1 files changed, 676 insertions, 166 deletions

diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index b7fc2d88495..8b4c857c142 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -15,31 +15,46 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
+#include <linux/capability.h>
+#include <linux/delay.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/completion.h>
+#include <linux/cpumask.h>
+#include <linux/memblock.h>
+#include <linux/slab.h>
+#include <linux/reboot.h>
 
 #include <asm/prom.h>
 #include <asm/rtas.h>
-#include <asm/semaphore.h>
+#include <asm/hvcall.h>
 #include <asm/machdep.h>
+#include <asm/firmware.h>
 #include <asm/page.h>
 #include <asm/param.h>
-#include <asm/system.h>
 #include <asm/delay.h>
 #include <asm/uaccess.h>
-#include <asm/lmb.h>
-#ifdef CONFIG_PPC64
-#include <asm/systemcfg.h>
-#endif
+#include <asm/udbg.h>
+#include <asm/syscalls.h>
+#include <asm/smp.h>
+#include <linux/atomic.h>
+#include <asm/time.h>
+#include <asm/mmu.h>
+#include <asm/topology.h>
 
 struct rtas_t rtas = {
-	.lock = SPIN_LOCK_UNLOCKED
+	.lock = __ARCH_SPIN_LOCK_UNLOCKED
 };
-
 EXPORT_SYMBOL(rtas);
 
 DEFINE_SPINLOCK(rtas_data_buf_lock);
+EXPORT_SYMBOL(rtas_data_buf_lock);
+
 char rtas_data_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned;
+EXPORT_SYMBOL(rtas_data_buf);
+
 unsigned long rtas_rmo_buf;
 
 /*
@@ -49,32 +64,54 @@ unsigned long rtas_rmo_buf;
 void (*rtas_flash_term_hook)(int);
 EXPORT_SYMBOL(rtas_flash_term_hook);
 
+/* RTAS use home made raw locking instead of spin_lock_irqsave
+ * because those can be called from within really nasty contexts
+ * such as having the timebase stopped which would lockup with
+ * normal locks and spinlock debugging enabled
+ */
+static unsigned long lock_rtas(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	preempt_disable();
+	arch_spin_lock_flags(&rtas.lock, flags);
+	return flags;
+}
+
+static void unlock_rtas(unsigned long flags)
+{
+	arch_spin_unlock(&rtas.lock);
+	local_irq_restore(flags);
+	preempt_enable();
+}
+
 /*
  * call_rtas_display_status and call_rtas_display_status_delay
  * are designed only for very early low-level debugging, which
  * is why the token is hard-coded to 10.
  */
-void call_rtas_display_status(unsigned char c)
+static void call_rtas_display_status(unsigned char c)
 {
 	struct rtas_args *args = &rtas.args;
 	unsigned long s;
 
 	if (!rtas.base)
 		return;
-	spin_lock_irqsave(&rtas.lock, s);
+	s = lock_rtas();
 
-	args->token = 10;
-	args->nargs = 1;
-	args->nret  = 1;
-	args->rets  = (rtas_arg_t *)&(args->args[1]);
-	args->args[0] = (int)c;
+	args->token = cpu_to_be32(10);
+	args->nargs = cpu_to_be32(1);
+	args->nret  = cpu_to_be32(1);
+	args->rets  = &(args->args[1]);
+	args->args[0] = cpu_to_be32(c);
 
 	enter_rtas(__pa(args));
 
-	spin_unlock_irqrestore(&rtas.lock, s);
+	unlock_rtas(s);
 }
 
-void call_rtas_display_status_delay(unsigned char c)
+static void call_rtas_display_status_delay(char c)
 {
 	static int pending_newline = 0;  /* did last write end with unprinted newline? */
 	static int width = 16;
@@ -83,7 +120,7 @@ void call_rtas_display_status_delay(unsigned char c)
 		while (width-- > 0)
 			call_rtas_display_status(' ');
 		width = 16;
-		udelay(500000);
+		mdelay(500);
 		pending_newline = 1;
 	} else {
 		if (pending_newline) {
@@ -98,13 +135,80 @@ void call_rtas_display_status_delay(unsigned char c)
 	}
 }
 
