Merge branch 'linus' into tracing-v28-for-linus-v3

Conflicts:
	init/main.c
	kernel/module.c
	scripts/bootgraph.pl

29 files changed, 600 insertions, 220 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a0123d75ec9a..8c6e1c17e6d3 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2735,6 +2735,8 @@ void cgroup_fork_callbacks(struct task_struct *child)
  * Called on every change to mm->owner. mm_init_owner() does not
  * invoke this routine, since it assigns the mm->owner the first time
  * and does not change it.
+ *
+ * The callbacks are invoked with mmap_sem held in read mode.
  */
 void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
 {
@@ -2750,7 +2752,7 @@ void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
 			if (oldcgrp == newcgrp)
 				continue;
 			if (ss->mm_owner_changed)
-				ss->mm_owner_changed(ss, oldcgrp, newcgrp);
+				ss->mm_owner_changed(ss, oldcgrp, newcgrp, new);
 		}
 	}
 }
diff --git a/kernel/compat.c b/kernel/compat.c
index 32c254a8ab9a..143990e48cb9 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -26,6 +26,64 @@
 
 #include <asm/uaccess.h>
 
+/*
+ * Note that the native side is already converted to a timespec, because
+ * that's what we want anyway.
+ */
+static int compat_get_timeval(struct timespec *o,
+		struct compat_timeval __user *i)
+{
+	long usec;
+
+	if (get_user(o->tv_sec, &i->tv_sec) ||
+	    get_user(usec, &i->tv_usec))
+		return -EFAULT;
+	o->tv_nsec = usec * 1000;
+	return 0;
+}
+
+static int compat_put_timeval(struct compat_timeval __user *o,
+		struct timeval *i)
+{
+	return (put_user(i->tv_sec, &o->tv_sec) ||
+		put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
+}
+
+asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
+		struct timezone __user *tz)
+{
+	if (tv) {
+		struct timeval ktv;
+		do_gettimeofday(&ktv);
+		if (compat_put_timeval(tv, &ktv))
+			return -EFAULT;
+	}
+	if (tz) {
+		if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
+		struct timezone __user *tz)
+{
+	struct timespec kts;
+	struct timezone ktz;
+
+	if (tv) {
+		if (compat_get_timeval(&kts, tv))
+			return -EFAULT;
+	}
+	if (tz) {
+		if (copy_from_user(&ktz, tz, sizeof(ktz)))
+			return -EFAULT;
+	}
+
+	return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
+}
+
 int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
 	return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
diff --git a/kernel/dma.c b/kernel/dma.c
index d2c60a822790..f903189c5304 100644
--- a/kernel/dma.c
+++ b/kernel/dma.c
@@ -1,4 +1,4 @@
-/* $Id: dma.c,v 1.7 1994/12/28 03:35:33 root Exp root $
+/*
  * linux/kernel/dma.c: A DMA channel allocator. Inspired by linux/kernel/irq.c.
  *
  * Written by Hennus Bergman, 1992.
diff --git a/kernel/exit.c b/kernel/exit.c
index 7b71f87f1207..138887881a11 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -644,24 +644,23 @@ retry:
 assign_new_owner:
 	BUG_ON(c == p);
 	get_task_struct(c);
+	read_unlock(&tasklist_lock);
+	down_write(&mm->mmap_sem);
 	/*
 	 * The task_lock protects c->mm from changing.
 	 * We always want mm->owner->mm == mm
 	 */
 	task_lock(c);
-	/*
-	 * Delay read_unlock() till we have the task_lock()
-	 * to ensure that c does not slip away underneath us
-	 */
-	read_unlock(&tasklist_lock);
 	if (c->mm != mm) {
 		task_unlock(c);
+		up_write(&mm->mmap_sem);
 		put_task_struct(c);
 		goto retry;
 	}
 	cgroup_mm_owner_callbacks(mm->owner, c);
 	mm->owner = c;
 	task_unlock(c);
+	up_write(&mm->mmap_sem);
 	put_task_struct(c);
 }
 #endif /* CONFIG_MM_OWNER */
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 38fc10ac7541..5072cf1685a2 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -260,7 +260,6 @@ const char *kallsyms_lookup(unsigned long addr,
 	/* see if it's in a module */
 	return module_address_lookup(addr, symbolsize, offset, modname,
 				     namebuf);
-	return NULL;
 }
 
 int lookup_symbol_name(unsigned long addr, char *symname)
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 2456d1a0befb..3d3c3ea3a023 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -113,7 +113,7 @@ int request_module(const char *fmt, ...)
 	return ret;
 }
 EXPORT_SYMBOL(request_module);
-#endif /* CONFIG_KMOD */
+#endif /* CONFIG_MODULES */
 
 struct subprocess_info {
 	struct work_struct work;
@@ -265,7 +265,7 @@ static void __call_usermodehelper(struct work_struct *work)
 	}
 }
 
-#ifdef CONFIG_PM
+#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
@@ -288,39 +288,37 @@ static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq);
  */
 #define RUNNING_HELPERS_TIMEOUT	(5 * HZ)
 
-static int usermodehelper_pm_callback(struct notifier_block *nfb,
-					unsigned long action,
-					void *ignored)
+/**
+ * usermodehelper_disable - prevent new helpers from being started
+ */
+int usermodehelper_disable(void)
 {
 	long retval;
 
