[PATCH] ppc64: SMU based macs cpufreq support

CPU freq support using 970FX powertune facility for iMac G5 and SMU
based single CPU desktop.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>

6 files changed, 412 insertions, 22 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 6ffae2d2b3fa..3ac9195dab35 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -404,6 +404,14 @@ config CPU_FREQ_PMAC
 	  this currently includes some models of iBook & Titanium
 	  PowerBook.
 
+config CPU_FREQ_PMAC64
+	bool "Support for some Apple G5s"
+	depends on CPU_FREQ && PMAC_SMU && PPC64
+	select CPU_FREQ_TABLE
+	help
+	  This adds support for frequency switching on Apple iMac G5,
+	  and some of the more recent desktop G5 machines as well.
+
 config PPC601_SYNC_FIX
 	bool "Workarounds for PPC601 bugs"
 	depends on 6xx && (PPC_PREP || PPC_PMAC)
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index b3e95ff0dba0..ae1433da09b2 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -604,6 +604,76 @@ _GLOBAL(real_writeb)
 #endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) */
 
 /*
+ * SCOM access functions for 970 (FX only for now)
+ *
+ * unsigned long scom970_read(unsigned int address);
+ * void scom970_write(unsigned int address, unsigned long value);
+ *
+ * The address passed in is the 24 bits register address. This code
+ * is 970 specific and will not check the status bits, so you should
+ * know what you are doing.
+ */
+_GLOBAL(scom970_read)
+	/* interrupts off */
+	mfmsr	r4
+	ori	r0,r4,MSR_EE
+	xori	r0,r0,MSR_EE
+	mtmsrd	r0,1
+
+	/* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
+	 * (including parity). On current CPUs they must be 0'd,
+	 * and finally or in RW bit
+	 */
+	rlwinm	r3,r3,8,0,15
+	ori	r3,r3,0x8000
+
+	/* do the actual scom read */
+	sync
+	mtspr	SPRN_SCOMC,r3
+	isync
+	mfspr	r3,SPRN_SCOMD
+	isync
+	mfspr	r0,SPRN_SCOMC
+	isync
+
+	/* XXX:	fixup result on some buggy 970's (ouch ! we lost a bit, bah
+	 * that's the best we can do). Not implemented yet as we don't use
+	 * the scom on any of the bogus CPUs yet, but may have to be done
+	 * ultimately
+	 */
+
+	/* restore interrupts */
+	mtmsrd	r4,1
+	blr
+
+
+_GLOBAL(scom970_write)
+	/* interrupts off */
+	mfmsr	r5
+	ori	r0,r5,MSR_EE
+	xori	r0,r0,MSR_EE
+	mtmsrd	r0,1
+
+	/* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
+	 * (including parity). On current CPUs they must be 0'd.
+	 */
+
+	rlwinm	r3,r3,8,0,15
+
+	sync
+	mtspr	SPRN_SCOMD,r4      /* write data */
+	isync
+	mtspr	SPRN_SCOMC,r3      /* write command */
+	isync
+	mfspr	3,SPRN_SCOMC
+	isync
+
+	/* restore interrupts */
+	mtmsrd	r5,1
+	blr
+
+
+/*
  * Create a kernel thread
  *   kernel_thread(fn, arg, flags)
  */
diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile
index 4369676f1d54..c9df44fcf571 100644
--- a/arch/powerpc/platforms/powermac/Makefile
+++ b/arch/powerpc/platforms/powermac/Makefile
@@ -1,7 +1,8 @@
 obj-y				+= pic.o setup.o time.o feature.o pci.o \
 				   sleep.o low_i2c.o cache.o
 obj-$(CONFIG_PMAC_BACKLIGHT)	+= backlight.o
-obj-$(CONFIG_CPU_FREQ_PMAC)	+= cpufreq.o
+obj-$(CONFIG_CPU_FREQ_PMAC)	+= cpufreq_32.o
+obj-$(CONFIG_CPU_FREQ_PMAC64)	+= cpufreq_64.o
 obj-$(CONFIG_NVRAM)		+= nvram.o
 # ppc64 pmac doesn't define CONFIG_NVRAM but needs nvram stuff
 obj-$(CONFIG_PPC64)		+= nvram.o
diff --git a/arch/powerpc/platforms/powermac/cpufreq.c b/arch/powerpc/platforms/powermac/cpufreq_32.c
index c47f8b69725c..7960a7bfca0a 100644
--- a/arch/powerpc/platforms/powermac/cpufreq.c
+++ b/arch/powerpc/platforms/powermac/cpufreq_32.c
@@ -397,18 +397,16 @@ static int pmac_cpufreq_target(	struct cpufreq_policy *policy,
 					unsigned int relation)
 {
 	unsigned int    newstate = 0;
+	int		rc;
 
