26 files changed, 236 insertions, 125 deletions
diff --git a/kernel/capability.c b/kernel/capability.c
index bf0c734d0c12..32a80e08ff4b 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -399,3 +399,15 @@ bool task_ns_capable(struct task_struct *t, int cap)
 	return ns_capable(task_cred_xxx(t, user)->user_ns, cap);
 }
 EXPORT_SYMBOL(task_ns_capable);
+
+/**
+ * nsown_capable - Check superior capability to one's own user_ns
+ * @cap: The capability in question
+ *
+ * Return true if the current task has the given superior capability
+ * targeted at its own user namespace.
+ */
+bool nsown_capable(int cap)
+{
+	return ns_capable(current_user_ns(), cap);
+}
diff --git a/kernel/cred.c b/kernel/cred.c
index 5557b55048df..8093c16b84b1 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -54,6 +54,7 @@ struct cred init_cred = {
 	.cap_effective		= CAP_INIT_EFF_SET,
 	.cap_bset		= CAP_INIT_BSET,
 	.user			= INIT_USER,
+	.user_ns		= &init_user_ns,
 	.group_info		= &init_groups,
 #ifdef CONFIG_KEYS
 	.tgcred			= &init_tgcred,
@@ -410,6 +411,11 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 			goto error_put;
 	}
 
+	/* cache user_ns in cred.  Doesn't need a refcount because it will
+	 * stay pinned by cred->user
+	 */
+	new->user_ns = new->user->user_ns;
+
 #ifdef CONFIG_KEYS
 	/* new threads get their own thread keyrings if their parent already
 	 * had one */
@@ -741,12 +747,6 @@ int set_create_files_as(struct cred *new, struct inode *inode)
 }
 EXPORT_SYMBOL(set_create_files_as);
 
-struct user_namespace *current_user_ns(void)
-{
-	return _current_user_ns();
-}
-EXPORT_SYMBOL(current_user_ns);
-
 #ifdef CONFIG_DEBUG_CREDENTIALS
 
 bool creds_are_invalid(const struct cred *cred)
diff --git a/kernel/exit.c b/kernel/exit.c
index f5d2f63bae0b..8dd874181542 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1016,7 +1016,7 @@ NORET_TYPE void do_exit(long code)
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
-	flush_ptrace_hw_breakpoint(tsk);
+	ptrace_put_breakpoints(tsk);
 
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 66ecd2ead215..7b01de98bb6a 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -17,7 +17,7 @@ static inline void frozen_process(void)
 {
 	if (!unlikely(current->flags & PF_NOFREEZE)) {
 		current->flags |= PF_FROZEN;
-		wmb();
+		smp_wmb();
 	}
 	clear_freeze_flag(current);
 }
@@ -93,7 +93,7 @@ bool freeze_task(struct task_struct *p, bool sig_only)
 	 * the task as frozen and next clears its TIF_FREEZE.
 	 */
 	if (!freezing(p)) {
-		rmb();
+		smp_rmb();
 		if (frozen(p))
 			return false;
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 9017478c5d4c..87fdb3f8db14 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -81,7 +81,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 	}
 };
 
-static int hrtimer_clock_to_base_table[MAX_CLOCKS];
+static int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
+	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
+	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
+};
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 {
@@ -1722,10 +1726,6 @@ static struct notifier_block __cpuinitdata hrtimers_nb = {
 
 void __init hrtimers_init(void)
 {
-	hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
-	hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
-	hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME;
-
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index dd201bd35103..834899f2500f 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -419,7 +419,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	} else {
 		seq_printf(p, " %8s", "None");
 	}
-#ifdef CONFIG_GENIRC_IRQ_SHOW_LEVEL
+#ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL
 	seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge");
 #endif
 	if (desc->name)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 55936f9cb251..8d814cbc8109 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -33,6 +33,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap.h>
 #include <linux/kmsg_dump.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -1530,8 +1531,7 @@ int kernel_kexec(void)
 		if (error)
 			goto Enable_cpus;
 		local_irq_disable();
-		/* Suspend system devices */
-		error = sysdev_suspend(PMSG_FREEZE);
+		error = syscore_suspend();
 		if (error)
 			goto Enable_irqs;
 	} else
@@ -1546,7 +1546,7 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
-		sysdev_resume();
+		syscore_resume();
  Enable_irqs:
 		local_irq_enable();
  Enable_cpus:
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 9cd0591c96a2..5ae0ff38425f 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -245,7 +245,6 @@ static void __call_usermodehelper(struct work_struct *work)
 	}
 }
 
