_cpuidle_devices);
- return;
-}
-
-/* pseries_idle_devices_init()
- * allocate, initialize and register cpuidle device
- */
-static int pseries_idle_devices_init(void)
-{
- int i;
- struct cpuidle_driver *drv = &pseries_idle_driver;
- struct cpuidle_device *dev;
-
- pseries_cpuidle_devices = alloc_percpu(struct cpuidle_device);
- if (pseries_cpuidle_devices == NULL)
- return -ENOMEM;
-
- for_each_possible_cpu(i) {
- dev = per_cpu_ptr(pseries_cpuidle_devices, i);
- dev->state_count = drv->state_count;
- dev->cpu = i;
- if (cpuidle_register_device(dev)) {
- printk(KERN_DEBUG \
- "cpuidle_register_device %d failed!\n", i);
- return -EIO;
- }
- }
-
- return 0;
-}
-
-/*
- * pseries_idle_probe()
- * Choose state table for shared versus dedicated partition
- */
-static int pseries_idle_probe(void)
-{
-
- if (!firmware_has_feature(FW_FEATURE_SPLPAR))
- return -ENODEV;
-
- if (cpuidle_disable != IDLE_NO_OVERRIDE)
- return -ENODEV;
-
- if (max_idle_state == 0) {
- printk(KERN_DEBUG "pseries processor idle disabled.\n");
- return -EPERM;
- }
-
- if (lppaca_shared_proc(get_lppaca()))
- cpuidle_state_table = shared_states;
- else
- cpuidle_state_table = dedicated_states;
-
- return 0;
-}
-
-static int __init pseries_processor_idle_init(void)
-{
- int retval;
-
- retval = pseries_idle_probe();
- if (retval)
- return retval;
-
- pseries_cpuidle_driver_init();
- retval = cpuidle_register_driver(&pseries_idle_driver);
- if (retval) {
- printk(KERN_DEBUG "Registration of pseries driver failed.\n");
- return retval;
- }
-
- retval = pseries_idle_devices_init();
- if (retval) {
- pseries_idle_devices_uninit();
- cpuidle_unregister_driver(&pseries_idle_driver);
- return retval;
- }
-
- register_cpu_notifier(&setup_hotplug_notifier);
- printk(KERN_DEBUG "pseries_idle_driver registered\n");
-
- return 0;
-}
-
-static void __exit pseries_processor_idle_exit(void)
-{
-
- unregister_cpu_notifier(&setup_hotplug_notifier);
- pseries_idle_devices_uninit();
- cpuidle_unregister_driver(&pseries_idle_driver);
-
- return;
-}
-
-module_init(pseries_processor_idle_init);
-module_exit(pseries_processor_idle_exit);
-
-MODULE_AUTHOR("Deepthi Dharwar <[email protected]>");
-MODULE_DESCRIPTION("Cpuidle driver for POWER");
-MODULE_LICENSE("GPL");
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index b3fb81d..f04e25f 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -35,6 +35,11 @@ depends on ARM
source "drivers/cpuidle/Kconfig.arm"
endmenu
+menu "POWERPC CPU Idle Drivers"
+depends on PPC
+source "drivers/cpuidle/Kconfig.powerpc"
+endmenu
+
endif
config ARCH_NEEDS_CPU_IDLE_COUPLED
diff --git a/drivers/cpuidle/Kconfig.powerpc b/drivers/cpuidle/Kconfig.powerpc
new file mode 100644
index 0000000..8147de5
--- /dev/null
+++ b/drivers/cpuidle/Kconfig.powerpc
@@ -0,0 +1,11 @@
+#
+# POWERPC CPU Idle Drivers
+#
+config PSERIES_CPUIDLE
+ bool "Cpuidle driver for pSeries platforms"
+ depends on CPU_IDLE
+ depends on PPC_PSERIES
+ default y
+ help
+ Select this option to enable processor idle state management
+ through cpuidle subsystem.
