Review/fastsleep

arch/powerpc/include/asm/cputhreads.h

@@ -31,9 +31,9 @@ extern cpumask_t threads_core_mask;
 /* cpu_thread_mask_to_cores - Return a cpumask of one per cores
  *                            hit by the argument
  *
- * @threads:	a cpumask of threads
+ * @threads:	a cpumask of online threads
  *
- * This function returns a cpumask which will have one "cpu" (or thread)
+ * This function returns a cpumask which will have one online cpu's
  * bit set for each core that has at least one thread set in the argument.
  *
  * This can typically be used for things like IPI for tlb invalidations
@@ -42,13 +42,16 @@ extern cpumask_t threads_core_mask;
 static inline cpumask_t cpu_thread_mask_to_cores(const struct cpumask *threads)
 {
 	cpumask_t	tmp, res;
-	int		i;
+	int		i, cpu;
 
 	cpumask_clear(&res);
 	for (i = 0; i < NR_CPUS; i += threads_per_core) {
 		cpumask_shift_left(&tmp, &threads_core_mask, i);
-		if (cpumask_intersects(threads, &tmp))
-			cpumask_set_cpu(i, &res);
+		if (cpumask_intersects(threads, &tmp)) {
+			cpu = cpumask_next_and(-1, &tmp, cpu_online_mask);
+			if (cpu < nr_cpu_ids)
+				cpumask_set_cpu(cpu, &res);
+		}
 	}
 	return res;
 }

arch/powerpc/include/asm/opal-api.h

@@ -165,6 +165,13 @@
 #define OPAL_PM_WINKLE_ENABLED		0x00040000
 #define OPAL_PM_SLEEP_ENABLED_ER1	0x00080000 /* with workaround */
 
+/*
+ * OPAL_CONFIG_CPU_IDLE_STATE parameters
+ */
+#define OPAL_CONFIG_IDLE_FASTSLEEP	1
+#define OPAL_CONFIG_IDLE_UNDO		0
+#define OPAL_CONFIG_IDLE_APPLY		1
+
 #ifndef __ASSEMBLY__
 
 /* Other enums */

arch/powerpc/include/asm/opal.h

@@ -186,6 +186,7 @@ int64_t opal_handle_hmi(void);
 int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end);
 int64_t opal_unregister_dump_region(uint32_t id);
 int64_t opal_slw_set_reg(uint64_t cpu_pir, uint64_t sprn, uint64_t val);
+int64_t opal_config_cpu_idle_state(uint64_t state, uint64_t flag);
 int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number);
 int64_t opal_ipmi_send(uint64_t interface, struct opal_ipmi_msg *msg,
 		uint64_t msg_len);

arch/powerpc/platforms/powernv/Makefile

@@ -1,4 +1,4 @@
-obj-y			+= setup.o opal-wrappers.o opal.o opal-async.o
+obj-y			+= setup.o opal-wrappers.o opal.o opal-async.o idle.o
 obj-y			+= opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y			+= rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
 obj-y			+= opal-msglog.o opal-hmi.o opal-power.o

