powerpc: Use correct sequence for putting CPU into nap mode
We weren't using the recommended sequence for putting the CPU into
nap mode. When I changed the idle loop, for some reason 7447A cpus
started hanging when we put them into nap mode. Changing to the
recommended sequence fixes that.
The complexity here is that the recommended sequence is a loop that
keeps putting the cpu back into nap mode. Clearly we need some way
to break out of the loop when an interrupt (external interrupt,
decrementer, performance monitor) occurs. Here we use a bit in
the thread_info struct to indicate that we need this, and the exception
entry code notices this and arranges for the exception to return
to the value in the link register, thus breaking out of the loop.
We use a new `local_flags' field in the thread_info which we can
alter without needing to use an atomic update sequence.
The PPC970 has the same recommended sequence, so we do the same thing
there too.
This also fixes a bug in the kernel stack overflow handling code on
32-bit, since it was causing a value that we needed in a register to
get trashed.
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 0cc0995..803858e 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -20,7 +20,7 @@
firmware.o sysfs.o
obj-$(CONFIG_PPC64) += vdso64/
obj-$(CONFIG_ALTIVEC) += vecemu.o vector.o
-obj-$(CONFIG_POWER4) += idle_power4.o
+obj-$(CONFIG_PPC_970_NAP) += idle_power4.o
obj-$(CONFIG_PPC_OF) += of_device.o prom_parse.o
procfs-$(CONFIG_PPC64) := proc_ppc64.o
obj-$(CONFIG_PROC_FS) += $(procfs-y)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 54b48f3..8f85c5e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -91,6 +91,7 @@
#endif /* CONFIG_PPC64 */
DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
+ DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
DEFINE(TI_TASK, offsetof(struct thread_info, task));
#ifdef CONFIG_PPC32
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index b3a9794..8866fd2 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -128,37 +128,36 @@
stw r12,4(r11)
#endif
b 3f
+
2: /* if from kernel, check interrupted DOZE/NAP mode and
* check for stack overflow
*/
+ lwz r9,THREAD_INFO-THREAD(r12)
+ cmplw r1,r9 /* if r1 <= current->thread_info */
+ ble- stack_ovf /* then the kernel stack overflowed */
+5:
#ifdef CONFIG_6xx
- mfspr r11,SPRN_HID0
- mtcr r11
-BEGIN_FTR_SECTION
- bt- 8,4f /* Check DOZE */
-END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
-BEGIN_FTR_SECTION
- bt- 9,4f /* Check NAP */
-END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+ tophys(r9,r9) /* check local flags */
+ lwz r12,TI_LOCAL_FLAGS(r9)
+ mtcrf 0x01,r12
+ bt- 31-TLF_NAPPING,4f
#endif /* CONFIG_6xx */
.globl transfer_to_handler_cont
transfer_to_handler_cont:
- lwz r11,THREAD_INFO-THREAD(r12)
- cmplw r1,r11 /* if r1 <= current->thread_info */
- ble- stack_ovf /* then the kernel stack overflowed */
3:
mflr r9
lwz r11,0(r9) /* virtual address of handler */
lwz r9,4(r9) /* where to go when done */
- FIX_SRR1(r10,r12)
mtspr SPRN_SRR0,r11
mtspr SPRN_SRR1,r10
mtlr r9
SYNC
RFI /* jump to handler, enable MMU */
-#ifdef CONFIG_6xx
-4: b power_save_6xx_restore
+#ifdef CONFIG_6xx
+4: rlwinm r12,r12,0,~_TLF_NAPPING
+ stw r12,TI_LOCAL_FLAGS(r9)
+ b power_save_6xx_restore
#endif
/*
@@ -167,10 +166,10 @@
*/
stack_ovf:
/* sometimes we use a statically-allocated stack, which is OK. */
- lis r11,_end@h
- ori r11,r11,_end@l
- cmplw r1,r11
- ble 3b /* r1 <= &_end is OK */
+ lis r12,_end@h
+ ori r12,r12,_end@l
+ cmplw r1,r12
+ ble 5b /* r1 <= &_end is OK */
SAVE_NVGPRS(r11)
addi r3,r1,STACK_FRAME_OVERHEAD
lis r1,init_thread_union@ha
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index a5ae04a..b7d1404 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -376,11 +376,28 @@
bl hdlr; \
b .ret_from_except
+/*
+ * Like STD_EXCEPTION_COMMON, but for exceptions that can occur
+ * in the idle task and therefore need the special idle handling.
+ */
+#define STD_EXCEPTION_COMMON_IDLE(trap, label, hdlr) \
+ .align 7; \
+ .globl label##_common; \
+label##_common: \
+ EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \
+ FINISH_NAP; \
+ DISABLE_INTS; \
+ bl .save_nvgprs; \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ bl hdlr; \
+ b .ret_from_except
+
#define STD_EXCEPTION_COMMON_LITE(trap, label, hdlr) \
.align 7; \
.globl label##_common; \
label##_common: \
EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN); \
+ FINISH_NAP; \
DISABLE_INTS; \
bl .ppc64_runlatch_on; \
addi r3,r1,STACK_FRAME_OVERHEAD; \
@@ -388,6 +405,25 @@
b .ret_from_except_lite
/*
+ * When the idle code in power4_idle puts the CPU into NAP mode,
+ * it has to do so in a loop, and relies on the external interrupt
+ * and decrementer interrupt entry code to get it out of the loop.
+ * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags
+ * to signal that it is in the loop and needs help to get out.
+ */
+#ifdef CONFIG_PPC_970_NAP
+#define FINISH_NAP \
+BEGIN_FTR_SECTION \
+ clrrdi r11,r1,THREAD_SHIFT; \
+ ld r9,TI_LOCAL_FLAGS(r11); \
+ andi. r10,r9,_TLF_NAPPING; \
+ bnel power4_fixup_nap; \
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+#else
+#define FINISH_NAP
+#endif
+
+/*
* Start of pSeries system interrupt routines
*/
. = 0x100
@@ -772,6 +808,7 @@
.globl machine_check_common
machine_check_common:
EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
+ FINISH_NAP
DISABLE_INTS
bl .save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
@@ -783,7 +820,7 @@
STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
- STD_EXCEPTION_COMMON(0xf00, performance_monitor, .performance_monitor_exception)
+ STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception)
STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
#ifdef CONFIG_ALTIVEC
STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
@@ -1034,6 +1071,7 @@
.globl hardware_interrupt_entry
hardware_interrupt_common:
EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN)
+ FINISH_NAP
hardware_interrupt_entry:
DISABLE_INTS
bl .ppc64_runlatch_on
@@ -1041,6 +1079,15 @@
bl .do_IRQ
b .ret_from_except_lite
+#ifdef CONFIG_PPC_970_NAP
+power4_fixup_nap:
+ andc r9,r9,r10
+ std r9,TI_LOCAL_FLAGS(r11)
+ ld r10,_LINK(r1) /* make idle task do the */
+ std r10,_NIP(r1) /* equivalent of a blr */
+ blr
+#endif
+
.align 7
.globl alignment_common
alignment_common:
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index 12a4efb..b45fa0e 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -22,8 +22,6 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
-#undef DEBUG
-
.text
/*
@@ -109,12 +107,6 @@
dcbf 0,r4
dcbf 0,r4
END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
-#ifdef DEBUG
- lis r6,nap_enter_count@ha
- lwz r4,nap_enter_count@l(r6)
- addi r4,r4,1
- stw r4,nap_enter_count@l(r6)
-#endif
2:
BEGIN_FTR_SECTION
/* Go to low speed mode on some 750FX */
@@ -144,48 +136,42 @@
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ rlwinm r9,r1,0,0,31-THREAD_SHIFT /* current thread_info */
+ lwz r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
+ ori r8,r8,_TLF_NAPPING /* so when we take an exception */
+ stw r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
mfmsr r7
ori r7,r7,MSR_EE
oris r7,r7,MSR_POW@h
- sync
- isync
+1: sync
mtmsr r7
isync
- sync
- blr
-
+ b 1b
+
/*
* Return from NAP/DOZE mode, restore some CPU specific registers,
* we are called with DR/IR still off and r2 containing physical
- * address of current.
+ * address of current. R11 points to the exception frame (physical
+ * address). We have to preserve r10.
*/
_GLOBAL(power_save_6xx_restore)
- mfspr r11,SPRN_HID0
- rlwinm. r11,r11,0,10,8 /* Clear NAP & copy NAP bit !state to cr1 EQ */
- cror 4*cr1+eq,4*cr0+eq,4*cr0+eq
-BEGIN_FTR_SECTION
- rlwinm r11,r11,0,9,7 /* Clear DOZE */
-END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
- mtspr SPRN_HID0, r11
+ lwz r9,_LINK(r11) /* interrupted in ppc6xx_idle: */
+ stw r9,_NIP(r11) /* make it do a blr */
-#ifdef DEBUG
- beq cr1,1f
- lis r11,(nap_return_count-KERNELBASE)@ha
- lwz r9,nap_return_count@l(r11)
- addi r9,r9,1
- stw r9,nap_return_count@l(r11)
-1:
-#endif
-
- rlwinm r9,r1,0,0,18
- tophys(r9,r9)
- lwz r11,TI_CPU(r9)
+#ifdef CONFIG_SMP
+ mfspr r12,SPRN_SPRG3
+ lwz r11,TI_CPU(r12) /* get cpu number * 4 */
slwi r11,r11,2
+#else
+ li r11,0
+#endif
/* Todo make sure all these are in the same page
- * and load r22 (@ha part + CPU offset) only once
+ * and load r11 (@ha part + CPU offset) only once
*/
BEGIN_FTR_SECTION
- beq cr1,1f
+ mfspr r9,SPRN_HID0
+ andis. r9,r9,HID0_NAP@h
+ beq 1f
addis r9,r11,(nap_save_msscr0-KERNELBASE)@ha
lwz r9,nap_save_msscr0@l(r9)
mtspr SPRN_MSSCR0, r9
@@ -210,10 +196,3 @@
_GLOBAL(powersave_lowspeed)
.long 0
-
-#ifdef DEBUG
-_GLOBAL(nap_enter_count)
- .space 4
-_GLOBAL(nap_return_count)
- .space 4
-#endif
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index 6dad1c0..d85c7c9 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -35,12 +35,16 @@
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ clrrdi r9,r1,THREAD_SHIFT /* current thread_info */
+ ld r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
+ ori r8,r8,_TLF_NAPPING /* so when we take an exception */
+ std r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
mfmsr r7
ori r7,r7,MSR_EE
oris r7,r7,MSR_POW@h
- sync
+1: sync
isync
mtmsrd r7
isync
- sync
- blr
+ b 1b
+