* [PATCH V5 3/8] cpuidle/ppc: Split timer_interrupt() into timer handling and interrupt handling routines
From: Preeti U Murthy @ 2014-01-15 8:08 UTC (permalink / raw)
To: daniel.lezcano, peterz, fweisbec, agraf, paul.gortmaker, paulus,
mingo, mikey, shangw, rafael.j.wysocki, galak, benh, paulmck,
arnd, linux-pm, rostedt, michael, john.stultz, anton, tglx,
chenhui.zhao, deepthi, r58472, geoff, linux-kernel, srivatsa.bhat,
schwidefsky, svaidy, linuxppc-dev
In-Reply-To: <20140115080555.20446.27238.stgit@preeti.in.ibm.com>
Split timer_interrupt(), which is the local timer interrupt handler on ppc
into routines called during regular interrupt handling and __timer_interrupt(),
which takes care of running local timers and collecting time related stats.
This will enable callers interested only in running expired local timers to
directly call into __timer_interupt(). One of the use cases of this is the
tick broadcast IPI handling in which the sleeping CPUs need to handle the local
timers that have expired.
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---
arch/powerpc/kernel/time.c | 73 +++++++++++++++++++++++++-------------------
1 file changed, 41 insertions(+), 32 deletions(-)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 42269c7..42cb603 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -478,6 +478,42 @@ void arch_irq_work_raise(void)
#endif /* CONFIG_IRQ_WORK */
+static void __timer_interrupt(void)
+{
+ struct pt_regs *regs = get_irq_regs();
+ u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+ struct clock_event_device *evt = &__get_cpu_var(decrementers);
+ u64 now;
+
+ __get_cpu_var(irq_stat).timer_irqs++;
+ trace_timer_interrupt_entry(regs);
+
+ if (test_irq_work_pending()) {
+ clear_irq_work_pending();
+ irq_work_run();
+ }
+
+ now = get_tb_or_rtc();
+ if (now >= *next_tb) {
+ *next_tb = ~(u64)0;
+ if (evt->event_handler)
+ evt->event_handler(evt);
+ } else {
+ now = *next_tb - now;
+ if (now <= DECREMENTER_MAX)
+ set_dec((int)now);
+ }
+
+#ifdef CONFIG_PPC64
+ /* collect purr register values often, for accurate calculations */
+ if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+ struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+ cu->current_tb = mfspr(SPRN_PURR);
+ }
+#endif
+ trace_timer_interrupt_exit(regs);
+}
+
/*
* timer_interrupt - gets called when the decrementer overflows,
* with interrupts disabled.
@@ -486,8 +522,6 @@ void timer_interrupt(struct pt_regs * regs)
{
struct pt_regs *old_regs;
u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
- struct clock_event_device *evt = &__get_cpu_var(decrementers);
- u64 now;
/* Ensure a positive value is written to the decrementer, or else
* some CPUs will continue to take decrementer exceptions.
@@ -510,8 +544,6 @@ void timer_interrupt(struct pt_regs * regs)
*/
may_hard_irq_enable();
- __get_cpu_var(irq_stat).timer_irqs++;
-
#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
if (atomic_read(&ppc_n_lost_interrupts) != 0)
do_IRQ(regs);
@@ -520,34 +552,7 @@ void timer_interrupt(struct pt_regs * regs)
old_regs = set_irq_regs(regs);
irq_enter();
- trace_timer_interrupt_entry(regs);
-
- if (test_irq_work_pending()) {
- clear_irq_work_pending();
- irq_work_run();
- }
-
- now = get_tb_or_rtc();
- if (now >= *next_tb) {
- *next_tb = ~(u64)0;
- if (evt->event_handler)
- evt->event_handler(evt);
- } else {
- now = *next_tb - now;
- if (now <= DECREMENTER_MAX)
- set_dec((int)now);
- }
-
-#ifdef CONFIG_PPC64
- /* collect purr register values often, for accurate calculations */
- if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
- struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
- cu->current_tb = mfspr(SPRN_PURR);
- }
-#endif
-
- trace_timer_interrupt_exit(regs);
-
+ __timer_interrupt();
irq_exit();
set_irq_regs(old_regs);
}
@@ -816,6 +821,10 @@ static void decrementer_set_mode(enum clock_event_mode mode,
/* Interrupt handler for the timer broadcast IPI */
void tick_broadcast_ipi_handler(void)
{
+ u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+
+ *next_tb = get_tb_or_rtc();
+ __timer_interrupt();
}
static void register_decrementer_clockevent(int cpu)
^ permalink raw reply related
* [PATCH V5 4/8] powernv/cpuidle: Add context management for Fast Sleep
From: Preeti U Murthy @ 2014-01-15 8:09 UTC (permalink / raw)
To: daniel.lezcano, peterz, fweisbec, agraf, paul.gortmaker, paulus,
mingo, mikey, shangw, rafael.j.wysocki, galak, benh, paulmck,
arnd, linux-pm, rostedt, michael, john.stultz, anton, tglx,
chenhui.zhao, deepthi, r58472, geoff, linux-kernel, srivatsa.bhat,
schwidefsky, svaidy, linuxppc-dev
In-Reply-To: <20140115080555.20446.27238.stgit@preeti.in.ibm.com>
From: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Before adding Fast-Sleep into the cpuidle framework, some low level
support needs to be added to enable it. This includes saving and
restoring of certain registers at entry and exit time of this state
respectively just like we do in the NAP idle state.
Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
[Changelog modified by Preeti U. Murthy <preeti@linux.vnet.ibm.com>]
Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/processor.h | 1 +
arch/powerpc/kernel/exceptions-64s.S | 10 ++++-
arch/powerpc/kernel/idle_power7.S | 63 ++++++++++++++++++++++++----------
3 files changed, 53 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 027fefd..22e547a 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -444,6 +444,7 @@ 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);
+extern void power7_sleep(void);
extern void flush_instruction_cache(void);
extern void hard_reset_now(void);
extern void poweroff_now(void);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 9f905e4..b8139fb 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -121,9 +121,10 @@ BEGIN_FTR_SECTION
cmpwi cr1,r13,2
/* Total loss of HV state is fatal, we could try to use the
* PIR to locate a PACA, then use an emergency stack etc...
- * but for now, let's just stay stuck here
+ * OPAL v3 based powernv platforms have new idle states
+ * which fall in this catagory.
*/
- bgt cr1,.
+ bgt cr1,8f
GET_PACA(r13)
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -141,6 +142,11 @@ BEGIN_FTR_SECTION
beq cr1,2f
b .power7_wakeup_noloss
2: b .power7_wakeup_loss
+
+ /* Fast Sleep wakeup on PowerNV */
+8: GET_PACA(r13)
+ b .power7_wakeup_loss
+
9:
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
#endif /* CONFIG_PPC_P7_NAP */
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 847e40e..e4bbca2 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -20,17 +20,27 @@
#undef DEBUG
- .text
+/* Idle state entry routines */
-_GLOBAL(power7_idle)
- /* Now check if user or arch enabled NAP mode */
- LOAD_REG_ADDRBASE(r3,powersave_nap)
- lwz r4,ADDROFF(powersave_nap)(r3)
- cmpwi 0,r4,0
- beqlr
- /* fall through */
+#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \
+ /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
+ std r0,0(r1); \
+ ptesync; \
+ ld r0,0(r1); \
+1: cmp cr0,r0,r0; \
+ bne 1b; \
+ IDLE_INST; \
+ b .
-_GLOBAL(power7_nap)
+ .text
+
+/*
+ * Pass requested state in r3:
+ * 0 - nap
+ * 1 - sleep
+ */
+_GLOBAL(power7_powersave_common)
+ /* Use r3 to pass state nap/sleep/winkle */
/* NAP is a state loss, we create a regs frame on the
* stack, fill it up with the state we care about and
* stick a pointer to it in PACAR1. We really only
@@ -79,8 +89,8 @@ _GLOBAL(power7_nap)
/* Continue saving state */
SAVE_GPR(2, r1)
SAVE_NVGPRS(r1)
- mfcr r3
- std r3,_CCR(r1)
+ mfcr r4
+ std r4,_CCR(r1)
std r9,_MSR(r1)
std r1,PACAR1(r13)
@@ -89,15 +99,30 @@ _GLOBAL(power7_nap)
li r4,KVM_HWTHREAD_IN_NAP
stb r4,HSTATE_HWTHREAD_STATE(r13)
#endif
+ cmpwi cr0,r3,1
+ beq 2f
+ IDLE_STATE_ENTER_SEQ(PPC_NAP)
+ /* No return */
+2: IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
+ /* No return */
- /* Magic NAP mode enter sequence */
- std r0,0(r1)
- ptesync
- ld r0,0(r1)
-1: cmp cr0,r0,r0
- bne 1b
- PPC_NAP
- b .
+_GLOBAL(power7_idle)
+ /* Now check if user or arch enabled NAP mode */
+ LOAD_REG_ADDRBASE(r3,powersave_nap)
+ lwz r4,ADDROFF(powersave_nap)(r3)
+ cmpwi 0,r4,0
+ beqlr
+ /* fall through */
+
+_GLOBAL(power7_nap)
+ li r3,0
+ b power7_powersave_common
+ /* No return */
+
+_GLOBAL(power7_sleep)
+ li r3,1
+ b power7_powersave_common
+ /* No return */
_GLOBAL(power7_wakeup_loss)
ld r1,PACAR1(r13)
^ permalink raw reply related
* [PATCH V5 5/8] powermgt: Add OPAL call to resync timebase on wakeup
From: Preeti U Murthy @ 2014-01-15 8:09 UTC (permalink / raw)
To: daniel.lezcano, peterz, fweisbec, agraf, paul.gortmaker, paulus,
mingo, mikey, shangw, rafael.j.wysocki, galak, benh, paulmck,
arnd, linux-pm, rostedt, michael, john.stultz, anton, tglx,
chenhui.zhao, deepthi, r58472, geoff, linux-kernel, srivatsa.bhat,
schwidefsky, svaidy, linuxppc-dev
In-Reply-To: <20140115080555.20446.27238.stgit@preeti.in.ibm.com>
From: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
During "Fast-sleep" and deeper power savings state, decrementer and
timebase could be stopped making it out of sync with rest
of the cores in the system.
Add a firmware call to request platform to resync timebase
using low level platform methods.
Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/opal.h | 2 ++
arch/powerpc/kernel/exceptions-64s.S | 2 +-
arch/powerpc/kernel/idle_power7.S | 27 ++++++++++++++++++++++++
arch/powerpc/platforms/powernv/opal-wrappers.S | 1 +
4 files changed, 31 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 033c06b..a662d06 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -132,6 +132,7 @@ extern int opal_enter_rtas(struct rtas_args *args,
#define OPAL_FLASH_VALIDATE 76
#define OPAL_FLASH_MANAGE 77
#define OPAL_FLASH_UPDATE 78
+#define OPAL_RESYNC_TIMEBASE 79
#ifndef __ASSEMBLY__
@@ -763,6 +764,7 @@ extern void opal_flash_init(void);
extern int opal_machine_check(struct pt_regs *regs);
extern void opal_shutdown(void);
+extern int opal_resync_timebase(void);
extern void opal_lpc_init(void);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index b8139fb..91e6417 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -145,7 +145,7 @@ BEGIN_FTR_SECTION
/* Fast Sleep wakeup on PowerNV */
8: GET_PACA(r13)
- b .power7_wakeup_loss
+ b .power7_wakeup_tb_loss
9:
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index e4bbca2..34c71e8 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -17,6 +17,7 @@
#include <asm/ppc-opcode.h>
#include <asm/hw_irq.h>
#include <asm/kvm_book3s_asm.h>
+#include <asm/opal.h>
#undef DEBUG
@@ -124,6 +125,32 @@ _GLOBAL(power7_sleep)
b power7_powersave_common
/* No return */
+_GLOBAL(power7_wakeup_tb_loss)
+ ld r2,PACATOC(r13);
+ ld r1,PACAR1(r13)
+
+ /* Time base re-sync */
+ li r0,OPAL_RESYNC_TIMEBASE
+ LOAD_REG_ADDR(r11,opal);
+ ld r12,8(r11);
+ ld r2,0(r11);
+ mtctr r12
+ bctrl
+
+ /* TODO: Check r3 for failure */
+
+ REST_NVGPRS(r1)
+ REST_GPR(2, r1)
+ ld r3,_CCR(r1)
+ ld r4,_MSR(r1)
+ ld r5,_NIP(r1)
+ addi r1,r1,INT_FRAME_SIZE
+ mtcr r3
+ mfspr r3,SPRN_SRR1 /* Return SRR1 */
+ mtspr SPRN_SRR1,r4
+ mtspr SPRN_SRR0,r5
+ rfid
+
_GLOBAL(power7_wakeup_loss)
ld r1,PACAR1(r13)
REST_NVGPRS(r1)
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index e780650..ddfe95a 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -126,3 +126,4 @@ OPAL_CALL(opal_return_cpu, OPAL_RETURN_CPU);
OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE);
OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE);
OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE);
+OPAL_CALL(opal_resync_timebase, OPAL_RESYNC_TIMEBASE);
^ permalink raw reply related
* [PATCH V5 6/8] time/cpuidle: Support in tick broadcast framework in the absence of external clock device
From: Preeti U Murthy @ 2014-01-15 8:09 UTC (permalink / raw)
To: daniel.lezcano, peterz, fweisbec, agraf, paul.gortmaker, paulus,
mingo, mikey, shangw, rafael.j.wysocki, galak, benh, paulmck,
arnd, linux-pm, rostedt, michael, john.stultz, anton, tglx,
chenhui.zhao, deepthi, r58472, geoff, linux-kernel, srivatsa.bhat,
schwidefsky, svaidy, linuxppc-dev
In-Reply-To: <20140115080555.20446.27238.stgit@preeti.in.ibm.com>
On some architectures, in certain CPU deep idle states the local timers stop.
An external clock device is used to wakeup these CPUs. The kernel support for the
wakeup of these CPUs is provided by the tick broadcast framework by using the
external clock device as the wakeup source.
However not all implementations of architectures provide such an external
clock device such as some PowerPC ones. This patch includes support in the
broadcast framework to handle the wakeup of the CPUs in deep idle states on such
systems by queuing a hrtimer on one of the CPUs, meant to handle the wakeup of
CPUs in deep idle states. This CPU is identified as the bc_cpu.
Each time the hrtimer expires, it is reprogrammed for the next wakeup of the
CPUs in deep idle state after handling broadcast. However when a CPU is about
to enter deep idle state with its wakeup time earlier than the time at which
the hrtimer is currently programmed, it *becomes the new bc_cpu* and restarts
the hrtimer on itself. This way the job of doing broadcast is handed around to
the CPUs that ask for the earliest wakeup just before entering deep idle
state. This is consistent with what happens in cases where an external clock
device is present. The smp affinity of this clock device is set to the CPU
with the earliest wakeup.
The important point here is that the bc_cpu cannot enter deep idle state
since it has a hrtimer queued to wakeup the other CPUs in deep idle. Hence it
cannot have its local timer stopped. Therefore for such a CPU, the
BROADCAST_ENTER notification has to fail implying that it cannot enter deep
idle state. On architectures where an external clock device is present, all
CPUs can enter deep idle.
During hotplug of the bc_cpu, the job of doing a broadcast is assigned to the
first cpu in the broadcast mask. This newly nominated bc_cpu is woken up by
an IPI so as to queue the above mentioned hrtimer on it.
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---
include/linux/clockchips.h | 4 -
kernel/time/clockevents.c | 9 +-
kernel/time/tick-broadcast.c | 192 ++++++++++++++++++++++++++++++++++++++----
kernel/time/tick-internal.h | 8 +-
4 files changed, 186 insertions(+), 27 deletions(-)
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 493aa02..bbda37b 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -186,9 +186,9 @@ static inline int tick_check_broadcast_expired(void) { return 0; }
#endif
#ifdef CONFIG_GENERIC_CLOCKEVENTS
-extern void clockevents_notify(unsigned long reason, void *arg);
+extern int clockevents_notify(unsigned long reason, void *arg);
#else
-static inline void clockevents_notify(unsigned long reason, void *arg) {}
+static inline int clockevents_notify(unsigned long reason, void *arg) {}
#endif
#else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 086ad60..d61404e 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -524,12 +524,13 @@ void clockevents_resume(void)
#ifdef CONFIG_GENERIC_CLOCKEVENTS
/**
* clockevents_notify - notification about relevant events
+ * Returns non zero on error.
*/
-void clockevents_notify(unsigned long reason, void *arg)
+int clockevents_notify(unsigned long reason, void *arg)
{
struct clock_event_device *dev, *tmp;
unsigned long flags;
- int cpu;
+ int cpu, ret = 0;
raw_spin_lock_irqsave(&clockevents_lock, flags);
@@ -542,11 +543,12 @@ void clockevents_notify(unsigned long reason, void *arg)
case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
- tick_broadcast_oneshot_control(reason);
+ ret = tick_broadcast_oneshot_control(reason);
break;
case CLOCK_EVT_NOTIFY_CPU_DYING:
tick_handover_do_timer(arg);
+ tick_handover_broadcast_cpu(arg);
break;
case CLOCK_EVT_NOTIFY_SUSPEND:
@@ -585,6 +587,7 @@ void clockevents_notify(unsigned long reason, void *arg)
break;
}
raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+ return ret;
}
EXPORT_SYMBOL_GPL(clockevents_notify);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 9532690..1c23912 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -20,6 +20,7 @@
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include "tick-internal.h"
@@ -35,6 +36,15 @@ static cpumask_var_t tmpmask;
static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
static int tick_broadcast_force;
+/*
+ * Helper variables for handling broadcast in the absence of a
+ * tick_broadcast_device.
+ * */
+static struct hrtimer *bc_hrtimer;
+static int bc_cpu = -1;
+static ktime_t bc_next_wakeup;
+static int hrtimer_initialized = 0;
+
#ifdef CONFIG_TICK_ONESHOT
static void tick_broadcast_clear_oneshot(int cpu);
#else
@@ -528,6 +538,20 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
return ret;
}
+static void tick_broadcast_set_next_wakeup(int cpu, ktime_t expires, int force)
+{
+ struct clock_event_device *bc;
+
+ bc = tick_broadcast_device.evtdev;
+
+ if (bc) {
+ tick_broadcast_set_event(bc, cpu, expires, force);
+ } else {
+ hrtimer_start(bc_hrtimer, expires, HRTIMER_MODE_ABS_PINNED);
+ bc_cpu = cpu;
+ }
+}
+
int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
{
clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
@@ -558,15 +582,13 @@ void tick_check_oneshot_broadcast(int cpu)
/*
* Handle oneshot mode broadcasting
*/
-static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
+static int tick_oneshot_broadcast(void)
{
struct tick_device *td;
ktime_t now, next_event;
int cpu, next_cpu = 0;
- raw_spin_lock(&tick_broadcast_lock);
-again:
- dev->next_event.tv64 = KTIME_MAX;
+ bc_next_wakeup.tv64 = KTIME_MAX;
next_event.tv64 = KTIME_MAX;
cpumask_clear(tmpmask);
now = ktime_get();
@@ -620,34 +642,95 @@ again:
* in the event mask
*/
if (next_event.tv64 != KTIME_MAX) {
- /*
- * Rearm the broadcast device. If event expired,
- * repeat the above
- */
- if (tick_broadcast_set_event(dev, next_cpu, next_event, 0))
+ bc_next_wakeup = next_event;
+ }
+
+ return next_cpu;
+}
+
+/*
+ * Handler in oneshot mode for the external clock device
+ */
+static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
+{
+ int next_cpu;
+
+ raw_spin_lock(&tick_broadcast_lock);
+
+again: next_cpu = tick_oneshot_broadcast();
+ /*
+ * Rearm the broadcast device. If event expired,
+ * repeat the above
+ */
+ if (bc_next_wakeup.tv64 != KTIME_MAX)
+ if (tick_broadcast_set_event(dev, next_cpu, bc_next_wakeup, 0))
goto again;
+
+ raw_spin_unlock(&tick_broadcast_lock);
+}
+
+/*
+ * Handler in oneshot mode for the hrtimer queued when there is no external
+ * clock device.
+ */
+static enum hrtimer_restart handle_broadcast(struct hrtimer *hrtmr)
+{
+ ktime_t now, interval;
+
+ raw_spin_lock(&tick_broadcast_lock);
+ tick_oneshot_broadcast();
+
+ now = ktime_get();
+
+ if (bc_next_wakeup.tv64 != KTIME_MAX) {
+ interval = ktime_sub(bc_next_wakeup, now);
+ hrtimer_forward_now(bc_hrtimer, interval);
+ raw_spin_unlock(&tick_broadcast_lock);
+ return HRTIMER_RESTART;
}
raw_spin_unlock(&tick_broadcast_lock);
+ return HRTIMER_NORESTART;
+}
+
+/* The CPU could be asked to take over from the previous bc_cpu,
+ * if it is being hotplugged out.
+ */
+static void tick_broadcast_exit_check(int cpu)
+{
+ if (cpu == bc_cpu)
+ hrtimer_start(bc_hrtimer, bc_next_wakeup,
+ HRTIMER_MODE_ABS_PINNED);
+}
+
+static int can_enter_broadcast(int cpu)
+{
+ return cpu != bc_cpu;
}
/*
* Powerstate information: The system enters/leaves a state, where
* affected devices might stop
+ *
+ * Returns non zero value if the entry into broadcast framework failed
+ * This scenario can arise on certain implementations of archs which do
+ * not have an external clock device to do the broadcast. Then one of the
+ * CPUs get nominated to handle broadcasting.
+ * Such a CPU cannot enter a state where its tick device can stop.
*/
-void tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(unsigned long reason)
{
- struct clock_event_device *bc, *dev;
+ struct clock_event_device *dev;
struct tick_device *td;
unsigned long flags;
ktime_t now;
- int cpu;
+ int cpu, ret = 0;
/*
* Periodic mode does not care about the enter/exit of power
* states
*/
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
- return;
+ return ret;
/*
* We are called with preemtion disabled from the depth of the
@@ -658,9 +741,8 @@ void tick_broadcast_oneshot_control(unsigned long reason)
dev = td->evtdev;
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
- return;
+ return ret;
- bc = tick_broadcast_device.evtdev;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
@@ -676,12 +758,22 @@ void tick_broadcast_oneshot_control(unsigned long reason)
* woken by the IPI right away.
*/
if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
- dev->next_event.tv64 < bc->next_event.tv64)
- tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
+ dev->next_event.tv64 < bc_next_wakeup.tv64) {
+ bc_next_wakeup = dev->next_event;
+ tick_broadcast_set_next_wakeup(cpu, dev->next_event, 1);
+ }
+
+ if (!can_enter_broadcast(cpu)) {
+ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+ ret = 1;
+ }
}
} else {
if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
+
+ tick_broadcast_exit_check(cpu);
/*
* The cpu which was handling the broadcast
* timer marked this cpu in the broadcast
@@ -746,6 +838,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
}
out:
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ return ret;
}
/*
@@ -821,17 +914,57 @@ void tick_broadcast_switch_to_oneshot(void)
{
struct clock_event_device *bc;
unsigned long flags;
+ int cpu = smp_processor_id();
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+ bc_next_wakeup.tv64 = KTIME_MAX;
+
tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
bc = tick_broadcast_device.evtdev;
- if (bc)
+ if (bc) {
tick_broadcast_setup_oneshot(bc);
+ bc_next_wakeup = bc->next_event;
+ } else if (hrtimer_initialized) {
+
+ /*
+ * There may be CPUs waiting for periodic broadcast. We need
+ * to set the oneshot bits for those and program the hrtimer
+ * to fire at the next tick period.