-#ifdef CONFIG_PM_SLEEP
 /*
  * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY
  * (used for preventing user land processes from being created after the user
@@ -301,6 +300,15 @@ void usermodehelper_enable(void)
 	usermodehelper_disabled = 0;
 }
 
+/**
+ * usermodehelper_is_disabled - check if new helpers are allowed to be started
+ */
+bool usermodehelper_is_disabled(void)
+{
+	return usermodehelper_disabled;
+}
+EXPORT_SYMBOL_GPL(usermodehelper_is_disabled);
+
 static void helper_lock(void)
 {
 	atomic_inc(&running_helpers);
@@ -312,12 +320,6 @@ static void helper_unlock(void)
 	if (atomic_dec_and_test(&running_helpers))
 		wake_up(&running_helpers_waitq);
 }
-#else /* CONFIG_PM_SLEEP */
-#define usermodehelper_disabled	0
-
-static inline void helper_lock(void) {}
-static inline void helper_unlock(void) {}
-#endif /* CONFIG_PM_SLEEP */
 
 /**
  * call_usermodehelper_setup - prepare to call a usermode helper
diff --git a/kernel/module.c b/kernel/module.c
index d5938a5c19c4..22879725678d 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -57,6 +57,7 @@
 #include <linux/kmemleak.h>
 #include <linux/jump_label.h>
 #include <linux/pfn.h>
+#include <linux/bsearch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
@@ -240,23 +241,24 @@ static bool each_symbol_in_section(const struct symsearch *arr,
 				   struct module *owner,
 				   bool (*fn)(const struct symsearch *syms,
 					      struct module *owner,
-					      unsigned int symnum, void *data),
+					      void *data),
 				   void *data)
 {
-	unsigned int i, j;
+	unsigned int j;
 
 	for (j = 0; j < arrsize; j++) {
-		for (i = 0; i < arr[j].stop - arr[j].start; i++)
-			if (fn(&arr[j], owner, i, data))
-				return true;
+		if (fn(&arr[j], owner, data))
+			return true;
 	}
 
 	return false;
 }
 
 /* Returns true as soon as fn returns true, otherwise false. */
-bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
-			    unsigned int symnum, void *data), void *data)
+bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
+				    struct module *owner,
+				    void *data),
+			 void *data)
 {
 	struct module *mod;
 	static const struct symsearch arr[] = {
@@ -309,7 +311,7 @@ bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
 	}
 	return false;
 }
-EXPORT_SYMBOL_GPL(each_symbol);
+EXPORT_SYMBOL_GPL(each_symbol_section);
 
 struct find_symbol_arg {
 	/* Input */
@@ -323,15 +325,12 @@ struct find_symbol_arg {
 	const struct kernel_symbol *sym;
 };
 
-static bool find_symbol_in_section(const struct symsearch *syms,
-				   struct module *owner,
-				   unsigned int symnum, void *data)
+static bool check_symbol(const struct symsearch *syms,
+				 struct module *owner,
+				 unsigned int symnum, void *data)
 {
 	struct find_symbol_arg *fsa = data;
 
-	if (strcmp(syms->start[symnum].name, fsa->name) != 0)
-		return false;
-
 	if (!fsa->gplok) {
 		if (syms->licence == GPL_ONLY)
 			return false;
@@ -365,6 +364,30 @@ static bool find_symbol_in_section(const struct symsearch *syms,
 	return true;
 }
 
+static int cmp_name(const void *va, const void *vb)
+{
+	const char *a;
+	const struct kernel_symbol *b;
+	a = va; b = vb;
+	return strcmp(a, b->name);
+}
+
+static bool find_symbol_in_section(const struct symsearch *syms,
+				   struct module *owner,
+				   void *data)
+{
+	struct find_symbol_arg *fsa = data;
+	struct kernel_symbol *sym;
+
+	sym = bsearch(fsa->name, syms->start, syms->stop - syms->start,
+			sizeof(struct kernel_symbol), cmp_name);
+
+	if (sym != NULL && check_symbol(syms, owner, sym - syms->start, data))
+		return true;
+
+	return false;
+}
+
 /* Find a symbol and return it, along with, (optional) crc and
  * (optional) module which owns it.  Needs preempt disabled or module_mutex. */
 const struct kernel_symbol *find_symbol(const char *name,
@@ -379,7 +402,7 @@ const struct kernel_symbol *find_symbol(const char *name,
 	fsa.gplok = gplok;
 	fsa.warn = warn;
 