-	switch (action) {
-	case PM_HIBERNATION_PREPARE:
-	case PM_SUSPEND_PREPARE:
-		usermodehelper_disabled = 1;
-		smp_mb();
-		/*
-		 * From now on call_usermodehelper_exec() won't start any new
-		 * helpers, so it is sufficient if running_helpers turns out to
-		 * be zero at one point (it may be increased later, but that
-		 * doesn't matter).
-		 */
-		retval = wait_event_timeout(running_helpers_waitq,
+	usermodehelper_disabled = 1;
+	smp_mb();
+	/*
+	 * From now on call_usermodehelper_exec() won't start any new
+	 * helpers, so it is sufficient if running_helpers turns out to
+	 * be zero at one point (it may be increased later, but that
+	 * doesn't matter).
+	 */
+	retval = wait_event_timeout(running_helpers_waitq,
 					atomic_read(&running_helpers) == 0,
 					RUNNING_HELPERS_TIMEOUT);
-		if (retval) {
-			return NOTIFY_OK;
-		} else {
-			usermodehelper_disabled = 0;
-			return NOTIFY_BAD;
-		}
-	case PM_POST_HIBERNATION:
-	case PM_POST_SUSPEND:
-		usermodehelper_disabled = 0;
-		return NOTIFY_OK;
-	}
+	if (retval)
+		return 0;
 
-	return NOTIFY_DONE;
+	usermodehelper_disabled = 0;
+	return -EAGAIN;
+}
+
+/**
+ * usermodehelper_enable - allow new helpers to be started again
+ */
+void usermodehelper_enable(void)
+{
+	usermodehelper_disabled = 0;
 }
 
 static void helper_lock(void)
@@ -334,18 +332,12 @@ static void helper_unlock(void)
 	if (atomic_dec_and_test(&running_helpers))
 		wake_up(&running_helpers_waitq);
 }
-
-static void register_pm_notifier_callback(void)
-{
-	pm_notifier(usermodehelper_pm_callback, 0);
-}
-#else /* CONFIG_PM */
+#else /* CONFIG_PM_SLEEP */
 #define usermodehelper_disabled	0
 
 static inline void helper_lock(void) {}
 static inline void helper_unlock(void) {}
-static inline void register_pm_notifier_callback(void) {}
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 /**
  * call_usermodehelper_setup - prepare to call a usermode helper
@@ -515,5 +507,4 @@ void __init usermodehelper_init(void)
 {
 	khelper_wq = create_singlethread_workqueue("khelper");
 	BUG_ON(!khelper_wq);
-	register_pm_notifier_callback();
 }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 75bc2cd9ebc6..8b57a2597f21 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -404,7 +404,7 @@ void kretprobe_hash_lock(struct task_struct *tsk,
 	spin_lock_irqsave(hlist_lock, *flags);
 }
 
-void kretprobe_table_lock(unsigned long hash, unsigned long *flags)
+static void kretprobe_table_lock(unsigned long hash, unsigned long *flags)
 {
 	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
 	spin_lock_irqsave(hlist_lock, *flags);
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index e53bc30e9ba5..08dd8ed86c77 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
+#include <linux/profile.h>
 #include <linux/sched.h>
 
 #define KERNEL_ATTR_RO(_name) \
@@ -53,6 +54,37 @@ static ssize_t uevent_helper_store(struct kobject *kobj,
 KERNEL_ATTR_RW(uevent_helper);
 #endif
 
+#ifdef CONFIG_PROFILING
+static ssize_t profiling_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", prof_on);
+}
+static ssize_t profiling_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t count)
+{
+	int ret;
+
+	if (prof_on)
+		return -EEXIST;
+	/*
+	 * This eventually calls into get_option() which
+	 * has a ton of callers and is not const.  It is
+	 * easiest to cast it away here.
+	 */
+	profile_setup((char *)buf);
+	ret = profile_init();
+	if (ret)
+		return ret;
+	ret = create_proc_profile();
+	if (ret)
+		return ret;
+	return count;
+}
+KERNEL_ATTR_RW(profiling);
+#endif
+
 #ifdef CONFIG_KEXEC
 static ssize_t kexec_loaded_show(struct kobject *kobj,
 				 struct kobj_attribute *attr, char *buf)
@@ -109,6 +141,9 @@ static struct attribute * kernel_attrs[] = {
 	&uevent_seqnum_attr.attr,
 	&uevent_helper_attr.attr,
 #endif
+#ifdef CONFIG_PROFILING
+	&profiling_attr.attr,
+#endif
 #ifdef CONFIG_KEXEC
 	&kexec_loaded_attr.attr,
 	&kexec_crash_loaded_attr.attr,
diff --git a/kernel/module.c b/kernel/module.c
index 7576c2d9462f..0d8d21ee792c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -102,7 +102,7 @@ static inline int strong_try_module_get(struct module *mod)
 static inline void add_taint_module(struct module *mod, unsigned flag)
 {
 	add_taint(flag);
-	mod->taints |= flag;
+	mod->taints |= (1U << flag);
 }
 
 /*
@@ -786,6 +786,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags)
 	mutex_lock(&module_mutex);
 	/* Store the name of the last unloaded module for diagnostic purposes */
 	strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
+	unregister_dynamic_debug_module(mod->name);
 	free_module(mod);
 
  out:
@@ -925,7 +926,7 @@ static const char vermagic[] = VERMAGIC_STRING;
 static int try_to_force_load(struct module *mod, const char *symname)
 {
 #ifdef CONFIG_MODULE_FORCE_LOAD
-	if (!(tainted & TAINT_FORCED_MODULE))
+	if (!test_taint(TAINT_FORCED_MODULE))
 		printk("%s: no version for \"%s\" found: kernel tainted.\n",
 		       mod->name, symname);
 	add_taint_module(mod, TAINT_FORCED_MODULE);
@@ -1035,7 +1036,7 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs,
 	const unsigned long *crc;
 
 	ret = find_symbol(name, &owner, &crc,
-			  !(mod->taints & TAINT_PROPRIETARY_MODULE), true);
+			  !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true);
 	if (!IS_ERR_VALUE(ret)) {
 		/* use_module can fail due to OOM,
 		   or module initialization or unloading */
@@ -1175,7 +1176,7 @@ static void free_notes_attrs(struct module_notes_attrs *notes_attrs,
 		while (i-- > 0)
 			sysfs_remove_bin_file(notes_attrs->dir,
 					      &notes_attrs->attrs[i]);
-		kobject_del(notes_attrs->dir);
+		kobject_put(notes_attrs->dir);
 	}
 	kfree(notes_attrs);
 }
@@ -1639,7 +1640,7 @@ static void set_license(struct module *mod, const char *license)
 		license = "unspecified";
 
 	if (!license_is_gpl_compatible(license)) {
-		if (!(tainted & TAINT_PROPRIETARY_MODULE))
+		if (!test_taint(TAINT_PROPRIETARY_MODULE))
 			printk(KERN_WARNING "%s: module license '%s' taints "
 				"kernel.\n", mod->name, license);
 		add_taint_module(mod, TAINT_PROPRIETARY_MODULE);
@@ -1788,6 +1789,33 @@ static inline void add_kallsyms(struct module *mod,
 }
 #endif /* CONFIG_KALLSYMS */
 