 	if (cpufreq_frequency_table_target(policy, pmac_cpu_freqs,
 			target_freq, relation, &newstate))
 		return -EINVAL;
 
-	return do_set_cpu_speed(newstate, 1);
-}
+	rc = do_set_cpu_speed(newstate, 1);
 
-unsigned int pmac_get_one_cpufreq(int i)
-{
-	/* Supports only one CPU for now */
-	return (i == 0) ? cur_freq : 0;
+	ppc_proc_freq = cur_freq * 1000ul;
+	return rc;
 }
 
 static int pmac_cpufreq_cpu_init(struct cpufreq_policy *policy)
@@ -464,7 +462,7 @@ static int pmac_cpufreq_resume(struct cpufreq_policy *policy)
 	/* If we resume, first check if we have a get() function */
 	if (get_speed_proc)
 		cur_freq = get_speed_proc();
-	else
+	else)
 		cur_freq = 0;
 
 	/* We don't, hrm... we don't really know our speed here, best
@@ -474,6 +472,8 @@ static int pmac_cpufreq_resume(struct cpufreq_policy *policy)
 	do_set_cpu_speed(sleep_freq == low_freq ?
 			 CPUFREQ_LOW : CPUFREQ_HIGH, 0);
 
+	ppc_proc_freq = cur_freq * 1000ul;
+
 	no_schedule = 0;
 	return 0;
 }
@@ -547,7 +547,7 @@ static int pmac_cpufreq_init_MacRISC3(struct device_node *cpunode)
 		 */
 		if (low_freq < 98000000)
 			low_freq = 101000000;
-			
+
 		/* Convert those to CPU core clocks */
 		low_freq = (low_freq * (*ratio)) / 2000;
 		hi_freq = (hi_freq * (*ratio)) / 2000;
@@ -714,6 +714,7 @@ out:
 
 	pmac_cpu_freqs[CPUFREQ_LOW].frequency = low_freq;
 	pmac_cpu_freqs[CPUFREQ_HIGH].frequency = hi_freq;
+	ppc_proc_freq = cur_freq * 1000ul;
 