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index 527be28..a6331ad 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -13,3 +13,7 @@ obj-$(CONFIG_ARM_KIRKWOOD_CPUIDLE) += cpuidle-kirkwood.o
obj-$(CONFIG_ARM_ZYNQ_CPUIDLE) += cpuidle-zynq.o
obj-$(CONFIG_ARM_U8500_CPUIDLE) += cpuidle-ux500.o
obj-$(CONFIG_ARM_AT91_CPUIDLE) += cpuidle-at91.o
+
+###############################################################################
+# POWERPC drivers
+obj-$(CONFIG_PSERIES_CPUIDLE) += cpuidle-pseries.o
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
new file mode 100644
index 0000000..2115478
--- /dev/null
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -0,0 +1,361 @@
+/*
+ * 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,
+};
+
+#define MAX_IDLE_STATE_COUNT 2
+
+static int max_idle_state = MAX_IDLE_STATE_COUNT - 1;
+static struct cpuidle_device __percpu *pseries_cpuidle_devices;
+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;
+ int cpu = dev->cpu;
+
+ idle_loop_prolog(&in_purr);
+ local_irq_enable();
+ set_thread_flag(TIF_POLLING_NRFLAG);
+
+ while ((!need_resched()) && cpu_online(cpu)) {
+ 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[MAX_IDLE_STATE_COUNT] = {
+ { /* Snooze */
+ .name = "snooze",
+ .desc = "snooze",
+ .flags = CPUIDLE_FLAG_TIME_VALID,
+ .exit_latency = 0,
+ .target_residency = 0,
+ .enter = &snooze_loop },
+ { /* CEDE */
+ .name = "CEDE",
+ .desc = "CEDE",
+ .flags = CPUIDLE_FLAG_TIME_VALID,
+ .exit_latency = 10,
+ .target_residency = 100,
+ .enter = &dedicated_cede_loop },
+};
+
+/*
+ * States for shared partition case.
+ */
+static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = {
+ { /* Shared Cede */
+ .name = "Shared Cede",
+ .desc = "Shared Cede",
+ .flags = CPUIDLE_FLAG_TIME_VALID,
+ .exit_latency = 0,
+ .target_residency = 0,
+ .enter = &shared_cede_loop },
+};
+
+void update_smt_snooze_delay(int cpu, int residency)
+{
+ struct cpuidle_driver *drv = cpuidle_get_driver();
+ struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
+
+ if (cpuidle_state_table != dedicated_states)
+ return;
+
+ if (residency < 0) {
+ /* Disable the Nap state on that cpu */
+ if (dev)
+ dev->states_usage[1].disable = 1;
+ } else
+ if (drv)
+ drv->states[1].target_residency = residency;
+}
+
+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_ptr(pseries_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_COUNT; ++idle_state) {
+
+ if (idle_state > max_idle_state)
+ break;
+
+ /* 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_devices_uninit(void)
+ * unregister cpuidle devices and de-allocate memory
+ */
+static void pseries_idle_devices_uninit(void)
+{
+ int i;
+ struct cpuidle_device *dev;
+
+ for_each_possible_cpu(i) {
+ dev = per_cpu_ptr(pseries_cpuidle_devices, i);
+ cpuidle_unregister_device(dev);
+ }
+
+ free_percpu(pseries_cpuidle_devices);
+ return;
+}
+
+/* pseries_idle_devices_init()
+ * allocate, initialize and register cpuidle device
+ */
+static int pseries_idle_devices_init(void)
+{
+ int i;
+ struct cpuidle_driver *drv = &pseries_idle_driver;
+ struct cpuidle_device *dev;
+
+ pseries_cpuidle_devices = alloc_percpu(struct cpuidle_device);
+ if (pseries_cpuidle_devices == NULL)
+ return -ENOMEM;
+
+ for_each_possible_cpu(i) {
+ dev = per_cpu_ptr(pseries_cpuidle_devices, i);
+ dev->state_count = drv->state_count;
+ dev->cpu = i;
+ if (cpuidle_register_device(dev)) {
+ printk(KERN_DEBUG \
+ "cpuidle_register_device %d failed!\n", i);
+ return -EIO;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * pseries_idle_probe()
+ * Choose state table for shared versus dedicated partition
+ */
+static int pseries_idle_probe(void)
+{
+
+ if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+ return -ENODEV;
+
