1 files changed, 103 insertions, 69 deletions
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index d32751994a62..3d97fb833834 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -15,7 +15,9 @@
 #include <asm/asm-offsets.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cpuidle.h>
+#include <asm/thread_info.h> /* TLF_NAPPING */
 
+#ifdef CONFIG_PPC_P7_NAP
 /*
  * Desired PSSCR in r3
  *
@@ -50,28 +52,32 @@ _GLOBAL(isa300_idle_stop_mayloss)
 	std	r1,PACAR1(r13)
 	mflr	r4
 	mfcr	r5
-	/* use stack red zone rather than a new frame for saving regs */
-	std	r2,-8*0(r1)
-	std	r14,-8*1(r1)
-	std	r15,-8*2(r1)
-	std	r16,-8*3(r1)
-	std	r17,-8*4(r1)
-	std	r18,-8*5(r1)
-	std	r19,-8*6(r1)
-	std	r20,-8*7(r1)
-	std	r21,-8*8(r1)
-	std	r22,-8*9(r1)
-	std	r23,-8*10(r1)
-	std	r24,-8*11(r1)
-	std	r25,-8*12(r1)
-	std	r26,-8*13(r1)
-	std	r27,-8*14(r1)
-	std	r28,-8*15(r1)
-	std	r29,-8*16(r1)
-	std	r30,-8*17(r1)
-	std	r31,-8*18(r1)
-	std	r4,-8*19(r1)
-	std	r5,-8*20(r1)
+	/*
+	 * Use the stack red zone rather than a new frame for saving regs since
+	 * in the case of no GPR loss the wakeup code branches directly back to
+	 * the caller without deallocating the stack frame first.
+	 */
+	std	r2,-8*1(r1)
+	std	r14,-8*2(r1)
+	std	r15,-8*3(r1)
+	std	r16,-8*4(r1)
+	std	r17,-8*5(r1)
+	std	r18,-8*6(r1)
+	std	r19,-8*7(r1)
+	std	r20,-8*8(r1)
+	std	r21,-8*9(r1)
+	std	r22,-8*10(r1)
+	std	r23,-8*11(r1)
+	std	r24,-8*12(r1)
+	std	r25,-8*13(r1)
+	std	r26,-8*14(r1)
+	std	r27,-8*15(r1)
+	std	r28,-8*16(r1)
+	std	r29,-8*17(r1)
+	std	r30,-8*18(r1)
+	std	r31,-8*19(r1)
+	std	r4,-8*20(r1)
+	std	r5,-8*21(r1)
 	/* 168 bytes */
 	PPC_STOP
 	b	.	/* catch bugs */
@@ -87,8 +93,8 @@ _GLOBAL(isa300_idle_stop_mayloss)
  */
 _GLOBAL(idle_return_gpr_loss)
 	ld	r1,PACAR1(r13)
-	ld	r4,-8*19(r1)
-	ld	r5,-8*20(r1)
+	ld	r4,-8*20(r1)
+	ld	r5,-8*21(r1)
 	mtlr	r4
 	mtcr	r5
 	/*
@@ -96,38 +102,40 @@ _GLOBAL(idle_return_gpr_loss)
 	 * from PACATOC. This could be avoided for that less common case
 	 * if KVM saved its r2.
 	 */
-	ld	r2,-8*0(r1)
-	ld	r14,-8*1(r1)
-	ld	r15,-8*2(r1)
-	ld	r16,-8*3(r1)
-	ld	r17,-8*4(r1)
-	ld	r18,-8*5(r1)
-	ld	r19,-8*6(r1)
-	ld	r20,-8*7(r1)
-	ld	r21,-8*8(r1)
-	ld	r22,-8*9(r1)
-	ld	r23,-8*10(r1)
-	ld	r24,-8*11(r1)
-	ld	r25,-8*12(r1)
-	ld	r26,-8*13(r1)
-	ld	r27,-8*14(r1)
-	ld	r28,-8*15(r1)
-	ld	r29,-8*16(r1)
-	ld	r30,-8*17(r1)
-	ld	r31,-8*18(r1)
+	ld	r2,-8*1(r1)
+	ld	r14,-8*2(r1)
+	ld	r15,-8*3(r1)
+	ld	r16,-8*4(r1)
+	ld	r17,-8*5(r1)
+	ld	r18,-8*6(r1)
+	ld	r19,-8*7(r1)
+	ld	r20,-8*8(r1)
+	ld	r21,-8*9(r1)
+	ld	r22,-8*10(r1)
+	ld	r23,-8*11(r1)
+	ld	r24,-8*12(r1)
+	ld	r25,-8*13(r1)
+	ld	r26,-8*14(r1)
+	ld	r27,-8*15(r1)
+	ld	r28,-8*16(r1)
+	ld	r29,-8*17(r1)
+	ld	r30,-8*18(r1)
+	ld	r31,-8*19(r1)
 	blr
 