 	printk(KERN_INFO "Registering PowerMac CPU frequency driver\n");
 	printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Boot: %d Mhz\n",
diff --git a/arch/powerpc/platforms/powermac/cpufreq_64.c b/arch/powerpc/platforms/powermac/cpufreq_64.c
new file mode 100644
index 000000000000..39150342c6f1
--- /dev/null
+++ b/arch/powerpc/platforms/powermac/cpufreq_64.c
@@ -0,0 +1,323 @@
+/*
+ *  Copyright (C) 2002 - 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ *  and                       Markus Demleitner <msdemlei@cl.uni-heidelberg.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This driver adds basic cpufreq support for SMU & 970FX based G5 Macs,
+ * that is iMac G5 and latest single CPU desktop.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/cpufreq.h>
+#include <linux/init.h>
+#include <linux/completion.h>
+#include <asm/prom.h>
+#include <asm/machdep.h>
+#include <asm/irq.h>
+#include <asm/sections.h>
+#include <asm/cputable.h>
+#include <asm/time.h>
+#include <asm/smu.h>
+
+#undef DEBUG
+
+#ifdef DEBUG
+#define DBG(fmt...) printk(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+/* see 970FX user manual */
+
+#define SCOM_PCR 0x0aa001			/* PCR scom addr */
+
+#define PCR_HILO_SELECT		0x80000000U	/* 1 = PCR, 0 = PCRH */
+#define PCR_SPEED_FULL		0x00000000U	/* 1:1 speed value */
+#define PCR_SPEED_HALF		0x00020000U	/* 1:2 speed value */
+#define PCR_SPEED_QUARTER	0x00040000U	/* 1:4 speed value */
+#define PCR_SPEED_MASK		0x000e0000U	/* speed mask */
+#define PCR_SPEED_SHIFT		17
+#define PCR_FREQ_REQ_VALID	0x00010000U	/* freq request valid */
+#define PCR_VOLT_REQ_VALID	0x00008000U	/* volt request valid */
+#define PCR_TARGET_TIME_MASK	0x00006000U	/* target time */
+#define PCR_STATLAT_MASK	0x00001f00U	/* STATLAT value */
+#define PCR_SNOOPLAT_MASK	0x000000f0U	/* SNOOPLAT value */
+#define PCR_SNOOPACC_MASK	0x0000000fU	/* SNOOPACC value */
+
+#define SCOM_PSR 0x408001			/* PSR scom addr */
+/* warning: PSR is a 64 bits register */
+#define PSR_CMD_RECEIVED	0x2000000000000000U   /* command received */
+#define PSR_CMD_COMPLETED	0x1000000000000000U   /* command completed */
+#define PSR_CUR_SPEED_MASK	0x0300000000000000U   /* current speed */
+#define PSR_CUR_SPEED_SHIFT	(56)
+
+/*
+ * The G5 only supports two frequencies (Quarter speed is not supported)
+ */
+#define CPUFREQ_HIGH                  0
+#define CPUFREQ_LOW                   1
+
+static struct cpufreq_frequency_table g5_cpu_freqs[] = {
+	{CPUFREQ_HIGH, 		0},
+	{CPUFREQ_LOW,		0},
+	{0,			CPUFREQ_TABLE_END},
+};
+
+static struct freq_attr* g5_cpu_freqs_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
+/* Power mode data is an array of the 32 bits PCR values to use for
+ * the various frequencies, retreived from the device-tree
+ */
+static u32 *g5_pmode_data;
+static int g5_pmode_max;
+static int g5_pmode_cur;
+
+static DECLARE_MUTEX(g5_switch_mutex);
+
+
+static struct smu_sdbp_fvt *g5_fvt_table;	/* table of op. points */
+static int g5_fvt_count;			/* number of op. points */
+static int g5_fvt_cur;				/* current op. point */
+
+/* ----------------- real hardware interface */
+
+static void g5_switch_volt(int speed_mode)
+{
+	struct smu_simple_cmd	cmd;
+
+	DECLARE_COMPLETION(comp);
+	smu_queue_simple(&cmd, SMU_CMD_POWER_COMMAND, 8, smu_done_complete,
+			 &comp, 'V', 'S', 'L', 'E', 'W',