+ */
+ cpumask_copy(tmpmask, tick_broadcast_mask);
+ cpumask_clear_cpu(cpu, tmpmask);
+ cpumask_or(tick_broadcast_oneshot_mask,
+ tick_broadcast_oneshot_mask, tmpmask);
+
+ if (!cpumask_empty(tmpmask)) {
+ tick_broadcast_init_next_event(tmpmask,
+ tick_next_period);
+ hrtimer_start(bc_hrtimer, tick_next_period, HRTIMER_MODE_ABS_PINNED);
+ bc_next_wakeup = tick_next_period;
+ }
+ }
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
+/*
+ * Use the broadcast function itself to wake up the new broadcast cpu
+ */
+void tick_handover_broadcast_cpu(int *cpup)
+{
+ struct tick_device *td;
+
+ if (*cpup == bc_cpu) {
+ int cpu = cpumask_first(tick_broadcast_oneshot_mask);
+
+ bc_cpu = (cpu < nr_cpu_ids) ? cpu : -1;
+ if (bc_cpu != -1) {
+ td = &per_cpu(tick_cpu_device, bc_cpu);
+ td->evtdev->broadcast(cpumask_of(bc_cpu));
+ }
+ }
+}
/*
* Remove a dead CPU from broadcasting
@@ -868,8 +1001,29 @@ int tick_broadcast_oneshot_active(void)
bool tick_broadcast_oneshot_available(void)
{
struct clock_event_device *bc = tick_broadcast_device.evtdev;
+ bool ret = true;
+ unsigned long flags;
- return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+
+ if (bc) {
+ ret = bc->features & CLOCK_EVT_FEAT_ONESHOT;
+ } else if (!hrtimer_initialized) {
+ /* An alternative to tick_broadcast_device on archs which do not have
+ * an external device
+ */
+ bc_hrtimer = kmalloc(sizeof(*bc_hrtimer), GFP_NOWAIT);
+ if (!bc_hrtimer) {
+ ret = false;
+ goto out;
+ }
+ hrtimer_init(bc_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+ bc_hrtimer->function = handle_broadcast;
+ hrtimer_initialized = 1;
+ }
+
+out: raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ return ret;
}
#endif
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 18e71f7..9e42177 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -46,23 +46,25 @@ extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
extern void tick_resume_oneshot(void);
# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
-extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern int tick_broadcast_oneshot_control(unsigned long reason);
extern void tick_broadcast_switch_to_oneshot(void);
extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
extern int tick_broadcast_oneshot_active(void);
extern void tick_check_oneshot_broadcast(int cpu);
+extern void tick_handover_broadcast_cpu(int *cpup);
bool tick_broadcast_oneshot_available(void);
# else /* BROADCAST */
static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
BUG();
}
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { }
static inline void tick_broadcast_switch_to_oneshot(void) { }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_broadcast_oneshot_active(void) { return 0; }
static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline void tick_handover_broadcast_cpu(int *cpup) {}
static inline bool tick_broadcast_oneshot_available(void) { return true; }
# endif /* !BROADCAST */
@@ -87,7 +89,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
BUG();
}
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
{
^ permalink raw reply related
* [PATCH V5 7/8] cpuidle/powernv: Add "Fast-Sleep" CPU idle state
From: Preeti U Murthy @ 2014-01-15 8:10 UTC (permalink / raw)
To: daniel.lezcano, peterz, fweisbec, agraf, paul.gortmaker, paulus,
mingo, mikey, shangw, rafael.j.wysocki, galak, benh, paulmck,
arnd, linux-pm, rostedt, michael, john.stultz, anton, tglx,
chenhui.zhao, deepthi, r58472, geoff, linux-kernel, srivatsa.bhat,
schwidefsky, svaidy, linuxppc-dev
In-Reply-To: <20140115080555.20446.27238.stgit@preeti.in.ibm.com>
Fast sleep is one of the deep idle states on Power8 in which local timers of
CPUs stop. On PowerPC we do not have an external clock device which can
handle wakeup of such CPUs. Now that we have the support in the tick broadcast
framework for archs that do not sport such a device and the low level support
for fast sleep, enable it in the cpuidle framework on PowerNV.
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---
arch/powerpc/Kconfig | 2 ++
arch/powerpc/kernel/time.c | 2 +-
drivers/cpuidle/cpuidle-powernv.c | 39 +++++++++++++++++++++++++++++++++++++
3 files changed, 42 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b44b52c..cafa788 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -129,6 +129,8 @@ config PPC
select GENERIC_CMOS_UPDATE
select GENERIC_TIME_VSYSCALL_OLD
select GENERIC_CLOCKEVENTS
+ select GENERIC_CLOCKEVENTS_BROADCAST
+ select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select HAVE_MOD_ARCH_SPECIFIC
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 42cb603..d9efd93 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -106,7 +106,7 @@ struct clock_event_device decrementer_clockevent = {
.irq = 0,
.set_next_event = decrementer_set_next_event,
.set_mode = decrementer_set_mode,
- .features = CLOCK_EVT_FEAT_ONESHOT,
+ .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP,
};
EXPORT_SYMBOL(decrementer_clockevent);
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 78fd174..e3aa62f 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -11,6 +11,7 @@
#include <linux/cpuidle.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
+#include <linux/clockchips.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
@@ -49,6 +50,37 @@ static int nap_loop(struct cpuidle_device *dev,
return index;
}
+static int fastsleep_loop(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv,
+ int index)
+{
+ int cpu = dev->cpu;
+ unsigned long old_lpcr = mfspr(SPRN_LPCR);
+ unsigned long new_lpcr;
+
+ new_lpcr = old_lpcr;
+ new_lpcr &= ~(LPCR_MER | LPCR_PECE); /* lpcr[mer] must be 0 */
+
+ /* exit powersave upon external interrupt, but not decrementer
+ * interrupt, Emulate sleep.
+ */
+ new_lpcr |= LPCR_PECE0;
+
+ if (clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu)) {
+ new_lpcr |= LPCR_PECE1;
+ mtspr(SPRN_LPCR, new_lpcr);
+ power7_nap();
+ } else {
+ mtspr(SPRN_LPCR, new_lpcr);
+ power7_sleep();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+ }
+
+ mtspr(SPRN_LPCR, old_lpcr);
+
+ return index;
+}
+
/*
* States for dedicated partition case.
*/
@@ -67,6 +99,13 @@ static struct cpuidle_state powernv_states[] = {
.exit_latency = 10,
.target_residency = 100,
.enter = &nap_loop },
+ { /* Fastsleep */
+ .name = "fastsleep",
+ .desc = "fastsleep",
+ .flags = CPUIDLE_FLAG_TIME_VALID,
+ .exit_latency = 10,
+ .target_residency = 100,
+ .enter = &fastsleep_loop },
};
static int powernv_cpuidle_add_cpu_notifier(struct notifier_block *n,
^ permalink raw reply related
* [PATCH V5 8/8] cpuidle/powernv: Parse device tree to setup idle states
From: Preeti U Murthy @ 2014-01-15 8:10 UTC (permalink / raw)
To: daniel.lezcano, peterz, fweisbec, agraf, paul.gortmaker, paulus,
mingo, mikey, shangw, rafael.j.wysocki, galak, benh, paulmck,
arnd, linux-pm, rostedt, michael, john.stultz, anton, tglx,
chenhui.zhao, deepthi, r58472, geoff, linux-kernel, srivatsa.bhat,
schwidefsky, svaidy, linuxppc-dev
In-Reply-To: <20140115080555.20446.27238.stgit@preeti.in.ibm.com>
Add deep idle states such as nap and fast sleep to the cpuidle state table
only if they are discovered from the device tree during cpuidle initialization.
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
---
drivers/cpuidle/cpuidle-powernv.c | 81 +++++++++++++++++++++++++++++--------
1 file changed, 64 insertions(+), 17 deletions(-)
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index e3aa62f..b01987d 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -12,10 +12,17 @@
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/clockchips.h>
+#include <linux/of.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
+/* Flags and constants used in PowerNV platform */
+
+#define MAX_POWERNV_IDLE_STATES 8
+#define IDLE_USE_INST_NAP 0x00010000 /* Use nap instruction */
+#define IDLE_USE_INST_SLEEP 0x00020000 /* Use sleep instruction */
+
struct cpuidle_driver powernv_idle_driver = {
.name = "powernv_idle",
.owner = THIS_MODULE,
@@ -84,7 +91,7 @@ static int fastsleep_loop(struct cpuidle_device *dev,
/*
* States for dedicated partition case.
*/
-static struct cpuidle_state powernv_states[] = {
+static struct cpuidle_state powernv_states[MAX_POWERNV_IDLE_STATES] = {
{ /* Snooze */
.name = "snooze",
.desc = "snooze",
@@ -92,20 +99,6 @@ static struct cpuidle_state powernv_states[] = {
.exit_latency = 0,
.target_residency = 0,
.enter = &snooze_loop },
- { /* NAP */
- .name = "NAP",
- .desc = "NAP",
- .flags = CPUIDLE_FLAG_TIME_VALID,
- .exit_latency = 10,
- .target_residency = 100,
- .enter = &nap_loop },
- { /* Fastsleep */
- .name = "fastsleep",
- .desc = "fastsleep",
- .flags = CPUIDLE_FLAG_TIME_VALID,
- .exit_latency = 10,
- .target_residency = 100,
- .enter = &fastsleep_loop },
};
static int powernv_cpuidle_add_cpu_notifier(struct notifier_block *n,
@@ -166,19 +159,73 @@ static int powernv_cpuidle_driver_init(void)
return 0;
}
+static int powernv_add_idle_states(void)
+{
+ struct device_node *power_mgt;
+ struct property *prop;
+ int nr_idle_states = 1; /* Snooze */
+ int dt_idle_states;
+ u32 *flags;
+ int i;
+
+ /* Currently we have snooze statically defined */
+
+ power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
+ if (!power_mgt) {
+ pr_warn("opal: PowerMgmt Node not found\n");
+ return nr_idle_states;
+ }
+
+ prop = of_find_property(power_mgt, "ibm,cpu-idle-state-flags", NULL);
+ if (!prop) {
+ pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n");
+ return nr_idle_states;
+ }
+
+ dt_idle_states = prop->length / sizeof(u32);
+ flags = (u32 *) prop->value;
+
+ for (i = 0; i < dt_idle_states; i++) {
+
+ if (flags[i] & IDLE_USE_INST_NAP) {
+ /* Add NAP state */
+ strcpy(powernv_states[nr_idle_states].name, "Nap");
+ strcpy(powernv_states[nr_idle_states].desc, "Nap");
+ powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIME_VALID;
+ powernv_states[nr_idle_states].exit_latency = 10;
+ powernv_states[nr_idle_states].target_residency = 100;
+ powernv_states[nr_idle_states].enter = &nap_loop;
+ nr_idle_states++;
+ }
+
+ if (flags[i] & IDLE_USE_INST_SLEEP) {
+ /* Add FASTSLEEP state */
+ strcpy(powernv_states[nr_idle_states].name, "FastSleep");
+ strcpy(powernv_states[nr_idle_states].desc, "FastSleep");
+ powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIME_VALID;
+ powernv_states[nr_idle_states].exit_latency = 300;
+ powernv_states[nr_idle_states].target_residency = 1000000;
+ powernv_states[nr_idle_states].enter = &fastsleep_loop;
+ nr_idle_states++;
+ }
+ }
+
+ return nr_idle_states;
+}
+
/*
* powernv_idle_probe()
* Choose state table for shared versus dedicated partition
*/
static int powernv_idle_probe(void)
{
-
if (cpuidle_disable != IDLE_NO_OVERRIDE)
return -ENODEV;
if (firmware_has_feature(FW_FEATURE_OPALv3)) {
cpuidle_state_table = powernv_states;
- max_idle_state = ARRAY_SIZE(powernv_states);
+ /* Device tree can indicate more idle states */
+ max_idle_state = powernv_add_idle_states();
} else
return -ENODEV;
^ permalink raw reply related
* Re: [git pull] Please pull powerpc.git merge branch
From: Benjamin Herrenschmidt @ 2014-01-15 10:28 UTC (permalink / raw)
To: Linus Torvalds; +Cc: linuxppc-dev list, Andrew Morton, Linux Kernel list
In-Reply-To: <CA+55aFyfY5kEezwx8-jhgdgOX+EG__v3QRZmGnGstDpUP-UVWQ@mail.gmail.com>
On Wed, 2014-01-15 at 15:05 +0700, Linus Torvalds wrote:
> On Wed, Jan 15, 2014 at 12:01 PM, Benjamin Herrenschmidt
> <benh@kernel.crashing.org> wrote:
> >
> > My original intend was to put it in powerpc-next and then shoot it to
> > stable, but it got a tad annoying (due to churn it needs to be applied
> > at least on rc4 or later while my next is at rc1 and clean that way), so
> > I put it in the merge branch.
