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>

5 files changed, 121 insertions, 2 deletions

diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 78289ed..54eca8b 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -284,6 +284,7 @@ OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
 OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
 OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
 OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
+OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
 OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CXL_MODE);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 2e9b53b..b700a32 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -41,6 +41,7 @@
 #include <asm/code-patching.h>
 
 #include "powernv.h"
+#include "subcore.h"
 
 static void __init pnv_setup_arch(void)
 {
@@ -293,6 +294,72 @@ static void __init pnv_setup_machdep_rtas(void)
 
 static u32 supported_cpuidle_states;
 
+int pnv_save_sprs_for_winkle(void)
+{
+	int cpu;
+	int rc;
+
+	/*
+	 * hid0, hid1, hid4, hid5, hmeer and lpcr values are symmetric accross
+	 * all cpus at boot. Get these reg values of current cpu and use the
+	 * same accross all cpus.
+	 */
+	uint64_t lpcr_val = mfspr(SPRN_LPCR);
+	uint64_t hid0_val = mfspr(SPRN_HID0);
+	uint64_t hid1_val = mfspr(SPRN_HID1);
+	uint64_t hid4_val = mfspr(SPRN_HID4);
+	uint64_t hid5_val = mfspr(SPRN_HID5);
+	uint64_t hmeer_val = mfspr(SPRN_HMEER);
+
+	for_each_possible_cpu(cpu) {
+		uint64_t pir = get_hard_smp_processor_id(cpu);
+		uint64_t hsprg0_val = (uint64_t)&paca[cpu];
+
+		/*
+		 * HSPRG0 is used to store the cpu's pointer to paca. Hence last
+		 * 3 bits are guaranteed to be 0. Program slw to restore HSPRG0
+		 * with 63rd bit set, so that when a thread wakes up at 0x100 we
+		 * can use this bit to distinguish between fastsleep and
+		 * deep winkle.
+		 */
+		hsprg0_val |= 1;
+
+		rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
+		if (rc != 0)
+			return rc;
+
+		rc = opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
+		if (rc != 0)
+			return rc;
+
+		/* HIDs are per core registers */
+		if (cpu_thread_in_core(cpu) == 0) {
+
+			rc = opal_slw_set_reg(pir, SPRN_HMEER, hmeer_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID0, hid0_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val);
+			if (rc != 0)
+				return rc;
+		}
+	}
+
+	return 0;
+}
+
 static void pnv_alloc_idle_core_states(void)
 {
 	int i, j;
@@ -325,6 +392,11 @@ static void pnv_alloc_idle_core_states(void)
 			paca[cpu].thread_mask = 1 << j;
 		}
 	}
+
+	update_subcore_sibling_mask();
+
+	if (supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED)
+		pnv_save_sprs_for_winkle();
 }
 
 u32 pnv_get_supported_cpuidle_states(void)
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index c0691d0..6c551a2 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -167,12 +167,17 @@ static void pnv_smp_cpu_kill_self(void)
 	 */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
+
 		ppc64_runlatch_off();
-		if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
+
+		if (idle_states & OPAL_PM_WINKLE_ENABLED)
+			srr1 = power7_winkle();
+		else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
 				(idle_states & OPAL_PM_SLEEP_ENABLED_ER1))
 			srr1 = power7_sleep();
 		else
 			srr1 = power7_nap(1);
+
 		ppc64_runlatch_on();
 
 		/*
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index c87f96b..f60f80a 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -160,6 +160,18 @@ static void wait_for_sync_step(int step)
 	mb();
 }
 
+static void update_hid_in_slw(u64 hid0)
+{
+	u64 idle_states = pnv_get_supported_cpuidle_states();
+
+	if (idle_states & OPAL_PM_WINKLE_ENABLED) {
+		/* OPAL call to patch slw with the new HID0 value */
+		u64 cpu_pir = hard_smp_processor_id();
+
+		opal_slw_set_reg(cpu_pir, SPRN_HID0, hid0);
+	}
+}
+
 static void unsplit_core(void)
 {
 	u64 hid0, mask;
@@ -179,6 +191,7 @@ static void unsplit_core(void)
 	hid0 = mfspr(SPRN_HID0);
 	hid0 &= ~HID0_POWER8_DYNLPARDIS;
 	mtspr(SPRN_HID0, hid0);
+	update_hid_in_slw(hid0);
 
 	while (mfspr(SPRN_HID0) & mask)
 		cpu_relax();
@@ -215,6 +228,7 @@ static void split_core(int new_mode)
 	hid0  = mfspr(SPRN_HID0);
 	hid0 |= HID0_POWER8_DYNLPARDIS | split_parms[i].value;
 	mtspr(SPRN_HID0, hid0);
+	update_hid_in_slw(hid0);
 
 	/* Wait for it to happen */
 	while (!(mfspr(SPRN_HID0) & split_parms[i].mask))
@@ -251,6 +265,25 @@ bool cpu_core_split_required(void)
 	return true;
 }
 
+void update_subcore_sibling_mask(void)
+{
+	int cpu;
+	/*
+	 * sibling mask for the first cpu. Left shift this by required bits
+	 * to get sibling mask for the rest of the cpus.
+	 */
+	int sibling_mask_first_cpu =  (1 << threads_per_subcore) - 1;
+
+	for_each_possible_cpu(cpu) {
+		int tid = cpu_thread_in_core(cpu);
+		int offset = (tid / threads_per_subcore) * threads_per_subcore;
+		int mask = sibling_mask_first_cpu << offset;
+
+		paca[cpu].subcore_sibling_mask = mask;
+
+	}
+}
+
 static int cpu_update_split_mode(void *data)
 {
 	int cpu, new_mode = *(int *)data;
@@ -284,6 +317,7 @@ static int cpu_update_split_mode(void *data)
 		/* Make the new mode public */
 		subcores_per_core = new_mode;
 		threads_per_subcore = threads_per_core / subcores_per_core;
+		update_subcore_sibling_mask();
 
 		/* Make sure the new mode is written before we exit */
 		mb();
diff --git a/arch/powerpc/platforms/powernv/subcore.h b/arch/powerpc/platforms/powernv/subcore.h
index 148abc9..84e02ae 100644
--- a/arch/powerpc/platforms/powernv/subcore.h
+++ b/arch/powerpc/platforms/powernv/subcore.h
@@ -14,5 +14,12 @@
 #define SYNC_STEP_FINISHED	3	/* Set by secondary when split/unsplit is done */
 
 #ifndef __ASSEMBLY__
+
+#ifdef CONFIG_SMP
 void split_core_secondary_loop(u8 *state);
-#endif
+extern void update_subcore_sibling_mask(void);
+#else
+static inline void update_subcore_sibling_mask(void) { };
+#endif /* CONFIG_SMP */
+
+#endif /* __ASSEMBLY__ */