powerpc/64s/idle: Avoid SRR usage in idle sleep/wake paths

Idle code now always runs at the 0xc... effective address whether
in real or virtual mode. This means rfid can be ditched, along
with a lot of SRR manipulations.

In the wakeup path, carry SRR1 around in r12. Use mtmsrd to change
MSR states as required.

This also balances the return prediction for the idle call, by
doing blr rather than rfid to return to the idle caller.

On POWER9, 2-process context switch on different cores, with snooze
disabled, increases performance by 2%.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Incorporate v2 fixes from Nick]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/kernel/exceptions-64s.S

@@ -130,6 +130,7 @@ EXC_VIRT_NONE(0x4100, 0x100)
 
 #ifdef CONFIG_PPC_P7_NAP
 EXC_COMMON_BEGIN(system_reset_idle_common)
+	mfspr	r12,SPRN_SRR1
 	b	pnv_powersave_wakeup
 #endif
 

arch/powerpc/kernel/idle_book3s.S

@@ -111,7 +111,7 @@ core_idle_lock_held:
  *	r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8
  *	   - Requested PSSCR value in POWER9
  *
- * Address of idle handler to 'rfid' to in r4
+ * Address of idle handler to branch to in realmode in r4
  */
 pnv_powersave_common:
 	/* Use r3 to pass state nap/sleep/winkle */
@@ -121,14 +121,14 @@ pnv_powersave_common:
 	 * need to save PC, some CR bits and the NV GPRs,
 	 * but for now an interrupt frame will do.
 	 */
+	mtctr	r4
+
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-INT_FRAME_SIZE(r1)
 	std	r0,_LINK(r1)
 	std	r0,_NIP(r1)
 
-	mfmsr   r9
-
 	/* We haven't lost state ... yet */
 	li	r0,0
 	stb	r0,PACA_NAPSTATELOST(r13)
@@ -138,7 +138,6 @@ pnv_powersave_common:
 	SAVE_NVGPRS(r1)
 	mfcr	r5
 	std	r5,_CCR(r1)
-	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
 	/*
@@ -148,12 +147,8 @@ pnv_powersave_common:
 	 * the MMU context to the guest.
 	 */
 	LOAD_REG_IMMEDIATE(r7, MSR_IDLE)
-	li	r6, MSR_RI
-	andc	r6, r9, r6
-	mtmsrd	r6, 1		/* clear RI before setting SRR0/1 */
-	mtspr	SPRN_SRR0, r4
-	mtspr	SPRN_SRR1, r7
-	rfid
+	mtmsrd	r7,0
+	bctr
 
 	.globl pnv_enter_arch207_idle_mode
 pnv_enter_arch207_idle_mode:
@@ -305,11 +300,10 @@ _GLOBAL(power7_idle_insn)
 	b	pnv_powersave_common
 
 #define CHECK_HMI_INTERRUPT						\
-	mfspr	r0,SPRN_SRR1;						\
 BEGIN_FTR_SECTION_NESTED(66);						\
-	rlwinm	r0,r0,45-31,0xf;  /* extract wake reason field (P8) */	\
+	rlwinm	r0,r12,45-31,0xf;  /* extract wake reason field (P8) */	\
 FTR_SECTION_ELSE_NESTED(66);						\
-	rlwinm	r0,r0,45-31,0xe;  /* P7 wake reason field is 3 bits */	\
+	rlwinm	r0,r12,45-31,0xe;  /* P7 wake reason field is 3 bits */	\
 ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66);		\
 	cmpwi	r0,0xa;			/* Hypervisor maintenance ? */	\
 	bne	20f;							\
@@ -388,17 +382,17 @@ pnv_powersave_wakeup_mce:
 
 	/*
 	 * Now put the original SRR1 with SRR1_WAKEMCE_RESVD as the wake
-	 * reason into SRR1, which allows reuse of the system reset wakeup
+	 * reason into r12, which allows reuse of the system reset wakeup
 	 * code without being mistaken for another type of wakeup.
 	 */
-	oris	r3,r3,SRR1_WAKEMCE_RESVD@h
-	mtspr	SPRN_SRR1,r3
+	oris	r12,r3,SRR1_WAKEMCE_RESVD@h
 
 	b	pnv_powersave_wakeup
 
 /*
  * Called from reset vector for powersave wakeups.
  * cr3 - set to gt if waking up with partial/complete hypervisor state loss
+ * r12 - SRR1
  */
 .global pnv_powersave_wakeup
 pnv_powersave_wakeup:
@@ -416,6 +410,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 	li	r0,PNV_THREAD_RUNNING
 	stb	r0,PACA_THREAD_IDLE_STATE(r13)	/* Clear thread state */
 