>
> Quite frankly, I'll prefer to not merge it now, and then 3.13 will get
> it from stable, when it does things like this.
>
> Partly because it fixes a power-only bug, but potentially changes
> non-power behavior. If it was all in arch/powerpc, I wouldn't mind.
Right, I wasn't too comfortable either. I'll resend the pull request
after the merge window is open.
Cheers,
Ben.
> Linus
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
^ permalink raw reply
* Re: Disable sleep states on P7+
From: Deepthi Dharwar @ 2014-01-15 11:02 UTC (permalink / raw)
To: Steven Pratt; +Cc: linuxppc-dev
In-Reply-To: <52D54B60.4090807@austin.ibm.com>
Hi Steven,
On 01/14/2014 08:06 PM, Steven Pratt wrote:
> I am looking for info on when and how we are able to disable power saving features of current (P7, P7+) chips in order to reduce latency. This is often done in latency sensitive applications when
power consumption is not an issue. On Intel boxes we can disable
P-state frequency changes as well as disabling C-State or sleep state
changes. In fact we can control how deep a sleep the processor can go
into.
I know we have control Dynamic Processor Scaling and Idle Power Savings,
but what states do these really affect? Can I really disable Nap mode
of a processor? If so how? Can I disable even the lightest winkle mode?
Looking for current information (read RHEL 6 and SLES11), future changes
are interesting.
>
On POWERVM platforms idle states currently supported are:
Snooze - reducing thread priority.
Nap
Sleep.
Snooze and Nap can be controlled through in-band kernel mechanisms and
Sleep state through AEM.
Currently you can turn off Idle Power Savings mode and run in dynamic
processor scaling mode. By doing so you will disable entry into Sleep
state on all CPUS.
If you further want to disable NAP, then you could just boot the kernel
with powersave=off. This will disable the entry into any of the idle
state like nap and just reduce the priority of the thread when there is
no work to be done. This is part of cpuidle framework which is available
on SLES 11 SP3 and RHEL7.
In the newer kernels cpuidle framework is adopted for POWERVM platform
but in case if you are using RHEL 6 or SLES 11 SP1/2, then you could use
the ppc64_cpu util and set a high smt-snooze-delay value say 1000.first
#> ppc64_cpu --smt-snooze-delay=1000.
smt-snooze-delay variable potentially delays entry to NAP state.
So if the idle time predicted on a cpu = 1000us and smt-snooze-delay is
set to 100 (which is default value), then on RHEL 6 and SLES 11 SP1/2
kernels cpus would reduce the thread priority and spin for first 100us
and if the cpu continues to be idle further then automatically go to NAP
state for remaining (1000-100us) time.
By setting a very high value, one would always be looping This could
potentially delay ure entry to NAP state and effectively disable entry
into NAP state most of the time.
Please let me know if you have any queries around it.
Regards,
Deepthi
> Steve
>
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@lists.ozlabs.org
> https://lists.ozlabs.org/listinfo/linuxppc-dev
>
^ permalink raw reply
* [PATCH 2/2][v2] powerpc/config: Enable memory driver
From: Prabhakar Kushwaha @ 2014-01-15 12:13 UTC (permalink / raw)
To: arnd, gregkh; +Cc: scottwood, linuxppc-dev, linux-kernel, Prabhakar Kushwaha
As Freescale IFC controller has been moved to driver to driver/memory.
So enable memory driver in powerpc config
Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
---
changes for v2: Sending as it is
arch/powerpc/configs/corenet32_smp_defconfig | 1 +
arch/powerpc/configs/corenet64_smp_defconfig | 1 +
arch/powerpc/configs/mpc85xx_defconfig | 1 +
arch/powerpc/configs/mpc85xx_smp_defconfig | 1 +
4 files changed, 4 insertions(+)
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index bbd794d..087d437 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -142,6 +142,7 @@ CONFIG_RTC_DRV_DS3232=y
CONFIG_RTC_DRV_CMOS=y
CONFIG_UIO=y
CONFIG_STAGING=y
+CONFIG_MEMORY=y
CONFIG_VIRT_DRIVERS=y
CONFIG_FSL_HV_MANAGER=y
CONFIG_EXT2_FS=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index 63508dd..25b03f8 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -129,6 +129,7 @@ CONFIG_EDAC=y
CONFIG_EDAC_MM_EDAC=y
CONFIG_DMADEVICES=y
CONFIG_FSL_DMA=y
+CONFIG_MEMORY=y
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
CONFIG_ISO9660_FS=m
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index d2e0fab..87aad6d 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -213,6 +213,7 @@ CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_CMOS=y
CONFIG_DMADEVICES=y
CONFIG_FSL_DMA=y
+CONFIG_MEMORY=y
# CONFIG_NET_DMA is not set
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index 4cb7b59..d5d6915 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -214,6 +214,7 @@ CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_CMOS=y
CONFIG_DMADEVICES=y
CONFIG_FSL_DMA=y
+CONFIG_MEMORY=y
# CONFIG_NET_DMA is not set
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
--
1.7.9.5
^ permalink raw reply related
* [PATCH 1/2][v2] driver/memory:Move Freescale IFC driver to a common driver
From: Prabhakar Kushwaha @ 2014-01-15 12:13 UTC (permalink / raw)
To: arnd, gregkh; +Cc: scottwood, linuxppc-dev, linux-kernel, Prabhakar Kushwaha
Freescale IFC controller has been used for mpc8xxx. It will be used
for ARM-based SoC as well. This patch moves the driver to driver/memory
and fix the header file includes.
Also remove module_platform_driver() and instead call
platform_driver_register() from subsys_initcall() to make sure this module
has been loaded before MTD partition parsing starts.
Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
---
Changes for v2:
- Move fsl_ifc in driver/memory
arch/powerpc/sysdev/Makefile | 1 -
drivers/memory/Makefile | 1 +
{arch/powerpc/sysdev => drivers/memory}/fsl_ifc.c | 8 ++++++--
drivers/mtd/nand/fsl_ifc_nand.c | 2 +-
.../include/asm => include/linux}/fsl_ifc.h | 0
5 files changed, 8 insertions(+), 4 deletions(-)
rename {arch/powerpc/sysdev => drivers/memory}/fsl_ifc.c (98%)
rename {arch/powerpc/include/asm => include/linux}/fsl_ifc.h (100%)
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index f67ac90..afbcc37 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -21,7 +21,6 @@ obj-$(CONFIG_FSL_SOC) += fsl_soc.o fsl_mpic_err.o
obj-$(CONFIG_FSL_PCI) += fsl_pci.o $(fsl-msi-obj-y)
obj-$(CONFIG_FSL_PMC) += fsl_pmc.o
obj-$(CONFIG_FSL_LBC) += fsl_lbc.o
-obj-$(CONFIG_FSL_IFC) += fsl_ifc.o
obj-$(CONFIG_FSL_GTM) += fsl_gtm.o
obj-$(CONFIG_FSL_85XX_CACHE_SRAM) += fsl_85xx_l2ctlr.o fsl_85xx_cache_sram.o
obj-$(CONFIG_SIMPLE_GPIO) += simple_gpio.o
diff --git a/drivers/memory/Makefile b/drivers/memory/Makefile
index 969d923..f2bf25c 100644
--- a/drivers/memory/Makefile
+++ b/drivers/memory/Makefile
@@ -6,6 +6,7 @@ ifeq ($(CONFIG_DDR),y)
obj-$(CONFIG_OF) += of_memory.o
endif
obj-$(CONFIG_TI_EMIF) += emif.o
+obj-$(CONFIG_FSL_IFC) += fsl_ifc.o
obj-$(CONFIG_MVEBU_DEVBUS) += mvebu-devbus.o
obj-$(CONFIG_TEGRA20_MC) += tegra20-mc.o
obj-$(CONFIG_TEGRA30_MC) += tegra30-mc.o
diff --git a/arch/powerpc/sysdev/fsl_ifc.c b/drivers/memory/fsl_ifc.c
similarity index 98%
rename from arch/powerpc/sysdev/fsl_ifc.c
rename to drivers/memory/fsl_ifc.c
index d7fc722..135a950 100644
--- a/arch/powerpc/sysdev/fsl_ifc.c
+++ b/drivers/memory/fsl_ifc.c
@@ -30,8 +30,8 @@
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/platform_device.h>
+#include <linux/fsl_ifc.h>
#include <asm/prom.h>
-#include <asm/fsl_ifc.h>
struct fsl_ifc_ctrl *fsl_ifc_ctrl_dev;
EXPORT_SYMBOL(fsl_ifc_ctrl_dev);
@@ -299,7 +299,11 @@ static struct platform_driver fsl_ifc_ctrl_driver = {
.remove = fsl_ifc_ctrl_remove,
};
-module_platform_driver(fsl_ifc_ctrl_driver);
+static int __init fsl_ifc_init(void)
+{
+ return platform_driver_register(&fsl_ifc_ctrl_driver);
+}
+subsys_initcall(fsl_ifc_init);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Freescale Semiconductor");
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index 4335577..865b323 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -30,7 +30,7 @@
#include <linux/mtd/nand.h>
#include <linux/mtd/partitions.h>
#include <linux/mtd/nand_ecc.h>
-#include <asm/fsl_ifc.h>
+#include <linux/fsl_ifc.h>
#define FSL_IFC_V1_1_0 0x01010000
#define ERR_BYTE 0xFF /* Value returned for read
diff --git a/arch/powerpc/include/asm/fsl_ifc.h b/include/linux/fsl_ifc.h
similarity index 100%
rename from arch/powerpc/include/asm/fsl_ifc.h
rename to include/linux/fsl_ifc.h
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH 1/2][v2] driver/memory:Move Freescale IFC driver to a common driver
From: Arnd Bergmann @ 2014-01-15 13:31 UTC (permalink / raw)
To: Prabhakar Kushwaha; +Cc: scottwood, gregkh, linuxppc-dev, linux-kernel
In-Reply-To: <1389788003-25442-1-git-send-email-prabhakar@freescale.com>
On Wednesday 15 January 2014, Prabhakar Kushwaha wrote:
> Freescale IFC controller has been used for mpc8xxx. It will be used
> for ARM-based SoC as well. This patch moves the driver to driver/memory
> and fix the header file includes.
>
> Also remove module_platform_driver() and instead call
> platform_driver_register() from subsys_initcall() to make sure this module
> has been loaded before MTD partition parsing starts.
>
> Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
provided that you also move the binding from powerpc/fsl/ifc.txt to
memory/fsl-ifc.txt.
^ permalink raw reply
* [PATCH] powerpc: mm: fix mmap errno when MAP_FIXED is set and mapping exceeds the allowed address space
From: Jerome Marchand @ 2014-01-15 15:27 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras
Cc: Jerome Marchand, linuxppc-dev, linux-kernel
According to Posix, if MAP_FIXED is specified mmap shall set ENOMEM if
the requested mapping exceeds the allowed range for address space of
the process. The generic code set it right, but the specific powerpc
slice_get_unmapped_area() function currently returns -EINVAL in that
case.
This patch corrects it.
Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
---
arch/powerpc/mm/slice.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 7ce9cf3..b0c75cc 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -408,7 +408,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
if (fixed && (addr & ((1ul << pshift) - 1)))
return -EINVAL;
if (fixed && addr > (mm->task_size - len))
- return -EINVAL;
+ return -ENOMEM;
/* If hint, make sure it matches our alignment restrictions */
if (!fixed && addr) {
--
1.7.7.6
^ permalink raw reply related
* Re: [PATCH V5 0/8] cpuidle/ppc: Enable deep idle states on PowerNV
From: Paul Gortmaker @ 2014-01-15 15:29 UTC (permalink / raw)
To: Preeti U Murthy, daniel.lezcano, peterz, fweisbec, agraf, paulus,
mingo, mikey, shangw, rafael.j.wysocki, galak, benh, paulmck,
arnd, linux-pm, rostedt, michael, john.stultz, anton, tglx,
chenhui.zhao, deepthi, r58472, geoff, linux-kernel, srivatsa.bhat,
schwidefsky, svaidy, linuxppc-dev
In-Reply-To: <20140115080555.20446.27238.stgit@preeti.in.ibm.com>
On 14-01-15 03:07 AM, Preeti U Murthy wrote:
[...]
>
> This patchset is based on mainline commit-id:8ae516aa8b8161254d3, and the
I figured I'd give this a quick sanity build test for a few
configs, but v3.13-rc1-141-g8ae516aa8b81 seems too old; Ben's
ppc next branch is at v3.13-rc1-160-gfac515db4520 and it fails:
-------
$ git am ppc-idle
Applying: powerpc: Free up the slot of PPC_MSG_CALL_FUNC_SINGLE IPI message
Applying: powerpc: Implement tick broadcast IPI as a fixed IPI message
Applying: cpuidle/ppc: Split timer_interrupt() into timer handling and interrupt handling routines
error: patch failed: arch/powerpc/kernel/time.c:510
error: arch/powerpc/kernel/time.c: patch does not apply
Patch failed at 0003 cpuidle/ppc: Split timer_interrupt() into timer handling and interrupt handling routines
The copy of the patch that failed is found in:
/home/paul/git/linux-head/.git/rebase-apply/patch
When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".
$ dry-run
patching file arch/powerpc/kernel/time.c
Hunk #3 FAILED at 544.
Hunk #4 FAILED at 554.
Hunk #5 succeeded at 862 (offset 12 lines).
2 out of 5 hunks FAILED -- saving rejects to file arch/powerpc/kernel/time.c.rej
--------
It appears to conflict with:
commit 0215f7d8c53fb192cd4491ede0ece5cca6b5db57
Author: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue Jan 14 17:11:39 2014 +1100
powerpc: Fix races with irq_work
Paul.
--
> cpuidle driver for powernv posted by Deepthi Dharwar:
> https://lkml.org/lkml/2014/1/14/172
>
>
> Changes in V5:
> -------------
> The primary change in this version is in Patch[6/8].
> As per the discussions in V4 posting of this patchset, it was decided to
> refine handling the wakeup of CPUs in fast-sleep by doing the following:
>
> 1. In V4, a polling mechanism was used by the CPU handling broadcast to
> find out the time of next wakeup of the CPUs in deep idle states. V5 avoids
> polling by a way described under PATCH[6/8] in this patchset.
>
> 2. The mechanism of broadcast handling of CPUs in deep idle in the absence of an
> external wakeup device should be generic and not arch specific code. Hence in this
> version this functionality has been integrated into the tick broadcast framework in
> the kernel unlike before where it was handled in powerpc specific code.
>
> 3. It was suggested that the "broadcast cpu" can be the time keeping cpu
> itself. However this has challenges of its own:
>
> a. The time keeping cpu need not exist when all cpus are idle. Hence there
> are phases in time when time keeping cpu is absent. But for the use case that
> this patchset is trying to address we rely on the presence of a broadcast cpu
> all the time.
>
> b. The nomination and un-assignment of the time keeping cpu is not protected
> by a lock today and need not be as well since such is its use case in the
> kernel. However we would need locks if we double up the time keeping cpu as the
> broadcast cpu.
>
> Hence the broadcast cpu is independent of the time-keeping cpu. However PATCH[6/8]
> proposes a simpler solution to pick a broadcast cpu in this version.
>
>
>
> Changes in V4:
> -------------
> https://lkml.org/lkml/2013/11/29/97
>
> 1. Add Fast Sleep CPU idle state on PowerNV.
>
> 2. Add the required context management for Fast Sleep and the call to OPAL
> to synchronize time base after wakeup from fast sleep.
>
> 4. Add parsing of CPU idle states from the device tree to populate the
> cpuidle
> state table.
>
> 5. Rename ambiguous functions in the code around waking up of CPUs from fast
> sleep.
>
> 6. Fixed a bug in re-programming of the hrtimer that is queued to wakeup the
> CPUs in fast sleep and modified Changelogs.
>
> 7. Added the ARCH_HAS_TICK_BROADCAST option. This signifies that we have a
> arch specific function to perform broadcast.
>
>
> Changes in V3:
> -------------
> http://thread.gmane.org/gmane.linux.power-management.general/38113
>
> 1. Fix the way in which a broadcast ipi is handled on the idling cpus. Timer
> handling on a broadcast ipi is being done now without missing out any timer
> stats generation.
>
> 2. Fix a bug in the programming of the hrtimer meant to do broadcast. Program
> it to trigger at the earlier of a "broadcast period", and the next wakeup
> event. By introducing the "broadcast period" as the maximum period after
> which the broadcast hrtimer can fire, we ensure that we do not miss
> wakeups in corner cases.
>
> 3. On hotplug of a broadcast cpu, trigger the hrtimer meant to do broadcast
> to fire immediately on the new broadcast cpu. This will ensure we do not miss
> doing a broadcast pending in the nearest future.
>
> 4. Change the type of allocation from GFP_KERNEL to GFP_NOWAIT while
> initializing bc_hrtimer since we are in an atomic context and cannot sleep.
>
> 5. Use the broadcast ipi to wakeup the newly nominated broadcast cpu on
> hotplug of the old instead of smp_call_function_single(). This is because we
> are interrupt disabled at this point and should not be using
> smp_call_function_single or its children in this context to send an ipi.
>
> 6. Move GENERIC_CLOCKEVENTS_BROADCAST to arch/powerpc/Kconfig.
>
> 7. Fix coding style issues.
>
>
> Changes in V2:
> -------------
> https://lkml.org/lkml/2013/8/14/239
>
> 1. Dynamically pick a broadcast CPU, instead of having a dedicated one.
> 2. Remove the constraint of having to disable tickless idle on the broadcast
> CPU by queueing a hrtimer dedicated to do broadcast.
>
>
>
> V1 posting: https://lkml.org/lkml/2013/7/25/740.
>
> 1. Added the infrastructure to wakeup CPUs in deep idle states in which the
> local timers stop.
> ---
>
> Preeti U Murthy (4):
> cpuidle/ppc: Split timer_interrupt() into timer handling and interrupt handling routines
> time/cpuidle: Support in tick broadcast framework in the absence of external clock device
> cpuidle/powernv: Add "Fast-Sleep" CPU idle state
> cpuidle/powernv: Parse device tree to setup idle states
>
> Srivatsa S. Bhat (2):
> powerpc: Free up the slot of PPC_MSG_CALL_FUNC_SINGLE IPI message
> powerpc: Implement tick broadcast IPI as a fixed IPI message
>
> Vaidyanathan Srinivasan (2):
> powernv/cpuidle: Add context management for Fast Sleep
> powermgt: Add OPAL call to resync timebase on wakeup
>
>
> arch/powerpc/Kconfig | 2
> arch/powerpc/include/asm/opal.h | 2
> arch/powerpc/include/asm/processor.h | 1
> arch/powerpc/include/asm/smp.h | 2
> arch/powerpc/include/asm/time.h | 1
> arch/powerpc/kernel/exceptions-64s.S | 10 +
> arch/powerpc/kernel/idle_power7.S | 90 +++++++++--
> arch/powerpc/kernel/smp.c | 23 ++-
> arch/powerpc/kernel/time.c | 80 ++++++----
> arch/powerpc/platforms/cell/interrupt.c | 2
> arch/powerpc/platforms/powernv/opal-wrappers.S | 1
> arch/powerpc/platforms/ps3/smp.c | 2
> drivers/cpuidle/cpuidle-powernv.c | 106 ++++++++++++-
> include/linux/clockchips.h | 4 -
> kernel/time/clockevents.c | 9 +
> kernel/time/tick-broadcast.c | 192 ++++++++++++++++++++++--
> kernel/time/tick-internal.h | 8 +
> 17 files changed, 434 insertions(+), 101 deletions(-)
>
^ permalink raw reply
* Please pull 'next' branch of 5xxx tree
From: Anatolij Gustschin @ 2014-01-15 21:18 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: linuxppc-dev
Hi Ben !
please pull mpc5xxx patches for v3.14:
Switch mpc512x to the common clock framework and adapt mpc512x
drivers to use the new clock driver. Old PPC_CLOCK code is
removed entirely since there are no users any more.
All these patches have been in linux-next for more then
two weeks now.
Thanks,
Anatolij
The following changes since commit dece8ada993e1764a115bdff0f1effffaa5fc8dc:
Merge branch 'merge' into next (2013-12-30 15:19:31 +1100)
are available in the git repository at:
git://git.denx.de/linux-2.6-agust.git next
for you to fetch changes up to bc75059422338197ce487d338ac9c898761e1e61:
powerpc/512x: dts: add MPC5125 clock specs (2014-01-12 18:59:50 +0100)
----------------------------------------------------------------
Gerhard Sittig (20):
dts: mpc512x: introduce dt-bindings/clock/ header
dts: mpc512x: add clock related device tree specs
clk: mpc512x: introduce COMMON_CLK for MPC512x (disabled)
clk: mpc512x: add backwards compat to the CCF code
dts: mpc512x: add clock specs for client lookups
clk: mpc5xxx: switch to COMMON_CLK, retire PPC_CLOCK
spi: mpc512x: adjust to OF based clock lookup
serial: mpc512x: adjust for OF based clock lookup
serial: mpc512x: setup the PSC FIFO clock as well
USB: fsl-mph-dr-of: adjust for OF based clock lookup
mtd: mpc5121_nfc: adjust for OF based clock lookup
fsl-viu: adjust for OF based clock lookup
net: can: mscan: adjust to common clock support for mpc512x
net: can: mscan: remove non-CCF code for MPC512x
powerpc/mpc512x: improve DIU related clock setup
clk: mpc512x: remove migration support workarounds
powerpc/512x: clk: minor comment updates
powerpc/512x: clk: enforce even SDHC divider values
powerpc/512x: clk: support MPC5121/5123/5125 SoC variants
powerpc/512x: dts: add MPC5125 clock specs
arch/powerpc/Kconfig | 5 -
arch/powerpc/boot/dts/ac14xx.dts | 7 +
arch/powerpc/boot/dts/mpc5121.dtsi | 113 ++-
arch/powerpc/boot/dts/mpc5125twr.dts | 53 +-
arch/powerpc/include/asm/clk_interface.h | 20 -
arch/powerpc/include/asm/mpc5121.h | 7 +-
arch/powerpc/kernel/Makefile | 1 -
arch/powerpc/kernel/clock.c | 82 --
arch/powerpc/platforms/512x/Kconfig | 2 +-
arch/powerpc/platforms/512x/Makefile | 3 +-
arch/powerpc/platforms/512x/clock-commonclk.c | 1221 +++++++++++++++++++++++++
arch/powerpc/platforms/512x/clock.c | 754 ---------------
arch/powerpc/platforms/512x/mpc512x_shared.c | 169 ++--
arch/powerpc/platforms/52xx/Kconfig | 2 +-
drivers/media/platform/fsl-viu.c | 2 +-
drivers/mtd/nand/mpc5121_nfc.c | 2 +-
drivers/net/can/mscan/mpc5xxx_can.c | 270 +++---
drivers/spi/spi-mpc512x-psc.c | 26 +-
drivers/tty/serial/mpc52xx_uart.c | 90 +-
drivers/usb/host/fsl-mph-dr-of.c | 13 +-
include/dt-bindings/clock/mpc512x-clock.h | 76 ++
include/linux/clk-provider.h | 16 +
22 files changed, 1840 insertions(+), 1094 deletions(-)
delete mode 100644 arch/powerpc/include/asm/clk_interface.h
delete mode 100644 arch/powerpc/kernel/clock.c
create mode 100644 arch/powerpc/platforms/512x/clock-commonclk.c
delete mode 100644 arch/powerpc/platforms/512x/clock.c
create mode 100644 include/dt-bindings/clock/mpc512x-clock.h
^ permalink raw reply
* [PATCH] drivers/tty/hvc: don't use module_init in non-modular hyp. console code
From: Paul Gortmaker @ 2014-01-15 21:24 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: Paul Gortmaker, linuxppc-dev, linux-kernel, Richard Weinberger
The HVC_OPAL/RTAS/UDBG options are all bool, and hence their support
is either present or absent. It will never be modular, so using
module_init as an alias for __initcall is rather misleading.