-	if (each_symbol(find_symbol_in_section, &fsa)) {
+	if (each_symbol_section(find_symbol_in_section, &fsa)) {
 		if (owner)
 			*owner = fsa.owner;
 		if (crc)
@@ -1607,27 +1630,28 @@ static void set_section_ro_nx(void *base,
 	}
 }
 
-/* Setting memory back to RW+NX before releasing it */
-void unset_section_ro_nx(struct module *mod, void *module_region)
+static void unset_module_core_ro_nx(struct module *mod)
 {
-	unsigned long total_pages;
-
-	if (mod->module_core == module_region) {
-		/* Set core as NX+RW */
-		total_pages = MOD_NUMBER_OF_PAGES(mod->module_core, mod->core_size);
-		set_memory_nx((unsigned long)mod->module_core, total_pages);
-		set_memory_rw((unsigned long)mod->module_core, total_pages);
+	set_page_attributes(mod->module_core + mod->core_text_size,
+		mod->module_core + mod->core_size,
+		set_memory_x);
+	set_page_attributes(mod->module_core,
+		mod->module_core + mod->core_ro_size,
+		set_memory_rw);
+}
 
-	} else if (mod->module_init == module_region) {
-		/* Set init as NX+RW */
-		total_pages = MOD_NUMBER_OF_PAGES(mod->module_init, mod->init_size);
-		set_memory_nx((unsigned long)mod->module_init, total_pages);
-		set_memory_rw((unsigned long)mod->module_init, total_pages);
-	}
+static void unset_module_init_ro_nx(struct module *mod)
+{
+	set_page_attributes(mod->module_init + mod->init_text_size,
+		mod->module_init + mod->init_size,
+		set_memory_x);
+	set_page_attributes(mod->module_init,
+		mod->module_init + mod->init_ro_size,
+		set_memory_rw);
 }
 
 /* Iterate through all modules and set each module's text as RW */
-void set_all_modules_text_rw()
+void set_all_modules_text_rw(void)
 {
 	struct module *mod;
 
@@ -1648,7 +1672,7 @@ void set_all_modules_text_rw()
 }
 
 /* Iterate through all modules and set each module's text as RO */
-void set_all_modules_text_ro()
+void set_all_modules_text_ro(void)
 {
 	struct module *mod;
 
@@ -1669,7 +1693,8 @@ void set_all_modules_text_ro()
 }
 #else
 static inline void set_section_ro_nx(void *base, unsigned long text_size, unsigned long ro_size, unsigned long total_size) { }
-static inline void unset_section_ro_nx(struct module *mod, void *module_region) { }
+static void unset_module_core_ro_nx(struct module *mod) { }
+static void unset_module_init_ro_nx(struct module *mod) { }
 #endif
 
 /* Free a module, remove from lists, etc. */
@@ -1696,7 +1721,7 @@ static void free_module(struct module *mod)
 	destroy_params(mod->kp, mod->num_kp);
 
 	/* This may be NULL, but that's OK */
-	unset_section_ro_nx(mod, mod->module_init);
+	unset_module_init_ro_nx(mod);
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
 	percpu_modfree(mod);
@@ -1705,7 +1730,7 @@ static void free_module(struct module *mod)
 	lockdep_free_key_range(mod->module_core, mod->core_size);
 
 	/* Finally, free the core (containing the module structure) */
-	unset_section_ro_nx(mod, mod->module_core);
+	unset_module_core_ro_nx(mod);
 	module_free(mod, mod->module_core);
 