+#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG
+static void dynamic_printk_setup(Elf_Shdr *sechdrs, unsigned int verboseindex)
+{
+	struct mod_debug *debug_info;
+	unsigned long pos, end;
+	unsigned int num_verbose;
+
+	pos = sechdrs[verboseindex].sh_addr;
+	num_verbose = sechdrs[verboseindex].sh_size /
+				sizeof(struct mod_debug);
+	end = pos + (num_verbose * sizeof(struct mod_debug));
+
+	for (; pos < end; pos += sizeof(struct mod_debug)) {
+		debug_info = (struct mod_debug *)pos;
+		register_dynamic_debug_module(debug_info->modname,
+			debug_info->type, debug_info->logical_modname,
+			debug_info->flag_names, debug_info->hash,
+			debug_info->hash2);
+	}
+}
+#else
+static inline void dynamic_printk_setup(Elf_Shdr *sechdrs,
+					unsigned int verboseindex)
+{
+}
+#endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */
+
 static void *module_alloc_update_bounds(unsigned long size)
 {
 	void *ret = module_alloc(size);
@@ -1811,6 +1839,7 @@ static noinline struct module *load_module(void __user *umod,
 	Elf_Ehdr *hdr;
 	Elf_Shdr *sechdrs;
 	char *secstrings, *args, *modmagic, *strtab = NULL;
+	char *staging;
 	unsigned int i;
 	unsigned int symindex = 0;
 	unsigned int strindex = 0;
@@ -1836,6 +1865,7 @@ static noinline struct module *load_module(void __user *umod,
 #endif
 	unsigned int markersindex;
 	unsigned int markersstringsindex;
+	unsigned int verboseindex;
 	unsigned int tracepointsindex;
 	unsigned int tracepointsstringsindex;
 	unsigned int mcountindex;
@@ -1969,6 +1999,14 @@ static noinline struct module *load_module(void __user *umod,
 		goto free_hdr;
 	}
 
+	staging = get_modinfo(sechdrs, infoindex, "staging");
+	if (staging) {
+		add_taint_module(mod, TAINT_CRAP);
+		printk(KERN_WARNING "%s: module is from the staging directory,"
+		       " the quality is unknown, you have been warned.\n",
+		       mod->name);
+	}
+
 	/* Now copy in args */
 	args = strndup_user(uargs, ~0UL >> 1);
 	if (IS_ERR(args)) {
@@ -2126,6 +2164,7 @@ static noinline struct module *load_module(void __user *umod,
 	markersindex = find_sec(hdr, sechdrs, secstrings, "__markers");
  	markersstringsindex = find_sec(hdr, sechdrs, secstrings,
 					"__markers_strings");
+	verboseindex = find_sec(hdr, sechdrs, secstrings, "__verbose");
 	tracepointsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints");
 	tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings,
 					"__tracepoints_strings");
@@ -2188,6 +2227,7 @@ static noinline struct module *load_module(void __user *umod,
 		marker_update_probe_range(mod->markers,
 			mod->markers + mod->num_markers);
 #endif
+	dynamic_printk_setup(sechdrs, verboseindex);
 #ifdef CONFIG_TRACEPOINTS
 		tracepoint_update_probe_range(mod->tracepoints,
 			mod->tracepoints + mod->num_tracepoints);
@@ -2584,10 +2624,12 @@ static char *module_flags(struct module *mod, char *buf)
 	    mod->state == MODULE_STATE_GOING ||
 	    mod->state == MODULE_STATE_COMING) {
 		buf[bx++] = '(';
-		if (mod->taints & TAINT_PROPRIETARY_MODULE)
+		if (mod->taints & (1 << TAINT_PROPRIETARY_MODULE))
 			buf[bx++] = 'P';
-		if (mod->taints & TAINT_FORCED_MODULE)
+		if (mod->taints & (1 << TAINT_FORCED_MODULE))
 			buf[bx++] = 'F';
+		if (mod->taints & (1 << TAINT_CRAP))
+			buf[bx++] = 'C';
 		/*
 		 * TAINT_FORCED_RMMOD: could be added.
 		 * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
diff --git a/kernel/panic.c b/kernel/panic.c
index 12c5a0a6c89b..bda561ef3cdf 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -23,7 +23,7 @@
 #include <linux/kallsyms.h>
 
 int panic_on_oops;
-int tainted;
+static unsigned long tainted_mask;
 static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
@@ -143,6 +143,27 @@ NORET_TYPE void panic(const char * fmt, ...)
 