+ if (cpuidle_disable != IDLE_NO_OVERRIDE)
+ return -ENODEV;
+
+ if (max_idle_state == 0) {
+ printk(KERN_DEBUG "pseries processor idle disabled.\n");
+ return -EPERM;
+ }
+
+ if (lppaca_shared_proc(get_lppaca()))
+ cpuidle_state_table = shared_states;
+ else
+ cpuidle_state_table = dedicated_states;
+
+ return 0;
+}
+
+static int __init pseries_processor_idle_init(void)
+{
+ int retval;
+
+ retval = pseries_idle_probe();
+ if (retval)
+ return retval;
+
+ pseries_cpuidle_driver_init();
+ retval = cpuidle_register_driver(&pseries_idle_driver);
+ if (retval) {
+ printk(KERN_DEBUG "Registration of pseries driver failed.\n");
+ return retval;
+ }
+
+ retval = pseries_idle_devices_init();
+ if (retval) {
+ pseries_idle_devices_uninit();
+ cpuidle_unregister_driver(&pseries_idle_driver);
+ return retval;
+ }
+
+ register_cpu_notifier(&setup_hotplug_notifier);
+ printk(KERN_DEBUG "pseries_idle_driver registered\n");
+
+ return 0;
+}
+
+static void __exit pseries_processor_idle_exit(void)
+{
+
+ unregister_cpu_notifier(&setup_hotplug_notifier);
+ pseries_idle_devices_uninit();
+ cpuidle_unregister_driver(&pseries_idle_driver);
+
+ return;
+}
+
+module_init(pseries_processor_idle_init);
+module_exit(pseries_processor_idle_exit);
+
+MODULE_AUTHOR("Deepthi Dharwar <[email protected]>");
+MODULE_DESCRIPTION("Cpuidle driver for POWER");
+MODULE_LICENSE("GPL");
This patch replaces the cpuidle driver and devices initialisation
calls with a single generic cpuidle_register() call
and also includes minor refactoring of the code around it.
Remove the cpu online check in snooze loop, as this code can
only locally run on a cpu only if it is online. Therefore,
this check is not required.
Signed-off-by: Deepthi Dharwar <[email protected]>
---
drivers/cpuidle/cpuidle-pseries.c | 78 +++++--------------------------------
1 file changed, 11 insertions(+), 67 deletions(-)
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 2115478..32d86bc 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -27,7 +27,6 @@ struct cpuidle_driver pseries_idle_driver = {
#define MAX_IDLE_STATE_COUNT 2
static int max_idle_state = MAX_IDLE_STATE_COUNT - 1;
-static struct cpuidle_device __percpu *pseries_cpuidle_devices;
static struct cpuidle_state *cpuidle_state_table;
static inline void idle_loop_prolog(unsigned long *in_purr)
@@ -55,13 +54,12 @@ static int snooze_loop(struct cpuidle_device *dev,
int index)
{
unsigned long in_purr;
- int cpu = dev->cpu;
idle_loop_prolog(&in_purr);
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);
- while ((!need_resched()) && cpu_online(cpu)) {
+ while (!need_resched()) {
HMT_low();
HMT_very_low();
}
@@ -188,7 +186,7 @@ static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n,
{
int hotcpu = (unsigned long)hcpu;
struct cpuidle_device *dev =
- per_cpu_ptr(pseries_cpuidle_devices, hotcpu);
+ per_cpu(cpuidle_devices, hotcpu);
if (dev && cpuidle_get_driver()) {
switch (action) {
@@ -245,50 +243,6 @@ static int pseries_cpuidle_driver_init(void)
return 0;
}
-/* pseries_idle_devices_uninit(void)
- * unregister cpuidle devices and de-allocate memory
- */
-static void pseries_idle_devices_uninit(void)
-{
- int i;
- struct cpuidle_device *dev;
-
- for_each_possible_cpu(i) {
- dev = per_cpu_ptr(pseries_cpuidle_devices, i);
- cpuidle_unregister_device(dev);
- }
-
- free_percpu(pseries_cpuidle_devices);
- return;
-}
-
-/* pseries_idle_devices_init()
- * allocate, initialize and register cpuidle device
- */
-static int pseries_idle_devices_init(void)
-{
- int i;
- struct cpuidle_driver *drv = &pseries_idle_driver;
- struct cpuidle_device *dev;
-
- pseries_cpuidle_devices = alloc_percpu(struct cpuidle_device);
- if (pseries_cpuidle_devices == NULL)
- return -ENOMEM;
-
- for_each_possible_cpu(i) {
