Merge with Paulus

15 files changed, 2923 insertions, 160 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1c44a1dac42..3cf03ab4611 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -278,7 +278,6 @@ config PPC_PSERIES
 	select PPC_I8259
 	select PPC_RTAS
 	select RTAS_ERROR_LOGGING
-	select RTAS_FW
 	default y
 
 config PPC_CHRP
@@ -324,7 +323,6 @@ config PPC_CELL
 	bool "  Cell Broadband Processor Architecture"
 	depends on PPC_MULTIPLATFORM && PPC64
 	select PPC_RTAS
-	select RTAS_FW
 	select MMIO_NVRAM
 
 config PPC_OF
@@ -356,10 +354,14 @@ config RTAS_ERROR_LOGGING
 	depends on PPC_RTAS
 	default n
 
-config RTAS_FW
-	bool
+config RTAS_PROC
+	bool "Proc interface to RTAS"
 	depends on PPC_RTAS
-	default n
+	default y
+
+config RTAS_FLASH
+	tristate "Firmware flash interface"
+	depends on PPC64 && RTAS_PROC
 
 config MMIO_NVRAM
 	bool
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index abad3059a21..7a3e1155ac9 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -13,12 +13,13 @@ endif
 obj-y				:= semaphore.o cputable.o ptrace.o syscalls.o \
 				   signal_32.o pmc.o
 obj-$(CONFIG_PPC64)		+= setup_64.o binfmt_elf32.o sys_ppc32.o \
-				   ptrace32.o systbl.o
+				   signal_64.o ptrace32.o systbl.o
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
 obj-$(CONFIG_POWER4)		+= idle_power4.o
 obj-$(CONFIG_PPC_OF)		+= of_device.o
 obj-$(CONFIG_PPC_RTAS)		+= rtas.o
-obj-$(CONFIG_RTAS_FW)		+= rtas_fw.o
+obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
+obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
 