 EXPORT_SYMBOL(panic);
 
+
+struct tnt {
+	u8 bit;
+	char true;
+	char false;
+};
+
+static const struct tnt tnts[] = {
+	{ TAINT_PROPRIETARY_MODULE, 'P', 'G' },
+	{ TAINT_FORCED_MODULE, 'F', ' ' },
+	{ TAINT_UNSAFE_SMP, 'S', ' ' },
+	{ TAINT_FORCED_RMMOD, 'R', ' ' },
+	{ TAINT_MACHINE_CHECK, 'M', ' ' },
+	{ TAINT_BAD_PAGE, 'B', ' ' },
+	{ TAINT_USER, 'U', ' ' },
+	{ TAINT_DIE, 'D', ' ' },
+	{ TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' },
+	{ TAINT_WARN, 'W', ' ' },
+	{ TAINT_CRAP, 'C', ' ' },
+};
+
 /**
  *	print_tainted - return a string to represent the kernel taint state.
  *
@@ -155,35 +176,45 @@ EXPORT_SYMBOL(panic);
  *  'U' - Userspace-defined naughtiness.
  *  'A' - ACPI table overridden.
  *  'W' - Taint on warning.
+ *  'C' - modules from drivers/staging are loaded.
  *
  *	The string is overwritten by the next call to print_taint().
  */
-
 const char *print_tainted(void)
 {
-	static char buf[20];
-	if (tainted) {
-		snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c%c%c%c%c",
-			tainted & TAINT_PROPRIETARY_MODULE ? 'P' : 'G',
-			tainted & TAINT_FORCED_MODULE ? 'F' : ' ',
-			tainted & TAINT_UNSAFE_SMP ? 'S' : ' ',
-			tainted & TAINT_FORCED_RMMOD ? 'R' : ' ',
-			tainted & TAINT_MACHINE_CHECK ? 'M' : ' ',
-			tainted & TAINT_BAD_PAGE ? 'B' : ' ',
-			tainted & TAINT_USER ? 'U' : ' ',
-			tainted & TAINT_DIE ? 'D' : ' ',
-			tainted & TAINT_OVERRIDDEN_ACPI_TABLE ? 'A' : ' ',
-			tainted & TAINT_WARN ? 'W' : ' ');
-	}
-	else
+	static char buf[ARRAY_SIZE(tnts) + sizeof("Tainted: ") + 1];
+
+	if (tainted_mask) {
+		char *s;
+		int i;
+
+		s = buf + sprintf(buf, "Tainted: ");
+		for (i = 0; i < ARRAY_SIZE(tnts); i++) {
+			const struct tnt *t = &tnts[i];
+			*s++ = test_bit(t->bit, &tainted_mask) ?
+					t->true : t->false;
+		}
+		*s = 0;
+	} else
 		snprintf(buf, sizeof(buf), "Not tainted");
 	return(buf);
 }
 
+int test_taint(unsigned flag)
+{
+	return test_bit(flag, &tainted_mask);
+}
+EXPORT_SYMBOL(test_taint);
+
+unsigned long get_taint(void)
+{
+	return tainted_mask;
+}
+
 void add_taint(unsigned flag)
 {
 	debug_locks = 0; /* can't trust the integrity of the kernel anymore */
-	tainted |= flag;
+	set_bit(flag, &tainted_mask);
 }
 EXPORT_SYMBOL(add_taint);
 
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index bbd85c60f741..331f9836383f 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -14,6 +14,7 @@
 #include <linux/reboot.h>
 #include <linux/string.h>
 #include <linux/device.h>
+#include <linux/kmod.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
@@ -520,6 +521,10 @@ int hibernate(void)
 	if (error)
 		goto Exit;
 
+	error = usermodehelper_disable();
+	if (error)
+		goto Exit;
+
 	/* Allocate memory management structures */
 	error = create_basic_memory_bitmaps();
 	if (error)
@@ -558,6 +563,7 @@ int hibernate(void)
 	thaw_processes();
  Finish:
 	free_basic_memory_bitmaps();
+	usermodehelper_enable();
  Exit:
 	pm_notifier_call_chain(PM_POST_HIBERNATION);
 	pm_restore_console();
@@ -634,6 +640,10 @@ static int software_resume(void)
 	if (error)
 		goto Finish;
 
+	error = usermodehelper_disable();
+	if (error)
+		goto Finish;
+
 	error = create_basic_memory_bitmaps();
 	if (error)
 		goto Finish;
@@ -656,6 +666,7 @@ static int software_resume(void)
 	thaw_processes();
  Done:
 	free_basic_memory_bitmaps();
+	usermodehelper_enable();
  Finish:
 	pm_notifier_call_chain(PM_POST_RESTORE);
 	pm_restore_console();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 540b16b68565..19122cf6d827 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -14,6 +14,7 @@
 #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>
@@ -237,6 +238,10 @@ static int suspend_prepare(void)
 	if (error)
 		goto Finish;
 
+	error = usermodehelper_disable();
+	if (error)
+		goto Finish;
+
 	if (suspend_freeze_processes()) {
 		error = -EAGAIN;
 		goto Thaw;
@@ -256,6 +261,7 @@ static int suspend_prepare(void)
 
  Thaw:
 	suspend_thaw_processes();
+	usermodehelper_enable();
  Finish:
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
@@ -376,6 +382,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 static void suspend_finish(void)
 {
 	suspend_thaw_processes();
+	usermodehelper_enable();
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
 }
diff --git a/kernel/power/user.c b/kernel/power/user.c
index a6332a313262..005b93d839ba 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -212,13 +212,20 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 	case SNAPSHOT_FREEZE:
 		if (data->frozen)
 			break;
+
 		printk("Syncing filesystems ... ");
 		sys_sync();
 		printk("done.\n");
 
-		error = freeze_processes();
+		error = usermodehelper_disable();
 		if (error)
+			break;
+
+		error = freeze_processes();
+		if (error) {
 			thaw_processes();
+			usermodehelper_enable();
+		}
 		if (!error)
 			data->frozen = 1;
 		break;
@@ -227,6 +234,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		if (!data->frozen || data->ready)
 			break;
 		thaw_processes();
+		usermodehelper_enable();
 		data->frozen = 0;
 		break;
 
diff --git a/kernel/printk.c b/kernel/printk.c
index a430fd04008b..6341af77eb65 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -13,7 +13,7 @@
  * Fixed SMP synchronization, 08/08/99, Manfred Spraul
  *     manfred@colorfullife.com
  * Rewrote bits to get rid of console_lock
- *	01Mar01 Andrew Morton <andrewm@uow.edu.au>
+ *	01Mar01 Andrew Morton
  */
 