- dev = per_cpu_ptr(pseries_cpuidle_devices, i);
- dev->state_count = drv->state_count;
- dev->cpu = i;
- if (cpuidle_register_device(dev)) {
- printk(KERN_DEBUG \
- "cpuidle_register_device %d failed!\n", i);
- return -EIO;
- }
- }
-
- return 0;
-}
-
/*
* pseries_idle_probe()
* Choose state table for shared versus dedicated partition
@@ -296,9 +250,6 @@ static int pseries_idle_devices_init(void)
static int pseries_idle_probe(void)
{
- if (!firmware_has_feature(FW_FEATURE_SPLPAR))
- return -ENODEV;
-
if (cpuidle_disable != IDLE_NO_OVERRIDE)
return -ENODEV;
@@ -307,10 +258,13 @@ static int pseries_idle_probe(void)
return -EPERM;
}
- if (lppaca_shared_proc(get_lppaca()))
- cpuidle_state_table = shared_states;
- else
- cpuidle_state_table = dedicated_states;
+ if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+ if (lppaca_shared_proc(get_lppaca()))
+ cpuidle_state_table = shared_states;
+ else
+ cpuidle_state_table = dedicated_states;
+ } else
+ return -ENODEV;
return 0;
}
@@ -324,22 +278,14 @@ static int __init pseries_processor_idle_init(void)
return retval;
pseries_cpuidle_driver_init();
- retval = cpuidle_register_driver(&pseries_idle_driver);
+ retval = cpuidle_register(&pseries_idle_driver, NULL);
if (retval) {
printk(KERN_DEBUG "Registration of pseries driver failed.\n");
return retval;
}
- retval = pseries_idle_devices_init();
- if (retval) {
- pseries_idle_devices_uninit();
- cpuidle_unregister_driver(&pseries_idle_driver);
- return retval;
- }
-
register_cpu_notifier(&setup_hotplug_notifier);
printk(KERN_DEBUG "pseries_idle_driver registered\n");
-
return 0;
}
@@ -347,9 +293,7 @@ static void __exit pseries_processor_idle_exit(void)
{
unregister_cpu_notifier(&setup_hotplug_notifier);
- pseries_idle_devices_uninit();
- cpuidle_unregister_driver(&pseries_idle_driver);
-
+ cpuidle_unregister(&pseries_idle_driver);
return;
}
Currently cpuidle-pseries backend driver cannot be
built as a module due to dependencies wrt cpuidle framework.
This patch removes all the module related code in the driver.
Signed-off-by: Deepthi Dharwar <[email protected]>
---
drivers/cpuidle/cpuidle-pseries.c | 15 +--------------
1 file changed, 1 insertion(+), 14 deletions(-)
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 32d86bc..5e13f6c 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -289,17 +289,4 @@ static int __init pseries_processor_idle_init(void)
return 0;
}
-static void __exit pseries_processor_idle_exit(void)
-{
-
- unregister_cpu_notifier(&setup_hotplug_notifier);
- cpuidle_unregister(&pseries_idle_driver);
- return;
-}
-
-module_init(pseries_processor_idle_init);
-module_exit(pseries_processor_idle_exit);
-
-MODULE_AUTHOR("Deepthi Dharwar <[email protected]>");
-MODULE_DESCRIPTION("Cpuidle driver for POWER");
-MODULE_LICENSE("GPL");
+device_initcall(pseries_processor_idle_init);
This patch removes the usage of MAX_IDLE_STATE macro
and dead code around it. The number of states
are determined at run time based on the cpuidle
state table selected on a given platform
Signed-off-by: Deepthi Dharwar <[email protected]>
---
drivers/cpuidle/cpuidle-pseries.c | 28 ++++++++++------------------
1 file changed, 10 insertions(+), 18 deletions(-)
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 5e13f6c..bb56091 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -24,9 +24,7 @@ struct cpuidle_driver pseries_idle_driver = {
.owner = THIS_MODULE,
};
-#define MAX_IDLE_STATE_COUNT 2
-
-static int max_idle_state = MAX_IDLE_STATE_COUNT - 1;
+static int max_idle_state;
static struct cpuidle_state *cpuidle_state_table;
static inline void idle_loop_prolog(unsigned long *in_purr)
@@ -134,7 +132,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
/*
* States for dedicated partition case.