 #ifdef CONFIG_MPU
@@ -2030,11 +2055,8 @@ static const struct kernel_symbol *lookup_symbol(const char *name,
 	const struct kernel_symbol *start,
 	const struct kernel_symbol *stop)
 {
-	const struct kernel_symbol *ks = start;
-	for (; ks < stop; ks++)
-		if (strcmp(ks->name, name) == 0)
-			return ks;
-	return NULL;
+	return bsearch(name, start, stop - start,
+			sizeof(struct kernel_symbol), cmp_name);
 }
 
 static int is_exported(const char *name, unsigned long value,
@@ -2931,10 +2953,11 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 	mod->symtab = mod->core_symtab;
 	mod->strtab = mod->core_strtab;
 #endif
-	unset_section_ro_nx(mod, mod->module_init);
+	unset_module_init_ro_nx(mod);
 	module_free(mod, mod->module_init);
 	mod->module_init = NULL;
 	mod->init_size = 0;
+	mod->init_ro_size = 0;
 	mod->init_text_size = 0;
 	mutex_unlock(&module_mutex);
 
diff --git a/kernel/params.c b/kernel/params.c
index 7ab388a48a2e..ed72e1330862 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -297,21 +297,15 @@ EXPORT_SYMBOL(param_ops_charp);
 int param_set_bool(const char *val, const struct kernel_param *kp)
 {
 	bool v;
+	int ret;
 
 	/* No equals means "set"... */
 	if (!val) val = "1";
 
 	/* One of =[yYnN01] */
-	switch (val[0]) {
-	case 'y': case 'Y': case '1':
-		v = true;
-		break;
-	case 'n': case 'N': case '0':
-		v = false;
-		break;
-	default:
-		return -EINVAL;
-	}
+	ret = strtobool(val, &v);
+	if (ret)
+		return ret;
 
 	if (kp->flags & KPARAM_ISBOOL)
 		*(bool *)kp->arg = v;
@@ -821,15 +815,18 @@ ssize_t __modver_version_show(struct module_attribute *mattr,
 	return sprintf(buf, "%s\n", vattr->version);
 }
 
-extern struct module_version_attribute __start___modver[], __stop___modver[];
+extern const struct module_version_attribute *__start___modver[];
+extern const struct module_version_attribute *__stop___modver[];
 
 static void __init version_sysfs_builtin(void)
 {
-	const struct module_version_attribute *vattr;
+	const struct module_version_attribute **p;
 	struct module_kobject *mk;
 	int err;
 
-	for (vattr = __start___modver; vattr < __stop___modver; vattr++) {
+	for (p = __start___modver; p < __stop___modver; p++) {
+		const struct module_version_attribute *vattr = *p;
+
 		mk = locate_module_kobject(vattr->module_name);
 		if (mk) {
 			err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 6de9a8fc3417..87f4d24b55b0 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -125,12 +125,6 @@ config PM_DEBUG
 	code. This is helpful when debugging and reporting PM bugs, like
 	suspend support.
 
-config PM_VERBOSE
-	bool "Verbose Power Management debugging"
-	depends on PM_DEBUG
-	---help---
-	This option enables verbose messages from the Power Management code.
-
 config PM_ADVANCED_DEBUG
 	bool "Extra PM attributes in sysfs for low-level debugging/testing"
 	depends on PM_DEBUG
@@ -229,3 +223,7 @@ config PM_OPP
 	  representing individual voltage domains and provides SOC
 	  implementations a ready to use framework to manage OPPs.
 	  For more information, read <file:Documentation/power/opp.txt>
+
+config PM_RUNTIME_CLK
+	def_bool y
+	depends on PM_RUNTIME && HAVE_CLK
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index aeabd26e3342..f9bec56d8825 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -272,9 +272,7 @@ static int create_image(int platform_mode)
 
 	local_irq_disable();
 
-	error = sysdev_suspend(PMSG_FREEZE);
-	if (!error)
-		error = syscore_suspend();
+	error = syscore_suspend();
 	if (error) {
 		printk(KERN_ERR "PM: Some system devices failed to power down, "
 			"aborting hibernation\n");
@@ -299,7 +297,6 @@ static int create_image(int platform_mode)
 
  Power_up:
 	syscore_resume();
-	sysdev_resume();
 	/* NOTE:  dpm_resume_noirq() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
@@ -330,20 +327,25 @@ static int create_image(int platform_mode)
 
 int hibernation_snapshot(int platform_mode)
 {
+	pm_message_t msg = PMSG_RECOVER;
 	int error;
 
 	error = platform_begin(platform_mode);
 	if (error)
 		goto Close;
 
+	error = dpm_prepare(PMSG_FREEZE);
+	if (error)
+		goto Complete_devices;
+
 	/* Preallocate image memory before shutting down devices. */
 	error = hibernate_preallocate_memory();
 	if (error)
-		goto Close;
+		goto Complete_devices;
 
 	suspend_console();
 	pm_restrict_gfp_mask();
-	error = dpm_suspend_start(PMSG_FREEZE);
+	error = dpm_suspend(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
 