+			 0xff, g5_fvt_cur+1, speed_mode);
+	wait_for_completion(&comp);
+}
+
+static int g5_switch_freq(int speed_mode)
+{
+	struct cpufreq_freqs freqs;
+	int to;
+
+	if (g5_pmode_cur == speed_mode)
+		return 0;
+
+	down(&g5_switch_mutex);
+
+	freqs.old = g5_cpu_freqs[g5_pmode_cur].frequency;
+	freqs.new = g5_cpu_freqs[speed_mode].frequency;
+	freqs.cpu = 0;
+
+	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	/* If frequency is going up, first ramp up the voltage */
+	if (speed_mode < g5_pmode_cur)
+		g5_switch_volt(speed_mode);
+
+	/* Clear PCR high */
+	scom970_write(SCOM_PCR, 0);
+	/* Clear PCR low */
+       	scom970_write(SCOM_PCR, PCR_HILO_SELECT | 0);
+	/* Set PCR low */
+	scom970_write(SCOM_PCR, PCR_HILO_SELECT |
+		      g5_pmode_data[speed_mode]);
+
+	/* Wait for completion */
+	for (to = 0; to < 10; to++) {
+		unsigned long psr = scom970_read(SCOM_PSR);
+
+		if ((psr & PSR_CMD_RECEIVED) == 0 &&
+		    (((psr >> PSR_CUR_SPEED_SHIFT) ^
+		      (g5_pmode_data[speed_mode] >> PCR_SPEED_SHIFT)) & 0x3)
+		    == 0)
+			break;
+		if (psr & PSR_CMD_COMPLETED)
+			break;
+		udelay(100);
+	}
+
+	/* If frequency is going down, last ramp the voltage */
+	if (speed_mode > g5_pmode_cur)
+		g5_switch_volt(speed_mode);
+
+	g5_pmode_cur = speed_mode;
+	ppc_proc_freq = g5_cpu_freqs[speed_mode].frequency * 1000ul;
+
+	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+
+	up(&g5_switch_mutex);
+
+	return 0;
+}
+
+static int g5_query_freq(void)
+{
+	unsigned long psr = scom970_read(SCOM_PSR);
+	int i;
+
+	for (i = 0; i <= g5_pmode_max; i++)
+		if ((((psr >> PSR_CUR_SPEED_SHIFT) ^
+		      (g5_pmode_data[i] >> PCR_SPEED_SHIFT)) & 0x3) == 0)
+			break;
+	return i;
+}
+
+/* ----------------- cpufreq bookkeeping */
+
+static int g5_cpufreq_verify(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy, g5_cpu_freqs);
+}
+
+static int g5_cpufreq_target(struct cpufreq_policy *policy,
+	unsigned int target_freq, unsigned int relation)
+{
+	unsigned int    newstate = 0;
+
+	if (cpufreq_frequency_table_target(policy, g5_cpu_freqs,
+			target_freq, relation, &newstate))
+		return -EINVAL;
+
+	return g5_switch_freq(newstate);
+}
+
+static unsigned int g5_cpufreq_get_speed(unsigned int cpu)
+{
+	return g5_cpu_freqs[g5_pmode_cur].frequency;
+}
+
+static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	if (policy->cpu != 0)
+		return -ENODEV;
+
+	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
+	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
+	policy->cur = g5_cpu_freqs[g5_query_freq()].frequency;
+	cpufreq_frequency_table_get_attr(g5_cpu_freqs, policy->cpu);
+
+	return cpufreq_frequency_table_cpuinfo(policy,
+		g5_cpu_freqs);
+}
+
+
+static struct cpufreq_driver g5_cpufreq_driver = {
+	.name		= "powermac",
+	.owner		= THIS_MODULE,
+	.flags		= CPUFREQ_CONST_LOOPS,
+	.init		= g5_cpufreq_cpu_init,
+	.verify		= g5_cpufreq_verify,
+	.target		= g5_cpufreq_target,
+	.get		= g5_cpufreq_get_speed,
+	.attr 		= g5_cpu_freqs_attr,
+};
+
+
+static int __init g5_cpufreq_init(void)
+{
+	struct device_node *cpunode;
+	unsigned int psize, ssize;
+	struct smu_sdbp_header *shdr;
+	unsigned long max_freq;
+	u32 *valp;
+	int rc = -ENODEV;
+
+	/* Look for CPU and SMU nodes */
+	cpunode = of_find_node_by_type(NULL, "cpu");
+	if (!cpunode) {
+		DBG("No CPU node !\n");
+		return -ENODEV;
+	}