arch/powerpc/platforms/powernv/idle.c

@@ -0,0 +1,293 @@
+/*
+ * PowerNV cpuidle code
+ *
+ * Copyright 2015 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/device.h>
+#include <linux/cpu.h>
+
+#include <asm/firmware.h>
+#include <asm/opal.h>
+#include <asm/cputhreads.h>
+#include <asm/cpuidle.h>
+#include <asm/code-patching.h>
+#include <asm/smp.h>
+
+#include "powernv.h"
+#include "subcore.h"
+
+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) & ~(u64)LPCR_PECE1;
+	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;
+	int nr_cores = cpu_nr_cores();
+	u32 *core_idle_state;
+
+	/*
+	 * core_idle_state - First 8 bits track the idle state of each thread
+	 * of the core. The 8th bit is the lock bit. Initially all thread bits
+	 * are set. They are cleared when the thread enters deep idle state
+	 * like sleep and winkle. Initially the lock bit is cleared.
+	 * The lock bit has 2 purposes
+	 * a. While the first thread is restoring core state, it prevents
+	 * other threads in the core from switching to process context.
+	 * b. While the last thread in the core is saving the core state, it
+	 * prevents a different thread from waking up.
+	 */
+	for (i = 0; i < nr_cores; i++) {
+		int first_cpu = i * threads_per_core;
+		int node = cpu_to_node(first_cpu);
+
+		core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
+		*core_idle_state = PNV_CORE_IDLE_THREAD_BITS;
+
+		for (j = 0; j < threads_per_core; j++) {
+			int cpu = first_cpu + j;
+
+			paca[cpu].core_idle_state_ptr = core_idle_state;
+			paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
+			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)
+{
+	return supported_cpuidle_states;
+}
+EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);
+
+
+static void pnv_fastsleep_workaround_apply(void *info)
+
+{
+	int rc;
+	int *err = info;
+
+	rc = opal_config_cpu_idle_state(OPAL_CONFIG_IDLE_FASTSLEEP,
+					OPAL_CONFIG_IDLE_APPLY);
+	if (rc)
+		*err = 1;
+}
+
+/*
+ * Used to store fastsleep workaround state
+ * 0 - Workaround applied/undone at fastsleep entry/exit path (Default)
+ * 1 - Workaround applied once, never undone.
+ */
+static u8 fastsleep_workaround_applyonce;
+
+static ssize_t show_fastsleep_workaround_applyonce(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", fastsleep_workaround_applyonce);
+}
+
+static ssize_t store_fastsleep_workaround_applyonce(struct device *dev,
+		struct device_attribute *attr, const char *buf,
+		size_t count)
+{
+	cpumask_t primary_thread_mask;
+	int err;
+	u8 val;
+
+	if (kstrtou8(buf, 0, &val) || val != 1)
+		return -EINVAL;
+
+	if (fastsleep_workaround_applyonce == 1)
+		return count;
+
+	/*
+	 * fastsleep_workaround_applyonce = 1 implies
+	 * fastsleep workaround needs to be left in 'applied' state on all
+	 * the cores. Do this by-
+	 * 1. Patching out the call to 'undo' workaround in fastsleep exit path
+	 * 2. Sending ipi to all the cores which have atleast one online thread
+	 * 3. Patching out the call to 'apply' workaround in fastsleep entry
+	 * path
+	 * There is no need to send ipi to cores which have all threads
+	 * offlined, as last thread of the core entering fastsleep or deeper
+	 * state would have applied workaround.
+	 */
+	err = patch_instruction(
+		(unsigned int *)pnv_fastsleep_workaround_at_exit,
+		PPC_INST_NOP);
+	if (err) {
+		pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_exit");
+		goto fail;
+	}
+
+	get_online_cpus();
+	primary_thread_mask = cpu_online_cores_map();
+	on_each_cpu_mask(&primary_thread_mask,
+				pnv_fastsleep_workaround_apply,
+				&err, 1);
+	put_online_cpus();
+	if (err) {
+		pr_err("fastsleep_workaround_applyonce change failed while running pnv_fastsleep_workaround_apply");
+		goto fail;
+	}
+
+	err = patch_instruction(
+		(unsigned int *)pnv_fastsleep_workaround_at_entry,
+		PPC_INST_NOP);
+	if (err) {
+		pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_entry");
+		goto fail;
+	}
+
+	fastsleep_workaround_applyonce = 1;
+
+	return count;
+fail:
+	return -EIO;
+}
+
+static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600,
+			show_fastsleep_workaround_applyonce,
+			store_fastsleep_workaround_applyonce);
+
+static int __init pnv_init_idle_states(void)
+{
+	struct device_node *power_mgt;
+	int dt_idle_states;
+	u32 *flags;
+	int i;
+
+	supported_cpuidle_states = 0;
+
+	if (cpuidle_disable != IDLE_NO_OVERRIDE)
+		goto out;
+
+	if (!firmware_has_feature(FW_FEATURE_OPALv3))
+		goto out;
+
+	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
+	if (!power_mgt) {
+		pr_warn("opal: PowerMgmt Node not found\n");
+		goto out;
+	}
+	dt_idle_states = of_property_count_u32_elems(power_mgt,
+			"ibm,cpu-idle-state-flags");
+	if (dt_idle_states < 0) {
+		pr_warn("cpuidle-powernv: no idle states found in the DT\n");
+		goto out;
+	}
+
+	flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL);
+	if (of_property_read_u32_array(power_mgt,
+			"ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
+		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n");
+		goto out_free;
+	}
+
+	for (i = 0; i < dt_idle_states; i++)
+		supported_cpuidle_states |= flags[i];
+
+	if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
+		patch_instruction(
+			(unsigned int *)pnv_fastsleep_workaround_at_entry,
+			PPC_INST_NOP);
+		patch_instruction(
+			(unsigned int *)pnv_fastsleep_workaround_at_exit,
+			PPC_INST_NOP);
+	} else {
+		/*
+		 * OPAL_PM_SLEEP_ENABLED_ER1 is set. It indicates that
+		 * workaround is needed to use fastsleep. Provide sysfs
+		 * control to choose how this workaround has to be applied.
+		 */
+		device_create_file(cpu_subsys.dev_root,
+				&dev_attr_fastsleep_workaround_applyonce);
+	}
+
+	pnv_alloc_idle_core_states();
+out_free:
+	kfree(flags);
+out:
+	return 0;
+}
+
+subsys_initcall(pnv_init_idle_states);

arch/powerpc/platforms/powernv/opal-wrappers.S

@@ -283,6 +283,7 @@ 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_config_cpu_idle_state,		OPAL_CONFIG_CPU_IDLE_STATE);
 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);