powernv/powerpc: Add winkle support for offline cpus

Winkle is a deep idle state supported in power8 chips. A core enters
winkle when all the threads of the core enter winkle. In this state
power supply to the entire chiplet i.e core, private L2 and private L3
is turned off. As a result it gives higher powersavings compared to
sleep.

But entering winkle results in a total hypervisor state loss. Hence the
hypervisor context has to be preserved before entering winkle and
restored upon wake up.

Power-on Reset Engine (PORE) is a dedicated engine which is responsible
for powering on the chiplet during wake up. It can be programmed to
restore the register contests of a few specific registers. This patch
uses PORE to restore register state wherever possible and uses stack to
save and restore rest of the necessary registers.

With hypervisor state restore things fall under three categories-
per-core state, per-subcore state and per-thread state. To manage this,
extend the infrastructure introduced for sleep. Mainly we add a paca
variable subcore_sibling_mask. Using this and the core_idle_state we can
distingush first thread in core and subcore.

Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3 files changed, 150 insertions, 10 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index bbd27fe0c03..f68de7a73fa 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -733,6 +733,8 @@ int main(void)
 			offsetof(struct paca_struct, thread_idle_state));
 	DEFINE(PACA_THREAD_MASK,
 			offsetof(struct paca_struct, thread_mask));
+	DEFINE(PACA_SUBCORE_SIBLING_MASK,
+			offsetof(struct paca_struct, subcore_sibling_mask));
 #endif
 
 	return 0;
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 289fe718ecd..c2df8150bd7 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -102,9 +102,7 @@ system_reset_pSeries:
 #ifdef CONFIG_PPC_P7_NAP
 BEGIN_FTR_SECTION
 	/* Running native on arch 2.06 or later, check if we are
-	 * waking up from nap. We only handle no state loss and
-	 * supervisor state loss. We do -not- handle hypervisor
-	 * state loss at this time.
+	 * waking up from nap/sleep/winkle.
 	 */
 	mfspr	r13,SPRN_SRR1
 	rlwinm.	r13,r13,47-31,30,31
@@ -112,7 +110,16 @@ BEGIN_FTR_SECTION
 
 	cmpwi	cr3,r13,2
 
+	/*
+	 * Check if last bit of HSPGR0 is set. This indicates whether we are
+	 * waking up from winkle.
+	 */
 	GET_PACA(r13)
+	clrldi	r5,r13,63
+	clrrdi	r13,r13,1
+	cmpwi	cr4,r5,1
+	mtspr	SPRN_HSPRG0,r13
+
 	lbz	r0,PACA_THREAD_IDLE_STATE(r13)
 	cmpwi   cr2,r0,PNV_THREAD_NAP
 	bgt     cr2,8f				/* Either sleep or Winkle */
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 0f2c113c8ca..05adc8bbdef 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -19,9 +19,24 @@
 #include <asm/kvm_book3s_asm.h>
 #include <asm/opal.h>
 #include <asm/cpuidle.h>
+#include <asm/mmu-hash64.h>
 
 #undef DEBUG
 
+/*
+ * Use unused space in the interrupt stack to save and restore
+ * registers for winkle support.
+ */
+#define _SDR1	GPR3
+#define _RPR	GPR4
+#define _SPURR	GPR5
+#define _PURR	GPR6
+#define _TSCR	GPR7
+#define _DSCR	GPR8
+#define _AMOR	GPR9
+#define _WORT	GPR10
+#define _WORC	GPR11
+
 /* Idle state entry routines */
 
 #define	IDLE_STATE_ENTER_SEQ(IDLE_INST)				\
@@ -124,8 +139,8 @@ power7_enter_nap_mode:
 	stb	r4,HSTATE_HWTHREAD_STATE(r13)
 #endif
 	stb	r3,PACA_THREAD_IDLE_STATE(r13)
-	cmpwi	cr1,r3,PNV_THREAD_SLEEP
-	bge	cr1,2f
+	cmpwi	cr3,r3,PNV_THREAD_SLEEP
+	bge	cr3,2f
 	IDLE_STATE_ENTER_SEQ(PPC_NAP)
 	/* No return */
 2:
@@ -154,7 +169,8 @@ pnv_fastsleep_workaround_at_entry:
 	bne-	lwarx_loop1
 	isync
 
-common_enter: /* common code for all the threads entering sleep */
+common_enter: /* common code for all the threads entering sleep or winkle */
+	bgt	cr3,enter_winkle
 	IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
 
 fastsleep_workaround_at_entry:
@@ -175,6 +191,30 @@ fastsleep_workaround_at_entry:
 	stw	r0,0(r14)
 	b	common_enter
 
+enter_winkle:
+	/*
+	 * Note all register i.e per-core, per-subcore or per-thread is saved
+	 * here since any thread in the core might wake up first
+	 */
+	mfspr	r3,SPRN_SDR1
+	std	r3,_SDR1(r1)
+	mfspr	r3,SPRN_RPR
+	std	r3,_RPR(r1)
+	mfspr	r3,SPRN_SPURR
+	std	r3,_SPURR(r1)
+	mfspr	r3,SPRN_PURR
+	std	r3,_PURR(r1)
+	mfspr	r3,SPRN_TSCR
+	std	r3,_TSCR(r1)
+	mfspr	r3,SPRN_DSCR
+	std	r3,_DSCR(r1)
+	mfspr	r3,SPRN_AMOR
+	std	r3,_AMOR(r1)
+	mfspr	r3,SPRN_WORT
+	std	r3,_WORT(r1)
+	mfspr	r3,SPRN_WORC
+	std	r3,_WORC(r1)
+	IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
 