+	mr	r3,r12
+
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	li	r0,KVM_HWTHREAD_IN_KERNEL
 	stb	r0,HSTATE_HWTHREAD_STATE(r13)
@@ -429,7 +425,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 #endif
 
 	/* Return SRR1 from power7_nap() */
-	mfspr	r3,SPRN_SRR1
 	blt	cr3,pnv_wakeup_noloss
 	b	pnv_wakeup_loss
 
@@ -529,9 +524,9 @@ pnv_wakeup_tb_loss:
 	 * is required to return back to reset vector after hypervisor state
 	 * restore is complete.
 	 */
+	mr	r19,r12
 	mr	r18,r4
 	mflr	r17
-	mfspr	r16,SPRN_SRR1
 BEGIN_FTR_SECTION
 	CHECK_HMI_INTERRUPT
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
@@ -781,7 +776,7 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 hypervisor_state_restored:
 
-	mtspr	SPRN_SRR1,r16
+	mr	r12,r19
 	mtlr	r17
 	blr		/* return to pnv_powersave_wakeup */
 
@@ -794,6 +789,7 @@ fastsleep_workaround_at_exit:
 /*
  * R3 here contains the value that will be returned to the caller
  * of power7_nap.
+ * R12 contains SRR1 for CHECK_HMI_INTERRUPT.
  */
 .global pnv_wakeup_loss
 pnv_wakeup_loss:
@@ -803,32 +799,33 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	REST_NVGPRS(r1)
 	REST_GPR(2, r1)
+	ld	r4,PACAKMSR(r13)
+	ld	r5,_LINK(r1)
 	ld	r6,_CCR(r1)
-	ld	r4,_MSR(r1)
-	ld	r5,_NIP(r1)
 	addi	r1,r1,INT_FRAME_SIZE
+	mtlr	r5
 	mtcr	r6
-	mtspr	SPRN_SRR1,r4
-	mtspr	SPRN_SRR0,r5
-	rfid
+	mtmsrd	r4
+	blr
 
 /*
  * R3 here contains the value that will be returned to the caller
  * of power7_nap.
+ * R12 contains SRR1 for CHECK_HMI_INTERRUPT.
  */
 pnv_wakeup_noloss:
 	lbz	r0,PACA_NAPSTATELOST(r13)
 	cmpwi	r0,0
 	bne	pnv_wakeup_loss
+	ld	r1,PACAR1(r13)
 BEGIN_FTR_SECTION
 	CHECK_HMI_INTERRUPT
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
-	ld	r1,PACAR1(r13)
-	ld	r6,_CCR(r1)
-	ld	r4,_MSR(r1)
+	ld	r4,PACAKMSR(r13)
 	ld	r5,_NIP(r1)
+	ld	r6,_CCR(r1)
 	addi	r1,r1,INT_FRAME_SIZE
+	mtlr	r5
 	mtcr	r6
-	mtspr	SPRN_SRR1,r4
-	mtspr	SPRN_SRR0,r5
-	rfid
+	mtmsrd	r4
+	blr

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -329,15 +329,21 @@ kvm_novcpu_exit:
  * We come in here when wakened from nap mode.
  * Relocation is off and most register values are lost.
  * r13 points to the PACA.
+ * r3 contains the SRR1 wakeup value, SRR1 is trashed.
  */
 	.globl	kvm_start_guest
 kvm_start_guest:
-
 	/* Set runlatch bit the minute you wake up from nap */
 	mfspr	r0, SPRN_CTRLF
 	ori 	r0, r0, 1
 	mtspr	SPRN_CTRLT, r0
 
+	/*
+	 * Could avoid this and pass it through in r3. For now,
+	 * code expects it to be in SRR1.
+	 */
+	mtspr	SPRN_SRR1,r3
+
 	ld	r2,PACATOC(r13)
 
 	li	r0,KVM_HWTHREAD_IN_KVM
@@ -456,13 +462,15 @@ kvm_no_guest:
 /*
  * We jump to pnv_wakeup_loss, which will return to the caller
  * of power7_nap in the powernv cpu offline loop.  The value we
- * put in r3 becomes the return value for power7_nap.
+ * put in r3 becomes the return value for power7_nap. pnv_wakeup_loss
+ * requires SRR1 in r12.
  */
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
 	li	r3, 0
+	mfspr	r12,SPRN_SRR1
 	b	pnv_wakeup_loss
 
 53:	HMT_LOW