Fix this up now, so that we can relocate module_init from
init.h into module.h in the future. If we don't do this, we'd
have to add module.h to obviously non-modular code, and that
would be a worse thing.
Note that direct use of __initcall is discouraged, vs. one
of the priority categorized subgroups. As __initcall gets
mapped onto device_initcall, our use of device_initcall
directly in this change means that the runtime impact is
zero -- it will remain at level 6 in initcall ordering.
Also the __exitcall functions have been outright deleted since
they are only ever of interest to UML, and UML will never be
using any of this code.
Cc: Richard Weinberger <richard@nod.at>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 6496872e2e47..b01659bd4f7c 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -255,13 +255,7 @@ static int __init hvc_opal_init(void)
/* Register as a vio device to receive callbacks */
return platform_driver_register(&hvc_opal_driver);
}
-module_init(hvc_opal_init);
-
-static void __exit hvc_opal_exit(void)
-{
- platform_driver_unregister(&hvc_opal_driver);
-}
-module_exit(hvc_opal_exit);
+device_initcall(hvc_opal_init);
static void udbg_opal_putc(char c)
{
diff --git a/drivers/tty/hvc/hvc_rtas.c b/drivers/tty/hvc/hvc_rtas.c
index 0069bb86ba49..08c87920b74a 100644
--- a/drivers/tty/hvc/hvc_rtas.c
+++ b/drivers/tty/hvc/hvc_rtas.c
@@ -102,17 +102,7 @@ static int __init hvc_rtas_init(void)
return 0;
}
-module_init(hvc_rtas_init);
-
-/* This will tear down the tty portion of the driver */
-static void __exit hvc_rtas_exit(void)
-{
- /* Really the fun isn't over until the worker thread breaks down and
- * the tty cleans up */
- if (hvc_rtas_dev)
- hvc_remove(hvc_rtas_dev);
-}
-module_exit(hvc_rtas_exit);
+device_initcall(hvc_rtas_init);
/* This will happen prior to module init. There is no tty at this time? */
static int __init hvc_rtas_console_init(void)
diff --git a/drivers/tty/hvc/hvc_udbg.c b/drivers/tty/hvc/hvc_udbg.c
index 72228276fe31..9cf573d06a29 100644
--- a/drivers/tty/hvc/hvc_udbg.c
+++ b/drivers/tty/hvc/hvc_udbg.c
@@ -80,14 +80,7 @@ static int __init hvc_udbg_init(void)
return 0;
}
-module_init(hvc_udbg_init);
-
-static void __exit hvc_udbg_exit(void)
-{
- if (hvc_udbg_dev)
- hvc_remove(hvc_udbg_dev);
-}
-module_exit(hvc_udbg_exit);
+device_initcall(hvc_udbg_init);
static int __init hvc_udbg_console_init(void)
{
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 636c9baad7a5..2dc2831840ca 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -561,18 +561,7 @@ static int __init xen_hvc_init(void)
#endif
return r;
}
-
-static void __exit xen_hvc_fini(void)
-{
- struct xencons_info *entry, *next;
-
- if (list_empty(&xenconsoles))
- return;
-
- list_for_each_entry_safe(entry, next, &xenconsoles, list) {
- xen_console_remove(entry);
- }
-}
+device_initcall(xen_hvc_init);
static int xen_cons_init(void)
{
@@ -598,10 +587,6 @@ static int xen_cons_init(void)
hvc_instantiate(HVC_COOKIE, 0, ops);
return 0;
}
-
-
-module_init(xen_hvc_init);
-module_exit(xen_hvc_fini);
console_initcall(xen_cons_init);
#ifdef CONFIG_EARLY_PRINTK
--
1.8.5.2
^ permalink raw reply related
* [PATCH v2] drivers/tty/hvc: don't use module_init in non-modular hyp. console code
From: Paul Gortmaker @ 2014-01-15 21:35 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: Konrad Rzeszutek Wilk, Richard Weinberger, linux-kernel,
Paul Gortmaker, David Vrabel, xen-devel, Boris Ostrovsky,
linuxppc-dev
The HVC_OPAL/RTAS/UDBG/XEN options are all bool, and hence their support
is either present or absent. It will never be modular, so using
module_init as an alias for __initcall is rather misleading.
Fix this up now, so that we can relocate module_init from
init.h into module.h in the future. If we don't do this, we'd
have to add module.h to obviously non-modular code, and that
would be a worse thing.
Note that direct use of __initcall is discouraged, vs. one
of the priority categorized subgroups. As __initcall gets
mapped onto device_initcall, our use of device_initcall
directly in this change means that the runtime impact is
zero -- it will remain at level 6 in initcall ordering.
Also the __exitcall functions have been outright deleted since
they are only ever of interest to UML, and UML will never be
using any of this code.
Cc: Richard Weinberger <richard@nod.at>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
---
[v2: unchanged; just added xen guys to Cc list, as hvc_xen isnt
hooked into the MAINTAINERS file as of yet, so I forgot them.]
diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 6496872e2e47..b01659bd4f7c 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -255,13 +255,7 @@ static int __init hvc_opal_init(void)
/* Register as a vio device to receive callbacks */
return platform_driver_register(&hvc_opal_driver);
}
-module_init(hvc_opal_init);
-
-static void __exit hvc_opal_exit(void)
-{
- platform_driver_unregister(&hvc_opal_driver);
-}
-module_exit(hvc_opal_exit);
+device_initcall(hvc_opal_init);
static void udbg_opal_putc(char c)
{
diff --git a/drivers/tty/hvc/hvc_rtas.c b/drivers/tty/hvc/hvc_rtas.c
index 0069bb86ba49..08c87920b74a 100644
--- a/drivers/tty/hvc/hvc_rtas.c
+++ b/drivers/tty/hvc/hvc_rtas.c
@@ -102,17 +102,7 @@ static int __init hvc_rtas_init(void)
return 0;
}
-module_init(hvc_rtas_init);
-
-/* This will tear down the tty portion of the driver */
-static void __exit hvc_rtas_exit(void)
-{
- /* Really the fun isn't over until the worker thread breaks down and
- * the tty cleans up */
- if (hvc_rtas_dev)
- hvc_remove(hvc_rtas_dev);
-}
-module_exit(hvc_rtas_exit);
+device_initcall(hvc_rtas_init);
/* This will happen prior to module init. There is no tty at this time? */
static int __init hvc_rtas_console_init(void)
diff --git a/drivers/tty/hvc/hvc_udbg.c b/drivers/tty/hvc/hvc_udbg.c
index 72228276fe31..9cf573d06a29 100644
--- a/drivers/tty/hvc/hvc_udbg.c
+++ b/drivers/tty/hvc/hvc_udbg.c
@@ -80,14 +80,7 @@ static int __init hvc_udbg_init(void)
return 0;
}
-module_init(hvc_udbg_init);
-
-static void __exit hvc_udbg_exit(void)
-{
- if (hvc_udbg_dev)
- hvc_remove(hvc_udbg_dev);
-}
-module_exit(hvc_udbg_exit);
+device_initcall(hvc_udbg_init);
static int __init hvc_udbg_console_init(void)
{
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 636c9baad7a5..2dc2831840ca 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -561,18 +561,7 @@ static int __init xen_hvc_init(void)
#endif
return r;
}
-
-static void __exit xen_hvc_fini(void)
-{
- struct xencons_info *entry, *next;
-
- if (list_empty(&xenconsoles))
- return;
-
- list_for_each_entry_safe(entry, next, &xenconsoles, list) {
- xen_console_remove(entry);
- }
-}
+device_initcall(xen_hvc_init);
static int xen_cons_init(void)
{
@@ -598,10 +587,6 @@ static int xen_cons_init(void)
hvc_instantiate(HVC_COOKIE, 0, ops);
return 0;
}
-
-
-module_init(xen_hvc_init);
-module_exit(xen_hvc_fini);
console_initcall(xen_cons_init);
#ifdef CONFIG_EARLY_PRINTK
--
1.8.5.2
^ permalink raw reply related
* Re: powerpc/powernv: Call OPAL sync before kexec'ing
From: Michael Ellerman @ 2014-01-16 0:58 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: linuxppc-dev list
In-Reply-To: <1389765724.6933.78.camel@pasglop>
On Wed, 2014-01-15 at 17:02 +1100, Benjamin Herrenschmidt wrote:
> From: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
>
> Its possible that OPAL may be writing to host memory during
> kexec (like dump retrieve scenario). In this situation we might
> end up corrupting host memory.
Are we happy with that happening during kdump? (which doesn't call any of the
shutdown paths)
cheers
^ permalink raw reply
* Re: powerpc/powernv: Call OPAL sync before kexec'ing
From: Benjamin Herrenschmidt @ 2014-01-16 1:02 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev list
In-Reply-To: <1389833903.31288.1.camel@concordia>
On Thu, 2014-01-16 at 11:58 +1100, Michael Ellerman wrote:
> On Wed, 2014-01-15 at 17:02 +1100, Benjamin Herrenschmidt wrote:
> > From: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
> >
> > Its possible that OPAL may be writing to host memory during
> > kexec (like dump retrieve scenario). In this situation we might
> > end up corrupting host memory.
>
> Are we happy with that happening during kdump? (which doesn't call any of the
> shutdown paths)
Obviously not ... There's a problem there. Not sure what the right fix
is. Might need some ifdef KDUMP to take over in the new driver.
Ben.
^ permalink raw reply
* Re: [PATCH V5 0/8] cpuidle/ppc: Enable deep idle states on PowerNV
From: Preeti U Murthy @ 2014-01-16 2:17 UTC (permalink / raw)
To: Paul Gortmaker
Cc: daniel.lezcano, peterz, fweisbec, paulus, mingo, mikey, shangw,
rafael.j.wysocki, agraf, paulmck, arnd, linux-pm, rostedt,
michael, john.stultz, anton, tglx, chenhui.zhao, deepthi, r58472,
geoff, linux-kernel, srivatsa.bhat, schwidefsky, linuxppc-dev
In-Reply-To: <52D6A971.4040301@windriver.com>
Hi Paul,
On 01/15/2014 08:59 PM, Paul Gortmaker wrote:
> On 14-01-15 03:07 AM, Preeti U Murthy wrote:
>
> [...]
>
>>
>> This patchset is based on mainline commit-id:8ae516aa8b8161254d3, and the
>
> I figured I'd give this a quick sanity build test for a few
> configs, but v3.13-rc1-141-g8ae516aa8b81 seems too old; Ben's
> ppc next branch is at v3.13-rc1-160-gfac515db4520 and it fails:
>
> -------
> $ git am ppc-idle
> Applying: powerpc: Free up the slot of PPC_MSG_CALL_FUNC_SINGLE IPI message
> Applying: powerpc: Implement tick broadcast IPI as a fixed IPI message
> Applying: cpuidle/ppc: Split timer_interrupt() into timer handling and interrupt handling routines
> error: patch failed: arch/powerpc/kernel/time.c:510
> error: arch/powerpc/kernel/time.c: patch does not apply
> Patch failed at 0003 cpuidle/ppc: Split timer_interrupt() into timer handling and interrupt handling routines
> The copy of the patch that failed is found in:
> /home/paul/git/linux-head/.git/rebase-apply/patch
> When you have resolved this problem, run "git am --continue".