 _GLOBAL(power7_idle)
 	/* Now check if user or arch enabled NAP mode */
@@ -197,6 +237,12 @@ _GLOBAL(power7_sleep)
 	b	power7_powersave_common
 	/* No return */
 
+_GLOBAL(power7_winkle)
+	li	r3,3
+	li	r4,1
+	b	power7_powersave_common
+	/* No return */
+
 #define CHECK_HMI_INTERRUPT						\
 	mfspr	r0,SPRN_SRR1;						\
 BEGIN_FTR_SECTION_NESTED(66);						\
@@ -250,11 +296,23 @@ lwarx_loop2:
 	bne	core_idle_lock_held
 
 	cmpwi	cr2,r15,0
+	lbz	r4,PACA_SUBCORE_SIBLING_MASK(r13)
+	and	r4,r4,r15
+	cmpwi	cr1,r4,0	/* Check if first in subcore */
+
+	/*
+	 * At this stage
+	 * cr1 - 0b0100 if first thread to wakeup in subcore
+	 * cr2 - 0b0100 if first thread to wakeup in core
+	 * cr3-  0b0010 if waking up from sleep or winkle
+	 * cr4 - 0b0100 if waking up from winkle
+	 */
+
 	or	r15,r15,r7		/* Set thread bit */
 
-	beq	cr2,first_thread
+	beq	cr1,first_thread_in_subcore
 
-	/* Not first thread in core to wake up */
+	/* Not first thread in subcore to wake up */
 	stwcx.	r15,0,r14
 	bne-	lwarx_loop2
 	isync
@@ -269,14 +327,37 @@ core_idle_lock_loop:
 	HMT_MEDIUM
 	b	lwarx_loop2
 
-first_thread:
-	/* First thread in core to wakeup */
+first_thread_in_subcore:
+	/* First thread in subcore to wakeup */
 	ori	r15,r15,PNV_CORE_IDLE_LOCK_BIT
 	stwcx.	r15,0,r14
 	bne-	lwarx_loop2
 	isync
 
 	/*
+	 * If waking up from sleep, subcore state is not lost. Hence
+	 * skip subcore state restore
+	 */
+	bne	cr4,subcore_state_restored
+
+	/* Restore per-subcore state */
+	ld      r4,_SDR1(r1)
+	mtspr   SPRN_SDR1,r4
+	ld      r4,_RPR(r1)
+	mtspr   SPRN_RPR,r4
+	ld	r4,_AMOR(r1)
+	mtspr	SPRN_AMOR,r4
+
+subcore_state_restored:
+	/*
+	 * Check if the thread is also the first thread in the core. If not,
+	 * skip to clear_lock.
+	 */
+	bne	cr2,clear_lock
+
+first_thread_in_core:
+
+	/*
 	 * First thread in the core waking up from fastsleep. It needs to
 	 * call the fastsleep workaround code if the platform requires it.
 	 * Call it unconditionally here. The below branch instruction will
@@ -296,12 +377,62 @@ timebase_resync:
 	bl	opal_call_realmode;
 	/* TODO: Check r3 for failure */
 
+	/*
+	 * If waking up from sleep, per core state is not lost, skip to
+	 * clear_lock.
+	 */
+	bne	cr4,clear_lock
+
+	/* Restore per core state */
+	ld	r4,_TSCR(r1)
+	mtspr	SPRN_TSCR,r4
+	ld	r4,_WORC(r1)
+	mtspr	SPRN_WORC,r4
+
 clear_lock:
 	andi.	r15,r15,PNV_CORE_IDLE_THREAD_BITS
 	lwsync
 	stw	r15,0(r14)
 
 common_exit:
+	/*
+	 * Common to all threads.
+	 *
+	 * If waking up from sleep, hypervisor state is not lost. Hence
+	 * skip hypervisor state restore.
+	 */
+	bne	cr4,hypervisor_state_restored
+
+	/* Waking up from winkle */
+
+	/* Restore per thread state */
+	bl	__restore_cpu_power8
+
+	/* Restore SLB  from PACA */
+	ld	r8,PACA_SLBSHADOWPTR(r13)
+
+	.rept	SLB_NUM_BOLTED
+	li	r3, SLBSHADOW_SAVEAREA
+	LDX_BE	r5, r8, r3
+	addi	r3, r3, 8
+	LDX_BE	r6, r8, r3
+	andis.	r7,r5,SLB_ESID_V@h
+	beq	1f
+	slbmte	r6,r5
+1:	addi	r8,r8,16
+	.endr
+
+	ld	r4,_SPURR(r1)
+	mtspr	SPRN_SPURR,r4
+	ld	r4,_PURR(r1)
+	mtspr	SPRN_PURR,r4
+	ld	r4,_DSCR(r1)
+	mtspr	SPRN_DSCR,r4
+	ld	r4,_WORT(r1)
+	mtspr	SPRN_WORT,r4
+
+hypervisor_state_restored:
+
 	li	r5,PNV_THREAD_RUNNING
 	stb     r5,PACA_THREAD_IDLE_STATE(r13)