 /*
  * This is the sequence required to execute idle instructions, as
  * specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
- *
- * The 0(r1) slot is used to save r2 in isa206, so use that here.
+ * We have to store a GPR somewhere, ptesync, then reload it, and create
+ * a false dependency on the result of the load. It doesn't matter which
+ * GPR we store, or where we store it. We have already stored r2 to the
+ * stack at -8(r1) in isa206_idle_insn_mayloss, so use that.
  */
 #define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST)			\
 	/* Magic NAP/SLEEP/WINKLE mode enter sequence */	\
-	std	r2,0(r1);					\
+	std	r2,-8(r1);					\
 	ptesync;						\
-	ld	r2,0(r1);					\
+	ld	r2,-8(r1);					\
 236:	cmpd	cr0,r2,r2;					\
 	bne	236b;						\
 	IDLE_INST;						\
@@ -152,28 +160,32 @@ _GLOBAL(isa206_idle_insn_mayloss)
 	std	r1,PACAR1(r13)
 	mflr	r4
 	mfcr	r5
-	/* use stack red zone rather than a new frame for saving regs */
-	std	r2,-8*0(r1)
-	std	r14,-8*1(r1)
-	std	r15,-8*2(r1)
-	std	r16,-8*3(r1)
-	std	r17,-8*4(r1)
-	std	r18,-8*5(r1)
-	std	r19,-8*6(r1)
-	std	r20,-8*7(r1)
-	std	r21,-8*8(r1)
-	std	r22,-8*9(r1)
-	std	r23,-8*10(r1)
-	std	r24,-8*11(r1)
-	std	r25,-8*12(r1)
-	std	r26,-8*13(r1)
-	std	r27,-8*14(r1)
-	std	r28,-8*15(r1)
-	std	r29,-8*16(r1)
-	std	r30,-8*17(r1)
-	std	r31,-8*18(r1)
-	std	r4,-8*19(r1)
-	std	r5,-8*20(r1)
+	/*
+	 * Use the stack red zone rather than a new frame for saving regs since
+	 * in the case of no GPR loss the wakeup code branches directly back to
+	 * the caller without deallocating the stack frame first.
+	 */
+	std	r2,-8*1(r1)
+	std	r14,-8*2(r1)
+	std	r15,-8*3(r1)
+	std	r16,-8*4(r1)
+	std	r17,-8*5(r1)
+	std	r18,-8*6(r1)
+	std	r19,-8*7(r1)
+	std	r20,-8*8(r1)
+	std	r21,-8*9(r1)
+	std	r22,-8*10(r1)
+	std	r23,-8*11(r1)
+	std	r24,-8*12(r1)
+	std	r25,-8*13(r1)
+	std	r26,-8*14(r1)
+	std	r27,-8*15(r1)
+	std	r28,-8*16(r1)
+	std	r29,-8*17(r1)
+	std	r30,-8*18(r1)
+	std	r31,-8*19(r1)
+	std	r4,-8*20(r1)
+	std	r5,-8*21(r1)
 	cmpwi	r3,PNV_THREAD_NAP
 	bne	1f
 	IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
@@ -181,4 +193,26 @@ _GLOBAL(isa206_idle_insn_mayloss)
 	bne	2f
 	IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
 2:	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
+#endif
 
+#ifdef CONFIG_PPC_970_NAP
+_GLOBAL(power4_idle_nap)
+	LOAD_REG_IMMEDIATE(r7, MSR_KERNEL|MSR_EE|MSR_POW)
+	ld	r9,PACA_THREAD_INFO(r13)
+	ld	r8,TI_LOCAL_FLAGS(r9)
+	ori	r8,r8,_TLF_NAPPING
+	std	r8,TI_LOCAL_FLAGS(r9)
+	/*
+	 * NAPPING bit is set, from this point onward power4_fixup_nap
+	 * will cause exceptions to return to power4_idle_nap_return.
+	 */
+1:	sync
+	isync
+	mtmsrd	r7
+	isync
+	b	1b
+
+	.globl power4_idle_nap_return
+power4_idle_nap_return:
+	blr
+#endif