@@ -361,13 +363,17 @@ int hibernation_snapshot(int platform_mode)
 	if (error || !in_suspend)
 		swsusp_free();
 
-	dpm_resume_end(in_suspend ?
-		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+	msg = in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE;
+	dpm_resume(msg);
 
 	if (error || !in_suspend)
 		pm_restore_gfp_mask();
 
 	resume_console();
+
+ Complete_devices:
+	dpm_complete(msg);
+
  Close:
 	platform_end(platform_mode);
 	return error;
@@ -406,9 +412,7 @@ static int resume_target_kernel(bool platform_mode)
 
 	local_irq_disable();
 
-	error = sysdev_suspend(PMSG_QUIESCE);
-	if (!error)
-		error = syscore_suspend();
+	error = syscore_suspend();
 	if (error)
 		goto Enable_irqs;
 
@@ -436,7 +440,6 @@ static int resume_target_kernel(bool platform_mode)
 	touch_softlockup_watchdog();
 
 	syscore_resume();
-	sysdev_resume();
 
  Enable_irqs:
 	local_irq_enable();
@@ -522,7 +525,6 @@ int hibernation_platform_enter(void)
 		goto Platform_finish;
 
 	local_irq_disable();
-	sysdev_suspend(PMSG_HIBERNATE);
 	syscore_suspend();
 	if (pm_wakeup_pending()) {
 		error = -EAGAIN;
@@ -535,7 +537,6 @@ int hibernation_platform_enter(void)
 
  Power_up:
 	syscore_resume();
-	sysdev_resume();
 	local_irq_enable();
 	enable_nonboot_cpus();
 
@@ -976,10 +977,33 @@ static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *att
 
 power_attr(image_size);
 
+static ssize_t reserved_size_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%lu\n", reserved_size);
+}
+
+static ssize_t reserved_size_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t n)
+{
+	unsigned long size;
+
+	if (sscanf(buf, "%lu", &size) == 1) {
+		reserved_size = size;
+		return n;
+	}
+
+	return -EINVAL;
+}
+
+power_attr(reserved_size);
+
 static struct attribute * g[] = {
 	&disk_attr.attr,
 	&resume_attr.attr,
 	&image_size_attr.attr,
+	&reserved_size_attr.attr,
 	NULL,
 };
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index de9aef8742f4..2981af4ce7cb 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -337,6 +337,7 @@ static int __init pm_init(void)
 	if (error)
 		return error;
 	hibernate_image_size_init();
+	hibernate_reserved_size_init();
 	power_kobj = kobject_create_and_add("power", NULL);
 	if (!power_kobj)
 		return -ENOMEM;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 03634be55f62..9a00a0a26280 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -15,6 +15,7 @@ struct swsusp_info {
 
 #ifdef CONFIG_HIBERNATION
 /* kernel/power/snapshot.c */
+extern void __init hibernate_reserved_size_init(void);
 extern void __init hibernate_image_size_init(void);
 
 #ifdef CONFIG_ARCH_HIBERNATION_HEADER
@@ -55,6 +56,7 @@ extern int hibernation_platform_enter(void);
 
 #else /* !CONFIG_HIBERNATION */
 
+static inline void hibernate_reserved_size_init(void) {}
 static inline void hibernate_image_size_init(void) {}
 #endif /* !CONFIG_HIBERNATION */
 
@@ -72,6 +74,8 @@ static struct kobj_attribute _name##_attr = {	\
 
 /* Preferred image size in bytes (default 500 MB) */
 extern unsigned long image_size;
+/* Size of memory reserved for drivers (default SPARE_PAGES x PAGE_SIZE) */
+extern unsigned long reserved_size;
 extern int in_suspend;
 extern dev_t swsusp_resume_device;
 extern sector_t swsusp_resume_block;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index ca0aacc24874..ace55889f702 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -41,16 +41,28 @@ static void swsusp_set_page_forbidden(struct page *);
 static void swsusp_unset_page_forbidden(struct page *);
 
 /*
+ * Number of bytes to reserve for memory allocations made by device drivers
+ * from their ->freeze() and ->freeze_noirq() callbacks so that they don't
+ * cause image creation to fail (tunable via /sys/power/reserved_size).
+ */
+unsigned long reserved_size;
+
+void __init hibernate_reserved_size_init(void)
+{
+	reserved_size = SPARE_PAGES * PAGE_SIZE;
+}
+
+/*
  * Preferred image size in bytes (tunable via /sys/power/image_size).
- * When it is set to N, the image creating code will do its best to
- * ensure the image size will not exceed N bytes, but if that is
- * impossible, it will try to create the smallest image possible.
+ * When it is set to N, swsusp will do its best to ensure the image
+ * size will not exceed N bytes, but if that is impossible, it will
+ * try to create the smallest image possible.
  */
 unsigned long image_size;
 
 void __init hibernate_image_size_init(void)
 {
-	image_size = (totalram_pages / 3) * PAGE_SIZE;
+	image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE;
 }
 
 /* List of PBEs needed for restoring the pages that were allocated before
@@ -1263,11 +1275,13 @@ static unsigned long minimum_image_size(unsigned long saveable)
  * frame in use.  We also need a number of page frames to be free during
  * hibernation for allocations made while saving the image and for device
  * drivers, in case they need to allocate memory from their hibernation
- * callbacks (these two numbers are given by PAGES_FOR_IO and SPARE_PAGES,
- * respectively, both of which are rough estimates).  To make this happen, we
- * compute the total number of available page frames and allocate at least
+ * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough
+ * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through
+ * /sys/power/reserved_size, respectively).  To make this happen, we compute the
+ * total number of available page frames and allocate at least
  *
- * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + 2 * SPARE_PAGES
+ * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2
+ *  + 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE)
  *
  * of them, which corresponds to the maximum size of a hibernation image.
  *
@@ -1322,7 +1336,8 @@ int hibernate_preallocate_memory(void)
 	count -= totalreserve_pages;
 
 	/* Compute the maximum number of saveable pages to leave in memory. */
-	max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES;
+	max_size = (count - (size + PAGES_FOR_IO)) / 2
+			- 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE);
 	/* Compute the desired number of image pages specified by image_size. */
 	size = DIV_ROUND_UP(image_size, PAGE_SIZE);
 	if (size > max_size)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 2814c32aed51..1c41ba215419 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -163,16 +163,13 @@ static int suspend_enter(suspend_state_t state)
 	arch_suspend_disable_irqs();
 	BUG_ON(!irqs_disabled());
 
-	error = sysdev_suspend(PMSG_SUSPEND);
-	if (!error)
-		error = syscore_suspend();
+	error = syscore_suspend();
 	if (!error) {
 		if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) {
 			error = suspend_ops->enter(state);
 			events_check_enabled = false;
 		}
 		syscore_resume();
-		sysdev_resume();
 	}
 
 	arch_suspend_enable_irqs();
@@ -213,7 +210,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
-	pm_restrict_gfp_mask();
 	suspend_test_start();
 	error = dpm_suspend_start(PMSG_SUSPEND);
 	if (error) {
@@ -224,13 +220,12 @@ int suspend_devices_and_enter(suspend_state_t state)
 	if (suspend_test(TEST_DEVICES))
 		goto Recover_platform;
 
-	suspend_enter(state);
+	error = suspend_enter(state);
 
  Resume_devices:
 	suspend_test_start();
 	dpm_resume_end(PMSG_RESUME);
 	suspend_test_finish("resume devices");
-	pm_restore_gfp_mask();
 	resume_console();
  Close:
 	if (suspend_ops->end)
@@ -291,7 +286,9 @@ int enter_state(suspend_state_t state)
 		goto Finish;
 
 	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
+	pm_restore_gfp_mask();
 
  Finish:
 	pr_debug("PM: Finishing wakeup.\n");
diff --git a/kernel/power/user.c b/kernel/power/user.c
index c36c3b9e8a84..7d02d33be699 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -135,8 +135,10 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 	free_basic_memory_bitmaps();
 	data = filp->private_data;
 	free_all_swap_pages(data->swap);
-	if (data->frozen)
+	if (data->frozen) {
+		pm_restore_gfp_mask();
 		thaw_processes();
+	}
 	pm_notifier_call_chain(data->mode == O_RDONLY ?
 			PM_POST_HIBERNATION : PM_POST_RESTORE);
 	atomic_inc(&snapshot_device_available);
@@ -379,6 +381,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		 * PM_HIBERNATION_PREPARE
 		 */
 		error = suspend_devices_and_enter(PM_SUSPEND_MEM);
+		data->ready = 0;
 		break;
 
 	case SNAPSHOT_PLATFORM_SUPPORT:
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 0fc1eed28d27..dc7ab65f3b36 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
 