 #include <linux/kernel.h>
@@ -577,9 +577,6 @@ static int have_callable_console(void)
  * @fmt: format string
  *
  * This is printk().  It can be called from any context.  We want it to work.
- * Be aware of the fact that if oops_in_progress is not set, we might try to
- * wake klogd up which could deadlock on runqueue lock if printk() is called
- * from scheduler code.
  *
  * We try to grab the console_sem.  If we succeed, it's easy - we log the output and
  * call the console drivers.  If we fail to get the semaphore we place the output
@@ -593,6 +590,8 @@ static int have_callable_console(void)
  *
  * See also:
  * printf(3)
+ *
+ * See the vsnprintf() documentation for format string extensions over C99.
  */
 
 asmlinkage int printk(const char *fmt, ...)
@@ -982,10 +981,25 @@ int is_console_locked(void)
 	return console_locked;
 }
 
-void wake_up_klogd(void)
+static DEFINE_PER_CPU(int, printk_pending);
+
+void printk_tick(void)
 {
-	if (!oops_in_progress && waitqueue_active(&log_wait))
+	if (__get_cpu_var(printk_pending)) {
+		__get_cpu_var(printk_pending) = 0;
 		wake_up_interruptible(&log_wait);
+	}
+}
+
+int printk_needs_cpu(int cpu)
+{
+	return per_cpu(printk_pending, cpu);
+}
+
+void wake_up_klogd(void)
+{
+	if (waitqueue_active(&log_wait))
+		__raw_get_cpu_var(printk_pending) = 1;
 }
 
 /**
diff --git a/kernel/profile.c b/kernel/profile.c
index cd26bed4cc26..a9e422df6bf6 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -22,6 +22,8 @@
 #include <linux/cpu.h>
 #include <linux/highmem.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm/sections.h>
 #include <asm/irq_regs.h>
 #include <asm/ptrace.h>
@@ -50,11 +52,11 @@ static DEFINE_PER_CPU(int, cpu_profile_flip);
 static DEFINE_MUTEX(profile_flip_mutex);
 #endif /* CONFIG_SMP */
 
-static int __init profile_setup(char *str)
+int profile_setup(char *str)
 {
-	static char __initdata schedstr[] = "schedule";
-	static char __initdata sleepstr[] = "sleep";
-	static char __initdata kvmstr[] = "kvm";
+	static char schedstr[] = "schedule";
+	static char sleepstr[] = "sleep";
+	static char kvmstr[] = "kvm";
 	int par;
 
 	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
@@ -100,14 +102,33 @@ static int __init profile_setup(char *str)
 __setup("profile=", profile_setup);
 
 
-void __init profile_init(void)
+int profile_init(void)
 {
+	int buffer_bytes;
 	if (!prof_on)
-		return;
+		return 0;
 
 	/* only text is profiled */
 	prof_len = (_etext - _stext) >> prof_shift;
-	prof_buffer = alloc_bootmem(prof_len*sizeof(atomic_t));
+	buffer_bytes = prof_len*sizeof(atomic_t);
+	if (!slab_is_available()) {
+		prof_buffer = alloc_bootmem(buffer_bytes);
+		return 0;
+	}
+
+	prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
+	if (prof_buffer)
+		return 0;
+
+	prof_buffer = alloc_pages_exact(buffer_bytes, GFP_KERNEL|__GFP_ZERO);
+	if (prof_buffer)
+		return 0;
+
+	prof_buffer = vmalloc(buffer_bytes);
+	if (prof_buffer)
+		return 0;
+
+	return -ENOMEM;
 }
 
 /* Profile event notifications */
@@ -527,7 +548,7 @@ static void __init profile_nop(void *unused)
 {
 }
 
-static int __init create_hash_tables(void)
+static int create_hash_tables(void)
 {
 	int cpu;
 
@@ -575,14 +596,14 @@ out_cleanup:
 #define create_hash_tables()			({ 0; })
 #endif
 
-static int __init create_proc_profile(void)
+int create_proc_profile(void)
 {
 	struct proc_dir_entry *entry;
 
 	if (!prof_on)
 		return 0;
 	if (create_hash_tables())
-		return -1;
+		return -ENOMEM;
 	entry = proc_create("profile", S_IWUSR | S_IRUGO,
 			    NULL, &proc_profile_operations);
 	if (!entry)
diff --git a/kernel/resource.c b/kernel/resource.c
index 414d6fc9131e..4089d12af6e0 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -38,10 +38,6 @@ EXPORT_SYMBOL(iomem_resource);
 
 static DEFINE_RWLOCK(resource_lock);
 
-#ifdef CONFIG_PROC_FS
-
-enum { MAX_IORES_LEVEL = 5 };
-
 static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct resource *p = v;
@@ -53,6 +49,10 @@ static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 	return p->sibling;
 }
 
+#ifdef CONFIG_PROC_FS
+
+enum { MAX_IORES_LEVEL = 5 };
+
 static void *r_start(struct seq_file *m, loff_t *pos)
 	__acquires(resource_lock)
 {
@@ -549,13 +549,9 @@ static void __init __reserve_region_with_split(struct resource *root,
 	}
 
 	if (!res) {
-		printk(KERN_DEBUG "    __reserve_region_with_split: (%s) [%llx, %llx], res: (%s) [%llx, %llx]\n",
-			 conflict->name, conflict->start, conflict->end,
-			 name, start, end);
-
 		/* failed, split and try again */
 
-		/* conflict coverred whole area */
+		/* conflict covered whole area */
 		if (conflict->start <= start && conflict->end >= end)
 			return;
 
@@ -630,33 +626,34 @@ struct resource * __request_region(struct resource *parent,
 {
 	struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL);
 
-	if (res) {
-		res->name = name;
-		res->start = start;
-		res->end = start + n - 1;
-		res->flags = IORESOURCE_BUSY;
+	if (!res)
+		return NULL;
 