> If you prefer to skip this patch, run "git am --skip" instead.
> To restore the original branch and stop patching, run "git am --abort".
> $ dry-run
> patching file arch/powerpc/kernel/time.c
> Hunk #3 FAILED at 544.
> Hunk #4 FAILED at 554.
> Hunk #5 succeeded at 862 (offset 12 lines).
> 2 out of 5 hunks FAILED -- saving rejects to file arch/powerpc/kernel/time.c.rej
> --------
>
> It appears to conflict with:
>
> commit 0215f7d8c53fb192cd4491ede0ece5cca6b5db57
> Author: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Date: Tue Jan 14 17:11:39 2014 +1100
>
> powerpc: Fix races with irq_work
>
>
Thanks for the build test.I will base it on the mainline at the latest
commit as well as on Ben's tree and send out this patchset.
Regards
Preeti U Murthy
> Paul.
> --
>
>> cpuidle driver for powernv posted by Deepthi Dharwar:
>> https://lkml.org/lkml/2014/1/14/172
>>
>>
>> Changes in V5:
>> -------------
>> The primary change in this version is in Patch[6/8].
>> As per the discussions in V4 posting of this patchset, it was decided to
>> refine handling the wakeup of CPUs in fast-sleep by doing the following:
>>
>> 1. In V4, a polling mechanism was used by the CPU handling broadcast to
>> find out the time of next wakeup of the CPUs in deep idle states. V5 avoids
>> polling by a way described under PATCH[6/8] in this patchset.
>>
>> 2. The mechanism of broadcast handling of CPUs in deep idle in the absence of an
>> external wakeup device should be generic and not arch specific code. Hence in this
>> version this functionality has been integrated into the tick broadcast framework in
>> the kernel unlike before where it was handled in powerpc specific code.
>>
>> 3. It was suggested that the "broadcast cpu" can be the time keeping cpu
>> itself. However this has challenges of its own:
>>
>> a. The time keeping cpu need not exist when all cpus are idle. Hence there
>> are phases in time when time keeping cpu is absent. But for the use case that
>> this patchset is trying to address we rely on the presence of a broadcast cpu
>> all the time.
>>
>> b. The nomination and un-assignment of the time keeping cpu is not protected
>> by a lock today and need not be as well since such is its use case in the
>> kernel. However we would need locks if we double up the time keeping cpu as the
>> broadcast cpu.
>>
>> Hence the broadcast cpu is independent of the time-keeping cpu. However PATCH[6/8]
>> proposes a simpler solution to pick a broadcast cpu in this version.
>>
>>
>>
>> Changes in V4:
>> -------------
>> https://lkml.org/lkml/2013/11/29/97
>>
>> 1. Add Fast Sleep CPU idle state on PowerNV.
>>
>> 2. Add the required context management for Fast Sleep and the call to OPAL
>> to synchronize time base after wakeup from fast sleep.
>>
>> 4. Add parsing of CPU idle states from the device tree to populate the
>> cpuidle
>> state table.
>>
>> 5. Rename ambiguous functions in the code around waking up of CPUs from fast
>> sleep.
>>
>> 6. Fixed a bug in re-programming of the hrtimer that is queued to wakeup the
>> CPUs in fast sleep and modified Changelogs.
>>
>> 7. Added the ARCH_HAS_TICK_BROADCAST option. This signifies that we have a
>> arch specific function to perform broadcast.
>>
>>
>> Changes in V3:
>> -------------
>> http://thread.gmane.org/gmane.linux.power-management.general/38113
>>
>> 1. Fix the way in which a broadcast ipi is handled on the idling cpus. Timer
>> handling on a broadcast ipi is being done now without missing out any timer
>> stats generation.
>>
>> 2. Fix a bug in the programming of the hrtimer meant to do broadcast. Program
>> it to trigger at the earlier of a "broadcast period", and the next wakeup
>> event. By introducing the "broadcast period" as the maximum period after
>> which the broadcast hrtimer can fire, we ensure that we do not miss
>> wakeups in corner cases.
>>
>> 3. On hotplug of a broadcast cpu, trigger the hrtimer meant to do broadcast
>> to fire immediately on the new broadcast cpu. This will ensure we do not miss
>> doing a broadcast pending in the nearest future.
>>
>> 4. Change the type of allocation from GFP_KERNEL to GFP_NOWAIT while
>> initializing bc_hrtimer since we are in an atomic context and cannot sleep.
>>
>> 5. Use the broadcast ipi to wakeup the newly nominated broadcast cpu on
>> hotplug of the old instead of smp_call_function_single(). This is because we
>> are interrupt disabled at this point and should not be using
>> smp_call_function_single or its children in this context to send an ipi.
>>
>> 6. Move GENERIC_CLOCKEVENTS_BROADCAST to arch/powerpc/Kconfig.
>>
>> 7. Fix coding style issues.
>>
>>
>> Changes in V2:
>> -------------
>> https://lkml.org/lkml/2013/8/14/239
>>
>> 1. Dynamically pick a broadcast CPU, instead of having a dedicated one.
>> 2. Remove the constraint of having to disable tickless idle on the broadcast
>> CPU by queueing a hrtimer dedicated to do broadcast.
>>
>>
>>
>> V1 posting: https://lkml.org/lkml/2013/7/25/740.
>>
>> 1. Added the infrastructure to wakeup CPUs in deep idle states in which the
>> local timers stop.
>> ---
>>
>> Preeti U Murthy (4):
>> cpuidle/ppc: Split timer_interrupt() into timer handling and interrupt handling routines
>> time/cpuidle: Support in tick broadcast framework in the absence of external clock device
>> cpuidle/powernv: Add "Fast-Sleep" CPU idle state
>> cpuidle/powernv: Parse device tree to setup idle states
>>
>> Srivatsa S. Bhat (2):
>> powerpc: Free up the slot of PPC_MSG_CALL_FUNC_SINGLE IPI message
>> powerpc: Implement tick broadcast IPI as a fixed IPI message
>>
>> Vaidyanathan Srinivasan (2):
>> powernv/cpuidle: Add context management for Fast Sleep
>> powermgt: Add OPAL call to resync timebase on wakeup
>>
>>
>> arch/powerpc/Kconfig | 2
>> arch/powerpc/include/asm/opal.h | 2
>> arch/powerpc/include/asm/processor.h | 1
>> arch/powerpc/include/asm/smp.h | 2
>> arch/powerpc/include/asm/time.h | 1
>> arch/powerpc/kernel/exceptions-64s.S | 10 +
>> arch/powerpc/kernel/idle_power7.S | 90 +++++++++--
>> arch/powerpc/kernel/smp.c | 23 ++-
>> arch/powerpc/kernel/time.c | 80 ++++++----
>> arch/powerpc/platforms/cell/interrupt.c | 2
>> arch/powerpc/platforms/powernv/opal-wrappers.S | 1
>> arch/powerpc/platforms/ps3/smp.c | 2
>> drivers/cpuidle/cpuidle-powernv.c | 106 ++++++++++++-
>> include/linux/clockchips.h | 4 -
>> kernel/time/clockevents.c | 9 +
>> kernel/time/tick-broadcast.c | 192 ++++++++++++++++++++++--
>> kernel/time/tick-internal.h | 8 +
>> 17 files changed, 434 insertions(+), 101 deletions(-)
>>
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@lists.ozlabs.org
> https://lists.ozlabs.org/listinfo/linuxppc-dev
>
^ permalink raw reply
* Re: [PATCH 3/3] powerpc/fsl: Use the new interface to save or restore registers
From: Scott Wood @ 2014-01-16 3:15 UTC (permalink / raw)
To: Wang Dongsheng-B40534
Cc: anton@enomsg.org, linuxppc-dev@lists.ozlabs.org,
Zhao Chenhui-B35336
In-Reply-To: <93a6a30cd8d240109405d45c8e143dea@BN1PR03MB188.namprd03.prod.outlook.com>
On Tue, 2014-01-14 at 20:57 -0600, Wang Dongsheng-B40534 wrote:
>
> > -----Original Message-----
> > From: Wood Scott-B07421
> > Sent: Wednesday, January 15, 2014 7:30 AM
> > To: Wang Dongsheng-B40534
> > Cc: benh@kernel.crashing.org; Zhao Chenhui-B35336; anton@enomsg.org; linuxppc-
> > dev@lists.ozlabs.org
> > Subject: Re: [PATCH 3/3] powerpc/fsl: Use the new interface to save or restore
> > registers
> >
> > On Tue, 2014-01-14 at 15:59 +0800, Dongsheng Wang wrote:
> > > From: Wang Dongsheng <dongsheng.wang@freescale.com>
> > >
> > > Use fsl_cpu_state_save/fsl_cpu_state_restore to save/restore registers.
> > > Use the functions to save/restore registers, so we don't need to
> > > maintain the code.
> > >
> > > Signed-off-by: Wang Dongsheng <dongsheng.wang@freescale.com>
> >
> > Is there any functional change with this patchset (e.g. suspend
> > supported on chips where it wasn't before), or is it just cleanup? A
> > cover letter would be useful to describe the purpose of the overall
> > patchset when it isn't obvious.
> >
>
> Yes, just cleanup..
It seems to be introducing complexity rather than removing it. Is this
cleanup needed to prepare for adding new functionality?
Plus, I'm skeptical that this is functionally equivalent. It looks like
the new code saves a lot more than the old code does. Why?
> > > +
> > > + /* Restore base register */
> > > + li r4, 0
> > > + bl fsl_cpu_state_restore
> >
> > Why are you calling anything with "fsl" in the name from code that is
> > supposed to be for all booke?
> >
> E200, E300 not support.
> Support E500, E500v2, E500MC, E5500, E6500.
>
> Do you have any suggestions about this?
What about non-FSL booke such as 44x?
Or if this file never supported 44x, rename it appropriately.
-Scott
^ permalink raw reply
* Re: [PATCH 2/3] powerpc/85xx: Provide two functions to save/restore the core registers
From: Scott Wood @ 2014-01-16 3:17 UTC (permalink / raw)
To: Wang Dongsheng-B40534
Cc: anton@enomsg.org, linuxppc-dev@lists.ozlabs.org,
Zhao Chenhui-B35336
In-Reply-To: <a11e0d7b3b954aa68483513340043452@BN1PR03MB188.namprd03.prod.outlook.com>
On Tue, 2014-01-14 at 21:30 -0600, Wang Dongsheng-B40534 wrote:
>
> > -----Original Message-----
> > From: Wood Scott-B07421
> > Sent: Wednesday, January 15, 2014 7:51 AM
> > To: Wang Dongsheng-B40534
> > Cc: benh@kernel.crashing.org; Zhao Chenhui-B35336; anton@enomsg.org; linuxppc-
> > dev@lists.ozlabs.org
> > Subject: Re: [PATCH 2/3] powerpc/85xx: Provide two functions to save/restore the
> > core registers
> >
> > On Tue, 2014-01-14 at 15:59 +0800, Dongsheng Wang wrote:
> > > From: Wang Dongsheng <dongsheng.wang@freescale.com>
> > >
> > > Add fsl_cpu_state_save/fsl_cpu_state_restore functions, used for deep
> > > sleep and hibernation to save/restore core registers. We abstract out
> > > save/restore code for use in various modules, to make them don't need
> > > to maintain.
> > >
> > > Currently supported processors type are E6500, E5500, E500MC, E500v2
> > > and E500v1.
> > >
> > > Signed-off-by: Wang Dongsheng <dongsheng.wang@freescale.com>
> >
> > What is there that is specfic to a particular core type that can't be handled
> > from C code?
> >
>
> In the context of the calling, maybe not in C environment.(Deep sleep without
> C environment when calling those interfaces)
Could you provide a concrete example?
> > > + /*
> > > + * Need to save float-point registers if MSR[FP] = 1.