*/
-static struct cpuidle_state dedicated_states[MAX_IDLE_STATE_COUNT] = {
+static struct cpuidle_state dedicated_states[] = {
{ /* Snooze */
.name = "snooze",
.desc = "snooze",
@@ -154,7 +152,7 @@ static struct cpuidle_state dedicated_states[MAX_IDLE_STATE_COUNT] = {
/*
* States for shared partition case.
*/
-static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = {
+static struct cpuidle_state shared_states[] = {
{ /* Shared Cede */
.name = "Shared Cede",
.desc = "Shared Cede",
@@ -225,12 +223,8 @@ static int pseries_cpuidle_driver_init(void)
drv->state_count = 0;
- for (idle_state = 0; idle_state < MAX_IDLE_STATE_COUNT; ++idle_state) {
-
- if (idle_state > max_idle_state)
- break;
-
- /* is the state not enabled? */
+ 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;
@@ -253,16 +247,14 @@ static int pseries_idle_probe(void)
if (cpuidle_disable != IDLE_NO_OVERRIDE)
return -ENODEV;
- if (max_idle_state == 0) {
- printk(KERN_DEBUG "pseries processor idle disabled.\n");
- return -EPERM;
- }
-
if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
- if (lppaca_shared_proc(get_lppaca()))
+ if (lppaca_shared_proc(get_lppaca())) {
cpuidle_state_table = shared_states;
- else
+ max_idle_state = ARRAY_SIZE(shared_states);
+ } else {
cpuidle_state_table = dedicated_states;
+ max_idle_state = ARRAY_SIZE(dedicated_states);
+ }
} else
return -ENODEV;
smt-snooze-delay was designed to disable NAP state or delay the entry
to the NAP state prior to adoption of cpuidle framework. This
is per-cpu variable. With the coming of CPUIDLE framework,
states can be disabled on per-cpu basis using the cpuidle/enable
sysfs entry.
Also, with the coming of cpuidle driver each state's target residency
is per-driver unlike earlier which was per-device. Therefore,
the per-cpu sysfs smt-snooze-delay which decides the target residency
of the idle state on a particular cpu causes more confusion to the user
as we cannot have different smt-snooze-delay (target residency)
values for each cpu.
In the current code, smt-snooze-delay functionality is completely broken.
It makes sense to remove smt-snooze-delay from idle driver with the
coming of cpuidle framework.
However, sysfs files are retained as ppc64_util currently
utilises it. Once we fix ppc64_util, propose to clean
up the kernel code.
Signed-off-by: Deepthi Dharwar <[email protected]>
---
arch/powerpc/include/asm/processor.h | 7 -------
arch/powerpc/kernel/sysfs.c | 2 --
drivers/cpuidle/cpuidle-pseries.c | 17 -----------------
3 files changed, 26 deletions(-)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index fa98fdf..027fefd 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -444,13 +444,6 @@ enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
extern int powersave_nap; /* set if nap mode can be used in idle loop */
extern void power7_nap(void);
-
-#ifdef CONFIG_PSERIES_CPUIDLE
-extern void update_smt_snooze_delay(int cpu, int residency);
-#else
-static inline void update_smt_snooze_delay(int cpu, int residency) {}
-#endif
-
extern void flush_instruction_cache(void);
extern void hard_reset_now(void);
extern void poweroff_now(void);
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index b4e6676..7f9e130 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -51,8 +51,6 @@ static ssize_t store_smt_snooze_delay(struct device *dev,
return -EINVAL;
per_cpu(smt_snooze_delay, cpu->dev.id) = snooze;
- update_smt_snooze_delay(cpu->dev.id, snooze);
-
return count;
}
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index bb56091..7ab564a 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -162,23 +162,6 @@ static struct cpuidle_state shared_states[] = {
.enter = &shared_cede_loop },
};
-void update_smt_snooze_delay(int cpu, int residency)
-{
- struct cpuidle_driver *drv = cpuidle_get_driver();
- struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
-
- if (cpuidle_state_table != dedicated_states)
- return;
-
- if (residency < 0) {
- /* Disable the Nap state on that cpu */
- if (dev)
- dev->states_usage[1].disable = 1;
- } else
- if (drv)
- drv->states[1].target_residency = residency;
-}
-
static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n,
unsigned long action, void *hcpu)
{