 ifeq ($(CONFIG_PPC_MERGE),y)
diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/kernel/ppc32.h
new file mode 100644
index 00000000000..90e56277179
--- /dev/null
+++ b/arch/powerpc/kernel/ppc32.h
@@ -0,0 +1,138 @@
+#ifndef _PPC64_PPC32_H
+#define _PPC64_PPC32_H
+
+#include <linux/compat.h>
+#include <asm/siginfo.h>
+#include <asm/signal.h>
+
+/*
+ * Data types and macros for providing 32b PowerPC support.
+ * 
+ * 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.
+ */
+
+/* These are here to support 32-bit syscalls on a 64-bit kernel. */
+
+typedef struct compat_siginfo {
+	int si_signo;
+	int si_errno;
+	int si_code;
+
+	union {
+		int _pad[SI_PAD_SIZE32];
+
+		/* kill() */
+		struct {
+			compat_pid_t _pid;		/* sender's pid */
+			compat_uid_t _uid;		/* sender's uid */
+		} _kill;
+
+		/* POSIX.1b timers */
+		struct {
+			compat_timer_t _tid;			/* timer id */
+			int _overrun;			/* overrun count */
+			compat_sigval_t _sigval;		/* same as below */
+			int _sys_private;		/* not to be passed to user */
+		} _timer;
+
+		/* POSIX.1b signals */
+		struct {
+			compat_pid_t _pid;		/* sender's pid */
+			compat_uid_t _uid;		/* sender's uid */
+			compat_sigval_t _sigval;
+		} _rt;
+
+		/* SIGCHLD */
+		struct {
+			compat_pid_t _pid;		/* which child */
+			compat_uid_t _uid;		/* sender's uid */
+			int _status;			/* exit code */
+			compat_clock_t _utime;
+			compat_clock_t _stime;
+		} _sigchld;
+
+		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */
+		struct {
+			unsigned int _addr; /* faulting insn/memory ref. */
+		} _sigfault;
+
+		/* SIGPOLL */
+		struct {
+			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
+			int _fd;
+		} _sigpoll;
+	} _sifields;
+} compat_siginfo_t;
+
+#define __old_sigaction32	old_sigaction32
+
+struct __old_sigaction32 {
+	compat_uptr_t		sa_handler;
+	compat_old_sigset_t  	sa_mask;
+	unsigned int    	sa_flags;
+	compat_uptr_t		sa_restorer;     /* not used by Linux/SPARC yet */
+};
+
+
+
+struct sigaction32 {
+       compat_uptr_t  sa_handler;	/* Really a pointer, but need to deal with 32 bits */
+       unsigned int sa_flags;
+       compat_uptr_t sa_restorer;	/* Another 32 bit pointer */
+       compat_sigset_t sa_mask;		/* A 32 bit mask */
+};
+
+typedef struct sigaltstack_32 {
+	unsigned int ss_sp;
+	int ss_flags;
+	compat_size_t ss_size;
+} stack_32_t;
+
+struct pt_regs32 {
+	unsigned int gpr[32];
+	unsigned int nip;
+	unsigned int msr;
+	unsigned int orig_gpr3;		/* Used for restarting system calls */
+	unsigned int ctr;
+	unsigned int link;
+	unsigned int xer;
+	unsigned int ccr;
+	unsigned int mq;		/* 601 only (not used at present) */
+	unsigned int trap;		/* Reason for being here */
+	unsigned int dar;		/* Fault registers */
+	unsigned int dsisr;
+	unsigned int result;		/* Result of a system call */
+};
+
+struct sigcontext32 {
+	unsigned int	_unused[4];
+	int		signal;
+	compat_uptr_t	handler;
+	unsigned int	oldmask;
+	compat_uptr_t	regs;  /* 4 byte pointer to the pt_regs32 structure. */
+};
+
+struct mcontext32 {
+	elf_gregset_t32		mc_gregs;
+	elf_fpregset_t		mc_fregs;
+	unsigned int		mc_pad[2];
+	elf_vrregset_t32	mc_vregs __attribute__((__aligned__(16)));
+};
+
+struct ucontext32 { 
+	unsigned int	  	uc_flags;
+	unsigned int 	  	uc_link;
+	stack_32_t	 	uc_stack;
+	int		 	uc_pad[7];
+	compat_uptr_t		uc_regs;	/* points to uc_mcontext field */
+	compat_sigset_t	 	uc_sigmask;	/* mask last for extensibility */
+	/* glibc has 1024-bit signal masks, ours are 64-bit */
+	int		 	uc_maskext[30];
+	int		 	uc_pad2[3];
+	struct mcontext32	uc_mcontext;
+};
+
+#endif  /* _PPC64_PPC32_H */
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
new file mode 100644
index 00000000000..5bdd5b079d9
--- /dev/null
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -0,0 +1,808 @@
+/*
+ *   arch/ppc64/kernel/rtas-proc.c
+ *   Copyright (C) 2000 Tilmann Bitterberg
+ *   (tilmann@bitterberg.de)
+ *
+ *   RTAS (Runtime Abstraction Services) stuff
+ *   Intention is to provide a clean user interface
+ *   to use the RTAS.
+ *
+ *   TODO:
+ *   Split off a header file and maybe move it to a different
+ *   location. Write Documentation on what the /proc/rtas/ entries
+ *   actually do.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/ctype.h>
+#include <linux/time.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/bitops.h>
+#include <linux/rtc.h>
+
+#include <asm/uaccess.h>
+#include <asm/processor.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/machdep.h> /* for ppc_md */
+#include <asm/time.h>
+#include <asm/systemcfg.h>
+
+/* Token for Sensors */
+#define KEY_SWITCH		0x0001
+#define ENCLOSURE_SWITCH	0x0002
+#define THERMAL_SENSOR		0x0003
+#define LID_STATUS		0x0004
+#define POWER_SOURCE		0x0005
+#define BATTERY_VOLTAGE		0x0006
+#define BATTERY_REMAINING	0x0007
+#define BATTERY_PERCENTAGE	0x0008
+#define EPOW_SENSOR		0x0009
+#define BATTERY_CYCLESTATE	0x000a
+#define BATTERY_CHARGING	0x000b
+
+/* IBM specific sensors */
+#define IBM_SURVEILLANCE	0x2328 /* 9000 */
+#define IBM_FANRPM		0x2329 /* 9001 */
+#define IBM_VOLTAGE		0x232a /* 9002 */
+#define IBM_DRCONNECTOR		0x232b /* 9003 */
+#define IBM_POWERSUPPLY		0x232c /* 9004 */
+
+/* Status return values */
+#define SENSOR_CRITICAL_HIGH	13
+#define SENSOR_WARNING_HIGH	12
+#define SENSOR_NORMAL		11
+#define SENSOR_WARNING_LOW	10
+#define SENSOR_CRITICAL_LOW	 9
+#define SENSOR_SUCCESS		 0
+#define SENSOR_HW_ERROR		-1
+#define SENSOR_BUSY		-2
+#define SENSOR_NOT_EXIST	-3
+#define SENSOR_DR_ENTITY	-9000
+
+/* Location Codes */
+#define LOC_SCSI_DEV_ADDR	'A'
+#define LOC_SCSI_DEV_LOC	'B'
+#define LOC_CPU			'C'
+#define LOC_DISKETTE		'D'
+#define LOC_ETHERNET		'E'
+#define LOC_FAN			'F'
+#define LOC_GRAPHICS		'G'
+/* reserved / not used		'H' */
+#define LOC_IO_ADAPTER		'I'
+/* reserved / not used		'J' */
+#define LOC_KEYBOARD		'K'
+#define LOC_LCD			'L'
+#define LOC_MEMORY		'M'
+#define LOC_NV_MEMORY		'N'
+#define LOC_MOUSE		'O'
+#define LOC_PLANAR		'P'
+#define LOC_OTHER_IO		'Q'
+#define LOC_PARALLEL		'R'
+#define LOC_SERIAL		'S'
+#define LOC_DEAD_RING		'T'
+#define LOC_RACKMOUNTED		'U' /* for _u_nit is rack mounted */
+#define LOC_VOLTAGE		'V'
+#define LOC_SWITCH_ADAPTER	'W'
+#define LOC_OTHER		'X'
+#define LOC_FIRMWARE		'Y'
+#define LOC_SCSI		'Z'
+
+/* Tokens for indicators */
+#define TONE_FREQUENCY		0x0001 /* 0 - 1000 (HZ)*/
+#define TONE_VOLUME		0x0002 /* 0 - 100 (%) */
+#define SYSTEM_POWER_STATE	0x0003 
+#define WARNING_LIGHT		0x0004
+#define DISK_ACTIVITY_LIGHT	0x0005
+#define HEX_DISPLAY_UNIT	0x0006
+#define BATTERY_WARNING_TIME	0x0007
+#define CONDITION_CYCLE_REQUEST	0x0008
+#define SURVEILLANCE_INDICATOR	0x2328 /* 9000 */
+#define DR_ACTION		0x2329 /* 9001 */
+#define DR_INDICATOR		0x232a /* 9002 */
+/* 9003 - 9004: Vendor specific */
+/* 9006 - 9999: Vendor specific */
+
+/* other */
+#define MAX_SENSORS		 17  /* I only know of 17 sensors */    
+#define MAX_LINELENGTH          256
+#define SENSOR_PREFIX		"ibm,sensor-"
+#define cel_to_fahr(x)		((x*9/5)+32)
+
+
+/* Globals */
+static struct rtas_sensors sensors;
+static struct device_node *rtas_node = NULL;
+static unsigned long power_on_time = 0; /* Save the time the user set */
+static char progress_led[MAX_LINELENGTH];
+
+static unsigned long rtas_tone_frequency = 1000;
+static unsigned long rtas_tone_volume = 0;
+
+/* ****************STRUCTS******************************************* */
+struct individual_sensor {
+	unsigned int token;
+	unsigned int quant;
+};
+
+struct rtas_sensors {
+        struct individual_sensor sensor[MAX_SENSORS];
+	unsigned int quant;
+};
+
+/* ****************************************************************** */
+/* Declarations */
+static int ppc_rtas_sensors_show(struct seq_file *m, void *v);
+static int ppc_rtas_clock_show(struct seq_file *m, void *v);
+static ssize_t ppc_rtas_clock_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos);
+static int ppc_rtas_progress_show(struct seq_file *m, void *v);
+static ssize_t ppc_rtas_progress_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos);
+static int ppc_rtas_poweron_show(struct seq_file *m, void *v);
+static ssize_t ppc_rtas_poweron_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos);
+
+static ssize_t ppc_rtas_tone_freq_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos);
+static int ppc_rtas_tone_freq_show(struct seq_file *m, void *v);
+static ssize_t ppc_rtas_tone_volume_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos);
+static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v);
+static int ppc_rtas_rmo_buf_show(struct seq_file *m, void *v);
+
+static int sensors_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ppc_rtas_sensors_show, NULL);
+}
+
+struct file_operations ppc_rtas_sensors_operations = {
+	.open		= sensors_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int poweron_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ppc_rtas_poweron_show, NULL);
+}
+
+struct file_operations ppc_rtas_poweron_operations = {
+	.open		= poweron_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.write		= ppc_rtas_poweron_write,
+	.release	= single_release,
+};
+
+static int progress_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ppc_rtas_progress_show, NULL);
+}
+
+struct file_operations ppc_rtas_progress_operations = {
+	.open		= progress_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.write		= ppc_rtas_progress_write,
+	.release	= single_release,
+};
+
+static int clock_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ppc_rtas_clock_show, NULL);
+}
+
+struct file_operations ppc_rtas_clock_operations = {
+	.open		= clock_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.write		= ppc_rtas_clock_write,
+	.release	= single_release,
+};
+
+static int tone_freq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ppc_rtas_tone_freq_show, NULL);
+}
+
+struct file_operations ppc_rtas_tone_freq_operations = {
+	.open		= tone_freq_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.write		= ppc_rtas_tone_freq_write,
+	.release	= single_release,
+};
+
+static int tone_volume_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ppc_rtas_tone_volume_show, NULL);
+}
+
+struct file_operations ppc_rtas_tone_volume_operations = {
+	.open		= tone_volume_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.write		= ppc_rtas_tone_volume_write,
+	.release	= single_release,
+};
+
+static int rmo_buf_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ppc_rtas_rmo_buf_show, NULL);
+}
+
+struct file_operations ppc_rtas_rmo_buf_ops = {
+	.open		= rmo_buf_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int ppc_rtas_find_all_sensors(void);
+static void ppc_rtas_process_sensor(struct seq_file *m,
+	struct individual_sensor *s, int state, int error, char *loc);
+static char *ppc_rtas_process_error(int error);
+static void get_location_code(struct seq_file *m,
+	struct individual_sensor *s, char *loc);
+static void check_location_string(struct seq_file *m, char *c);
+static void check_location(struct seq_file *m, char *c);
+
+static int __init proc_rtas_init(void)
+{
+	struct proc_dir_entry *entry;
+
+	if (!(systemcfg->platform & PLATFORM_PSERIES))
+		return 1;
+
+	rtas_node = of_find_node_by_name(NULL, "rtas");
+	if (rtas_node == NULL)
+		return 1;
+
+	entry = create_proc_entry("ppc64/rtas/progress", S_IRUGO|S_IWUSR, NULL);
+	if (entry)
+		entry->proc_fops = &ppc_rtas_progress_operations;
+
+	entry = create_proc_entry("ppc64/rtas/clock", S_IRUGO|S_IWUSR, NULL);
+	if (entry)
+		entry->proc_fops = &ppc_rtas_clock_operations;
+
+	entry = create_proc_entry("ppc64/rtas/poweron", S_IWUSR|S_IRUGO, NULL);
+	if (entry)
+		entry->proc_fops = &ppc_rtas_poweron_operations;
+
+	entry = create_proc_entry("ppc64/rtas/sensors", S_IRUGO, NULL);
+	if (entry)
+		entry->proc_fops = &ppc_rtas_sensors_operations;
+
+	entry = create_proc_entry("ppc64/rtas/frequency", S_IWUSR|S_IRUGO,
+				  NULL);
+	if (entry)
+		entry->proc_fops = &ppc_rtas_tone_freq_operations;
+
+	entry = create_proc_entry("ppc64/rtas/volume", S_IWUSR|S_IRUGO, NULL);
+	if (entry)
+		entry->proc_fops = &ppc_rtas_tone_volume_operations;
+
+	entry = create_proc_entry("ppc64/rtas/rmo_buffer", S_IRUSR, NULL);
+	if (entry)
+		entry->proc_fops = &ppc_rtas_rmo_buf_ops;
+
+	return 0;
+}
+
+__initcall(proc_rtas_init);
+
+static int parse_number(const char __user *p, size_t count, unsigned long *val)
+{
+	char buf[40];
+	char *end;
+
+	if (count > 39)
+		return -EINVAL;
+
+	if (copy_from_user(buf, p, count))
+		return -EFAULT;
+
+	buf[count] = 0;
+
+	*val = simple_strtoul(buf, &end, 10);
+	if (*end && *end != '\n')
+		return -EINVAL;
+
+	return 0;
+}
+
+/* ****************************************************************** */
+/* POWER-ON-TIME                                                      */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_poweron_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct rtc_time tm;
+	unsigned long nowtime;
+	int error = parse_number(buf, count, &nowtime);
+	if (error)
+		return error;
+
+	power_on_time = nowtime; /* save the time */
+
+	to_tm(nowtime, &tm);
+
+	error = rtas_call(rtas_token("set-time-for-power-on"), 7, 1, NULL, 
+			tm.tm_year, tm.tm_mon, tm.tm_mday, 
+			tm.tm_hour, tm.tm_min, tm.tm_sec, 0 /* nano */);
+	if (error)
+		printk(KERN_WARNING "error: setting poweron time returned: %s\n", 