-		write_lock(&resource_lock);
+	res->name = name;
+	res->start = start;
+	res->end = start + n - 1;
+	res->flags = IORESOURCE_BUSY;
 
-		for (;;) {
-			struct resource *conflict;
+	write_lock(&resource_lock);
 
-			conflict = __request_resource(parent, res);
-			if (!conflict)
-				break;
-			if (conflict != parent) {
-				parent = conflict;
-				if (!(conflict->flags & IORESOURCE_BUSY))
-					continue;
-			}
+	for (;;) {
+		struct resource *conflict;
 
-			/* Uhhuh, that didn't work out.. */
-			kfree(res);
-			res = NULL;
+		conflict = __request_resource(parent, res);
+		if (!conflict)
 			break;
+		if (conflict != parent) {
+			parent = conflict;
+			if (!(conflict->flags & IORESOURCE_BUSY))
+				continue;
 		}
-		write_unlock(&resource_lock);
+
+		/* Uhhuh, that didn't work out.. */
+		kfree(res);
+		res = NULL;
+		break;
 	}
+	write_unlock(&resource_lock);
 	return res;
 }
 EXPORT_SYMBOL(__request_region);
@@ -831,3 +828,40 @@ static int __init reserve_setup(char *str)
 }
 
 __setup("reserve=", reserve_setup);
+
+/*
+ * Check if the requested addr and size spans more than any slot in the
+ * iomem resource tree.
+ */
+int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
+{
+	struct resource *p = &iomem_resource;
+	int err = 0;
+	loff_t l;
+
+	read_lock(&resource_lock);
+	for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+		/*
+		 * We can probably skip the resources without
+		 * IORESOURCE_IO attribute?
+		 */
+		if (p->start >= addr + size)
+			continue;
+		if (p->end < addr)
+			continue;
+		if (p->start <= addr && (p->end >= addr + size - 1))
+			continue;
+		printk(KERN_WARNING "resource map sanity check conflict: "
+		       "0x%llx 0x%llx 0x%llx 0x%llx %s\n",
+		       (unsigned long long)addr,
+		       (unsigned long long)(addr + size - 1),
+		       (unsigned long long)p->start,
+		       (unsigned long long)p->end,
+		       p->name);
+		err = -1;
+		break;
+	}
+	read_unlock(&resource_lock);
+
+	return err;
+}
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index e8ab096ddfe3..81787248b60f 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -118,13 +118,13 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
 
 	/*
 	 * scd->clock = clamp(scd->tick_gtod + delta,
-	 * 		      max(scd->tick_gtod, scd->clock),
-	 * 		      scd->tick_gtod + TICK_NSEC);
+	 *		      max(scd->tick_gtod, scd->clock),
+	 *		      max(scd->clock, scd->tick_gtod + TICK_NSEC));
 	 */
 
 	clock = scd->tick_gtod + delta;
 	min_clock = wrap_max(scd->tick_gtod, scd->clock);
-	max_clock = scd->tick_gtod + TICK_NSEC;
+	max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC);
 
 	clock = wrap_max(clock, min_clock);
 	clock = wrap_min(clock, max_clock);
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index bbe6b31c3c56..ad958c1ec708 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -333,12 +333,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	unsigned long flags;
 	int num_threads = 1;
 
-	rcu_read_lock();
 	if (lock_task_sighand(p, &flags)) {
 		num_threads = atomic_read(&p->signal->count);
 		unlock_task_sighand(p, &flags);
 	}
-	rcu_read_unlock();
 
 	SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, p->pid, num_threads);
 	SEQ_printf(m,
diff --git a/kernel/softirq.c b/kernel/softirq.c
index c506f266a6b9..83ba21a13bd4 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -6,6 +6,8 @@
  *	Distribute under GPLv2.
  *
  *	Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
+ *
+ *	Remote softirq infrastructure is by Jens Axboe.
  */
 
 #include <linux/module.h>
@@ -46,7 +48,7 @@ irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
 EXPORT_SYMBOL(irq_stat);
 #endif
 
-static struct softirq_action softirq_vec[32] __cacheline_aligned_in_smp;
+static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
 
 static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
@@ -205,7 +207,18 @@ restart:
 
 	do {
 		if (pending & 1) {
+			int prev_count = preempt_count();
+
 			h->action(h);
+
+			if (unlikely(prev_count != preempt_count())) {
+				printk(KERN_ERR "huh, entered softirq %td %p"
+				       "with preempt_count %08x,"
+				       " exited with %08x?\n", h - softirq_vec,
+				       h->action, prev_count, preempt_count());
+				preempt_count() = prev_count;
+			}
+
 			rcu_bh_qsctr_inc(cpu);
 		}
 		h++;
@@ -463,17 +476,144 @@ void tasklet_kill(struct tasklet_struct *t)
 
 EXPORT_SYMBOL(tasklet_kill);
 
+DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
+EXPORT_PER_CPU_SYMBOL(softirq_work_list);
+
+static void __local_trigger(struct call_single_data *cp, int softirq)
+{
+	struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]);
+
+	list_add_tail(&cp->list, head);
+
+	/* Trigger the softirq only if the list was previously empty.  */
+	if (head->next == &cp->list)
+		raise_softirq_irqoff(softirq);
+}
+
+#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
+static void remote_softirq_receive(void *data)
+{
+	struct call_single_data *cp = data;
+	unsigned long flags;
+	int softirq;
+
+	softirq = cp->priv;
+
+	local_irq_save(flags);
+	__local_trigger(cp, softirq);
+	local_irq_restore(flags);
+}
+
+static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
+{
+	if (cpu_online(cpu)) {
+		cp->func = remote_softirq_receive;
+		cp->info = cp;
+		cp->flags = 0;
+		cp->priv = softirq;
+
+		__smp_call_function_single(cpu, cp);
+		return 0;
+	}
+	return 1;
+}
+#else /* CONFIG_USE_GENERIC_SMP_HELPERS */
+static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
+{
+	return 1;
+}
+#endif
+
+/**
+ * __send_remote_softirq - try to schedule softirq work on a remote cpu
+ * @cp: private SMP call function data area
+ * @cpu: the remote cpu
+ * @this_cpu: the currently executing cpu
+ * @softirq: the softirq for the work
+ *
+ * Attempt to schedule softirq work on a remote cpu.  If this cannot be
+ * done, the work is instead queued up on the local cpu.
+ *
+ * Interrupts must be disabled.
+ */
+void __send_remote_softirq(struct call_single_data *cp, int cpu, int this_cpu, int softirq)
+{
+	if (cpu == this_cpu || __try_remote_softirq(cp, cpu, softirq))
+		__local_trigger(cp, softirq);
+}
+EXPORT_SYMBOL(__send_remote_softirq);
+
+/**
+ * send_remote_softirq - try to schedule softirq work on a remote cpu
+ * @cp: private SMP call function data area
+ * @cpu: the remote cpu
+ * @softirq: the softirq for the work
+ *
+ * Like __send_remote_softirq except that disabling interrupts and
+ * computing the current cpu is done for the caller.
+ */
+void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
+{
+	unsigned long flags;
+	int this_cpu;
+
+	local_irq_save(flags);
+	this_cpu = smp_processor_id();
+	__send_remote_softirq(cp, cpu, this_cpu, softirq);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(send_remote_softirq);
+
+static int __cpuinit remote_softirq_cpu_notify(struct notifier_block *self,
+					       unsigned long action, void *hcpu)
+{
+	/*
+	 * If a CPU goes away, splice its entries to the current CPU
+	 * and trigger a run of the softirq
+	 */
+	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+		int cpu = (unsigned long) hcpu;
+		int i;
+
+		local_irq_disable();
+		for (i = 0; i < NR_SOFTIRQS; i++) {
+			struct list_head *head = &per_cpu(softirq_work_list[i], cpu);
+			struct list_head *local_head;
+
+			if (list_empty(head))
+				continue;
+
+			local_head = &__get_cpu_var(softirq_work_list[i]);
+			list_splice_init(head, local_head);
+			raise_softirq_irqoff(i);
+		}
+		local_irq_enable();
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata remote_softirq_cpu_notifier = {
+	.notifier_call	= remote_softirq_cpu_notify,
+};
+
 void __init softirq_init(void)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
+		int i;
+
 		per_cpu(tasklet_vec, cpu).tail =
 			&per_cpu(tasklet_vec, cpu).head;
 		per_cpu(tasklet_hi_vec, cpu).tail =
 			&per_cpu(tasklet_hi_vec, cpu).head;
+		for (i = 0; i < NR_SOFTIRQS; i++)
+			INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
 	}
 
+	register_hotcpu_notifier(&remote_softirq_cpu_notifier);
+
 	open_softirq(TASKLET_SOFTIRQ, tasklet_action);
 	open_softirq(HI_SOFTIRQ, tasklet_hi_action);
 }
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index cb838ee93a82..3953e4aed733 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -226,7 +226,7 @@ static void check_hung_uninterruptible_tasks(int this_cpu)
 	 * If the system crashed already then all bets are off,
 	 * do not report extra hung tasks:
 	 */
-	if ((tainted & TAINT_DIE) || did_panic)
+	if (test_taint(TAINT_DIE) || did_panic)
 		return;
 
 	read_lock(&tasklist_lock);
diff --git a/kernel/sys.c b/kernel/sys.c
index 234d9454294e..0bc8fa3c2288 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1349,8 +1349,10 @@ asmlinkage long sys_sethostname(char __user *name, int len)
 	down_write(&uts_sem);
 	errno = -EFAULT;
 	if (!copy_from_user(tmp, name, len)) {
-		memcpy(utsname()->nodename, tmp, len);
-		utsname()->nodename[len] = 0;
+		struct new_utsname *u = utsname();
+
+		memcpy(u->nodename, tmp, len);
+		memset(u->nodename + len, 0, sizeof(u->nodename) - len);
 		errno = 0;
 	}
 	up_write(&uts_sem);
@@ -1362,15 +1364,17 @@ asmlinkage long sys_sethostname(char __user *name, int len)
 asmlinkage long sys_gethostname(char __user *name, int len)
 {
 	int i, errno;
+	struct new_utsname *u;
 
 	if (len < 0)
 		return -EINVAL;
 	down_read(&uts_sem);
-	i = 1 + strlen(utsname()->nodename);
+	u = utsname();
+	i = 1 + strlen(u->nodename);
 	if (i > len)
 		i = len;
 	errno = 0;
-	if (copy_to_user(name, utsname()->nodename, i))
+	if (copy_to_user(name, u->nodename, i))
 		errno = -EFAULT;
 	up_read(&uts_sem);
 	return errno;
@@ -1395,8 +1399,10 @@ asmlinkage long sys_setdomainname(char __user *name, int len)
 	down_write(&uts_sem);
 	errno = -EFAULT;
 	if (!copy_from_user(tmp, name, len)) {
-		memcpy(utsname()->domainname, tmp, len);
-		utsname()->domainname[len] = 0;
+		struct new_utsname *u = utsname();
+
+		memcpy(u->domainname, tmp, len);
+		memset(u->domainname + len, 0, sizeof(u->domainname) - len);
 		errno = 0;
 	}
 	up_write(&uts_sem);
@@ -1450,14 +1456,22 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
 		return -EINVAL;
 	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
 		return -EFAULT;
-	if (new_rlim.rlim_cur > new_rlim.rlim_max)
-		return -EINVAL;
 	old_rlim = current->signal->rlim + resource;
 	if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
 	    !capable(CAP_SYS_RESOURCE))
 		return -EPERM;
-	if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
-		return -EPERM;
+
+	if (resource == RLIMIT_NOFILE) {
+		if (new_rlim.rlim_max == RLIM_INFINITY)
+			new_rlim.rlim_max = sysctl_nr_open;
+		if (new_rlim.rlim_cur == RLIM_INFINITY)
+			new_rlim.rlim_cur = sysctl_nr_open;
+		if (new_rlim.rlim_max > sysctl_nr_open)
+			return -EPERM;
+	}
+
+	if (new_rlim.rlim_cur > new_rlim.rlim_max)
+		return -EINVAL;
 