+void __init udbg_init_rtas_panel(void)
+{
+	udbg_putc = call_rtas_display_status_delay;
+}
+
+#ifdef CONFIG_UDBG_RTAS_CONSOLE
+
+/* If you think you're dying before early_init_dt_scan_rtas() does its
+ * work, you can hard code the token values for your firmware here and
+ * hardcode rtas.base/entry etc.
+ */
+static unsigned int rtas_putchar_token = RTAS_UNKNOWN_SERVICE;
+static unsigned int rtas_getchar_token = RTAS_UNKNOWN_SERVICE;
+
+static void udbg_rtascon_putc(char c)
+{
+	int tries;
+
+	if (!rtas.base)
+		return;
+
+	/* Add CRs before LFs */
+	if (c == '\n')
+		udbg_rtascon_putc('\r');
+
+	/* if there is more than one character to be displayed, wait a bit */
+	for (tries = 0; tries < 16; tries++) {
+		if (rtas_call(rtas_putchar_token, 1, 1, NULL, c) == 0)
+			break;
+		udelay(1000);
+	}
+}
+
+static int udbg_rtascon_getc_poll(void)
+{
+	int c;
+
+	if (!rtas.base)
+		return -1;
+
+	if (rtas_call(rtas_getchar_token, 0, 2, &c))
+		return -1;
+
+	return c;
+}
+
+static int udbg_rtascon_getc(void)
+{
+	int c;
+
+	while ((c = udbg_rtascon_getc_poll()) == -1)
+		;
+
+	return c;
+}
+
+
+void __init udbg_init_rtas_console(void)
+{
+	udbg_putc = udbg_rtascon_putc;
+	udbg_getc = udbg_rtascon_getc;
+	udbg_getc_poll = udbg_rtascon_getc_poll;
+}
+#endif /* CONFIG_UDBG_RTAS_CONSOLE */
+
 void rtas_progress(char *s, unsigned short hex)
 {
 	struct device_node *root;
-	int width, *p;
+	int width;
+	const __be32 *p;
 	char *os;
 	static int display_character, set_indicator;
-	static int display_width, display_lines, *row_width, form_feed;
+	static int display_width, display_lines, form_feed;
+	static const int *row_width;
 	static DEFINE_SPINLOCK(progress_lock);
 	static int current_line;
 	static int pending_newline = 0;  /* did last write end with unprinted newline? */
@@ -114,18 +218,19 @@ void rtas_progress(char *s, unsigned short hex)
 
 	if (display_width == 0) {
 		display_width = 0x10;
-		if ((root = find_path_device("/rtas"))) {
-			if ((p = (unsigned int *)get_property(root,
+		if ((root = of_find_node_by_path("/rtas"))) {
+			if ((p = of_get_property(root,
 					"ibm,display-line-length", NULL)))
-				display_width = *p;
-			if ((p = (unsigned int *)get_property(root,
+				display_width = be32_to_cpu(*p);
+			if ((p = of_get_property(root,
 					"ibm,form-feed", NULL)))
-				form_feed = *p;
-			if ((p = (unsigned int *)get_property(root,
+				form_feed = be32_to_cpu(*p);
+			if ((p = of_get_property(root,
 					"ibm,display-number-of-lines", NULL)))
-				display_lines = *p;
-			row_width = (unsigned int *)get_property(root,
+				display_lines = be32_to_cpu(*p);
+			row_width = of_get_property(root,
 					"ibm,display-truncation-length", NULL);
+			of_node_put(root);
 		}
 		display_character = rtas_token("display-character");
 		set_indicator = rtas_token("set-indicator");
@@ -217,12 +322,19 @@ EXPORT_SYMBOL(rtas_progress);		/* needed by rtas_flash module */
 
 int rtas_token(const char *service)
 {
-	int *tokp;
+	const __be32 *tokp;
 	if (rtas.dev == NULL)
 		return RTAS_UNKNOWN_SERVICE;
-	tokp = (int *) get_property(rtas.dev, service, NULL);
-	return tokp ? *tokp : RTAS_UNKNOWN_SERVICE;
+	tokp = of_get_property(rtas.dev, service, NULL);
+	return tokp ? be32_to_cpu(*tokp) : RTAS_UNKNOWN_SERVICE;
+}
+EXPORT_SYMBOL(rtas_token);
+
+int rtas_service_present(const char *service)
+{
+	return rtas_token(service) != RTAS_UNKNOWN_SERVICE;
 }
+EXPORT_SYMBOL(rtas_service_present);
 
 #ifdef CONFIG_RTAS_ERROR_LOGGING
 /*
@@ -248,8 +360,8 @@ int rtas_get_error_log_max(void)
 EXPORT_SYMBOL(rtas_get_error_log_max);
 
 
-char rtas_err_buf[RTAS_ERROR_LOG_MAX];
-int rtas_last_error_token;
+static char rtas_err_buf[RTAS_ERROR_LOG_MAX];
+static int rtas_last_error_token;
 
 /** Return a copy of the detailed error text associated with the
  *  most recent failed call to rtas.  Because the error text
@@ -268,11 +380,11 @@ static char *__fetch_rtas_last_error(char *altbuf)
 
 	bufsz = rtas_get_error_log_max();
 