+				ppc_rtas_process_error(error));
+	return count;
+}
+/* ****************************************************************** */
+static int ppc_rtas_poweron_show(struct seq_file *m, void *v)
+{
+	if (power_on_time == 0)
+		seq_printf(m, "Power on time not set\n");
+	else
+		seq_printf(m, "%lu\n",power_on_time);
+	return 0;
+}
+
+/* ****************************************************************** */
+/* PROGRESS                                                           */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_progress_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	unsigned long hex;
+
+	if (count >= MAX_LINELENGTH)
+		count = MAX_LINELENGTH -1;
+	if (copy_from_user(progress_led, buf, count)) { /* save the string */
+		return -EFAULT;
+	}
+	progress_led[count] = 0;
+
+	/* Lets see if the user passed hexdigits */
+	hex = simple_strtoul(progress_led, NULL, 10);
+
+	rtas_progress ((char *)progress_led, hex);
+	return count;
+
+	/* clear the line */
+	/* rtas_progress("                   ", 0xffff);*/
+}
+/* ****************************************************************** */
+static int ppc_rtas_progress_show(struct seq_file *m, void *v)
+{
+	if (progress_led)
+		seq_printf(m, "%s\n", progress_led);
+	return 0;
+}
+
+/* ****************************************************************** */
+/* CLOCK                                                              */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_clock_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct rtc_time tm;
+	unsigned long nowtime;
+	int error = parse_number(buf, count, &nowtime);
+	if (error)
+		return error;
+
+	to_tm(nowtime, &tm);
+	error = rtas_call(rtas_token("set-time-of-day"), 7, 1, NULL, 
+			tm.tm_year, tm.tm_mon, tm.tm_mday, 
+			tm.tm_hour, tm.tm_min, tm.tm_sec, 0);
+	if (error)
+		printk(KERN_WARNING "error: setting the clock returned: %s\n", 
+				ppc_rtas_process_error(error));
+	return count;
+}
+/* ****************************************************************** */
+static int ppc_rtas_clock_show(struct seq_file *m, void *v)
+{
+	int ret[8];
+	int error = rtas_call(rtas_token("get-time-of-day"), 0, 8, ret);
+
+	if (error) {
+		printk(KERN_WARNING "error: reading the clock returned: %s\n", 
+				ppc_rtas_process_error(error));
+		seq_printf(m, "0");
+	} else { 
+		unsigned int year, mon, day, hour, min, sec;
+		year = ret[0]; mon  = ret[1]; day  = ret[2];
+		hour = ret[3]; min  = ret[4]; sec  = ret[5];
+		seq_printf(m, "%lu\n",
+				mktime(year, mon, day, hour, min, sec));
+	}
+	return 0;
+}
+
+/* ****************************************************************** */
+/* SENSOR STUFF                                                       */
+/* ****************************************************************** */
+static int ppc_rtas_sensors_show(struct seq_file *m, void *v)
+{
+	int i,j;
+	int state, error;
+	int get_sensor_state = rtas_token("get-sensor-state");
+
+	seq_printf(m, "RTAS (RunTime Abstraction Services) Sensor Information\n");
+	seq_printf(m, "Sensor\t\tValue\t\tCondition\tLocation\n");
+	seq_printf(m, "********************************************************\n");
+
+	if (ppc_rtas_find_all_sensors() != 0) {
+		seq_printf(m, "\nNo sensors are available\n");
+		return 0;
+	}
+
+	for (i=0; i<sensors.quant; i++) {
+		struct individual_sensor *p = &sensors.sensor[i];
+		char rstr[64];
+		char *loc;
+		int llen, offs;
+
+		sprintf (rstr, SENSOR_PREFIX"%04d", p->token);
+		loc = (char *) get_property(rtas_node, rstr, &llen);
+
+		/* A sensor may have multiple instances */
+		for (j = 0, offs = 0; j <= p->quant; j++) {
+			error =	rtas_call(get_sensor_state, 2, 2, &state, 
+				  	  p->token, j);
+
+			ppc_rtas_process_sensor(m, p, state, error, loc);
+			seq_putc(m, '\n');
+			if (loc) {
+				offs += strlen(loc) + 1;
+				loc += strlen(loc) + 1;
+				if (offs >= llen)
+					loc = NULL;
+			}
+		}
+	}
+	return 0;
+}
+
+/* ****************************************************************** */
+
+static int ppc_rtas_find_all_sensors(void)
+{
+	unsigned int *utmp;
+	int len, i;
+
+	utmp = (unsigned int *) get_property(rtas_node, "rtas-sensors", &len);
+	if (utmp == NULL) {
+		printk (KERN_ERR "error: could not get rtas-sensors\n");
+		return 1;
+	}
+
+	sensors.quant = len / 8;      /* int + int */
+
+	for (i=0; i<sensors.quant; i++) {
+		sensors.sensor[i].token = *utmp++;
+		sensors.sensor[i].quant = *utmp++;
+	}
+	return 0;
+}
+
+/* ****************************************************************** */
+/*
+ * Builds a string of what rtas returned
+ */
+static char *ppc_rtas_process_error(int error)
+{
+	switch (error) {
+		case SENSOR_CRITICAL_HIGH:
+			return "(critical high)";
+		case SENSOR_WARNING_HIGH:
+			return "(warning high)";
+		case SENSOR_NORMAL:
+			return "(normal)";
+		case SENSOR_WARNING_LOW:
+			return "(warning low)";
+		case SENSOR_CRITICAL_LOW:
+			return "(critical low)";
+		case SENSOR_SUCCESS:
+			return "(read ok)";
+		case SENSOR_HW_ERROR:
+			return "(hardware error)";
+		case SENSOR_BUSY:
+			return "(busy)";
+		case SENSOR_NOT_EXIST:
+			return "(non existent)";
+		case SENSOR_DR_ENTITY:
+			return "(dr entity removed)";
+		default:
+			return "(UNKNOWN)";
+	}
+}
+
+/* ****************************************************************** */
+/*
+ * Builds a string out of what the sensor said
+ */
+
+static void ppc_rtas_process_sensor(struct seq_file *m,
+	struct individual_sensor *s, int state, int error, char *loc)
+{
+	/* Defined return vales */
+	const char * key_switch[]        = { "Off\t", "Normal\t", "Secure\t", 
+						"Maintenance" };
+	const char * enclosure_switch[]  = { "Closed", "Open" };
+	const char * lid_status[]        = { " ", "Open", "Closed" };
+	const char * power_source[]      = { "AC\t", "Battery", 
+		  				"AC & Battery" };
+	const char * battery_remaining[] = { "Very Low", "Low", "Mid", "High" };
+	const char * epow_sensor[]       = { 
+		"EPOW Reset", "Cooling warning", "Power warning",
+		"System shutdown", "System halt", "EPOW main enclosure",
+		"EPOW power off" };
+	const char * battery_cyclestate[]  = { "None", "In progress", 
+						"Requested" };
+	const char * battery_charging[]    = { "Charging", "Discharching", 
+						"No current flow" };
+	const char * ibm_drconnector[]     = { "Empty", "Present", "Unusable", 
+						"Exchange" };
+
+	int have_strings = 0;
+	int num_states = 0;
+	int temperature = 0;
+	int unknown = 0;
+
+	/* What kind of sensor do we have here? */
+	
+	switch (s->token) {
+		case KEY_SWITCH:
+			seq_printf(m, "Key switch:\t");
+			num_states = sizeof(key_switch) / sizeof(char *);
+			if (state < num_states) {
+				seq_printf(m, "%s\t", key_switch[state]);
+				have_strings = 1;
+			}
+			break;
+		case ENCLOSURE_SWITCH:
+			seq_printf(m, "Enclosure switch:\t");
+			num_states = sizeof(enclosure_switch) / sizeof(char *);
+			if (state < num_states) {
+				seq_printf(m, "%s\t", 
+						enclosure_switch[state]);
+				have_strings = 1;
+			}
+			break;
+		case THERMAL_SENSOR:
+			seq_printf(m, "Temp. (C/F):\t");
+			temperature = 1;
+			break;
+		case LID_STATUS:
+			seq_printf(m, "Lid status:\t");
+			num_states = sizeof(lid_status) / sizeof(char *);
+			if (state < num_states) {
+				seq_printf(m, "%s\t", lid_status[state]);
+				have_strings = 1;
+			}
+			break;
+		case POWER_SOURCE:
+			seq_printf(m, "Power source:\t");
+			num_states = sizeof(power_source) / sizeof(char *);
+			if (state < num_states) {
+				seq_printf(m, "%s\t", 
+						power_source[state]);
+				have_strings = 1;
+			}
+			break;
+		case BATTERY_VOLTAGE:
+			seq_printf(m, "Battery voltage:\t");
+			break;
+		case BATTERY_REMAINING:
+			seq_printf(m, "Battery remaining:\t");
+			num_states = sizeof(battery_remaining) / sizeof(char *);
+			if (state < num_states)
+			{
+				seq_printf(m, "%s\t", 
+						battery_remaining[state]);
+				have_strings = 1;
+			}
+			break;
+		case BATTERY_PERCENTAGE:
+			seq_printf(m, "Battery percentage:\t");
+			break;
+		case EPOW_SENSOR:
+			seq_printf(m, "EPOW Sensor:\t");
+			num_states = sizeof(epow_sensor) / sizeof(char *);
+			if (state < num_states) {
+				seq_printf(m, "%s\t", epow_sensor[state]);
+				have_strings = 1;
+			}
+			break;
+		case BATTERY_CYCLESTATE:
+			seq_printf(m, "Battery cyclestate:\t");
+			num_states = sizeof(battery_cyclestate) / 
+				     	sizeof(char *);
+			if (state < num_states) {
+				seq_printf(m, "%s\t", 
+						battery_cyclestate[state]);
+				have_strings = 1;
+			}
+			break;
+		case BATTERY_CHARGING:
+			seq_printf(m, "Battery Charging:\t");
+			num_states = sizeof(battery_charging) / sizeof(char *);
+			if (state < num_states) {
+				seq_printf(m, "%s\t", 
+						battery_charging[state]);
+				have_strings = 1;
+			}
+			break;
+		case IBM_SURVEILLANCE:
+			seq_printf(m, "Surveillance:\t");
+			break;
+		case IBM_FANRPM:
+			seq_printf(m, "Fan (rpm):\t");
+			break;
+		case IBM_VOLTAGE:
+			seq_printf(m, "Voltage (mv):\t");
+			break;
+		case IBM_DRCONNECTOR:
+			seq_printf(m, "DR connector:\t");
+			num_states = sizeof(ibm_drconnector) / sizeof(char *);
+			if (state < num_states) {
+				seq_printf(m, "%s\t", 
+						ibm_drconnector[state]);
+				have_strings = 1;
+			}
+			break;
+		case IBM_POWERSUPPLY:
+			seq_printf(m, "Powersupply:\t");
+			break;
+		default:
+			seq_printf(m,  "Unknown sensor (type %d), ignoring it\n",
+					s->token);
+			unknown = 1;
+			have_strings = 1;
+			break;
+	}
+	if (have_strings == 0) {
+		if (temperature) {
+			seq_printf(m, "%4d /%4d\t", state, cel_to_fahr(state));
+		} else
+			seq_printf(m, "%10d\t", state);
+	}
+	if (unknown == 0) {
+		seq_printf(m, "%s\t", ppc_rtas_process_error(error));
+		get_location_code(m, s, loc);
+	}
+}
+
+/* ****************************************************************** */
+
+static void check_location(struct seq_file *m, char *c)
+{
+	switch (c[0]) {
+		case LOC_PLANAR:
+			seq_printf(m, "Planar #%c", c[1]);
+			break;
+		case LOC_CPU:
+			seq_printf(m, "CPU #%c", c[1]);
+			break;
+		case LOC_FAN:
+			seq_printf(m, "Fan #%c", c[1]);
+			break;
+		case LOC_RACKMOUNTED:
+			seq_printf(m, "Rack #%c", c[1]);
+			break;
+		case LOC_VOLTAGE:
+			seq_printf(m, "Voltage #%c", c[1]);
+			break;
+		case LOC_LCD:
+			seq_printf(m, "LCD #%c", c[1]);
+			break;
+		case '.':
+			seq_printf(m, "- %c", c[1]);
+			break;
+		default:
+			seq_printf(m, "Unknown location");
+			break;
+	}
+}
+
+
+/* ****************************************************************** */
+/* 
+ * Format: 
+ * ${LETTER}${NUMBER}[[-/]${LETTER}${NUMBER} [ ... ] ]
+ * the '.' may be an abbrevation
+ */
+static void check_location_string(struct seq_file *m, char *c)
+{
+	while (*c) {
+		if (isalpha(*c) || *c == '.')
+			check_location(m, c);
+		else if (*c == '/' || *c == '-')
+			seq_printf(m, " at ");
+		c++;
+	}
+}
+
+
+/* ****************************************************************** */
+
+static void get_location_code(struct seq_file *m, struct individual_sensor *s, char *loc)
+{
+	if (!loc || !*loc) {
+		seq_printf(m, "---");/* does not have a location */
+	} else {
+		check_location_string(m, loc);
+	}
+	seq_putc(m, ' ');
+}
+/* ****************************************************************** */
+/* INDICATORS - Tone Frequency                                        */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_tone_freq_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	unsigned long freq;
+	int error = parse_number(buf, count, &freq);
+	if (error)
+		return error;
+
+	rtas_tone_frequency = freq; /* save it for later */
+	error = rtas_call(rtas_token("set-indicator"), 3, 1, NULL,
+			TONE_FREQUENCY, 0, freq);
+	if (error)
+		printk(KERN_WARNING "error: setting tone frequency returned: %s\n", 
+				ppc_rtas_process_error(error));
+	return count;
+}
+/* ****************************************************************** */
+static int ppc_rtas_tone_freq_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "%lu\n", rtas_tone_frequency);
+	return 0;
+}
+/* ****************************************************************** */
+/* INDICATORS - Tone Volume                                           */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_tone_volume_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	unsigned long volume;
+	int error = parse_number(buf, count, &volume);
+	if (error)
+		return error;
+
+	if (volume > 100)
+		volume = 100;
+	
+        rtas_tone_volume = volume; /* save it for later */
+	error = rtas_call(rtas_token("set-indicator"), 3, 1, NULL,
+			TONE_VOLUME, 0, volume);
+	if (error)
+		printk(KERN_WARNING "error: setting tone volume returned: %s\n", 
+				ppc_rtas_process_error(error));
+	return count;
+}
+/* ****************************************************************** */
+static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "%lu\n", rtas_tone_volume);
+	return 0;
+}
+
+#define RMO_READ_BUF_MAX 30
+
+/* RTAS Userspace access */
+static int ppc_rtas_rmo_buf_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "%016lx %x\n", rtas_rmo_buf, RTAS_RMOBUF_MAX);
+	return 0;
+}
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 4d22eeeeb91..b7fc2d88495 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -43,6 +43,13 @@ char rtas_data_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned;
 unsigned long rtas_rmo_buf;
 
 /*
+ * If non-NULL, this gets called when the kernel terminates.
+ * This is done like this so rtas_flash can be a module.
+ */
+void (*rtas_flash_term_hook)(int);
+EXPORT_SYMBOL(rtas_flash_term_hook);
+
+/*
  * 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.
@@ -206,6 +213,7 @@ void rtas_progress(char *s, unsigned short hex)
  
 	spin_unlock(&progress_lock);
 }
+EXPORT_SYMBOL(rtas_progress);		/* needed by rtas_flash module */
 
 int rtas_token(const char *service)
 {
@@ -492,6 +500,8 @@ int rtas_set_indicator(int indicator, int index, int new_value)
 
 void rtas_restart(char *cmd)
 {
+	if (rtas_flash_term_hook)
+		rtas_flash_term_hook(SYS_RESTART);
 	printk("RTAS system-reboot returned %d\n",
 	       rtas_call(rtas_token("system-reboot"), 0, 1, NULL));
 	for (;;);
@@ -499,6 +509,8 @@ void rtas_restart(char *cmd)
 
 void rtas_power_off(void)
 {
+	if (rtas_flash_term_hook)
+		rtas_flash_term_hook(SYS_POWER_OFF);
 	/* allow power on only with power button press */
 	printk("RTAS power-off returned %d\n",
 	       rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1));
@@ -507,7 +519,12 @@ void rtas_power_off(void)
 
 void rtas_halt(void)
 {
-	rtas_power_off();
+	if (rtas_flash_term_hook)
+		rtas_flash_term_hook(SYS_HALT);
+	/* allow power on only with power button press */
+	printk("RTAS power-off returned %d\n",
+	       rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1));
+	for (;;);
 }
 
 /* Must be in the RMO region, so we place it here */
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
new file mode 100644
index 00000000000..50500093c97
--- /dev/null
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -0,0 +1,834 @@
+/*
+ *  c 2001 PPC 64 Team, 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.
+ *
+ * /proc/ppc64/rtas/firmware_flash interface
+ *
+ * This file implements a firmware_flash interface to pump a firmware
+ * image into the kernel.  At reboot time rtas_restart() will see the
+ * firmware image and flash it as it reboots (see rtas.c).
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <asm/delay.h>
+#include <asm/uaccess.h>
+#include <asm/rtas.h>
+#include <asm/abs_addr.h>
+
+#define MODULE_VERS "1.0"
+#define MODULE_NAME "rtas_flash"
+
+#define FIRMWARE_FLASH_NAME "firmware_flash"   
+#define FIRMWARE_UPDATE_NAME "firmware_update"
+#define MANAGE_FLASH_NAME "manage_flash"
+#define VALIDATE_FLASH_NAME "validate_flash"
+
+/* General RTAS Status Codes */
+#define RTAS_RC_SUCCESS  0
+#define RTAS_RC_HW_ERR	-1
+#define RTAS_RC_BUSY	-2
+
+/* Flash image status values */
+#define FLASH_AUTH           -9002 /* RTAS Not Service Authority Partition */
+#define FLASH_NO_OP          -1099 /* No operation initiated by user */	
+#define FLASH_IMG_SHORT	     -1005 /* Flash image shorter than expected */
+#define FLASH_IMG_BAD_LEN    -1004 /* Bad length value in flash list block */
+#define FLASH_IMG_NULL_DATA  -1003 /* Bad data value in flash list block */
+#define FLASH_IMG_READY      0     /* Firmware img ready for flash on reboot */
+
+/* Manage image status values */
+#define MANAGE_AUTH          -9002 /* RTAS Not Service Authority Partition */
+#define MANAGE_ACTIVE_ERR    -9001 /* RTAS Cannot Overwrite Active Img */
+#define MANAGE_NO_OP         -1099 /* No operation initiated by user */
+#define MANAGE_PARAM_ERR     -3    /* RTAS Parameter Error */
+#define MANAGE_HW_ERR        -1    /* RTAS Hardware Error */
+
+/* Validate image status values */
+#define VALIDATE_AUTH          -9002 /* RTAS Not Service Authority Partition */
+#define VALIDATE_NO_OP         -1099 /* No operation initiated by the user */
+#define VALIDATE_INCOMPLETE    -1002 /* User copied < VALIDATE_BUF_SIZE */
+#define VALIDATE_READY	       -1001 /* Firmware image ready for validation */
+#define VALIDATE_PARAM_ERR     -3    /* RTAS Parameter Error */
+#define VALIDATE_HW_ERR        -1    /* RTAS Hardware Error */
+#define VALIDATE_TMP_UPDATE    0     /* Validate Return Status */
+#define VALIDATE_FLASH_AUTH    1     /* Validate Return Status */
+#define VALIDATE_INVALID_IMG   2     /* Validate Return Status */
+#define VALIDATE_CUR_UNKNOWN   3     /* Validate Return Status */
+#define VALIDATE_TMP_COMMIT_DL 4     /* Validate Return Status */
+#define VALIDATE_TMP_COMMIT    5     /* Validate Return Status */
+#define VALIDATE_TMP_UPDATE_DL 6     /* Validate Return Status */
+
+/* ibm,manage-flash-image operation tokens */
+#define RTAS_REJECT_TMP_IMG   0
+#define RTAS_COMMIT_TMP_IMG   1
+
+/* Array sizes */
+#define VALIDATE_BUF_SIZE 4096    
+#define RTAS_MSG_MAXLEN   64
+
+struct flash_block {
+	char *data;
+	unsigned long length;
+};
+
+/* This struct is very similar but not identical to
+ * that needed by the rtas flash update.
+ * All we need to do for rtas is rewrite num_blocks
+ * into a version/length and translate the pointers
+ * to absolute.
+ */
+#define FLASH_BLOCKS_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct flash_block))
+struct flash_block_list {
+	unsigned long num_blocks;
+	struct flash_block_list *next;
+	struct flash_block blocks[FLASH_BLOCKS_PER_NODE];
+};
+struct flash_block_list_header { /* just the header of flash_block_list */
+	unsigned long num_blocks;
+	struct flash_block_list *next;
+};
+
+static struct flash_block_list_header rtas_firmware_flash_list = {0, NULL};
+
+#define FLASH_BLOCK_LIST_VERSION (1UL)
+
+/* Local copy of the flash block list.
+ * We only allow one open of the flash proc file and create this
+ * list as we go.  This list will be put in the
+ * rtas_firmware_flash_list var once it is fully read.
+ *
+ * For convenience as we build the list we use virtual addrs,
+ * we do not fill in the version number, and the length field
+ * is treated as the number of entries currently in the block
+ * (i.e. not a byte count).  This is all fixed on release.
+ */
+
+/* Status int must be first member of struct */
+struct rtas_update_flash_t
+{
+	int status;			/* Flash update status */
+	struct flash_block_list *flist; /* Local copy of flash block list */
+};
+
+/* Status int must be first member of struct */
+struct rtas_manage_flash_t
+{
+	int status;			/* Returned status */
+	unsigned int op;		/* Reject or commit image */
+};
+
+/* Status int must be first member of struct */
+struct rtas_validate_flash_t
+{
+	int status;		 	/* Returned status */	
+	char buf[VALIDATE_BUF_SIZE]; 	/* Candidate image buffer */
+	unsigned int buf_size;		/* Size of image buf */
+	unsigned int update_results;	/* Update results token */
+};
+
+static DEFINE_SPINLOCK(flash_file_open_lock);
+static struct proc_dir_entry *firmware_flash_pde;
+static struct proc_dir_entry *firmware_update_pde;
+static struct proc_dir_entry *validate_pde;
+static struct proc_dir_entry *manage_pde;
+
+/* Do simple sanity checks on the flash image. */
+static int flash_list_valid(struct flash_block_list *flist)
+{
+	struct flash_block_list *f;
+	int i;
+	unsigned long block_size, image_size;
+
+	/* Paranoid self test here.  We also collect the image size. */
+	image_size = 0;
+	for (f = flist; f; f = f->next) {
+		for (i = 0; i < f->num_blocks; i++) {
+			if (f->blocks[i].data == NULL) {
+				return FLASH_IMG_NULL_DATA;
+			}
+			block_size = f->blocks[i].length;
+			if (block_size <= 0 || block_size > PAGE_SIZE) {
+				return FLASH_IMG_BAD_LEN;
+			}
+			image_size += block_size;
+		}
+	}
+
+	if (image_size < (256 << 10)) {
+		if (image_size < 2) 
+			return FLASH_NO_OP;
+	}
+
+	printk(KERN_INFO "FLASH: flash image with %ld bytes stored for hardware flash on reboot\n", image_size);
+
+	return FLASH_IMG_READY;
+}
+
+static void free_flash_list(struct flash_block_list *f)
+{
+	struct flash_block_list *next;
+	int i;
+
+	while (f) {
+		for (i = 0; i < f->num_blocks; i++)
+			free_page((unsigned long)(f->blocks[i].data));
+		next = f->next;
+		free_page((unsigned long)f);
+		f = next;
+	}
+}
+
+static int rtas_flash_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	struct rtas_update_flash_t *uf;
+	
+	uf = (struct rtas_update_flash_t *) dp->data;
+	if (uf->flist) {    
+		/* File was opened in write mode for a new flash attempt */
+		/* Clear saved list */
+		if (rtas_firmware_flash_list.next) {
+			free_flash_list(rtas_firmware_flash_list.next);
+			rtas_firmware_flash_list.next = NULL;
+		}
+
+		if (uf->status != FLASH_AUTH)  
+			uf->status = flash_list_valid(uf->flist);
+
+		if (uf->status == FLASH_IMG_READY) 
+			rtas_firmware_flash_list.next = uf->flist;
+		else
+			free_flash_list(uf->flist);
+
+		uf->flist = NULL;
+	}
+
+	atomic_dec(&dp->count);
+	return 0;
+}
+
+static void get_flash_status_msg(int status, char *buf)
+{
+	char *msg;
+
+	switch (status) {
+	case FLASH_AUTH:
+		msg = "error: this partition does not have service authority\n";
+		break;
+	case FLASH_NO_OP:
+		msg = "info: no firmware image for flash\n";
+		break;
+	case FLASH_IMG_SHORT:
+		msg = "error: flash image short\n";
+		break;
+	case FLASH_IMG_BAD_LEN:
+		msg = "error: internal error bad length\n";
+		break;
+	case FLASH_IMG_NULL_DATA:
+		msg = "error: internal error null data\n";
+		break;
+	case FLASH_IMG_READY:
+		msg = "ready: firmware image ready for flash on reboot\n";
+		break;
+	default:
+		sprintf(buf, "error: unexpected status value %d\n", status);
+		return;
+	}
+
+	strcpy(buf, msg);	
+}
+
+/* Reading the proc file will show status (not the firmware contents) */
+static ssize_t rtas_flash_read(struct file *file, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	struct rtas_update_flash_t *uf;
+	char msg[RTAS_MSG_MAXLEN];
+	int msglen;
+
+	uf = (struct rtas_update_flash_t *) dp->data;
+
+	if (!strcmp(dp->name, FIRMWARE_FLASH_NAME)) {
+		get_flash_status_msg(uf->status, msg);
+	} else {	   /* FIRMWARE_UPDATE_NAME */
+		sprintf(msg, "%d\n", uf->status);
+	}
+	msglen = strlen(msg);
+	if (msglen > count)
+		msglen = count;
+
+	if (ppos && *ppos != 0)
+		return 0;	/* be cheap */
+
+	if (!access_ok(VERIFY_WRITE, buf, msglen))
+		return -EINVAL;
+
+	if (copy_to_user(buf, msg, msglen))
+		return -EFAULT;
+
+	if (ppos)
+		*ppos = msglen;
+	return msglen;
+}
+
+/* We could be much more efficient here.  But to keep this function
+ * simple we allocate a page to the block list no matter how small the
+ * count is.  If the system is low on memory it will be just as well
+ * that we fail....
+ */
+static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
+				size_t count, loff_t *off)
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	struct rtas_update_flash_t *uf;
+	char *p;
+	int next_free;
+	struct flash_block_list *fl;
+
+	uf = (struct rtas_update_flash_t *) dp->data;
+
+	if (uf->status == FLASH_AUTH || count == 0)
+		return count;	/* discard data */
+
+	/* In the case that the image is not ready for flashing, the memory
+	 * allocated for the block list will be freed upon the release of the 
+	 * proc file
+	 */
+	if (uf->flist == NULL) {
+		uf->flist = (struct flash_block_list *) get_zeroed_page(GFP_KERNEL);
+		if (!uf->flist)
+			return -ENOMEM;
+	}
+
+	fl = uf->flist;
+	while (fl->next)
+		fl = fl->next; /* seek to last block_list for append */
+	next_free = fl->num_blocks;
+	if (next_free == FLASH_BLOCKS_PER_NODE) {
+		/* Need to allocate another block_list */
+		fl->next = (struct flash_block_list *)get_zeroed_page(GFP_KERNEL);
+		if (!fl->next)
+			return -ENOMEM;
+		fl = fl->next;
+		next_free = 0;
+	}
+
+	if (count > PAGE_SIZE)
+		count = PAGE_SIZE;
+	p = (char *)get_zeroed_page(GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+	
+	if(copy_from_user(p, buffer, count)) {
+		free_page((unsigned long)p);
+		return -EFAULT;
+	}
+	fl->blocks[next_free].data = p;
+	fl->blocks[next_free].length = count;
+	fl->num_blocks++;
+
+	return count;
+}
+
+static int rtas_excl_open(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *dp = PDE(inode);
+
+	/* Enforce exclusive open with use count of PDE */
+	spin_lock(&flash_file_open_lock);
+	if (atomic_read(&dp->count) > 1) {
+		spin_unlock(&flash_file_open_lock);
+		return -EBUSY;
+	}
+
+	atomic_inc(&dp->count);
+	spin_unlock(&flash_file_open_lock);
+	
+	return 0;
+}
+
+static int rtas_excl_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *dp = PDE(inode);
+
+	atomic_dec(&dp->count);
+
+	return 0;
+}
+
+static void manage_flash(struct rtas_manage_flash_t *args_buf)
+{
+	unsigned int wait_time;
+	s32 rc;
+
+	while (1) {
+		rc = rtas_call(rtas_token("ibm,manage-flash-image"), 1, 
+			       1, NULL, args_buf->op);
+		if (rc == RTAS_RC_BUSY)
+			udelay(1);
+		else if (rtas_is_extended_busy(rc)) {
+			wait_time = rtas_extended_busy_delay_time(rc);
+			udelay(wait_time * 1000);
+		} else
+			break;
+	}
+
+	args_buf->status = rc;
+}
+
+static ssize_t manage_flash_read(struct file *file, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	struct rtas_manage_flash_t *args_buf;
+	char msg[RTAS_MSG_MAXLEN];
+	int msglen;
+
+	args_buf = (struct rtas_manage_flash_t *) dp->data;
+	if (args_buf == NULL)
+		return 0;
+
+	msglen = sprintf(msg, "%d\n", args_buf->status);
+	if (msglen > count)
+		msglen = count;
+
+	if (ppos && *ppos != 0)
+		return 0;	/* be cheap */
+
+	if (!access_ok(VERIFY_WRITE, buf, msglen))
+		return -EINVAL;
+
+	if (copy_to_user(buf, msg, msglen))
+		return -EFAULT;
+
+	if (ppos)
+		*ppos = msglen;
+	return msglen;
+}
+
+static ssize_t manage_flash_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *off)
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	struct rtas_manage_flash_t *args_buf;
+	const char reject_str[] = "0";
+	const char commit_str[] = "1";
+	char stkbuf[10];
+	int op;
+
+	args_buf = (struct rtas_manage_flash_t *) dp->data;
+	if ((args_buf->status == MANAGE_AUTH) || (count == 0))
+		return count;
+		
+	op = -1;
+	if (buf) {
+		if (count > 9) count = 9;
+		if (copy_from_user (stkbuf, buf, count)) {
+			return -EFAULT;
+		}
+		if (strncmp(stkbuf, reject_str, strlen(reject_str)) == 0) 
+			op = RTAS_REJECT_TMP_IMG;
+		else if (strncmp(stkbuf, commit_str, strlen(commit_str)) == 0) 
+			op = RTAS_COMMIT_TMP_IMG;
+	}
+	
+	if (op == -1)   /* buf is empty, or contains invalid string */
+		return -EINVAL;
+
+	args_buf->op = op;
+	manage_flash(args_buf);
+
+	return count;
+}
+
+static void validate_flash(struct rtas_validate_flash_t *args_buf)
+{
+	int token = rtas_token("ibm,validate-flash-image");
+	unsigned int wait_time;
+	int update_results;
+	s32 rc;	
+
+	rc = 0;
+	while(1) {
+		spin_lock(&rtas_data_buf_lock);
+		memcpy(rtas_data_buf, args_buf->buf, VALIDATE_BUF_SIZE);
+		rc = rtas_call(token, 2, 2, &update_results, 
+			       (u32) __pa(rtas_data_buf), args_buf->buf_size);
+		memcpy(args_buf->buf, rtas_data_buf, VALIDATE_BUF_SIZE);
+		spin_unlock(&rtas_data_buf_lock);
+			
+		if (rc == RTAS_RC_BUSY)
+			udelay(1);
+		else if (rtas_is_extended_busy(rc)) {
+			wait_time = rtas_extended_busy_delay_time(rc);
+			udelay(wait_time * 1000);
+		} else
+			break;
+	}
+
+	args_buf->status = rc;
+	args_buf->update_results = update_results;
+}
+
+static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf, 
+		                   char *msg)
+{
+	int n;
+
+	if (args_buf->status >= VALIDATE_TMP_UPDATE) { 
+		n = sprintf(msg, "%d\n", args_buf->update_results);
+		if ((args_buf->update_results >= VALIDATE_CUR_UNKNOWN) ||
+		    (args_buf->update_results == VALIDATE_TMP_UPDATE))
+			n += sprintf(msg + n, "%s\n", args_buf->buf);
+	} else {
+		n = sprintf(msg, "%d\n", args_buf->status);
+	}
+	return n;
+}
+
+static ssize_t validate_flash_read(struct file *file, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	struct rtas_validate_flash_t *args_buf;
+	char msg[RTAS_MSG_MAXLEN];
+	int msglen;
+
+	args_buf = (struct rtas_validate_flash_t *) dp->data;
+
+	if (ppos && *ppos != 0)
+		return 0;	/* be cheap */
+	
+	msglen = get_validate_flash_msg(args_buf, msg);
+	if (msglen > count)
+		msglen = count;
+
+	if (!access_ok(VERIFY_WRITE, buf, msglen))
+		return -EINVAL;
+
+	if (copy_to_user(buf, msg, msglen))
+		return -EFAULT;
+
+	if (ppos)
+		*ppos = msglen;
+	return msglen;
+}
+
+static ssize_t validate_flash_write(struct file *file, const char __user *buf,
+				    size_t count, loff_t *off)
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	struct rtas_validate_flash_t *args_buf;
+	int rc;
+
+	args_buf = (struct rtas_validate_flash_t *) dp->data;
+
+	if (dp->data == NULL) {
+		dp->data = kmalloc(sizeof(struct rtas_validate_flash_t), 
+				GFP_KERNEL);
+		if (dp->data == NULL) 
+			return -ENOMEM;
+	}
+
+	/* We are only interested in the first 4K of the
+	 * candidate image */
+	if ((*off >= VALIDATE_BUF_SIZE) || 
+		(args_buf->status == VALIDATE_AUTH)) {
+		*off += count;
+		return count;
+	}
+
+	if (*off + count >= VALIDATE_BUF_SIZE)  {
+		count = VALIDATE_BUF_SIZE - *off;
+		args_buf->status = VALIDATE_READY;	
+	} else {
+		args_buf->status = VALIDATE_INCOMPLETE;
+	}
+
+	if (!access_ok(VERIFY_READ, buf, count)) {
+		rc = -EFAULT;
+		goto done;
+	}
+	if (copy_from_user(args_buf->buf + *off, buf, count)) {
+		rc = -EFAULT;
+		goto done;
+	}
+
+	*off += count;
+	rc = count;
+done:
+	if (rc < 0) {
+		kfree(dp->data);
+		dp->data = NULL;
+	}
+	return rc;
+}
+
+static int validate_flash_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	struct rtas_validate_flash_t *args_buf;
+
+	args_buf = (struct rtas_validate_flash_t *) dp->data;
+
+	if (args_buf->status == VALIDATE_READY) {
+		args_buf->buf_size = VALIDATE_BUF_SIZE;
+		validate_flash(args_buf);
+	}
+
+	/* The matching atomic_inc was in rtas_excl_open() */
+	atomic_dec(&dp->count);
+
+	return 0;
+}
+
+static void rtas_flash_firmware(int reboot_type)
+{
+	unsigned long image_size;
+	struct flash_block_list *f, *next, *flist;
+	unsigned long rtas_block_list;
+	int i, status, update_token;
+
+	if (rtas_firmware_flash_list.next == NULL)
+		return;		/* nothing to do */
+
+	if (reboot_type != SYS_RESTART) {
+		printk(KERN_ALERT "FLASH: firmware flash requires a reboot\n");
+		printk(KERN_ALERT "FLASH: the firmware image will NOT be flashed\n");
+		return;
+	}
+
+	update_token = rtas_token("ibm,update-flash-64-and-reboot");
+	if (update_token == RTAS_UNKNOWN_SERVICE) {
+		printk(KERN_ALERT "FLASH: ibm,update-flash-64-and-reboot "
+		       "is not available -- not a service partition?\n");
+		printk(KERN_ALERT "FLASH: firmware will not be flashed\n");
+		return;
+	}
+
+	/* NOTE: the "first" block list is a global var with no data
+	 * blocks in the kernel data segment.  We do this because
+	 * we want to ensure this block_list addr is under 4GB.
+	 */
+	rtas_firmware_flash_list.num_blocks = 0;
+	flist = (struct flash_block_list *)&rtas_firmware_flash_list;
+	rtas_block_list = virt_to_abs(flist);
+	if (rtas_block_list >= 4UL*1024*1024*1024) {
+		printk(KERN_ALERT "FLASH: kernel bug...flash list header addr above 4GB\n");
+		return;
+	}
+
+	printk(KERN_ALERT "FLASH: preparing saved firmware image for flash\n");
+	/* Update the block_list in place. */
+	image_size = 0;
+	for (f = flist; f; f = next) {
+		/* Translate data addrs to absolute */
+		for (i = 0; i < f->num_blocks; i++) {
+			f->blocks[i].data = (char *)virt_to_abs(f->blocks[i].data);
+			image_size += f->blocks[i].length;
+		}
+		next = f->next;
+		/* Don't translate NULL pointer for last entry */
+		if (f->next)
+			f->next = (struct flash_block_list *)virt_to_abs(f->next);
+		else
+			f->next = NULL;
+		/* make num_blocks into the version/length field */
+		f->num_blocks = (FLASH_BLOCK_LIST_VERSION << 56) | ((f->num_blocks+1)*16);
+	}
+
+	printk(KERN_ALERT "FLASH: flash image is %ld bytes\n", image_size);
+	printk(KERN_ALERT "FLASH: performing flash and reboot\n");
+	rtas_progress("Flashing        \n", 0x0);
+	rtas_progress("Please Wait...  ", 0x0);
+	printk(KERN_ALERT "FLASH: this will take several minutes.  Do not power off!\n");
+	status = rtas_call(update_token, 1, 1, NULL, rtas_block_list);
+	switch (status) {	/* should only get "bad" status */
+	    case 0:
+		printk(KERN_ALERT "FLASH: success\n");
+		break;
+	    case -1:
+		printk(KERN_ALERT "FLASH: hardware error.  Firmware may not be not flashed\n");
+		break;
+	    case -3:
+		printk(KERN_ALERT "FLASH: image is corrupt or not correct for this platform.  Firmware not flashed\n");
+		break;
+	    case -4:
+		printk(KERN_ALERT "FLASH: flash failed when partially complete.  System may not reboot\n");
+		break;
+	    default:
+		printk(KERN_ALERT "FLASH: unknown flash return code %d\n", status);
+		break;
+	}
+}
+
+static void remove_flash_pde(struct proc_dir_entry *dp)
+{
+	if (dp) {
+		if (dp->data != NULL)
+			kfree(dp->data);
+		dp->owner = NULL;
+		remove_proc_entry(dp->name, dp->parent);
+	}
+}
+
+static int initialize_flash_pde_data(const char *rtas_call_name,
+				     size_t buf_size,
+				     struct proc_dir_entry *dp)
+{
+	int *status;
+	int token;
+
+	dp->data = kmalloc(buf_size, GFP_KERNEL);
+	if (dp->data == NULL) {
+		remove_flash_pde(dp);
+		return -ENOMEM;
+	}
+
+	memset(dp->data, 0, buf_size);
+
+	/*
+	 * This code assumes that the status int is the first member of the
+	 * struct 
+	 */
+	status = (int *) dp->data;
+	token = rtas_token(rtas_call_name);
+	if (token == RTAS_UNKNOWN_SERVICE)
+		*status = FLASH_AUTH;
+	else
+		*status = FLASH_NO_OP;
+
+	return 0;
+}
+
+static struct proc_dir_entry *create_flash_pde(const char *filename,
+					       struct file_operations *fops)
+{
+	struct proc_dir_entry *ent = NULL;
+
+	ent = create_proc_entry(filename, S_IRUSR | S_IWUSR, NULL);
+	if (ent != NULL) {
+		ent->nlink = 1;
+		ent->proc_fops = fops;
+		ent->owner = THIS_MODULE;
+	}
+
+	return ent;
+}
+
+static struct file_operations rtas_flash_operations = {
+	.read		= rtas_flash_read,
+	.write		= rtas_flash_write,
+	.open		= rtas_excl_open,
+	.release	= rtas_flash_release,
+};
+
+static struct file_operations manage_flash_operations = {
+	.read		= manage_flash_read,
+	.write		= manage_flash_write,
+	.open		= rtas_excl_open,
+	.release	= rtas_excl_release,
+};
+
+static struct file_operations validate_flash_operations = {
+	.read		= validate_flash_read,
+	.write		= validate_flash_write,
+	.open		= rtas_excl_open,
+	.release	= validate_flash_release,
+};
+
+int __init rtas_flash_init(void)
+{
+	int rc;
+
+	if (rtas_token("ibm,update-flash-64-and-reboot") ==
+		       RTAS_UNKNOWN_SERVICE) {
+		printk(KERN_ERR "rtas_flash: no firmware flash support\n");
+		return 1;
+	}
+
+	firmware_flash_pde = create_flash_pde("ppc64/rtas/"
+					      FIRMWARE_FLASH_NAME,
+					      &rtas_flash_operations);
+	if (firmware_flash_pde == NULL) {
+		rc = -ENOMEM;
+		goto cleanup;
+	}
+
+	rc = initialize_flash_pde_data("ibm,update-flash-64-and-reboot",
+			 	       sizeof(struct rtas_update_flash_t), 
+				       firmware_flash_pde);
+	if (rc != 0)
+		goto cleanup;
+
+	firmware_update_pde = create_flash_pde("ppc64/rtas/"
+					       FIRMWARE_UPDATE_NAME,
+					       &rtas_flash_operations);
+	if (firmware_update_pde == NULL) {
+		rc = -ENOMEM;
+		goto cleanup;
+	}
+
+	rc = initialize_flash_pde_data("ibm,update-flash-64-and-reboot",
+			 	       sizeof(struct rtas_update_flash_t), 
+				       firmware_update_pde);
+	if (rc != 0)
+		goto cleanup;
+
+	validate_pde = create_flash_pde("ppc64/rtas/" VALIDATE_FLASH_NAME,
+			      		&validate_flash_operations);
+	if (validate_pde == NULL) {
+		rc = -ENOMEM;
+		goto cleanup;
+	}
+
+	rc = initialize_flash_pde_data("ibm,validate-flash-image",
+		                       sizeof(struct rtas_validate_flash_t), 
+				       validate_pde);
+	if (rc != 0)
+		goto cleanup;
+
+	manage_pde = create_flash_pde("ppc64/rtas/" MANAGE_FLASH_NAME,
+				      &manage_flash_operations);
+	if (manage_pde == NULL) {
+		rc = -ENOMEM;
+		goto cleanup;
+	}
+
+	rc = initialize_flash_pde_data("ibm,manage-flash-image",
+			               sizeof(struct rtas_manage_flash_t),
+				       manage_pde);
+	if (rc != 0)
+		goto cleanup;
+
+	rtas_flash_term_hook = rtas_flash_firmware;
+	return 0;
+
+cleanup:
+	remove_flash_pde(firmware_flash_pde);
+	remove_flash_pde(firmware_update_pde);
+	remove_flash_pde(validate_pde);
+	remove_flash_pde(manage_pde);
+
+	return rc;
+}
+
+void __exit rtas_flash_cleanup(void)
+{
+	rtas_flash_term_hook = NULL;
+	remove_flash_pde(firmware_flash_pde);
+	remove_flash_pde(firmware_update_pde);
+	remove_flash_pde(validate_pde);
+	remove_flash_pde(manage_pde);
+}
+
+module_init(rtas_flash_init);
+module_exit(rtas_flash_cleanup);
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kernel/rtas_fw.c b/arch/powerpc/kernel/rtas_fw.c
deleted file mode 100644
index 448922e8af1..00000000000
--- a/arch/powerpc/kernel/rtas_fw.c
+++ /dev/null
@@ -1,136 +0,0 @@
-/*
- *
- * Procedures for firmware flash updates.
- *
- * Peter Bergner, IBM	March 2001.
- * Copyright (C) 2001 IBM.
- *
- *      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 <stdarg.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/spinlock.h>
-#include <linux/module.h>
-#include <linux/init.h>
-
-#include <asm/prom.h>
-#include <asm/rtas.h>
-#include <asm/semaphore.h>
-#include <asm/machdep.h>
-#include <asm/page.h>
-#include <asm/param.h>
-#include <asm/system.h>
-#include <asm/abs_addr.h>
-#include <asm/udbg.h>
-#include <asm/delay.h>
-#include <asm/uaccess.h>
-#include <asm/systemcfg.h>
-
-struct flash_block_list_header rtas_firmware_flash_list = {0, NULL};
-
-#define FLASH_BLOCK_LIST_VERSION (1UL)
-
-static void rtas_flash_firmware(void)
-{
-	unsigned long image_size;
-	struct flash_block_list *f, *next, *flist;
-	unsigned long rtas_block_list;
-	int i, status, update_token;
-
-	update_token = rtas_token("ibm,update-flash-64-and-reboot");
-	if (update_token == RTAS_UNKNOWN_SERVICE) {
-		printk(KERN_ALERT "FLASH: ibm,update-flash-64-and-reboot is not available -- not a service partition?\n");
-		printk(KERN_ALERT "FLASH: firmware will not be flashed\n");
-		return;
-	}
-
-	/* NOTE: the "first" block list is a global var with no data
-	 * blocks in the kernel data segment.  We do this because
-	 * we want to ensure this block_list addr is under 4GB.
-	 */
-	rtas_firmware_flash_list.num_blocks = 0;
-	flist = (struct flash_block_list *)&rtas_firmware_flash_list;
-	rtas_block_list = virt_to_abs(flist);
-	if (rtas_block_list >= 4UL*1024*1024*1024) {
-		printk(KERN_ALERT "FLASH: kernel bug...flash list header addr above 4GB\n");
-		return;
-	}
-
-	printk(KERN_ALERT "FLASH: preparing saved firmware image for flash\n");
-	/* Update the block_list in place. */
-	image_size = 0;
-	for (f = flist; f; f = next) {
-		/* Translate data addrs to absolute */
-		for (i = 0; i < f->num_blocks; i++) {
-			f->blocks[i].data = (char *)virt_to_abs(f->blocks[i].data);
-			image_size += f->blocks[i].length;
-		}
-		next = f->next;
-		/* Don't translate NULL pointer for last entry */
-		if (f->next)
-			f->next = (struct flash_block_list *)virt_to_abs(f->next);
-		else
-			f->next = NULL;
-		/* make num_blocks into the version/length field */
-		f->num_blocks = (FLASH_BLOCK_LIST_VERSION << 56) | ((f->num_blocks+1)*16);
-	}
-
-	printk(KERN_ALERT "FLASH: flash image is %ld bytes\n", image_size);
-	printk(KERN_ALERT "FLASH: performing flash and reboot\n");
-	rtas_progress("Flashing        \n", 0x0);
-	rtas_progress("Please Wait...  ", 0x0);
-	printk(KERN_ALERT "FLASH: this will take several minutes.  Do not power off!\n");
-	status = rtas_call(update_token, 1, 1, NULL, rtas_block_list);
-	switch (status) {	/* should only get "bad" status */
-	    case 0:
-		printk(KERN_ALERT "FLASH: success\n");
-		break;
-	    case -1:
-		printk(KERN_ALERT "FLASH: hardware error.  Firmware may not be not flashed\n");
-		break;
-	    case -3:
-		printk(KERN_ALERT "FLASH: image is corrupt or not correct for this platform.  Firmware not flashed\n");
-		break;
-	    case -4:
-		printk(KERN_ALERT "FLASH: flash failed when partially complete.  System may not reboot\n");
-		break;
-	    default:
-		printk(KERN_ALERT "FLASH: unknown flash return code %d\n", status);
-		break;
-	}
-}
-
-void rtas_flash_bypass_warning(void)
-{
-	printk(KERN_ALERT "FLASH: firmware flash requires a reboot\n");
-	printk(KERN_ALERT "FLASH: the firmware image will NOT be flashed\n");
-}
-
-
-void rtas_fw_restart(char *cmd)
-{
-	if (rtas_firmware_flash_list.next)
-		rtas_flash_firmware();
-	rtas_restart(cmd);
-}
-
-void rtas_fw_power_off(void)
-{
-	if (rtas_firmware_flash_list.next)
-		rtas_flash_bypass_warning();
-	rtas_power_off();
-}
-
-void rtas_fw_halt(void)
-{
-	if (rtas_firmware_flash_list.next)
-		rtas_flash_bypass_warning();
-	rtas_halt();
-}
-
-EXPORT_SYMBOL(rtas_firmware_flash_list);
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 444c3e81884..876c57c1136 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -43,7 +43,7 @@
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 #ifdef CONFIG_PPC64
-#include <asm/ppc32.h>
+#include "ppc32.h"
 #include <asm/ppcdebug.h>
 #include <asm/unistd.h>
 #include <asm/vdso.h>
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
new file mode 100644
index 00000000000..ec9d0984b6a
--- /dev/null
+++ b/arch/powerpc/kernel/signal_64.c
@@ -0,0 +1,581 @@
+/*
+ *  linux/arch/ppc64/kernel/signal.c
+ *
+ *  PowerPC version 
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Derived from "arch/i386/kernel/signal.c"
+ *    Copyright (C) 1991, 1992 Linus Torvalds
+ *    1997-11-28  Modified for POSIX.1b signals by Richard Henderson
+ *
+ *  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/config.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/elf.h>
+#include <linux/ptrace.h>
+#include <linux/module.h>
+
+#include <asm/sigcontext.h>
+#include <asm/ucontext.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/ppcdebug.h>
+#include <asm/unistd.h>
+#include <asm/cacheflush.h>
+#include <asm/vdso.h>
+
+#define DEBUG_SIG 0
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+#define GP_REGS_SIZE	min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
+#define FP_REGS_SIZE	sizeof(elf_fpregset_t)
+
+#define TRAMP_TRACEBACK	3
+#define TRAMP_SIZE	6
+
+/*
+ * When we have signals to deliver, we set up on the user stack,
+ * going down from the original stack pointer:
+ *	1) a rt_sigframe struct which contains the ucontext	
+ *	2) a gap of __SIGNAL_FRAMESIZE bytes which acts as a dummy caller
+ *	   frame for the signal handler.
+ */
+
+struct rt_sigframe {
+	/* sys_rt_sigreturn requires the ucontext be the first field */
+	struct ucontext uc;
+	unsigned long _unused[2];
+	unsigned int tramp[TRAMP_SIZE];
+	struct siginfo *pinfo;
+	void *puc;
+	struct siginfo info;
+	/* 64 bit ABI allows for 288 bytes below sp before decrementing it. */
+	char abigap[288];
+} __attribute__ ((aligned (16)));
+
+
+/*
+ * Atomically swap in the new signal mask, and wait for a signal.
+ */
+long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize, int p3, int p4,
+		       int p6, int p7, struct pt_regs *regs)
+{
+	sigset_t saveset, newset;
+
+	/* XXX: Don't preclude handling different sized sigset_t's.  */
+	if (sigsetsize != sizeof(sigset_t))
+		return -EINVAL;
+
+	if (copy_from_user(&newset, unewset, sizeof(newset)))
+		return -EFAULT;
+	sigdelsetmask(&newset, ~_BLOCKABLE);
+
+	spin_lock_irq(&current->sighand->siglock);
+	saveset = current->blocked;
+	current->blocked = newset;
+	recalc_sigpending();
+	spin_unlock_irq(&current->sighand->siglock);
+
+	regs->result = -EINTR;
+	regs->gpr[3] = EINTR;
+	regs->ccr |= 0x10000000;
+	while (1) {
+		current->state = TASK_INTERRUPTIBLE;
+		schedule();
+		if (do_signal(&saveset, regs))
+			return 0;
+	}
+}
+
+long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, unsigned long r5,
+		     unsigned long r6, unsigned long r7, unsigned long r8,
+		     struct pt_regs *regs)
+{
+	return do_sigaltstack(uss, uoss, regs->gpr[1]);
+}
+
+
+/*
+ * Set up the sigcontext for the signal frame.
+ */
+
+static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
+		 int signr, sigset_t *set, unsigned long handler)
+{
+	/* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the
+	 * process never used altivec yet (MSR_VEC is zero in pt_regs of
+	 * the context). This is very important because we must ensure we
+	 * don't lose the VRSAVE content that may have been set prior to
+	 * the process doing its first vector operation
+	 * Userland shall check AT_HWCAP to know wether it can rely on the
+	 * v_regs pointer or not
+	 */
+#ifdef CONFIG_ALTIVEC
+	elf_vrreg_t __user *v_regs = (elf_vrreg_t __user *)(((unsigned long)sc->vmx_reserve + 15) & ~0xful);
+#endif
+	long err = 0;
+
+	flush_fp_to_thread(current);
+
+	/* Make sure signal doesn't get spurrious FP exceptions */
+	current->thread.fpscr.val = 0;
+
+#ifdef CONFIG_ALTIVEC
+	err |= __put_user(v_regs, &sc->v_regs);
+
+	/* save altivec registers */
+	if (current->thread.used_vr) {
+		flush_altivec_to_thread(current);
+		/* Copy 33 vec registers (vr0..31 and vscr) to the stack */
+		err |= __copy_to_user(v_regs, current->thread.vr, 33 * sizeof(vector128));
+		/* set MSR_VEC in the MSR value in the frame to indicate that sc->v_reg)
+		 * contains valid data.
+		 */
+		regs->msr |= MSR_VEC;
+	}
+	/* We always copy to/from vrsave, it's 0 if we don't have or don't
+	 * use altivec.
+	 */
+	err |= __put_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
+#else /* CONFIG_ALTIVEC */
+	err |= __put_user(0, &sc->v_regs);
+#endif /* CONFIG_ALTIVEC */
+	err |= __put_user(&sc->gp_regs, &sc->regs);
+	err |= __copy_to_user(&sc->gp_regs, regs, GP_REGS_SIZE);
+	err |= __copy_to_user(&sc->fp_regs, &current->thread.fpr, FP_REGS_SIZE);
+	err |= __put_user(signr, &sc->signal);
+	err |= __put_user(handler, &sc->handler);
+	if (set != NULL)
+		err |=  __put_user(set->sig[0], &sc->oldmask);
+
+	return err;
+}
+
+/*
+ * Restore the sigcontext from the signal frame.
+ */
+
+static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig,
+			      struct sigcontext __user *sc)
+{
+#ifdef CONFIG_ALTIVEC
+	elf_vrreg_t __user *v_regs;
+#endif
+	unsigned long err = 0;
+	unsigned long save_r13 = 0;
+	elf_greg_t *gregs = (elf_greg_t *)regs;
+#ifdef CONFIG_ALTIVEC
+	unsigned long msr;
+#endif
+	int i;
+
+	/* If this is not a signal return, we preserve the TLS in r13 */
+	if (!sig)
+		save_r13 = regs->gpr[13];
+
+	/* copy everything before MSR */
+	err |= __copy_from_user(regs, &sc->gp_regs,
+				PT_MSR*sizeof(unsigned long));
+
+	/* skip MSR and SOFTE */
+	for (i = PT_MSR+1; i <= PT_RESULT; i++) {
+		if (i == PT_SOFTE)
+			continue;
+		err |= __get_user(gregs[i], &sc->gp_regs[i]);
+	}
+
+	if (!sig)
+		regs->gpr[13] = save_r13;
+	err |= __copy_from_user(&current->thread.fpr, &sc->fp_regs, FP_REGS_SIZE);
+	if (set != NULL)
+		err |=  __get_user(set->sig[0], &sc->oldmask);
+
+#ifdef CONFIG_ALTIVEC
+	err |= __get_user(v_regs, &sc->v_regs);
+	err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
+	if (err)
+		return err;
+	/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
+	if (v_regs != 0 && (msr & MSR_VEC) != 0)
+		err |= __copy_from_user(current->thread.vr, v_regs,
+					33 * sizeof(vector128));
+	else if (current->thread.used_vr)
+		memset(current->thread.vr, 0, 33 * sizeof(vector128));
+	/* Always get VRSAVE back */
+	if (v_regs != 0)
+		err |= __get_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
+	else
+		current->thread.vrsave = 0;
+#endif /* CONFIG_ALTIVEC */
+
+#ifndef CONFIG_SMP
+	preempt_disable();
+	if (last_task_used_math == current)
+		last_task_used_math = NULL;
+	if (last_task_used_altivec == current)
+		last_task_used_altivec = NULL;
+	preempt_enable();
+#endif
+	/* Force reload of FP/VEC */
+	regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC);
+
+	return err;
+}
+
+/*
+ * Allocate space for the signal frame
+ */
+static inline void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
+				  size_t frame_size)
+{
+        unsigned long newsp;
+
+        /* Default to using normal stack */
+        newsp = regs->gpr[1];
+
+	if (ka->sa.sa_flags & SA_ONSTACK) {
+		if (! on_sig_stack(regs->gpr[1]))
+			newsp = (current->sas_ss_sp + current->sas_ss_size);
+	}
+
+        return (void __user *)((newsp - frame_size) & -16ul);
+}
+
+/*
+ * Setup the trampoline code on the stack
+ */
+static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp)
+{
+	int i;
+	long err = 0;
+
+	/* addi r1, r1, __SIGNAL_FRAMESIZE  # Pop the dummy stackframe */
+	err |= __put_user(0x38210000UL | (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]);
+	/* li r0, __NR_[rt_]sigreturn| */
+	err |= __put_user(0x38000000UL | (syscall & 0xffff), &tramp[1]);
+	/* sc */
+	err |= __put_user(0x44000002UL, &tramp[2]);
+
+	/* Minimal traceback info */
+	for (i=TRAMP_TRACEBACK; i < TRAMP_SIZE ;i++)
+		err |= __put_user(0, &tramp[i]);
+
+	if (!err)
+		flush_icache_range((unsigned long) &tramp[0],
+			   (unsigned long) &tramp[TRAMP_SIZE]);
+
+	return err;
+}
+
+/*
+ * Restore the user process's signal mask (also used by signal32.c)
+ */
+void restore_sigmask(sigset_t *set)
+{
+	sigdelsetmask(set, ~_BLOCKABLE);
+	spin_lock_irq(&current->sighand->siglock);
+	current->blocked = *set;
+	recalc_sigpending();
+	spin_unlock_irq(&current->sighand->siglock);
+}
+
+
+/*
+ * Handle {get,set,swap}_context operations
+ */
+int sys_swapcontext(struct ucontext __user *old_ctx,
+		    struct ucontext __user *new_ctx,
+		    long ctx_size, long r6, long r7, long r8, struct pt_regs *regs)
+{
+	unsigned char tmp;
+	sigset_t set;
+
+	/* Context size is for future use. Right now, we only make sure
+	 * we are passed something we understand
+	 */
+	if (ctx_size < sizeof(struct ucontext))
+		return -EINVAL;
+
+	if (old_ctx != NULL) {
+		if (!access_ok(VERIFY_WRITE, old_ctx, sizeof(*old_ctx))
+		    || setup_sigcontext(&old_ctx->uc_mcontext, regs, 0, NULL, 0)
+		    || __copy_to_user(&old_ctx->uc_sigmask,
+				      &current->blocked, sizeof(sigset_t)))
+			return -EFAULT;
+	}
+	if (new_ctx == NULL)
+		return 0;
+	if (!access_ok(VERIFY_READ, new_ctx, sizeof(*new_ctx))
+	    || __get_user(tmp, (u8 __user *) new_ctx)
+	    || __get_user(tmp, (u8 __user *) (new_ctx + 1) - 1))
+		return -EFAULT;
+
+	/*
+	 * If we get a fault copying the context into the kernel's
+	 * image of the user's registers, we can't just return -EFAULT
+	 * because the user's registers will be corrupted.  For instance
+	 * the NIP value may have been updated but not some of the
+	 * other registers.  Given that we have done the access_ok
+	 * and successfully read the first and last bytes of the region
+	 * above, this should only happen in an out-of-memory situation
+	 * or if another thread unmaps the region containing the context.
+	 * We kill the task with a SIGSEGV in this situation.
+	 */
+
+	if (__copy_from_user(&set, &new_ctx->uc_sigmask, sizeof(set)))
+		do_exit(SIGSEGV);
+	restore_sigmask(&set);
+	if (restore_sigcontext(regs, NULL, 0, &new_ctx->uc_mcontext))
+		do_exit(SIGSEGV);
+
+	/* This returns like rt_sigreturn */
+	return 0;
+}
+
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+
+int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
+		     unsigned long r6, unsigned long r7, unsigned long r8,
+		     struct pt_regs *regs)
+{
+	struct ucontext __user *uc = (struct ucontext __user *)regs->gpr[1];
+	sigset_t set;
+
+	/* Always make any pending restarted system calls return -EINTR */
+	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+	if (!access_ok(VERIFY_READ, uc, sizeof(*uc)))
+		goto badframe;
+
+	if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
+		goto badframe;
+	restore_sigmask(&set);
+	if (restore_sigcontext(regs, NULL, 1, &uc->uc_mcontext))
+		goto badframe;
+
+	/* do_sigaltstack expects a __user pointer and won't modify
+	 * what's in there anyway
+	 */
+	do_sigaltstack(&uc->uc_stack, NULL, regs->gpr[1]);
+
+	return regs->result;
+
+badframe:
+#if DEBUG_SIG
+	printk("badframe in sys_rt_sigreturn, regs=%p uc=%p &uc->uc_mcontext=%p\n",
+	       regs, uc, &uc->uc_mcontext);
+#endif
+	force_sig(SIGSEGV, current);
+	return 0;
+}
+
+static int setup_rt_frame(int signr, struct k_sigaction *ka, siginfo_t *info,
+		sigset_t *set, struct pt_regs *regs)
+{
+	/* Handler is *really* a pointer to the function descriptor for
+	 * the signal routine.  The first entry in the function
+	 * descriptor is the entry address of signal and the second
+	 * entry is the TOC value we need to use.
+	 */
+	func_descr_t __user *funct_desc_ptr;
+	struct rt_sigframe __user *frame;
+	unsigned long newsp = 0;
+	long err = 0;
+
+	frame = get_sigframe(ka, regs, sizeof(*frame));
+
+	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+		goto badframe;
+
+	err |= __put_user(&frame->info, &frame->pinfo);
+	err |= __put_user(&frame->uc, &frame->puc);
+	err |= copy_siginfo_to_user(&frame->info, info);
+	if (err)
+		goto badframe;
+
+	/* Create the ucontext.  */
+	err |= __put_user(0, &frame->uc.uc_flags);
+	err |= __put_user(0, &frame->uc.uc_link);
+	err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+	err |= __put_user(sas_ss_flags(regs->gpr[1]),
+			  &frame->uc.uc_stack.ss_flags);
+	err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+	err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, signr, NULL,
+				(unsigned long)ka->sa.sa_handler);
+	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+	if (err)
+		goto badframe;
+
+	/* Set up to return from userspace. */
+	if (vdso64_rt_sigtramp && current->thread.vdso_base) {
+		regs->link = current->thread.vdso_base + vdso64_rt_sigtramp;
+	} else {
+		err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]);
+		if (err)
+			goto badframe;
+		regs->link = (unsigned long) &frame->tramp[0];
+	}
+	funct_desc_ptr = (func_descr_t __user *) ka->sa.sa_handler;
+
+	/* Allocate a dummy caller frame for the signal handler. */
+	newsp = (unsigned long)frame - __SIGNAL_FRAMESIZE;
+	err |= put_user(regs->gpr[1], (unsigned long __user *)newsp);
+
+	/* Set up "regs" so we "return" to the signal handler. */
+	err |= get_user(regs->nip, &funct_desc_ptr->entry);
+	regs->gpr[1] = newsp;
+	err |= get_user(regs->gpr[2], &funct_desc_ptr->toc);
+	regs->gpr[3] = signr;
+	regs->result = 0;
+	if (ka->sa.sa_flags & SA_SIGINFO) {
+		err |= get_user(regs->gpr[4], (unsigned long __user *)&frame->pinfo);
+		err |= get_user(regs->gpr[5], (unsigned long __user *)&frame->puc);
+		regs->gpr[6] = (unsigned long) frame;
+	} else {
+		regs->gpr[4] = (unsigned long)&frame->uc.uc_mcontext;
+	}
+	if (err)
+		goto badframe;
+
+	if (test_thread_flag(TIF_SINGLESTEP))
+		ptrace_notify(SIGTRAP);
+
+	return 1;
+
+badframe:
+#if DEBUG_SIG
+	printk("badframe in setup_rt_frame, regs=%p frame=%p newsp=%lx\n",
+	       regs, frame, newsp);
+#endif
+	force_sigsegv(signr, current);
+	return 0;
+}
+
+
+/*
+ * OK, we're invoking a handler
+ */
+static int handle_signal(unsigned long sig, struct k_sigaction *ka,
+			 siginfo_t *info, sigset_t *oldset, struct pt_regs *regs)
+{
+	int ret;
+
+	/* Set up Signal Frame */
+	ret = setup_rt_frame(sig, ka, info, oldset, regs);
+
+	if (ret) {
+		spin_lock_irq(&current->sighand->siglock);
+		sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
+		if (!(ka->sa.sa_flags & SA_NODEFER))
+			sigaddset(&current->blocked,sig);
+		recalc_sigpending();
+		spin_unlock_irq(&current->sighand->siglock);
+	}
+
+	return ret;
+}
+
+static inline void syscall_restart(struct pt_regs *regs, struct k_sigaction *ka)
+{
+	switch ((int)regs->result) {
+	case -ERESTART_RESTARTBLOCK:
+	case -ERESTARTNOHAND:
+		/* ERESTARTNOHAND means that the syscall should only be
+		 * restarted if there was no handler for the signal, and since
+		 * we only get here if there is a handler, we dont restart.
+		 */
+		regs->result = -EINTR;
+		break;
+	case -ERESTARTSYS:
+		/* ERESTARTSYS means to restart the syscall if there is no
+		 * handler or the handler was registered with SA_RESTART
+		 */
+		if (!(ka->sa.sa_flags & SA_RESTART)) {
+			regs->result = -EINTR;
+			break;
+		}
+		/* fallthrough */
+	case -ERESTARTNOINTR:
+		/* ERESTARTNOINTR means that the syscall should be
+		 * called again after the signal handler returns.
+		 */
+		regs->gpr[3] = regs->orig_gpr3;
+		regs->nip -= 4;
+		regs->result = 0;
+		break;
+	}
+}
+
+/*
+ * Note that 'init' is a special process: it doesn't get signals it doesn't
+ * want to handle. Thus you cannot kill init even with a SIGKILL even by
+ * mistake.
+ */
+int do_signal(sigset_t *oldset, struct pt_regs *regs)
+{
+	siginfo_t info;
+	int signr;
+	struct k_sigaction ka;
+
+	/*
+	 * If the current thread is 32 bit - invoke the
+	 * 32 bit signal handling code
+	 */
+	if (test_thread_flag(TIF_32BIT))
+		return do_signal32(oldset, regs);
+
+	if (!oldset)
+		oldset = &current->blocked;
+
+	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
+	if (signr > 0) {
+		/* Whee!  Actually deliver the signal.  */
+		if (TRAP(regs) == 0x0C00)
+			syscall_restart(regs, &ka);
+
+		/*
+		 * Reenable the DABR before delivering the signal to
+		 * user space. The DABR will have been cleared if it
+		 * triggered inside the kernel.
+		 */
+		if (current->thread.dabr)
+			set_dabr(current->thread.dabr);
+
+		return handle_signal(signr, &ka, &info, oldset, regs);
+	}
+
+	if (TRAP(regs) == 0x0C00) {	/* System Call! */
+		if ((int)regs->result == -ERESTARTNOHAND ||
+		    (int)regs->result == -ERESTARTSYS ||
+		    (int)regs->result == -ERESTARTNOINTR) {
+			regs->gpr[3] = regs->orig_gpr3;
+			regs->nip -= 4; /* Back up & retry system call */
+			regs->result = 0;
+		} else if ((int)regs->result == -ERESTART_RESTARTBLOCK) {
+			regs->gpr[0] = __NR_restart_syscall;
+			regs->nip -= 4;
+			regs->result = 0;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(do_signal);
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index d8bdaaf74c9..80b58c1ec41 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -351,7 +351,7 @@ void __init pmac_setup_arch(void)
 	find_via_pmu();
 	smu_init();
 
-#ifdef CONFIG_NVRAM
+#if defined(CONFIG_NVRAM) || defined(CONFIG_PPC64)
 	pmac_nvram_init();
 #endif
 
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 2d57f588151..e3fc3407bb1 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -21,15 +21,6 @@ config EEH
 	depends on PPC_PSERIES
 	default y if !EMBEDDED
 
-config RTAS_PROC
-	bool "Proc interface to RTAS"
-	depends on PPC_RTAS
-	default y
-
-config RTAS_FLASH
-	tristate "Firmware flash interface"
-	depends on PPC64 && RTAS_PROC
-
 config SCANLOG
 	tristate "Scanlog dump interface"
 	depends on RTAS_PROC && PPC_PSERIES
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 91909a84473..b9938fece78 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -1,5 +1,5 @@
 obj-y			:= pci.o lpar.o hvCall.o nvram.o reconfig.o \
-			   setup.o iommu.o ras.o
+			   setup.o iommu.o ras.o rtasd.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_IBMVIO)	+= vio.o
 obj-$(CONFIG_XICS)	+= xics.o
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 9e58a192210..513e2723149 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -499,7 +499,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
 
 	switch (action) {
 	case PSERIES_RECONFIG_REMOVE:
-		if (pci->iommu_table &&
+		if (pci && pci->iommu_table &&
 		    get_property(np, "ibm,dma-window", NULL))
 			iommu_free_table(np);
 		break;
diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c
new file mode 100644
index 00000000000..e26b0420b6d
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/rtasd.c
@@ -0,0 +1,527 @@
+/*
+ * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * 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.
+ *
+ * Communication to userspace based on kernel/printk.c
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/vmalloc.h>
+#include <linux/spinlock.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/rtas.h>
+#include <asm/prom.h>
+#include <asm/nvram.h>
+#include <asm/atomic.h>
+#include <asm/systemcfg.h>
+
+#if 0
+#define DEBUG(A...)	printk(KERN_ERR A)
+#else
+#define DEBUG(A...)
+#endif
+
+static DEFINE_SPINLOCK(rtasd_log_lock);
+
+DECLARE_WAIT_QUEUE_HEAD(rtas_log_wait);
+
+static char *rtas_log_buf;
+static unsigned long rtas_log_start;
+static unsigned long rtas_log_size;
+
+static int surveillance_timeout = -1;
+static unsigned int rtas_event_scan_rate;
+static unsigned int rtas_error_log_max;
+static unsigned int rtas_error_log_buffer_max;
+
+static int full_rtas_msgs = 0;
+
+extern int no_logging;
+
+volatile int error_log_cnt = 0;
+
+/*
+ * Since we use 32 bit RTAS, the physical address of this must be below
+ * 4G or else bad things happen. Allocate this in the kernel data and
+ * make it big enough.
+ */
+static unsigned char logdata[RTAS_ERROR_LOG_MAX];
+
+static int get_eventscan_parms(void);
+
+static char *rtas_type[] = {
+	"Unknown", "Retry", "TCE Error", "Internal Device Failure",
+	"Timeout", "Data Parity", "Address Parity", "Cache Parity",
+	"Address Invalid", "ECC Uncorrected", "ECC Corrupted",
+};
+
+static char *rtas_event_type(int type)
+{
+	if ((type > 0) && (type < 11))
+		return rtas_type[type];
+
+	switch (type) {
+		case RTAS_TYPE_EPOW:
+			return "EPOW";
+		case RTAS_TYPE_PLATFORM:
+			return "Platform Error";
+		case RTAS_TYPE_IO:
+			return "I/O Event";
+		case RTAS_TYPE_INFO:
+			return "Platform Information Event";
+		case RTAS_TYPE_DEALLOC:
+			return "Resource Deallocation Event";
+		case RTAS_TYPE_DUMP:
+			return "Dump Notification Event";
+	}
+
+	return rtas_type[0];
+}
+
+/* To see this info, grep RTAS /var/log/messages and each entry
+ * will be collected together with obvious begin/end.
+ * There will be a unique identifier on the begin and end lines.
+ * This will persist across reboots.
+ *
+ * format of error logs returned from RTAS:
+ * bytes	(size)	: contents
+ * --------------------------------------------------------
+ * 0-7		(8)	: rtas_error_log
+ * 8-47		(40)	: extended info
+ * 48-51	(4)	: vendor id
+ * 52-1023 (vendor specific) : location code and debug data
+ */
+static void printk_log_rtas(char *buf, int len)
+{
+
+	int i,j,n = 0;
+	int perline = 16;
+	char buffer[64];
+	char * str = "RTAS event";
+
+	if (full_rtas_msgs) {
+		printk(RTAS_DEBUG "%d -------- %s begin --------\n",
+		       error_log_cnt, str);
+
+		/*
+		 * Print perline bytes on each line, each line will start
+		 * with RTAS and a changing number, so syslogd will
+		 * print lines that are otherwise the same.  Separate every
+		 * 4 bytes with a space.
+		 */
+		for (i = 0; i < len; i++) {
+			j = i % perline;
+			if (j == 0) {
+				memset(buffer, 0, sizeof(buffer));
+				n = sprintf(buffer, "RTAS %d:", i/perline);
+			}
+
+			if ((i % 4) == 0)
+				n += sprintf(buffer+n, " ");
+
+			n += sprintf(buffer+n, "%02x", (unsigned char)buf[i]);
+
+			if (j == (perline-1))
+				printk(KERN_DEBUG "%s\n", buffer);
+		}
+		if ((i % perline) != 0)
+			printk(KERN_DEBUG "%s\n", buffer);
+
+		printk(RTAS_DEBUG "%d -------- %s end ----------\n",
+		       error_log_cnt, str);
+	} else {
+		struct rtas_error_log *errlog = (struct rtas_error_log *)buf;
+
+		printk(RTAS_DEBUG "event: %d, Type: %s, Severity: %d\n",
+		       error_log_cnt, rtas_event_type(errlog->type),
+		       errlog->severity);
+	}
+}
+
+static int log_rtas_len(char * buf)
+{
+	int len;
+	struct rtas_error_log *err;
+
+	/* rtas fixed header */
+	len = 8;
+	err = (struct rtas_error_log *)buf;
+	if (err->extended_log_length) {
+
+		/* extended header */
+		len += err->extended_log_length;
+	}
+
+	if (rtas_error_log_max == 0) {
+		get_eventscan_parms();
+	}
+	if (len > rtas_error_log_max)
+		len = rtas_error_log_max;
+
+	return len;
+}
+
+/*
+ * First write to nvram, if fatal error, that is the only
+ * place we log the info.  The error will be picked up
+ * on the next reboot by rtasd.  If not fatal, run the
+ * method for the type of error.  Currently, only RTAS
+ * errors have methods implemented, but in the future
+ * there might be a need to store data in nvram before a
+ * call to panic().
+ *
+ * XXX We write to nvram periodically, to indicate error has
+ * been written and sync'd, but there is a possibility
+ * that if we don't shutdown correctly, a duplicate error
+ * record will be created on next reboot.
+ */
+void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
+{
+	unsigned long offset;
+	unsigned long s;
+	int len = 0;
+
+	DEBUG("logging event\n");
+	if (buf == NULL)
+		return;
+
+	spin_lock_irqsave(&rtasd_log_lock, s);
+
+	/* get length and increase count */
+	switch (err_type & ERR_TYPE_MASK) {
+	case ERR_TYPE_RTAS_LOG:
+		len = log_rtas_len(buf);
+		if (!(err_type & ERR_FLAG_BOOT))
+			error_log_cnt++;
+		break;
+	case ERR_TYPE_KERNEL_PANIC:
+	default:
+		spin_unlock_irqrestore(&rtasd_log_lock, s);
+		return;
+	}
+
+	/* Write error to NVRAM */
+	if (!no_logging && !(err_type & ERR_FLAG_BOOT))
+		nvram_write_error_log(buf, len, err_type);
+
+	/*
+	 * rtas errors can occur during boot, and we do want to capture
+	 * those somewhere, even if nvram isn't ready (why not?), and even
+	 * if rtasd isn't ready. Put them into the boot log, at least.
+	 */
+	if ((err_type & ERR_TYPE_MASK) == ERR_TYPE_RTAS_LOG)
+		printk_log_rtas(buf, len);
+
+	/* Check to see if we need to or have stopped logging */
+	if (fatal || no_logging) {
+		no_logging = 1;
+		spin_unlock_irqrestore(&rtasd_log_lock, s);
+		return;
+	}
+
+	/* call type specific method for error */
+	switch (err_type & ERR_TYPE_MASK) {
+	case ERR_TYPE_RTAS_LOG:
+		offset = rtas_error_log_buffer_max *
+			((rtas_log_start+rtas_log_size) & LOG_NUMBER_MASK);
+
+		/* First copy over sequence number */
+		memcpy(&rtas_log_buf[offset], (void *) &error_log_cnt, sizeof(int));
+
+		/* Second copy over error log data */
+		offset += sizeof(int);
+		memcpy(&rtas_log_buf[offset], buf, len);
+
+		if (rtas_log_size < LOG_NUMBER)
+			rtas_log_size += 1;
+		else
+			rtas_log_start += 1;
+
+		spin_unlock_irqrestore(&rtasd_log_lock, s);
+		wake_up_interruptible(&rtas_log_wait);
+		break;
+	case ERR_TYPE_KERNEL_PANIC:
+	default:
+		spin_unlock_irqrestore(&rtasd_log_lock, s);
+		return;
+	}
+
+}
+
+
+static int rtas_log_open(struct inode * inode, struct file * file)
+{
+	return 0;
+}
+
+static int rtas_log_release(struct inode * inode, struct file * file)
+{
+	return 0;
+}
+
+/* This will check if all events are logged, if they are then, we
+ * know that we can safely clear the events in NVRAM.
+ * Next we'll sit and wait for something else to log.
+ */
+static ssize_t rtas_log_read(struct file * file, char __user * buf,
+			 size_t count, loff_t *ppos)
+{
+	int error;
+	char *tmp;
+	unsigned long s;
+	unsigned long offset;
+
+	if (!buf || count < rtas_error_log_buffer_max)
+		return -EINVAL;
+
+	count = rtas_error_log_buffer_max;
+
+	if (!access_ok(VERIFY_WRITE, buf, count))
+		return -EFAULT;
+
+	tmp = kmalloc(count, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+
+	spin_lock_irqsave(&rtasd_log_lock, s);
+	/* if it's 0, then we know we got the last one (the one in NVRAM) */
+	if (rtas_log_size == 0 && !no_logging)
+		nvram_clear_error_log();
+	spin_unlock_irqrestore(&rtasd_log_lock, s);
+
+
+	error = wait_event_interruptible(rtas_log_wait, rtas_log_size);
+	if (error)
+		goto out;
+
+	spin_lock_irqsave(&rtasd_log_lock, s);
+	offset = rtas_error_log_buffer_max * (rtas_log_start & LOG_NUMBER_MASK);
+	memcpy(tmp, &rtas_log_buf[offset], count);
+
+	rtas_log_start += 1;
+	rtas_log_size -= 1;
+	spin_unlock_irqrestore(&rtasd_log_lock, s);
+
+	error = copy_to_user(buf, tmp, count) ? -EFAULT : count;
+out:
+	kfree(tmp);
+	return error;
+}
+
+static unsigned int rtas_log_poll(struct file *file, poll_table * wait)
+{
+	poll_wait(file, &rtas_log_wait, wait);
+	if (rtas_log_size)
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+
+struct file_operations proc_rtas_log_operations = {
+	.read =		rtas_log_read,
+	.poll =		rtas_log_poll,
+	.open =		rtas_log_open,
+	.release =	rtas_log_release,
+};
+
+static int enable_surveillance(int timeout)
+{
+	int error;
+
+	error = rtas_set_indicator(SURVEILLANCE_TOKEN, 0, timeout);
+
+	if (error == 0)
+		return 0;
+
+	if (error == -EINVAL) {
+		printk(KERN_INFO "rtasd: surveillance not supported\n");
+		return 0;
+	}
+
+	printk(KERN_ERR "rtasd: could not update surveillance\n");
+	return -1;
+}
+
+static int get_eventscan_parms(void)
+{
+	struct device_node *node;
+	int *ip;
+
+	node = of_find_node_by_path("/rtas");
+
+	ip = (int *)get_property(node, "rtas-event-scan-rate", NULL);
+	if (ip == NULL) {
+		printk(KERN_ERR "rtasd: no rtas-event-scan-rate\n");
+		of_node_put(node);
+		return -1;
+	}
+	rtas_event_scan_rate = *ip;
+	DEBUG("rtas-event-scan-rate %d\n", rtas_event_scan_rate);
+
+	/* Make room for the sequence number */
+	rtas_error_log_max = rtas_get_error_log_max();
+	rtas_error_log_buffer_max = rtas_error_log_max + sizeof(int);
+
+	of_node_put(node);
+
+	return 0;
+}
+
+static void do_event_scan(int event_scan)
+{
+	int error;
+	do {
+		memset(logdata, 0, rtas_error_log_max);
+		error = rtas_call(event_scan, 4, 1, NULL,
+				  RTAS_EVENT_SCAN_ALL_EVENTS, 0,
+				  __pa(logdata), rtas_error_log_max);
+		if (error == -1) {
+			printk(KERN_ERR "event-scan failed\n");
+			break;
+		}
+
+		if (error == 0)
+			pSeries_log_error(logdata, ERR_TYPE_RTAS_LOG, 0);
+
+	} while(error == 0);
+}
+
+static void do_event_scan_all_cpus(long delay)
+{
+	int cpu;
+
+	lock_cpu_hotplug();
+	cpu = first_cpu(cpu_online_map);
+	for (;;) {
+		set_cpus_allowed(current, cpumask_of_cpu(cpu));
+		do_event_scan(rtas_token("event-scan"));
+		set_cpus_allowed(current, CPU_MASK_ALL);
+
+		/* Drop hotplug lock, and sleep for the specified delay */
+		unlock_cpu_hotplug();
+		msleep_interruptible(delay);
+		lock_cpu_hotplug();
+
+		cpu = next_cpu(cpu, cpu_online_map);
+		if (cpu == NR_CPUS)
+			break;
+	}
+	unlock_cpu_hotplug();
+}
+
+static int rtasd(void *unused)
+{
+	unsigned int err_type;
+	int event_scan = rtas_token("event-scan");
+	int rc;
+
+	daemonize("rtasd");
+
+	if (event_scan == RTAS_UNKNOWN_SERVICE || get_eventscan_parms() == -1)
+		goto error;
+
+	rtas_log_buf = vmalloc(rtas_error_log_buffer_max*LOG_NUMBER);
+	if (!rtas_log_buf) {
+		printk(KERN_ERR "rtasd: no memory\n");
+		goto error;
+	}
+
+	printk(KERN_INFO "RTAS daemon started\n");
+
+	DEBUG("will sleep for %d milliseconds\n", (30000/rtas_event_scan_rate));
+
+	/* See if we have any error stored in NVRAM */
+	memset(logdata, 0, rtas_error_log_max);
+
+	rc = nvram_read_error_log(logdata, rtas_error_log_max, &err_type);
+
+	/* We can use rtas_log_buf now */
+	no_logging = 0;
+
+	if (!rc) {
+		if (err_type != ERR_FLAG_ALREADY_LOGGED) {
+			pSeries_log_error(logdata, err_type | ERR_FLAG_BOOT, 0);
+		}
+	}
+
+	/* First pass. */
+	do_event_scan_all_cpus(1000);
+
+	if (surveillance_timeout != -1) {
+		DEBUG("enabling surveillance\n");
+		enable_surveillance(surveillance_timeout);
+		DEBUG("surveillance enabled\n");
+	}
+
+	/* Delay should be at least one second since some
+	 * machines have problems if we call event-scan too
+	 * quickly. */
+	for (;;)
+		do_event_scan_all_cpus(30000/rtas_event_scan_rate);
+
+error:
+	/* Should delete proc entries */
+	return -EINVAL;
+}
+
+static int __init rtas_init(void)
+{
+	struct proc_dir_entry *entry;
+
+	/* No RTAS, only warn if we are on a pSeries box  */
+	if (rtas_token("event-scan") == RTAS_UNKNOWN_SERVICE) {
+		if (systemcfg->platform & PLATFORM_PSERIES)
+			printk(KERN_INFO "rtasd: no event-scan on system\n");
+		return 1;
+	}
+
+	entry = create_proc_entry("ppc64/rtas/error_log", S_IRUSR, NULL);
+	if (entry)
+		entry->proc_fops = &proc_rtas_log_operations;
+	else
+		printk(KERN_ERR "Failed to create error_log proc entry\n");
+
+	if (kernel_thread(rtasd, NULL, CLONE_FS) < 0)
+		printk(KERN_ERR "Failed to start RTAS daemon\n");
+
+	return 0;
+}
+
+static int __init surveillance_setup(char *str)
+{
+	int i;
+
+	if (get_option(&str,&i)) {
+		if (i >= 0 && i <= 255)
+			surveillance_timeout = i;
+	}
+
+	return 1;
+}
+
+static int __init rtasmsgs_setup(char *str)
+{
+	if (strcmp(str, "on") == 0)
+		full_rtas_msgs = 1;
+	else if (strcmp(str, "off") == 0)
+		full_rtas_msgs = 0;
+
+	return 1;
+}
+__initcall(rtas_init);
+__setup("surveillance=", surveillance_setup);
+__setup("rtasmsgs=", rtasmsgs_setup);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index d54e1e4c7c6..65bee939eec 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -602,9 +602,9 @@ struct machdep_calls __initdata pSeries_md = {
 	.pcibios_fixup		= pSeries_final_fixup,
 	.pci_probe_mode		= pSeries_pci_probe_mode,
 	.irq_bus_setup		= pSeries_irq_bus_setup,
-	.restart		= rtas_fw_restart,
-	.power_off		= rtas_fw_power_off,
-	.halt			= rtas_fw_halt,
+	.restart		= rtas_restart,
+	.power_off		= rtas_power_off,
+	.halt			= rtas_halt,
 	.panic			= rtas_os_term,
 	.cpu_die		= pSeries_mach_cpu_die,
 	.get_boot_time		= rtas_get_boot_time,