powerpc/powernv: Enable Offline CPUs to enter deep idle states

The secondary threads should enter deep idle states so as to gain maximum
powersavings when the entire core is offline. To do so the offline path
must be made aware of the available deepest idle state. Hence probe the
device tree for the possible idle states in powernv core code and
expose the deepest idle state through flags.

Since the  device tree is probed by the cpuidle driver as well, move
the parameters required to discover the idle states into an appropriate
common place to both the driver and the powernv core code.

Another point is that fastsleep idle state may require workarounds in
the kernel to function properly. This workaround is introduced in the
subsequent patches. However neither the cpuidle driver or the hotplug
path need be bothered about this workaround.

They will be taken care of by the core powernv code.

Originally-by: Srivatsa S. Bhat <srivatsa@mit.edu>
Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Reviewed-by: Paul Mackerras <paulus@samba.org>

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: linux-pm@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/opal.h

@@ -168,6 +168,14 @@ struct opal_sg_list {
 #define OPAL_IPMI_RECV				108
 #define OPAL_I2C_REQUEST			109
 
+/* Device tree flags */
+
+/* Flags set in power-mgmt nodes in device tree if
+ * respective idle states are supported in the platform.
+ */
+#define OPAL_PM_NAP_ENABLED	0x00010000
+#define OPAL_PM_SLEEP_ENABLED	0x00020000
+
 #ifndef __ASSEMBLY__
 
 #include <linux/notifier.h>

arch/powerpc/platforms/powernv/powernv.h

@@ -29,6 +29,8 @@ static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
 }
 #endif
 
+extern u32 pnv_get_supported_cpuidle_states(void);
+
 extern void pnv_lpc_init(void);
 
 bool cpu_core_split_required(void);

arch/powerpc/platforms/powernv/setup.c

@@ -288,6 +288,55 @@ static void __init pnv_setup_machdep_rtas(void)
 }
 #endif /* CONFIG_PPC_POWERNV_RTAS */
 
+static u32 supported_cpuidle_states;
+
+u32 pnv_get_supported_cpuidle_states(void)
+{
+	return supported_cpuidle_states;
+}
+
+static int __init pnv_init_idle_states(void)
+{
+	struct device_node *power_mgt;
+	int dt_idle_states;
+	const __be32 *idle_state_flags;
+	u32 len_flags, flags;
+	int i;
+
+	supported_cpuidle_states = 0;
+
+	if (cpuidle_disable != IDLE_NO_OVERRIDE)
+		return 0;
+
+	if (!firmware_has_feature(FW_FEATURE_OPALv3))
+		return 0;
+
+	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
+	if (!power_mgt) {
+		pr_warn("opal: PowerMgmt Node not found\n");
+		return 0;
+	}
+
+	idle_state_flags = of_get_property(power_mgt,
+			"ibm,cpu-idle-state-flags", &len_flags);
+	if (!idle_state_flags) {
+		pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n");
+		return 0;
+	}
+
+	dt_idle_states = len_flags / sizeof(u32);
+
+	for (i = 0; i < dt_idle_states; i++) {
+		flags = be32_to_cpu(idle_state_flags[i]);
+		supported_cpuidle_states |= flags;
+	}
+
+	return 0;
+}
+
+subsys_initcall(pnv_init_idle_states);
+
+
 static int __init pnv_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();

arch/powerpc/platforms/powernv/smp.c

@@ -150,6 +150,7 @@ static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
 	unsigned long srr1;
+	u32 idle_states;
 
 	/* Standard hot unplug procedure */
 	local_irq_disable();
@@ -160,13 +161,17 @@ static void pnv_smp_cpu_kill_self(void)
 	generic_set_cpu_dead(cpu);
 	smp_wmb();
 
+	idle_states = pnv_get_supported_cpuidle_states();
 	/* We don't want to take decrementer interrupts while we are offline,
 	 * so clear LPCR:PECE1. We keep PECE2 enabled.
 	 */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
 		ppc64_runlatch_off();
-		srr1 = power7_nap(1);
+		if (idle_states & OPAL_PM_SLEEP_ENABLED)
+			srr1 = power7_sleep();
+		else
+			srr1 = power7_nap(1);
 		ppc64_runlatch_on();
 
 		/*

drivers/cpuidle/cpuidle-powernv.c

@@ -16,13 +16,10 @@
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
+#include <asm/opal.h>
 #include <asm/runlatch.h>
 
-/* Flags and constants used in PowerNV platform */
-
 #define MAX_POWERNV_IDLE_STATES	8
-#define IDLE_USE_INST_NAP	0x00010000 /* Use nap instruction */
-#define IDLE_USE_INST_SLEEP	0x00020000 /* Use sleep instruction */
 
 struct cpuidle_driver powernv_idle_driver = {
 	.name             = "powernv_idle",
@@ -198,7 +195,7 @@ static int powernv_add_idle_states(void)
 		 * target residency to be 10x exit_latency
 		 */
 		latency_ns = be32_to_cpu(idle_state_latency[i]);
-		if (flags & IDLE_USE_INST_NAP) {
+		if (flags & OPAL_PM_NAP_ENABLED) {
 			/* Add NAP state */
 			strcpy(powernv_states[nr_idle_states].name, "Nap");
 			strcpy(powernv_states[nr_idle_states].desc, "Nap");
@@ -211,7 +208,7 @@ static int powernv_add_idle_states(void)
 			nr_idle_states++;
 		}
 
-		if (flags & IDLE_USE_INST_SLEEP) {
+		if (flags & OPAL_PM_SLEEP_ENABLED) {
 			/* Add FASTSLEEP state */
 			strcpy(powernv_states[nr_idle_states].name, "FastSleep");
 			strcpy(powernv_states[nr_idle_states].desc, "FastSleep");