-	err_args.token = rtas_last_error_token;
-	err_args.nargs = 2;
-	err_args.nret = 1;
-	err_args.args[0] = (rtas_arg_t)__pa(rtas_err_buf);
-	err_args.args[1] = bufsz;
+	err_args.token = cpu_to_be32(rtas_last_error_token);
+	err_args.nargs = cpu_to_be32(2);
+	err_args.nret = cpu_to_be32(1);
+	err_args.args[0] = cpu_to_be32(__pa(rtas_err_buf));
+	err_args.args[1] = cpu_to_be32(bufsz);
 	err_args.args[2] = 0;
 
 	save_args = rtas.args;
@@ -315,20 +427,19 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 	char *buff_copy = NULL;
 	int ret;
 
-	if (token == RTAS_UNKNOWN_SERVICE)
+	if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
 		return -1;
 
-	/* Gotta do something different here, use global lock for now... */
-	spin_lock_irqsave(&rtas.lock, s);
+	s = lock_rtas();
 	rtas_args = &rtas.args;
 
-	rtas_args->token = token;
-	rtas_args->nargs = nargs;
-	rtas_args->nret  = nret;
-	rtas_args->rets  = (rtas_arg_t *)&(rtas_args->args[nargs]);
+	rtas_args->token = cpu_to_be32(token);
+	rtas_args->nargs = cpu_to_be32(nargs);
+	rtas_args->nret  = cpu_to_be32(nret);
+	rtas_args->rets  = &(rtas_args->args[nargs]);
 	va_start(list, outputs);
 	for (i = 0; i < nargs; ++i)
-		rtas_args->args[i] = va_arg(list, rtas_arg_t);
+		rtas_args->args[i] = cpu_to_be32(va_arg(list, __u32));
 	va_end(list);
 
 	for (i = 0; i < nret; ++i)
@@ -338,16 +449,15 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 
 	/* A -1 return code indicates that the last command couldn't
 	   be completed due to a hardware error. */
-	if (rtas_args->rets[0] == -1)
+	if (be32_to_cpu(rtas_args->rets[0]) == -1)
 		buff_copy = __fetch_rtas_last_error(NULL);
 
 	if (nret > 1 && outputs != NULL)
 		for (i = 0; i < nret-1; ++i)
-			outputs[i] = rtas_args->rets[i+1];
-	ret = (nret > 0)? rtas_args->rets[0]: 0;
+			outputs[i] = be32_to_cpu(rtas_args->rets[i+1]);
+	ret = (nret > 0)? be32_to_cpu(rtas_args->rets[0]): 0;
 
-	/* Gotta do something different here, use global lock for now... */
-	spin_unlock_irqrestore(&rtas.lock, s);
+	unlock_rtas(s);
 
 	if (buff_copy) {
 		log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
@@ -356,28 +466,43 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 	}
 	return ret;
 }
+EXPORT_SYMBOL(rtas_call);
 
-/* Given an RTAS status code of 990n compute the hinted delay of 10^n
- * (last digit) milliseconds.  For now we bound at n=5 (100 sec).
+/* For RTAS_BUSY (-2), delay for 1 millisecond.  For an extended busy status
+ * code of 990n, perform the hinted delay of 10^n (last digit) milliseconds.
  */
-unsigned int rtas_extended_busy_delay_time(int status)
+unsigned int rtas_busy_delay_time(int status)
 {
-	int order = status - 9900;
-	unsigned long ms;
+	int order;
+	unsigned int ms = 0;
+
+	if (status == RTAS_BUSY) {
+		ms = 1;
+	} else if (status >= 9900 && status <= 9905) {
+		order = status - 9900;
+		for (ms = 1; order > 0; order--)
+			ms *= 10;
+	}
+
+	return ms;
+}
+EXPORT_SYMBOL(rtas_busy_delay_time);
 
-	if (order < 0)
-		order = 0;	/* RTC depends on this for -2 clock busy */
-	else if (order > 5)
-		order = 5;	/* bound */
+/* For an RTAS busy status code, perform the hinted delay. */
+unsigned int rtas_busy_delay(int status)
+{
+	unsigned int ms;
 
-	/* Use microseconds for reasonable accuracy */
-	for (ms = 1; order > 0; order--)
-		ms *= 10;
+	might_sleep();
+	ms = rtas_busy_delay_time(status);
+	if (ms && need_resched())
+		msleep(ms);
 
-	return ms; 
+	return ms;
 }
+EXPORT_SYMBOL(rtas_busy_delay);
 
-int rtas_error_rc(int rtas_rc)
+static int rtas_error_rc(int rtas_rc)
 {
 	int rc;
 
@@ -399,7 +524,7 @@ int rtas_error_rc(int rtas_rc)
 			break;
 		default:
 			printk(KERN_ERR "%s: unexpected RTAS error %d\n",
-					__FUNCTION__, rtas_rc);
+					__func__, rtas_rc);
 			rc = -ERANGE;
 			break;
 	}
@@ -421,80 +546,106 @@ int rtas_get_power_level(int powerdomain, int *level)
 		return rtas_error_rc(rc);
 	return rc;
 }
+EXPORT_SYMBOL(rtas_get_power_level);
 
 int rtas_set_power_level(int powerdomain, int level, int *setlevel)
 {
 	int token = rtas_token("set-power-level");
-	unsigned int wait_time;
 	int rc;
 
 	if (token == RTAS_UNKNOWN_SERVICE)
 		return -ENOENT;
 
-	while (1) {
+	do {
 		rc = rtas_call(token, 2, 2, setlevel, powerdomain, level);
-		if (rc == RTAS_BUSY)
-			udelay(1);
-		else if (rtas_is_extended_busy(rc)) {
-			wait_time = rtas_extended_busy_delay_time(rc);
-			udelay(wait_time * 1000);
-		} else
-			break;
-	}
+	} while (rtas_busy_delay(rc));
 
 	if (rc < 0)
 		return rtas_error_rc(rc);
 	return rc;
 }
+EXPORT_SYMBOL(rtas_set_power_level);
 
 int rtas_get_sensor(int sensor, int index, int *state)
 {
 	int token = rtas_token("get-sensor-state");
-	unsigned int wait_time;
 	int rc;
 
 	if (token == RTAS_UNKNOWN_SERVICE)
 		return -ENOENT;
 
-	while (1) {
+	do {
 		rc = rtas_call(token, 2, 2, state, sensor, index);
-		if (rc == RTAS_BUSY)
-			udelay(1);
-		else if (rtas_is_extended_busy(rc)) {
-			wait_time = rtas_extended_busy_delay_time(rc);
-			udelay(wait_time * 1000);
-		} else
-			break;
-	}
+	} while (rtas_busy_delay(rc));
 
 	if (rc < 0)
 		return rtas_error_rc(rc);
 	return rc;
 }
+EXPORT_SYMBOL(rtas_get_sensor);
+
+bool rtas_indicator_present(int token, int *maxindex)
+{
+	int proplen, count, i;
+	const struct indicator_elem {
+		__be32 token;
+		__be32 maxindex;
+	} *indicators;
+
+	indicators = of_get_property(rtas.dev, "rtas-indicators", &proplen);
+	if (!indicators)
+		return false;
+
+	count = proplen / sizeof(struct indicator_elem);
+
+	for (i = 0; i < count; i++) {
+		if (__be32_to_cpu(indicators[i].token) != token)
+			continue;
+		if (maxindex)
+			*maxindex = __be32_to_cpu(indicators[i].maxindex);
+		return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(rtas_indicator_present);
 
 int rtas_set_indicator(int indicator, int index, int new_value)
 {
 	int token = rtas_token("set-indicator");
-	unsigned int wait_time;
 	int rc;
 
 	if (token == RTAS_UNKNOWN_SERVICE)
 		return -ENOENT;
 
-	while (1) {
+	do {
 		rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value);
-		if (rc == RTAS_BUSY)
-			udelay(1);
-		else if (rtas_is_extended_busy(rc)) {
-			wait_time = rtas_extended_busy_delay_time(rc);
-			udelay(wait_time * 1000);
-		}
-		else
-			break;
-	}
+	} while (rtas_busy_delay(rc));
+
+	if (rc < 0)
+		return rtas_error_rc(rc);
+	return rc;
+}
+EXPORT_SYMBOL(rtas_set_indicator);
+
+/*
+ * Ignoring RTAS extended delay
+ */
+int rtas_set_indicator_fast(int indicator, int index, int new_value)
+{
+	int rc;
+	int token = rtas_token("set-indicator");
+
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value);
+
+	WARN_ON(rc == -2 || (rc >= 9900 && rc <= 9905));
 
 	if (rc < 0)
 		return rtas_error_rc(rc);
+
 	return rc;
 }
 
@@ -534,7 +685,14 @@ void rtas_os_term(char *str)
 {
 	int status;
 
-	if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term"))
+	/*
+	 * Firmware with the ibm,extended-os-term property is guaranteed
+	 * to always return from an ibm,os-term call. Earlier versions without
+	 * this property may terminate the partition which we want to avoid
+	 * since it interferes with panic_timeout.
+	 */
+	if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term") ||
+	    RTAS_UNKNOWN_SERVICE == rtas_token("ibm,extended-os-term"))
 		return;
 
 	snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
@@ -542,22 +700,330 @@ void rtas_os_term(char *str)
 	do {
 		status = rtas_call(rtas_token("ibm,os-term"), 1, 1, NULL,
 				   __pa(rtas_os_term_buf));
+	} while (rtas_busy_delay(status));
+
+	if (status != 0)
+		printk(KERN_EMERG "ibm,os-term call failed %d\n", status);
+}
+
+static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
+#ifdef CONFIG_PPC_PSERIES
+static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_when_done)
+{
+	u16 slb_size = mmu_slb_size;
+	int rc = H_MULTI_THREADS_ACTIVE;
+	int cpu;
+
+	slb_set_size(SLB_MIN_SIZE);
+	printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id());
+
+	while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) &&
+	       !atomic_read(&data->error))
+		rc = rtas_call(data->token, 0, 1, NULL);
+
+	if (rc || atomic_read(&data->error)) {
+		printk(KERN_DEBUG "ibm,suspend-me returned %d\n", rc);
+		slb_set_size(slb_size);
+	}
+
+	if (atomic_read(&data->error))
+		rc = atomic_read(&data->error);
+
+	atomic_set(&data->error, rc);
+	pSeries_coalesce_init();
+
+	if (wake_when_done) {
+		atomic_set(&data->done, 1);
+
+		for_each_online_cpu(cpu)
+			plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu));
+	}
+
+	if (atomic_dec_return(&data->working) == 0)
+		complete(data->complete);
+
+	return rc;
+}
+
+int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data)
+{
+	atomic_inc(&data->working);
+	return __rtas_suspend_last_cpu(data, 0);
+}
+
+static int __rtas_suspend_cpu(struct rtas_suspend_me_data *data, int wake_when_done)
+{
+	long rc = H_SUCCESS;
+	unsigned long msr_save;
+	int cpu;
+
+	atomic_inc(&data->working);
+
+	/* really need to ensure MSR.EE is off for H_JOIN */
+	msr_save = mfmsr();
+	mtmsr(msr_save & ~(MSR_EE));
 
-		if (status == RTAS_BUSY)
-			udelay(1);
-		else if (status != 0)
-			printk(KERN_EMERG "ibm,os-term call failed %d\n",
-			       status);
-	} while (status == RTAS_BUSY);
+	while (rc == H_SUCCESS && !atomic_read(&data->done) && !atomic_read(&data->error))
+		rc = plpar_hcall_norets(H_JOIN);
+
+	mtmsr(msr_save);
+
+	if (rc == H_SUCCESS) {
+		/* This cpu was prodded and the suspend is complete. */
+		goto out;
+	} else if (rc == H_CONTINUE) {
+		/* All other cpus are in H_JOIN, this cpu does
+		 * the suspend.
+		 */
+		return __rtas_suspend_last_cpu(data, wake_when_done);
+	} else {
+		printk(KERN_ERR "H_JOIN on cpu %i failed with rc = %ld\n",
+		       smp_processor_id(), rc);
+		atomic_set(&data->error, rc);
+	}
+
+	if (wake_when_done) {
+		atomic_set(&data->done, 1);
+
+		/* This cpu did the suspend or got an error; in either case,
+		 * we need to prod all other other cpus out of join state.
+		 * Extra prods are harmless.
+		 */
+		for_each_online_cpu(cpu)
+			plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu));
+	}
+out:
+	if (atomic_dec_return(&data->working) == 0)
+		complete(data->complete);
+	return rc;
+}
+
+int rtas_suspend_cpu(struct rtas_suspend_me_data *data)
+{
+	return __rtas_suspend_cpu(data, 0);
+}
+
+static void rtas_percpu_suspend_me(void *info)
+{
+	__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
+}
+
+enum rtas_cpu_state {
+	DOWN,
+	UP,
+};
+
+#ifndef CONFIG_SMP
+static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
+				cpumask_var_t cpus)
+{
+	if (!cpumask_empty(cpus)) {
+		cpumask_clear(cpus);
+		return -EINVAL;
+	} else
+		return 0;
 }
+#else
+/* On return cpumask will be altered to indicate CPUs changed.
+ * CPUs with states changed will be set in the mask,
+ * CPUs with status unchanged will be unset in the mask. */
+static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
+				cpumask_var_t cpus)
+{
+	int cpu;
+	int cpuret = 0;
+	int ret = 0;
+
+	if (cpumask_empty(cpus))
+		return 0;
 
+	for_each_cpu(cpu, cpus) {
+		switch (state) {
+		case DOWN:
+			cpuret = cpu_down(cpu);
+			break;
+		case UP:
+			cpuret = cpu_up(cpu);
+			break;
+		}
+		if (cpuret) {
+			pr_debug("%s: cpu_%s for cpu#%d returned %d.\n",
+					__func__,
+					((state == UP) ? "up" : "down"),
+					cpu, cpuret);
+			if (!ret)
+				ret = cpuret;
+			if (state == UP) {
+				/* clear bits for unchanged cpus, return */
+				cpumask_shift_right(cpus, cpus, cpu);
+				cpumask_shift_left(cpus, cpus, cpu);
+				break;
+			} else {
+				/* clear bit for unchanged cpu, continue */
+				cpumask_clear_cpu(cpu, cpus);
+			}
+		}
+	}
 
+	return ret;
+}
+#endif
+
+int rtas_online_cpus_mask(cpumask_var_t cpus)
+{
+	int ret;
+
+	ret = rtas_cpu_state_change_mask(UP, cpus);
+
+	if (ret) {
+		cpumask_var_t tmp_mask;
+
+		if (!alloc_cpumask_var(&tmp_mask, GFP_TEMPORARY))
+			return ret;
+
+		/* Use tmp_mask to preserve cpus mask from first failure */
+		cpumask_copy(tmp_mask, cpus);
+		rtas_offline_cpus_mask(tmp_mask);
+		free_cpumask_var(tmp_mask);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(rtas_online_cpus_mask);
+
+int rtas_offline_cpus_mask(cpumask_var_t cpus)
+{
+	return rtas_cpu_state_change_mask(DOWN, cpus);
+}
+EXPORT_SYMBOL(rtas_offline_cpus_mask);
+
+int rtas_ibm_suspend_me(struct rtas_args *args)
+{
+	long state;
+	long rc;
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	struct rtas_suspend_me_data data;
+	DECLARE_COMPLETION_ONSTACK(done);
+	cpumask_var_t offline_mask;
+	int cpuret;
+
+	if (!rtas_service_present("ibm,suspend-me"))
+		return -ENOSYS;
+
+	/* Make sure the state is valid */
+	rc = plpar_hcall(H_VASI_STATE, retbuf,
+			 ((u64)args->args[0] << 32) | args->args[1]);
+
+	state = retbuf[0];
+
+	if (rc) {
+		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned %ld\n",rc);
+		return rc;
+	} else if (state == H_VASI_ENABLED) {
+		args->args[args->nargs] = RTAS_NOT_SUSPENDABLE;
+		return 0;
+	} else if (state != H_VASI_SUSPENDING) {
+		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned state %ld\n",
+		       state);
+		args->args[args->nargs] = -1;
+		return 0;
+	}
+
+	if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY))
+		return -ENOMEM;
+
+	atomic_set(&data.working, 0);
+	atomic_set(&data.done, 0);
+	atomic_set(&data.error, 0);
+	data.token = rtas_token("ibm,suspend-me");
+	data.complete = &done;
+
+	/* All present CPUs must be online */
+	cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask);
+	cpuret = rtas_online_cpus_mask(offline_mask);
+	if (cpuret) {
+		pr_err("%s: Could not bring present CPUs online.\n", __func__);
+		atomic_set(&data.error, cpuret);
+		goto out;
+	}
+
+	stop_topology_update();
+
+	/* Call function on all CPUs.  One of us will make the
+	 * rtas call
+	 */
+	if (on_each_cpu(rtas_percpu_suspend_me, &data, 0))
+		atomic_set(&data.error, -EINVAL);
+
+	wait_for_completion(&done);
+
+	if (atomic_read(&data.error) != 0)
+		printk(KERN_ERR "Error doing global join\n");
+
+	start_topology_update();
+
+	/* Take down CPUs not online prior to suspend */
+	cpuret = rtas_offline_cpus_mask(offline_mask);
+	if (cpuret)
+		pr_warn("%s: Could not restore CPUs to offline state.\n",
+				__func__);
+
+out:
+	free_cpumask_var(offline_mask);
+	return atomic_read(&data.error);
+}
+#else /* CONFIG_PPC_PSERIES */
+int rtas_ibm_suspend_me(struct rtas_args *args)
+{
+	return -ENOSYS;
+}
+#endif
+
+/**
+ * Find a specific pseries error log in an RTAS extended event log.
+ * @log: RTAS error/event log
+ * @section_id: two character section identifier
+ *
+ * Returns a pointer to the specified errorlog or NULL if not found.
+ */
+struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
+					      uint16_t section_id)
+{
+	struct rtas_ext_event_log_v6 *ext_log =
+		(struct rtas_ext_event_log_v6 *)log->buffer;
+	struct pseries_errorlog *sect;
+	unsigned char *p, *log_end;
+	uint32_t ext_log_length = rtas_error_extended_log_length(log);
+	uint8_t log_format = rtas_ext_event_log_format(ext_log);
+	uint32_t company_id = rtas_ext_event_company_id(ext_log);
+
+	/* Check that we understand the format */
+	if (ext_log_length < sizeof(struct rtas_ext_event_log_v6) ||
+	    log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG ||
+	    company_id != RTAS_V6EXT_COMPANY_ID_IBM)
+		return NULL;
+
+	log_end = log->buffer + ext_log_length;
+	p = ext_log->vendor_log;
+
+	while (p < log_end) {
+		sect = (struct pseries_errorlog *)p;
+		if (pseries_errorlog_id(sect) == section_id)
+			return sect;
+		p += pseries_errorlog_length(sect);
+	}
+
+	return NULL;
+}
+
+/* We assume to be passed big endian arguments */
 asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 {
 	struct rtas_args args;
 	unsigned long flags;
 	char *buff_copy, *errbuf = NULL;
-	int nargs;
+	int nargs, nret, token;
+	int rc;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -565,10 +1031,13 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 	if (copy_from_user(&args, uargs, 3 * sizeof(u32)) != 0)
 		return -EFAULT;
 
-	nargs = args.nargs;
+	nargs = be32_to_cpu(args.nargs);
+	nret  = be32_to_cpu(args.nret);
+	token = be32_to_cpu(args.token);
+
 	if (nargs > ARRAY_SIZE(args.args)
-	    || args.nret > ARRAY_SIZE(args.args)
-	    || nargs + args.nret > ARRAY_SIZE(args.args))
+	    || nret > ARRAY_SIZE(args.args)
+	    || nargs + nret > ARRAY_SIZE(args.args))
 		return -EINVAL;
 
 	/* Copy in args. */
@@ -576,22 +1045,34 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 			   nargs * sizeof(rtas_arg_t)) != 0)
 		return -EFAULT;
 
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -EINVAL;
+
+	args.rets = &args.args[nargs];
+	memset(args.rets, 0, nret * sizeof(rtas_arg_t));
+
+	/* Need to handle ibm,suspend_me call specially */
+	if (token == ibm_suspend_me_token) {
+		rc = rtas_ibm_suspend_me(&args);
+		if (rc)
+			return rc;
+		goto copy_return;
+	}
+
 	buff_copy = get_errorlog_buffer();
 
-	spin_lock_irqsave(&rtas.lock, flags);
+	flags = lock_rtas();
 
 	rtas.args = args;
 	enter_rtas(__pa(&rtas.args));
 	args = rtas.args;
 
-	args.rets = &args.args[nargs];
-
 	/* A -1 return code indicates that the last command couldn't
 	   be completed due to a hardware error. */
-	if (args.rets[0] == -1)
+	if (be32_to_cpu(args.rets[0]) == -1)
 		errbuf = __fetch_rtas_last_error(buff_copy);
 
-	spin_unlock_irqrestore(&rtas.lock, flags);
+	unlock_rtas(flags);
 
 	if (buff_copy) {
 		if (errbuf)
@@ -599,44 +1080,18 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 		kfree(buff_copy);
 	}
 
+ copy_return:
 	/* Copy out args. */
 	if (copy_to_user(uargs->args + nargs,
 			 args.args + nargs,
-			 args.nret * sizeof(rtas_arg_t)) != 0)
+			 nret * sizeof(rtas_arg_t)) != 0)
 		return -EFAULT;
 
 	return 0;
 }
 
-#ifdef CONFIG_SMP
-/* This version can't take the spinlock, because it never returns */
-
-struct rtas_args rtas_stop_self_args = {
-	/* The token is initialized for real in setup_system() */
-	.token = RTAS_UNKNOWN_SERVICE,
-	.nargs = 0,
-	.nret = 1,
-	.rets = &rtas_stop_self_args.args[0],
-};
-
-void rtas_stop_self(void)
-{
-	struct rtas_args *rtas_args = &rtas_stop_self_args;
-
-	local_irq_disable();
-
-	BUG_ON(rtas_args->token == RTAS_UNKNOWN_SERVICE);
-
-	printk("cpu %u (hwid %u) Ready to die...\n",
-	       smp_processor_id(), hard_smp_processor_id());
-	enter_rtas(__pa(rtas_args));
-
-	panic("Alas, I survived.\n");
-}
-#endif
-
 /*
- * Call early during boot, before mem init or bootmem, to retreive the RTAS
+ * Call early during boot, before mem init or bootmem, to retrieve the RTAS
  * informations from the device-tree and allocate the RMO buffer for userland
  * accesses.
  */
@@ -649,19 +1104,19 @@ void __init rtas_initialize(void)
 	 */
 	rtas.dev = of_find_node_by_name(NULL, "rtas");
 	if (rtas.dev) {
-		u32 *basep, *entryp;
-		u32 *sizep;
+		const __be32 *basep, *entryp, *sizep;
 