+
+	/* Check 970FX for now */
+	valp = (u32 *)get_property(cpunode, "cpu-version", NULL);
+	if (!valp) {
+		DBG("No cpu-version property !\n");
+		goto bail_noprops;
+	}
+	if (((*valp) >> 16) != 0x3c) {
+		DBG("Wrong CPU version: %08x\n", *valp);
+		goto bail_noprops;
+	}
+
+	/* Look for the powertune data in the device-tree */
+	g5_pmode_data = (u32 *)get_property(cpunode, "power-mode-data",&psize);
+	if (!g5_pmode_data) {
+		DBG("No power-mode-data !\n");
+		goto bail_noprops;
+	}
+	g5_pmode_max = psize / sizeof(u32) - 1;
+
+	/* Look for the FVT table */
+	shdr = smu_get_sdb_partition(SMU_SDB_FVT_ID, NULL);
+	if (!shdr)
+		goto bail_noprops;
+	g5_fvt_table = (struct smu_sdbp_fvt *)&shdr[1];
+	ssize = (shdr->len * sizeof(u32)) - sizeof(struct smu_sdbp_header);
+	g5_fvt_count = ssize / sizeof(struct smu_sdbp_fvt);
+	g5_fvt_cur = 0;
+
+	/* Sanity checking */
+	if (g5_fvt_count < 1 || g5_pmode_max < 1)
+		goto bail_noprops;
+
+	/*
+	 * From what I see, clock-frequency is always the maximal frequency.
+	 * The current driver can not slew sysclk yet, so we really only deal
+	 * with powertune steps for now. We also only implement full freq and
+	 * half freq in this version. So far, I haven't yet seen a machine
+	 * supporting anything else.
+	 */
+	valp = (u32 *)get_property(cpunode, "clock-frequency", NULL);
+	if (!valp)
+		return -ENODEV;
+	max_freq = (*valp)/1000;
+	g5_cpu_freqs[0].frequency = max_freq;
+	g5_cpu_freqs[1].frequency = max_freq/2;
+
+	/* Check current frequency */
+	g5_pmode_cur = g5_query_freq();
+	if (g5_pmode_cur > 1)
+		/* We don't support anything but 1:1 and 1:2, fixup ... */
+		g5_pmode_cur = 1;
+
+	/* Force apply current frequency to make sure everything is in
+	 * sync (voltage is right for example). Firmware may leave us with
+	 * a strange setting ...
+	 */
+	g5_switch_freq(g5_pmode_cur);
+
+	printk(KERN_INFO "Registering G5 CPU frequency driver\n");
+	printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n",
+		g5_cpu_freqs[1].frequency/1000,
+		g5_cpu_freqs[0].frequency/1000,
+		g5_cpu_freqs[g5_pmode_cur].frequency/1000);
+
+	rc = cpufreq_register_driver(&g5_cpufreq_driver);
+
+	/* We keep the CPU node on hold... hopefully, Apple G5 don't have
+	 * hotplug CPU with a dynamic device-tree ...
+	 */
+	return rc;
+
+ bail_noprops:
+	of_node_put(cpunode);
+
+	return rc;
+}
+
+module_init(g5_cpufreq_init);
+
+
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 80b58c1ec412..7acb0546671f 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -193,18 +193,6 @@ static void pmac_show_cpuinfo(struct seq_file *m)
 		   pmac_newworld ? "NewWorld" : "OldWorld");
 }
 
-static void pmac_show_percpuinfo(struct seq_file *m, int i)
-{
-#ifdef CONFIG_CPU_FREQ_PMAC
-	extern unsigned int pmac_get_one_cpufreq(int i);
-	unsigned int freq = pmac_get_one_cpufreq(i);
-	if (freq != 0) {
-		seq_printf(m, "clock\t\t: %dMHz\n", freq/1000);
-		return;
-	}
-#endif /* CONFIG_CPU_FREQ_PMAC */
-}
-
 #ifndef CONFIG_ADB_CUDA
 int find_via_cuda(void)
 {
@@ -767,7 +755,6 @@ struct machdep_calls __initdata pmac_md = {
 	.setup_arch		= pmac_setup_arch,
 	.init_early		= pmac_init_early,
 	.show_cpuinfo		= pmac_show_cpuinfo,
-	.show_percpuinfo	= pmac_show_percpuinfo,
 	.init_IRQ		= pmac_pic_init,
 	.get_irq		= mpic_get_irq,	/* changed later */
 	.pcibios_fixup		= pmac_pcibios_fixup,