> > > + */
> > > + mfmsr r12
> > > + andi. r12, r12, MSR_FP
> > > + beq 1f
> > > + do_sr_fpr_regs(save)
> >
> > C code should have already ensured that MSR[FP] is not 1 (and thus the FP
> > context has been saved).
> >
>
> Yes, right. But I mean if the FP still use in core save flow, we need to save it.
> In this process, i don't care what other code do, we need to focus on not losing
> valuable data.
It is not allowed to use FP at that point.
-Scott
^ permalink raw reply
* [PATCH 1/2][v3] driver/memory:Move Freescale IFC driver to a common driver
From: Prabhakar Kushwaha @ 2014-01-16 5:42 UTC (permalink / raw)
To: arnd, gregkh; +Cc: scottwood, linuxppc-dev, linux-kernel, Prabhakar Kushwaha
Freescale IFC controller has been used for mpc8xxx. It will be used
for ARM-based SoC as well. This patch moves the driver to driver/memory
and fix the header file includes.
Also remove module_platform_driver() and instead call
platform_driver_register() from subsys_initcall() to make sure this module
has been loaded before MTD partition parsing starts.
Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
---
Changes for v2:
- Move fsl_ifc in driver/memory
Changes for v3:
- move device tree bindings to memory
.../{powerpc => memory-controllers}/fsl/ifc.txt | 0
arch/powerpc/sysdev/Makefile | 1 -
drivers/memory/Makefile | 1 +
{arch/powerpc/sysdev => drivers/memory}/fsl_ifc.c | 8 ++++++--
drivers/mtd/nand/fsl_ifc_nand.c | 2 +-
.../include/asm => include/linux}/fsl_ifc.h | 0
6 files changed, 8 insertions(+), 4 deletions(-)
rename Documentation/devicetree/bindings/{powerpc => memory-controllers}/fsl/ifc.txt (100%)
rename {arch/powerpc/sysdev => drivers/memory}/fsl_ifc.c (98%)
rename {arch/powerpc/include/asm => include/linux}/fsl_ifc.h (100%)
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/ifc.txt b/Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt
similarity index 100%
rename from Documentation/devicetree/bindings/powerpc/fsl/ifc.txt
rename to Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index f67ac90..afbcc37 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -21,7 +21,6 @@ obj-$(CONFIG_FSL_SOC) += fsl_soc.o fsl_mpic_err.o
obj-$(CONFIG_FSL_PCI) += fsl_pci.o $(fsl-msi-obj-y)
obj-$(CONFIG_FSL_PMC) += fsl_pmc.o
obj-$(CONFIG_FSL_LBC) += fsl_lbc.o
-obj-$(CONFIG_FSL_IFC) += fsl_ifc.o
obj-$(CONFIG_FSL_GTM) += fsl_gtm.o
obj-$(CONFIG_FSL_85XX_CACHE_SRAM) += fsl_85xx_l2ctlr.o fsl_85xx_cache_sram.o
obj-$(CONFIG_SIMPLE_GPIO) += simple_gpio.o
diff --git a/drivers/memory/Makefile b/drivers/memory/Makefile
index 969d923..f2bf25c 100644
--- a/drivers/memory/Makefile
+++ b/drivers/memory/Makefile
@@ -6,6 +6,7 @@ ifeq ($(CONFIG_DDR),y)
obj-$(CONFIG_OF) += of_memory.o
endif
obj-$(CONFIG_TI_EMIF) += emif.o
+obj-$(CONFIG_FSL_IFC) += fsl_ifc.o
obj-$(CONFIG_MVEBU_DEVBUS) += mvebu-devbus.o
obj-$(CONFIG_TEGRA20_MC) += tegra20-mc.o
obj-$(CONFIG_TEGRA30_MC) += tegra30-mc.o
diff --git a/arch/powerpc/sysdev/fsl_ifc.c b/drivers/memory/fsl_ifc.c
similarity index 98%
rename from arch/powerpc/sysdev/fsl_ifc.c
rename to drivers/memory/fsl_ifc.c
index d7fc722..135a950 100644
--- a/arch/powerpc/sysdev/fsl_ifc.c
+++ b/drivers/memory/fsl_ifc.c
@@ -30,8 +30,8 @@
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/platform_device.h>
+#include <linux/fsl_ifc.h>
#include <asm/prom.h>
-#include <asm/fsl_ifc.h>
struct fsl_ifc_ctrl *fsl_ifc_ctrl_dev;
EXPORT_SYMBOL(fsl_ifc_ctrl_dev);
@@ -299,7 +299,11 @@ static struct platform_driver fsl_ifc_ctrl_driver = {
.remove = fsl_ifc_ctrl_remove,
};
-module_platform_driver(fsl_ifc_ctrl_driver);
+static int __init fsl_ifc_init(void)
+{
+ return platform_driver_register(&fsl_ifc_ctrl_driver);
+}
+subsys_initcall(fsl_ifc_init);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Freescale Semiconductor");
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index 4335577..865b323 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -30,7 +30,7 @@
#include <linux/mtd/nand.h>
#include <linux/mtd/partitions.h>
#include <linux/mtd/nand_ecc.h>
-#include <asm/fsl_ifc.h>
+#include <linux/fsl_ifc.h>
#define FSL_IFC_V1_1_0 0x01010000
#define ERR_BYTE 0xFF /* Value returned for read
diff --git a/arch/powerpc/include/asm/fsl_ifc.h b/include/linux/fsl_ifc.h
similarity index 100%
rename from arch/powerpc/include/asm/fsl_ifc.h
rename to include/linux/fsl_ifc.h
--
1.7.9.5
^ permalink raw reply related
* [PATCH 2/2][v3] powerpc/config: Enable memory driver
From: Prabhakar Kushwaha @ 2014-01-16 5:42 UTC (permalink / raw)
To: arnd, gregkh; +Cc: scottwood, linuxppc-dev, linux-kernel, Prabhakar Kushwaha
As Freescale IFC controller has been moved to driver to driver/memory.
So enable memory driver in powerpc config
Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
---
Changes for v2: Sending as it is
Changes for v3: Sending as it is
arch/powerpc/configs/corenet32_smp_defconfig | 1 +
arch/powerpc/configs/corenet64_smp_defconfig | 1 +
arch/powerpc/configs/mpc85xx_defconfig | 1 +
arch/powerpc/configs/mpc85xx_smp_defconfig | 1 +
4 files changed, 4 insertions(+)
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index bbd794d..087d437 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -142,6 +142,7 @@ CONFIG_RTC_DRV_DS3232=y
CONFIG_RTC_DRV_CMOS=y
CONFIG_UIO=y
CONFIG_STAGING=y
+CONFIG_MEMORY=y
CONFIG_VIRT_DRIVERS=y
CONFIG_FSL_HV_MANAGER=y
CONFIG_EXT2_FS=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index 63508dd..25b03f8 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -129,6 +129,7 @@ CONFIG_EDAC=y
CONFIG_EDAC_MM_EDAC=y
CONFIG_DMADEVICES=y
CONFIG_FSL_DMA=y
+CONFIG_MEMORY=y
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
CONFIG_ISO9660_FS=m
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index d2e0fab..87aad6d 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -213,6 +213,7 @@ CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_CMOS=y
CONFIG_DMADEVICES=y
CONFIG_FSL_DMA=y
+CONFIG_MEMORY=y
# CONFIG_NET_DMA is not set
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index 4cb7b59..d5d6915 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -214,6 +214,7 @@ CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_CMOS=y
CONFIG_DMADEVICES=y
CONFIG_FSL_DMA=y
+CONFIG_MEMORY=y
# CONFIG_NET_DMA is not set
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
--
1.7.9.5
^ permalink raw reply related
* [PATCH 0/7] DMA: Freescale: driver cleanups and enhancements
From: hongbo.zhang @ 2014-01-16 5:47 UTC (permalink / raw)
To: vinod.koul, dan.j.williams, dmaengine
Cc: scottwood, Hongbo Zhang, linuxppc-dev, linux-kernel
From: Hongbo Zhang <hongbo.zhang@freescale.com>
Hi Vinod Koul and Dan Williams,
Please have a look at these patches.
Note that patch 2~6 had beed sent out for upstream before, but were together
with other storage patches at that time, that was not easy for being reviewed
and merged, so I send them separately this time.
Thanks.
Hongbo Zhang (7):
DMA: Freescale: unify register access methods
DMA: Freescale: remove attribute DMA_INTERRUPT of dmaengine
DMA: Freescale: add fsl_dma_free_descriptor() to reduce code
duplication
DMA: Freescale: move functions to avoid forward declarations
DMA: Freescale: change descriptor release process for supporting
async_tx
DMA: Freescale: use spin_lock_bh instead of spin_lock_irqsave
DMA: Freescale: add suspend resume functions for DMA driver
drivers/dma/fsldma.c | 592 ++++++++++++++++++++++++++++++++------------------
drivers/dma/fsldma.h | 33 ++-
2 files changed, 412 insertions(+), 213 deletions(-)
--
1.7.9.5
^ permalink raw reply
* [PATCH 2/7] DMA: Freescale: remove attribute DMA_INTERRUPT of dmaengine
From: hongbo.zhang @ 2014-01-16 5:47 UTC (permalink / raw)
To: vinod.koul, dan.j.williams, dmaengine
Cc: scottwood, Hongbo Zhang, linuxppc-dev, linux-kernel
In-Reply-To: <1389851246-8564-1-git-send-email-hongbo.zhang@freescale.com>
From: Hongbo Zhang <hongbo.zhang@freescale.com>
Delete attribute DMA_INTERRUPT because fsldma doesn't support this function,
exception will be thrown if talitos is used to offload xor at the same time.
Signed-off-by: Hongbo Zhang <hongbo.zhang@freescale.com>
Signed-off-by: Qiang Liu <qiang.liu@freescale.com>
---
drivers/dma/fsldma.c | 31 -------------------------------
1 file changed, 31 deletions(-)
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index fbf19d3..95236e6 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -534,35 +534,6 @@ static void fsl_dma_free_chan_resources(struct dma_chan *dchan)
}
static struct dma_async_tx_descriptor *
-fsl_dma_prep_interrupt(struct dma_chan *dchan, unsigned long flags)
-{
- struct fsldma_chan *chan;
- struct fsl_desc_sw *new;
-
- if (!dchan)
- return NULL;
-
- chan = to_fsl_chan(dchan);
-
- new = fsl_dma_alloc_descriptor(chan);
- if (!new) {
- chan_err(chan, "%s\n", msg_ld_oom);
- return NULL;
- }
-
- new->async_tx.cookie = -EBUSY;
- new->async_tx.flags = flags;
-
- /* Insert the link descriptor to the LD ring */
- list_add_tail(&new->node, &new->tx_list);
-
- /* Set End-of-link to the last link descriptor of new list */
- set_ld_eol(chan, new);
-
- return &new->async_tx;
-}
-
-static struct dma_async_tx_descriptor *
fsl_dma_prep_memcpy(struct dma_chan *dchan,
dma_addr_t dma_dst, dma_addr_t dma_src,
size_t len, unsigned long flags)
@@ -1318,12 +1289,10 @@ static int fsldma_of_probe(struct platform_device *op)
fdev->irq = irq_of_parse_and_map(op->dev.of_node, 0);
dma_cap_set(DMA_MEMCPY, fdev->common.cap_mask);
- dma_cap_set(DMA_INTERRUPT, fdev->common.cap_mask);
dma_cap_set(DMA_SG, fdev->common.cap_mask);
dma_cap_set(DMA_SLAVE, fdev->common.cap_mask);
fdev->common.device_alloc_chan_resources = fsl_dma_alloc_chan_resources;
fdev->common.device_free_chan_resources = fsl_dma_free_chan_resources;
- fdev->common.device_prep_dma_interrupt = fsl_dma_prep_interrupt;
fdev->common.device_prep_dma_memcpy = fsl_dma_prep_memcpy;
fdev->common.device_prep_dma_sg = fsl_dma_prep_sg;
fdev->common.device_tx_status = fsl_tx_status;
--
1.7.9.5
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox