Merge commit 'linus/master' into HEAD

Conflicts:
	MAINTAINERS

Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>

20 files changed, 953 insertions, 834 deletions

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 10457854123..065205bdd92 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -45,7 +45,7 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
 static void __init init_irq_default_affinity(void)
 {
-	alloc_bootmem_cpumask_var(&irq_default_affinity);
+	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
 	cpumask_setall(irq_default_affinity);
 }
 #else
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 374faf9bfdc..3a29dbe7898 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -30,12 +30,16 @@
 #define all_var 0
 #endif
 
-/* These will be re-linked against their real values during the second link stage */
+/*
+ * These will be re-linked against their real values
+ * during the second link stage.
+ */
 extern const unsigned long kallsyms_addresses[] __attribute__((weak));
 extern const u8 kallsyms_names[] __attribute__((weak));
 
-/* tell the compiler that the count isn't in the small data section if the arch
- * has one (eg: FRV)
+/*
+ * Tell the compiler that the count isn't in the small data section if the arch
+ * has one (eg: FRV).
  */
 extern const unsigned long kallsyms_num_syms
 __attribute__((weak, section(".rodata")));
@@ -75,31 +79,37 @@ static int is_ksym_addr(unsigned long addr)
 	return is_kernel_text(addr) || is_kernel_inittext(addr);
 }
 
-/* expand a compressed symbol data into the resulting uncompressed string,
-   given the offset to where the symbol is in the compressed stream */
+/*
+ * Expand a compressed symbol data into the resulting uncompressed string,
+ * given the offset to where the symbol is in the compressed stream.
+ */
 static unsigned int kallsyms_expand_symbol(unsigned int off, char *result)
 {
 	int len, skipped_first = 0;
 	const u8 *tptr, *data;
 
-	/* get the compressed symbol length from the first symbol byte */
+	/* Get the compressed symbol length from the first symbol byte. */
 	data = &kallsyms_names[off];
 	len = *data;
 	data++;
 
-	/* update the offset to return the offset for the next symbol on
-	 * the compressed stream */
+	/*
+	 * Update the offset to return the offset for the next symbol on
+	 * the compressed stream.
+	 */
 	off += len + 1;
 
-	/* for every byte on the compressed symbol data, copy the table
-	   entry for that byte */
-	while(len) {
-		tptr = &kallsyms_token_table[ kallsyms_token_index[*data] ];
+	/*
+	 * For every byte on the compressed symbol data, copy the table
+	 * entry for that byte.
+	 */
+	while (len) {
+		tptr = &kallsyms_token_table[kallsyms_token_index[*data]];
 		data++;
 		len--;
 
 		while (*tptr) {
-			if(skipped_first) {
+			if (skipped_first) {
 				*result = *tptr;
 				result++;
 			} else
@@ -110,36 +120,46 @@ static unsigned int kallsyms_expand_symbol(unsigned int off, char *result)
 
 	*result = '\0';
 
-	/* return to offset to the next symbol */
+	/* Return to offset to the next symbol. */
 	return off;
 }
 
-/* get symbol type information. This is encoded as a single char at the
- * begining of the symbol name */
+/*
+ * Get symbol type information. This is encoded as a single char at the
+ * beginning of the symbol name.
+ */
 static char kallsyms_get_symbol_type(unsigned int off)
 {
-	/* get just the first code, look it up in the token table, and return the
-	 * first char from this token */
-	return kallsyms_token_table[ kallsyms_token_index[ kallsyms_names[off+1] ] ];
+	/*
+	 * Get just the first code, look it up in the token table,
+	 * and return the first char from this token.
+	 */
+	return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]];
 }
 
 
-/* find the offset on the compressed stream given and index in the
- * kallsyms array */
+/*
+ * Find the offset on the compressed stream given and index in the
+ * kallsyms array.
+ */
 static unsigned int get_symbol_offset(unsigned long pos)
 {
 	const u8 *name;
 	int i;
 
-	/* use the closest marker we have. We have markers every 256 positions,
-	 * so that should be close enough */
-	name = &kallsyms_names[ kallsyms_markers[pos>>8] ];
+	/*
+	 * Use the closest marker we have. We have markers every 256 positions,
+	 * so that should be close enough.
+	 */
+	name = &kallsyms_names[kallsyms_markers[pos >> 8]];
 
-	/* sequentially scan all the symbols up to the point we're searching for.
-	 * Every symbol is stored in a [<len>][<len> bytes of data] format, so we
-	 * just need to add the len to the current pointer for every symbol we
-	 * wish to skip */
-	for(i = 0; i < (pos&0xFF); i++)
+	/*
+	 * Sequentially scan all the symbols up to the point we're searching
+	 * for. Every symbol is stored in a [<len>][<len> bytes of data] format,
+	 * so we just need to add the len to the current pointer for every
+	 * symbol we wish to skip.
+	 */
+	for (i = 0; i < (pos & 0xFF); i++)
 		name = name + (*name) + 1;
 
 	return name - kallsyms_names;
@@ -190,7 +210,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
 	/* This kernel should never had been booted. */
 	BUG_ON(!kallsyms_addresses);
 
-	/* do a binary search on the sorted kallsyms_addresses array */
+	/* Do a binary search on the sorted kallsyms_addresses array. */
 	low = 0;
 	high = kallsyms_num_syms;
 
@@ -203,15 +223,15 @@ static unsigned long get_symbol_pos(unsigned long addr,
 	}
 
 	/*
-	 * search for the first aliased symbol. Aliased
-	 * symbols are symbols with the same address
+	 * Search for the first aliased symbol. Aliased
+	 * symbols are symbols with the same address.
 	 */
 	while (low && kallsyms_addresses[low-1] == kallsyms_addresses[low])
 		--low;
 
 	symbol_start = kallsyms_addresses[low];
 
-	/* Search for next non-aliased symbol */
+	/* Search for next non-aliased symbol. */
 	for (i = low + 1; i < kallsyms_num_syms; i++) {
 		if (kallsyms_addresses[i] > symbol_start) {
 			symbol_end = kallsyms_addresses[i];
@@ -219,7 +239,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
 		}
 	}
 
-	/* if we found no next symbol, we use the end of the section */
+	/* If we found no next symbol, we use the end of the section. */
 	if (!symbol_end) {
 		if (is_kernel_inittext(addr))
 			symbol_end = (unsigned long)_einittext;
@@ -252,10 +272,10 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
 
 /*
  * Lookup an address
- * - modname is set to NULL if it's in the kernel
- * - we guarantee that the returned name is valid until we reschedule even if
- *   it resides in a module
- * - we also guarantee that modname will be valid until rescheduled
+ * - modname is set to NULL if it's in the kernel.
+ * - We guarantee that the returned name is valid until we reschedule even if.
+ *   It resides in a module.
+ * - We also guarantee that modname will be valid until rescheduled.
  */
 const char *kallsyms_lookup(unsigned long addr,
 			    unsigned long *symbolsize,
@@ -276,7 +296,7 @@ const char *kallsyms_lookup(unsigned long addr,
 		return namebuf;
 	}
 
-	/* see if it's in a module */
+	/* See if it's in a module. */
 	return module_address_lookup(addr, symbolsize, offset, modname,
 				     namebuf);
 }
@@ -294,7 +314,7 @@ int lookup_symbol_name(unsigned long addr, char *symname)
 		kallsyms_expand_symbol(get_symbol_offset(pos), symname);
 		return 0;
 	}
-	/* see if it's in a module */
+	/* See if it's in a module. */
 	return lookup_module_symbol_name(addr, symname);
 }
 
@@ -313,7 +333,7 @@ int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
 		modname[0] = '\0';
 		return 0;
 	}
-	/* see if it's in a module */
+	/* See if it's in a module. */
 	return lookup_module_symbol_attrs(addr, size, offset, modname, name);
 }
 
@@ -342,6 +362,7 @@ int sprint_symbol(char *buffer, unsigned long address)
 
 	return len;
 }
+EXPORT_SYMBOL_GPL(sprint_symbol);
 
 /* Look up a kernel symbol and print it to the kernel messages. */
 void __print_symbol(const char *fmt, unsigned long address)
@@ -352,13 +373,13 @@ void __print_symbol(const char *fmt, unsigned long address)
 
 	printk(fmt, buffer);
 }
+EXPORT_SYMBOL(__print_symbol);
 
 /* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
-struct kallsym_iter
-{
+struct kallsym_iter {
 	loff_t pos;
 	unsigned long value;
-	unsigned int nameoff; /* If iterating in core kernel symbols */
+	unsigned int nameoff; /* If iterating in core kernel symbols. */
 	char type;
 	char name[KSYM_NAME_LEN];
 	char module_name[MODULE_NAME_LEN];
@@ -404,7 +425,7 @@ static int update_iter(struct kallsym_iter *iter, loff_t pos)
 		iter->pos = pos;
 		return get_ksymbol_mod(iter);
 	}
-	
+
 	/* If we're not on the desired position, reset to new position. */
 	if (pos != iter->pos)
 		reset_iter(iter, pos);
@@ -439,23 +460,25 @@ static int s_show(struct seq_file *m, void *p)
 {
 	struct kallsym_iter *iter = m->private;
 
-	/* Some debugging symbols have no name.  Ignore them. */ 
+	/* Some debugging symbols have no name.  Ignore them. */
 	if (!iter->name[0])
 		return 0;
 
 	if (iter->module_name[0]) {
 		char type;
 
-		/* Label it "global" if it is exported,
-		 * "local" if not exported. */
+		/*
+		 * Label it "global" if it is exported,
+		 * "local" if not exported.
+		 */
 		type = iter->exported ? toupper(iter->type) :
 					tolower(iter->type);
 		seq_printf(m, "%0*lx %c %s\t[%s]\n",
-			   (int)(2*sizeof(void*)),
+			   (int)(2 * sizeof(void *)),
 			   iter->value, type, iter->name, iter->module_name);
 	} else
 		seq_printf(m, "%0*lx %c %s\n",
-			   (int)(2*sizeof(void*)),
+			   (int)(2 * sizeof(void *)),
 			   iter->value, iter->type, iter->name);
 	return 0;
 }
@@ -469,9 +492,11 @@ static const struct seq_operations kallsyms_op = {
 
 static int kallsyms_open(struct inode *inode, struct file *file)
 {
-	/* We keep iterator in m->private, since normal case is to
+	/*
+	 * We keep iterator in m->private, since normal case is to
 	 * s_start from where we left off, so we avoid doing
-	 * using get_symbol_offset for every symbol */
+	 * using get_symbol_offset for every symbol.
+	 */
 	struct kallsym_iter *iter;
 	int ret;
 
@@ -500,7 +525,4 @@ static int __init kallsyms_init(void)
 	proc_create("kallsyms", 0444, NULL, &kallsyms_operations);
 	return 0;
 }
-__initcall(kallsyms_init);
-
-EXPORT_SYMBOL(__print_symbol);
-EXPORT_SYMBOL_GPL(sprint_symbol);
+device_initcall(kallsyms_init);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index e4983770913..ae1c35201cc 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1448,17 +1448,17 @@ int kernel_kexec(void)
 			goto Restore_console;
 		}
 		suspend_console();
-		error = device_suspend(PMSG_FREEZE);
+		error = dpm_suspend_start(PMSG_FREEZE);
 		if (error)
 			goto Resume_console;
-		/* At this point, device_suspend() has been called,
-		 * but *not* device_power_down(). We *must*
-		 * device_power_down() now.  Otherwise, drivers for
+		/* At this point, dpm_suspend_start() has been called,
+		 * but *not* dpm_suspend_noirq(). We *must* call
+		 * dpm_suspend_noirq() now.  Otherwise, drivers for
 		 * some devices (e.g. interrupt controllers) become
 		 * desynchronized with the actual state of the
 		 * hardware at resume time, and evil weirdness ensues.
 		 */
-		error = device_power_down(PMSG_FREEZE);
+		error = dpm_suspend_noirq(PMSG_FREEZE);
 		if (error)
 			goto Resume_devices;
 		error = disable_nonboot_cpus();
@@ -1486,9 +1486,9 @@ int kernel_kexec(void)
 		local_irq_enable();
  Enable_cpus:
 		enable_nonboot_cpus();
-		device_power_up(PMSG_RESTORE);
+		dpm_resume_noirq(PMSG_RESTORE);
  Resume_devices:
-		device_resume(PMSG_RESTORE);
+		dpm_resume_end(PMSG_RESTORE);
  Resume_console:
 		resume_console();
 		thaw_processes();
diff --git a/kernel/module.c b/kernel/module.c
index 35f7de00bf0..e4ab36ce767 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2455,6 +2455,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 	mutex_lock(&module_mutex);
 	/* Drop initial reference. */
 	module_put(mod);
+	trim_init_extable(mod);
 	module_free(mod, mod->module_init);
 	mod->module_init = NULL;
 	mod->init_size = 0;
diff --git a/kernel/params.c b/kernel/params.c
index de273ec85bd..7f6912ced2b 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -24,9 +24,6 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
-/* We abuse the high bits of "perm" to record whether we kmalloc'ed. */
-#define KPARAM_KMALLOCED	0x80000000
-
 #if 0
 #define DEBUGP printk
 #else
@@ -220,13 +217,13 @@ int param_set_charp(const char *val, struct kernel_param *kp)
 		return -ENOSPC;
 	}
 
-	if (kp->perm & KPARAM_KMALLOCED)
+	if (kp->flags & KPARAM_KMALLOCED)
 		kfree(*(char **)kp->arg);
 
 	/* This is a hack.  We can't need to strdup in early boot, and we
 	 * don't need to; this mangled commandline is preserved. */
 	if (slab_is_available()) {
-		kp->perm |= KPARAM_KMALLOCED;
+		kp->flags |= KPARAM_KMALLOCED;
 		*(char **)kp->arg = kstrdup(val, GFP_KERNEL);
 		if (!kp->arg)
 			return -ENOMEM;
@@ -241,44 +238,63 @@ int param_get_charp(char *buffer, struct kernel_param *kp)
 	return sprintf(buffer, "%s", *((char **)kp->arg));
 }
 
+/* Actually could be a bool or an int, for historical reasons. */
 int param_set_bool(const char *val, struct kernel_param *kp)
 {
+	bool v;
+
 	/* No equals means "set"... */
 	if (!val) val = "1";
 
 	/* One of =[yYnN01] */
 	switch (val[0]) {
 	case 'y': case 'Y': case '1':
-		*(int *)kp->arg = 1;
-		return 0;
+		v = true;
+		break;
 	case 'n': case 'N': case '0':
-		*(int *)kp->arg = 0;
-		return 0;
+		v = false;
+		break;
+	default:
+		return -EINVAL;
 	}
-	return -EINVAL;
+
+	if (kp->flags & KPARAM_ISBOOL)
+		*(bool *)kp->arg = v;
+	else
+		*(int *)kp->arg = v;
+	return 0;
 }
 
 int param_get_bool(char *buffer, struct kernel_param *kp)
 {
+	bool val;
+	if (kp->flags & KPARAM_ISBOOL)
+		val = *(bool *)kp->arg;
+	else
+		val = *(int *)kp->arg;
+
 	/* Y and N chosen as being relatively non-coder friendly */
-	return sprintf(buffer, "%c", (*(int *)kp->arg) ? 'Y' : 'N');
+	return sprintf(buffer, "%c", val ? 'Y' : 'N');
 }
 
+/* This one must be bool. */
 int param_set_invbool(const char *val, struct kernel_param *kp)
 {
-	int boolval, ret;
+	int ret;
+	bool boolval;
 	struct kernel_param dummy;
 
 	dummy.arg = &boolval;
+	dummy.flags = KPARAM_ISBOOL;
 	ret = param_set_bool(val, &dummy);
 	if (ret == 0)
-		*(int *)kp->arg = !boolval;
+		*(bool *)kp->arg = !boolval;
 	return ret;
 }
 
 int param_get_invbool(char *buffer, struct kernel_param *kp)
 {
-	return sprintf(buffer, "%c", (*(int *)kp->arg) ? 'N' : 'Y');
+	return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y');
 }
 
 /* We break the rule and mangle the string. */
@@ -591,7 +607,7 @@ void destroy_params(const struct kernel_param *params, unsigned num)
 	unsigned int i;
 
 	for (i = 0; i < num; i++)
-		if (params[i].perm & KPARAM_KMALLOCED)
+		if (params[i].flags & KPARAM_KMALLOCED)
 			kfree(*(char **)params[i].arg);
 }
 
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index ef5d8a5b245..29b685f551a 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -3570,12 +3570,8 @@ perf_counter_alloc(struct perf_counter_attr *attr,
 	if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP))
 		goto done;
 
-	if (attr->type == PERF_TYPE_RAW) {
-		pmu = hw_perf_counter_init(counter);
-		goto done;
-	}
-
 	switch (attr->type) {
+	case PERF_TYPE_RAW:
 	case PERF_TYPE_HARDWARE:
 	case PERF_TYPE_HW_CACHE:
 		pmu = hw_perf_counter_init(counter);
@@ -3588,6 +3584,9 @@ perf_counter_alloc(struct perf_counter_attr *attr,
 	case PERF_TYPE_TRACEPOINT:
 		pmu = tp_perf_counter_init(counter);
 		break;
+
+	default:
+		break;
 	}
 done:
 	err = 0;
@@ -3614,6 +3613,85 @@ done:
 	return counter;
 }
 
+static int perf_copy_attr(struct perf_counter_attr __user *uattr,
+			  struct perf_counter_attr *attr)
+{
+	int ret;
+	u32 size;
+
+	if (!access_ok(VERIFY_WRITE, uattr, PERF_ATTR_SIZE_VER0))
+		return -EFAULT;
+
+	/*
+	 * zero the full structure, so that a short copy will be nice.
+	 */
+	memset(attr, 0, sizeof(*attr));
+
+	ret = get_user(size, &uattr->size);
+	if (ret)
+		return ret;
+
+	if (size > PAGE_SIZE)	/* silly large */
+		goto err_size;
+
+	if (!size)		/* abi compat */
+		size = PERF_ATTR_SIZE_VER0;
+
+	if (size < PERF_ATTR_SIZE_VER0)
+		goto err_size;
+
+	/*
+	 * If we're handed a bigger struct than we know of,
+	 * ensure all the unknown bits are 0.
+	 */
+	if (size > sizeof(*attr)) {
+		unsigned long val;
+		unsigned long __user *addr;
+		unsigned long __user *end;
+
+		addr = PTR_ALIGN((void __user *)uattr + sizeof(*attr),
+				sizeof(unsigned long));
+		end  = PTR_ALIGN((void __user *)uattr + size,
+				sizeof(unsigned long));
+
+		for (; addr < end; addr += sizeof(unsigned long)) {
+			ret = get_user(val, addr);
+			if (ret)
+				return ret;
+			if (val)
+				goto err_size;
+		}
+	}
+
+	ret = copy_from_user(attr, uattr, size);
+	if (ret)
+		return -EFAULT;
+
+	/*
+	 * If the type exists, the corresponding creation will verify
+	 * the attr->config.
+	 */
+	if (attr->type >= PERF_TYPE_MAX)
+		return -EINVAL;
+
+	if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3)
+		return -EINVAL;
+
+	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
+		return -EINVAL;
+
+	if (attr->read_format & ~(PERF_FORMAT_MAX-1))
+		return -EINVAL;
+
+out:
+	return ret;
+
+err_size:
+	put_user(sizeof(*attr), &uattr->size);
+	ret = -E2BIG;
+	goto out;
+}
+
 /**
  * sys_perf_counter_open - open a performance counter, associate it to a task/cpu
  *
@@ -3623,7 +3701,7 @@ done:
  * @group_fd:		group leader counter fd
  */
 SYSCALL_DEFINE5(perf_counter_open,
-		const struct perf_counter_attr __user *, attr_uptr,
+		struct perf_counter_attr __user *, attr_uptr,
 		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
 {
 	struct perf_counter *counter, *group_leader;
@@ -3639,8 +3717,9 @@ SYSCALL_DEFINE5(perf_counter_open,
 	if (flags)
 		return -EINVAL;
 
-	if (copy_from_user(&attr, attr_uptr, sizeof(attr)) != 0)
-		return -EFAULT;
+	ret = perf_copy_attr(attr_uptr, &attr);
+	if (ret)
+		return ret;
 
 	if (!attr.exclude_kernel) {
 		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 23bd4daeb96..72067cbdb37 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -116,9 +116,13 @@ config SUSPEND_FREEZER
 
 	  Turning OFF this setting is NOT recommended! If in doubt, say Y.
 
+config HIBERNATION_NVS
+	bool
+
 config HIBERNATION
 	bool "Hibernation (aka 'suspend to disk')"
 	depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE
+	select HIBERNATION_NVS if HAS_IOMEM
 	---help---
 	  Enable the suspend to disk (STD) functionality, which is usually
 	  called "hibernation" in user interfaces.  STD checkpoints the
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 720ea4f781b..c3b81c30e5d 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -6,6 +6,9 @@ endif
 obj-$(CONFIG_PM)		+= main.o
 obj-$(CONFIG_PM_SLEEP)		+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
-obj-$(CONFIG_HIBERNATION)	+= swsusp.o disk.o snapshot.o swap.o user.o
+obj-$(CONFIG_SUSPEND)		+= suspend.o
+obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
+obj-$(CONFIG_HIBERNATION)	+= swsusp.o hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_HIBERNATION_NVS)	+= hibernate_nvs.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff --git a/kernel/power/disk.c b/kernel/power/hibernate.c
index 5cb080e7eeb..81d2e746489 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/hibernate.c
@@ -1,12 +1,12 @@
 /*
- * kernel/power/disk.c - Suspend-to-disk support.
+ * kernel/power/hibernate.c - Hibernation (a.k.a suspend-to-disk) support.
  *
  * Copyright (c) 2003 Patrick Mochel
  * Copyright (c) 2003 Open Source Development Lab
  * Copyright (c) 2004 Pavel Machek <pavel@suse.cz>
+ * Copyright (c) 2009 Rafael J. Wysocki, Novell Inc.
  *
  * This file is released under the GPLv2.
- *
  */
 
 #include <linux/suspend.h>
@@ -215,13 +215,13 @@ static int create_image(int platform_mode)
 	if (error)
 		return error;
 
-	/* At this point, device_suspend() has been called, but *not*
-	 * device_power_down(). We *must* call device_power_down() now.
+	/* At this point, dpm_suspend_start() has been called, but *not*
+	 * dpm_suspend_noirq(). We *must* call dpm_suspend_noirq() now.
 	 * Otherwise, drivers for some devices (e.g. interrupt controllers)
 	 * become desynchronized with the actual state of the hardware
 	 * at resume time, and evil weirdness ensues.
 	 */
-	error = device_power_down(PMSG_FREEZE);
+	error = dpm_suspend_noirq(PMSG_FREEZE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting hibernation\n");
@@ -262,7 +262,7 @@ static int create_image(int platform_mode)
 
  Power_up:
 	sysdev_resume();
-	/* NOTE:  device_power_up() is just a resume() for devices
+	/* NOTE:  dpm_resume_noirq() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
 
@@ -275,7 +275,7 @@ static int create_image(int platform_mode)
  Platform_finish:
 	platform_finish(platform_mode);
 
-	device_power_up(in_suspend ?
+	dpm_resume_noirq(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
 
 	return error;
@@ -304,7 +304,7 @@ int hibernation_snapshot(int platform_mode)
 		goto Close;
 
 	suspend_console();
-	error = device_suspend(PMSG_FREEZE);
+	error = dpm_suspend_start(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
 
@@ -315,7 +315,7 @@ int hibernation_snapshot(int platform_mode)
 	/* Control returns here after successful restore */
 
  Resume_devices:
-	device_resume(in_suspend ?
+	dpm_resume_end(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
 	resume_console();
  Close:
@@ -339,7 +339,7 @@ static int resume_target_kernel(bool platform_mode)
 {
 	int error;
 
-	error = device_power_down(PMSG_QUIESCE);
+	error = dpm_suspend_noirq(PMSG_QUIESCE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting resume\n");
@@ -394,7 +394,7 @@ static int resume_target_kernel(bool platform_mode)
  Cleanup:
 	platform_restore_cleanup(platform_mode);
 
-	device_power_up(PMSG_RECOVER);
+	dpm_resume_noirq(PMSG_RECOVER);
 
 	return error;
 }
@@ -414,10 +414,10 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	suspend_console();
-	error = device_suspend(PMSG_QUIESCE);
+	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
-		device_resume(PMSG_RECOVER);
+		dpm_resume_end(PMSG_RECOVER);
 	}
 	resume_console();
 	pm_restore_console();
@@ -447,14 +447,14 @@ int hibernation_platform_enter(void)
 
 	entering_platform_hibernation = true;
 	suspend_console();
-	error = device_suspend(PMSG_HIBERNATE);
+	error = dpm_suspend_start(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
 			hibernation_ops->recover();
 		goto Resume_devices;
 	}
 
-	error = device_power_down(PMSG_HIBERNATE);
+	error = dpm_suspend_noirq(PMSG_HIBERNATE);
 	if (error)
 		goto Resume_devices;
 
@@ -479,11 +479,11 @@ int hibernation_platform_enter(void)
  Platofrm_finish:
 	hibernation_ops->finish();
 
-	device_power_up(PMSG_RESTORE);
+	dpm_suspend_noirq(PMSG_RESTORE);
 
  Resume_devices:
 	entering_platform_hibernation = false;
-	device_resume(PMSG_RESTORE);
+	dpm_resume_end(PMSG_RESTORE);
 	resume_console();
 
  Close:
diff --git a/kernel/power/hibernate_nvs.c b/kernel/power/hibernate_nvs.c
new file mode 100644
index 00000000000..39ac698ef83
--- /dev/null
+++ b/kernel/power/hibernate_nvs.c
@@ -0,0 +1,135 @@
+/*
+ * linux/kernel/power/hibernate_nvs.c - Routines for handling NVS memory
+ *
+ * Copyright (C) 2008,2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/suspend.h>
+
+/*
+ * Platforms, like ACPI, may want us to save some memory used by them during
+ * hibernation and to restore the contents of this memory during the subsequent
+ * resume.  The code below implements a mechanism allowing us to do that.
+ */
+
+struct nvs_page {
+	unsigned long phys_start;
+	unsigned int size;
+	void *kaddr;
+	void *data;
+	struct list_head node;
+};
+
+static LIST_HEAD(nvs_list);
+
+/**
+ *	hibernate_nvs_register - register platform NVS memory region to save
+ *	@start - physical address of the region
+ *	@size - size of the region
+ *
+ *	The NVS region need not be page-aligned (both ends) and we arrange
+ *	things so that the data from page-aligned addresses in this region will
+ *	be copied into separate RAM pages.
+ */
+int hibernate_nvs_register(unsigned long start, unsigned long size)
+{
+	struct nvs_page *entry, *next;
+
+	while (size > 0) {
+		unsigned int nr_bytes;
+
+		entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
+		if (!entry)
+			goto Error;
+
+		list_add_tail(&entry->node, &nvs_list);
+		entry->phys_start = start;
+		nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
+		entry->size = (size < nr_bytes) ? size : nr_bytes;
+
+		start += entry->size;
+		size -= entry->size;
+	}
+	return 0;
+
+ Error:
+	list_for_each_entry_safe(entry, next, &nvs_list, node) {
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	return -ENOMEM;
+}
+
+/**
+ *	hibernate_nvs_free - free data pages allocated for saving NVS regions
+ */
+void hibernate_nvs_free(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			free_page((unsigned long)entry->data);
+			entry->data = NULL;
+			if (entry->kaddr) {
+				iounmap(entry->kaddr);
+				entry->kaddr = NULL;
+			}
+		}
+}
+
+/**
+ *	hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
+ */
+int hibernate_nvs_alloc(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node) {
+		entry->data = (void *)__get_free_page(GFP_KERNEL);
+		if (!entry->data) {
+			hibernate_nvs_free();
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+/**
+ *	hibernate_nvs_save - save NVS memory regions
+ */
+void hibernate_nvs_save(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Saving platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			entry->kaddr = ioremap(entry->phys_start, entry->size);
+			memcpy(entry->data, entry->kaddr, entry->size);
+		}
+}
+
+/**
+ *	hibernate_nvs_restore - restore NVS memory regions
+ *
+ *	This function is going to be called with interrupts disabled, so it
+ *	cannot iounmap the virtual addresses used to access the NVS region.
+ */
+void hibernate_nvs_restore(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Restoring platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data)
+			memcpy(entry->kaddr, entry->data, entry->size);
+}
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 868028280d1..f710e36930c 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -8,20 +8,9 @@
  *
  */
 
-#include <linux/module.h>
-#include <linux/suspend.h>
 #include <linux/kobject.h>
 #include <linux/string.h>
-#include <linux/delay.h>
-#include <linux/errno.h>
-#include <linux/kmod.h>
-#include <linux/init.h>
-#include <linux/console.h>
-#include <linux/cpu.h>
 #include <linux/resume-trace.h>
-#include <linux/freezer.h>
-#include <linux/vmstat.h>
-#include <linux/syscalls.h>
 
 #include "power.h"
 
@@ -119,373 +108,6 @@ power_attr(pm_test);
 
 #endif /* CONFIG_PM_SLEEP */
 
-#ifdef CONFIG_SUSPEND
-
-static int suspend_test(int level)
-{
-#ifdef CONFIG_PM_DEBUG
-	if (pm_test_level == level) {
-		printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
-		mdelay(5000);
-		return 1;
-	}
-#endif /* !CONFIG_PM_DEBUG */
-	return 0;