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>

1 files changed, 21 insertions, 42 deletions

diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index 12a4efbaa08..b45fa0e3721 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 @@ BEGIN_FTR_SECTION
 	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 @@ BEGIN_FTR_SECTION
 	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(nap_save_hid1)
 
 _GLOBAL(powersave_lowspeed)
 	.long	0
-
-#ifdef DEBUG
-_GLOBAL(nap_enter_count)
-	.space	4
-_GLOBAL(nap_return_count)
-	.space	4
-#endif