-		basep = (u32 *)get_property(rtas.dev, "linux,rtas-base", NULL);
-		sizep = (u32 *)get_property(rtas.dev, "rtas-size", NULL);
+		basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
+		sizep = of_get_property(rtas.dev, "rtas-size", NULL);
 		if (basep != NULL && sizep != NULL) {
-			rtas.base = *basep;
-			rtas.size = *sizep;
-			entryp = (u32 *)get_property(rtas.dev, "linux,rtas-entry", NULL);
+			rtas.base = __be32_to_cpu(*basep);
+			rtas.size = __be32_to_cpu(*sizep);
+			entryp = of_get_property(rtas.dev,
+					"linux,rtas-entry", NULL);
 			if (entryp == NULL) /* Ugh */
 				rtas.entry = rtas.base;
 			else
-				rtas.entry = *entryp;
+				rtas.entry = __be32_to_cpu(*entryp);
 		} else
 			rtas.dev = NULL;
 	}
@@ -672,26 +1127,81 @@ void __init rtas_initialize(void)
 	 * the stop-self token if any
 	 */
 #ifdef CONFIG_PPC64
-	if (systemcfg->platform == PLATFORM_PSERIES_LPAR)
-		rtas_region = min(lmb.rmo_size, RTAS_INSTANTIATE_MAX);
+	if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR)) {
+		rtas_region = min(ppc64_rma_size, RTAS_INSTANTIATE_MAX);
+		ibm_suspend_me_token = rtas_token("ibm,suspend-me");
+	}
 #endif
-	rtas_rmo_buf = lmb_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region);
+	rtas_rmo_buf = memblock_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region);
 
-#ifdef CONFIG_HOTPLUG_CPU
-	rtas_stop_self_args.token = rtas_token("stop-self");
-#endif /* CONFIG_HOTPLUG_CPU */
 #ifdef CONFIG_RTAS_ERROR_LOGGING
 	rtas_last_error_token = rtas_token("rtas-last-error");
 #endif
 }
 
+int __init early_init_dt_scan_rtas(unsigned long node,
+		const char *uname, int depth, void *data)
+{
+	const u32 *basep, *entryp, *sizep;
 
-EXPORT_SYMBOL(rtas_token);
-EXPORT_SYMBOL(rtas_call);
-EXPORT_SYMBOL(rtas_data_buf);
-EXPORT_SYMBOL(rtas_data_buf_lock);
-EXPORT_SYMBOL(rtas_extended_busy_delay_time);
-EXPORT_SYMBOL(rtas_get_sensor);
-EXPORT_SYMBOL(rtas_get_power_level);
-EXPORT_SYMBOL(rtas_set_power_level);
-EXPORT_SYMBOL(rtas_set_indicator);
+	if (depth != 1 || strcmp(uname, "rtas") != 0)
+		return 0;
+
+	basep  = of_get_flat_dt_prop(node, "linux,rtas-base", NULL);
+	entryp = of_get_flat_dt_prop(node, "linux,rtas-entry", NULL);
+	sizep  = of_get_flat_dt_prop(node, "rtas-size", NULL);
+
+	if (basep && entryp && sizep) {
+		rtas.base = *basep;
+		rtas.entry = *entryp;
+		rtas.size = *sizep;
+	}
+
+#ifdef CONFIG_UDBG_RTAS_CONSOLE
+	basep = of_get_flat_dt_prop(node, "put-term-char", NULL);
+	if (basep)
+		rtas_putchar_token = *basep;
+
+	basep = of_get_flat_dt_prop(node, "get-term-char", NULL);
+	if (basep)
+		rtas_getchar_token = *basep;
+
+	if (rtas_putchar_token != RTAS_UNKNOWN_SERVICE &&
+	    rtas_getchar_token != RTAS_UNKNOWN_SERVICE)
+		udbg_init_rtas_console();
+
+#endif
+
+	/* break now */
+	return 1;
+}
+
+static arch_spinlock_t timebase_lock;
+static u64 timebase = 0;
+
+void rtas_give_timebase(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	hard_irq_disable();
+	arch_spin_lock(&timebase_lock);
+	rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
+	timebase = get_tb();
+	arch_spin_unlock(&timebase_lock);
+
+	while (timebase)
+		barrier();
+	rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
+	local_irq_restore(flags);
+}
+
+void rtas_take_timebase(void)
+{
+	while (!timebase)
+		barrier();
+	arch_spin_lock(&timebase_lock);
+	set_tb(timebase >> 32, timebase & 0xffffffff);
+	timebase = 0;
+	arch_spin_unlock(&timebase_lock);
+}