 
 /*
@@ -879,3 +880,19 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 	return ret;
 }
 #endif	/* CONFIG_COMPAT */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+int ptrace_get_breakpoints(struct task_struct *tsk)
+{
+	if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt))
+		return 0;
+
+	return -1;
+}
+
+void ptrace_put_breakpoints(struct task_struct *tsk)
+{
+	if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt))
+		flush_ptrace_hw_breakpoint(tsk);
+}
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
diff --git a/kernel/sys.c b/kernel/sys.c
index af468edf096a..f0c10385f30c 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -315,7 +315,6 @@ void kernel_restart_prepare(char *cmd)
 	blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
 	system_state = SYSTEM_RESTART;
 	device_shutdown();
-	sysdev_shutdown();
 	syscore_shutdown();
 }
 
@@ -354,7 +353,6 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
-	sysdev_shutdown();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
@@ -374,7 +372,6 @@ void kernel_power_off(void)
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
 	disable_nonboot_cpus();
-	sysdev_shutdown();
 	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 6519cf62d9cd..0e17c10f8a9d 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -685,8 +685,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 	/* Add clocksource to the clcoksource list */
 	mutex_lock(&clocksource_mutex);
 	clocksource_enqueue(cs);
-	clocksource_select();
 	clocksource_enqueue_watchdog(cs);
+	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -706,8 +706,8 @@ int clocksource_register(struct clocksource *cs)
 
 	mutex_lock(&clocksource_mutex);
 	clocksource_enqueue(cs);
-	clocksource_select();
 	clocksource_enqueue_watchdog(cs);
+	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index da800ffa810c..723c7637e55a 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -522,10 +522,11 @@ static void tick_broadcast_init_next_event(struct cpumask *mask,
  */
 void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
+	int cpu = smp_processor_id();
+
 	/* Set it up only once ! */
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
 		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
-		int cpu = smp_processor_id();
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
 		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
@@ -551,6 +552,15 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 			tick_broadcast_set_event(tick_next_period, 1);
 		} else
 			bc->next_event.tv64 = KTIME_MAX;
+	} else {
+		/*
+		 * The first cpu which switches to oneshot mode sets
+		 * the bit for all other cpus which are in the general
+		 * (periodic) broadcast mask. So the bit is set and
+		 * would prevent the first broadcast enter after this
+		 * to program the bc device.
+		 */
+		tick_broadcast_clear_oneshot(cpu);
 	}
 }
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61d7d59f4a1a..2ad39e556cb4 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -141,7 +141,7 @@ if FTRACE
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	select FRAME_POINTER if !ARM_UNWIND && !S390
+	select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d38c16a06a6f..1cb49be7c7fb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1110,6 +1110,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
+	entry->padding			= 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e88f74fe1d4c..2fe110341359 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,6 +116,7 @@ static int trace_define_common_fields(void)
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
+	__common_field(int, padding);
 
 	return ret;
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 140dce750450..14733d4d156b 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -430,9 +430,12 @@ static int watchdog_enable(int cpu)
 		p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu);
 		if (IS_ERR(p)) {
 			printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu);
-			if (!err)
+			if (!err) {
 				/* if hardlockup hasn't already set this */
 				err = PTR_ERR(p);
+				/* and disable the perf event */
+				watchdog_nmi_disable(cpu);
+			}
 			goto out;
 		}
 		kthread_bind(p, cpu);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 8859a41806dd..e3378e8d3a5c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1291,8 +1291,14 @@ __acquires(&gcwq->lock)
 			return true;
 		spin_unlock_irq(&gcwq->lock);
 
-		/* CPU has come up in between, retry migration */
+		/*
+		 * We've raced with CPU hot[un]plug.  Give it a breather
+		 * and retry migration.  cond_resched() is required here;
+		 * otherwise, we might deadlock against cpu_stop trying to
+		 * bring down the CPU on non-preemptive kernel.
+		 */
 		cpu_relax();
+		cond_resched();
 	}
 }