 	retval = security_task_setrlimit(resource, &new_rlim);
 	if (retval)
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 08d6e1bb99ac..a77b27b11b04 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -125,6 +125,12 @@ cond_syscall(sys_vm86old);
 cond_syscall(sys_vm86);
 cond_syscall(compat_sys_ipc);
 cond_syscall(compat_sys_sysctl);
+cond_syscall(sys_flock);
+cond_syscall(sys_io_setup);
+cond_syscall(sys_io_destroy);
+cond_syscall(sys_io_submit);
+cond_syscall(sys_io_cancel);
+cond_syscall(sys_io_getevents);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 1bf369bd4423..617d41e4d6a0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -80,7 +80,6 @@ extern int pid_max_min, pid_max_max;
 extern int sysctl_drop_caches;
 extern int percpu_pagelist_fraction;
 extern int compat_log;
-extern int maps_protect;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
 #ifdef CONFIG_RCU_TORTURE_TEST
@@ -97,7 +96,7 @@ static int sixty = 60;
 static int neg_one = -1;
 #endif
 
-#ifdef CONFIG_MMU
+#if defined(CONFIG_MMU) && defined(CONFIG_FILE_LOCKING)
 static int two = 2;
 #endif
 
@@ -150,7 +149,7 @@ extern int max_lock_depth;
 #ifdef CONFIG_PROC_SYSCTL
 static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);
-static int proc_dointvec_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write, struct file *filp,
 			       void __user *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
@@ -380,10 +379,9 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_PROC_SYSCTL
 	{
 		.procname	= "tainted",
-		.data		= &tainted,
-		.maxlen		= sizeof(int),
+		.maxlen 	= sizeof(long),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_taint,
+		.proc_handler	= &proc_taint,
 	},
 #endif
 #ifdef CONFIG_LATENCYTOP
@@ -808,16 +806,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_PROC_FS
-	{
-		.ctl_name       = CTL_UNNUMBERED,
-		.procname       = "maps_protect",
-		.data           = &maps_protect,
-		.maxlen         = sizeof(int),
-		.mode           = 0644,
-		.proc_handler   = &proc_dointvec,
-	},
-#endif
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "poweroff_cmd",
@@ -1259,6 +1247,7 @@ static struct ctl_table fs_table[] = {
 		.extra1		= &minolduid,
 		.extra2		= &maxolduid,
 	},
+#ifdef CONFIG_FILE_LOCKING
 	{
 		.ctl_name	= FS_LEASES,
 		.procname	= "leases-enable",
@@ -1267,6 +1256,7 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+#endif
 #ifdef CONFIG_DNOTIFY
 	{
 		.ctl_name	= FS_DIR_NOTIFY,
@@ -1278,6 +1268,7 @@ static struct ctl_table fs_table[] = {
 	},
 #endif
 #ifdef CONFIG_MMU
+#ifdef CONFIG_FILE_LOCKING
 	{
 		.ctl_name	= FS_LEASE_TIME,
 		.procname	= "lease-break-time",
@@ -1289,6 +1280,8 @@ static struct ctl_table fs_table[] = {
 		.extra1		= &zero,
 		.extra2		= &two,
 	},
+#endif
+#ifdef CONFIG_AIO
 	{
 		.procname	= "aio-nr",
 		.data		= &aio_nr,
@@ -1303,6 +1296,7 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_doulongvec_minmax,
 	},
+#endif /* CONFIG_AIO */
 #ifdef CONFIG_INOTIFY_USER
 	{
 		.ctl_name	= FS_INOTIFY,
@@ -1508,7 +1502,6 @@ void register_sysctl_root(struct ctl_table_root *root)
 /* Perform the actual read/write of a sysctl table entry. */
 static int do_sysctl_strategy(struct ctl_table_root *root,
 			struct ctl_table *table,
-			int __user *name, int nlen,
 			void __user *oldval, size_t __user *oldlenp,
 			void __user *newval, size_t newlen)
 {
@@ -1522,8 +1515,7 @@ static int do_sysctl_strategy(struct ctl_table_root *root,
 		return -EPERM;
 
 	if (table->strategy) {
-		rc = table->strategy(table, name, nlen, oldval, oldlenp,
-				     newval, newlen);
+		rc = table->strategy(table, oldval, oldlenp, newval, newlen);
 		if (rc < 0)
 			return rc;
 		if (rc > 0)
@@ -1533,8 +1525,7 @@ static int do_sysctl_strategy(struct ctl_table_root *root,
 	/* If there is no strategy routine, or if the strategy returns
 	 * zero, proceed with automatic r/w */
 	if (table->data && table->maxlen) {
-		rc = sysctl_data(table, name, nlen, oldval, oldlenp,
-				 newval, newlen);
+		rc = sysctl_data(table, oldval, oldlenp, newval, newlen);
 		if (rc < 0)
 			return rc;
 	}
@@ -1566,7 +1557,7 @@ repeat:
 				table = table->child;
 				goto repeat;
 			}
-			error = do_sysctl_strategy(root, table, name, nlen,
+			error = do_sysctl_strategy(root, table,
 						   oldval, oldlenp,
 						   newval, newlen);
 			return error;
@@ -2235,49 +2226,39 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
 		    	    NULL,NULL);
 }
 
-#define OP_SET	0
-#define OP_AND	1
-#define OP_OR	2
-
-static int do_proc_dointvec_bset_conv(int *negp, unsigned long *lvalp,
-				      int *valp,
-				      int write, void *data)
-{
-	int op = *(int *)data;
-	if (write) {
-		int val = *negp ? -*lvalp : *lvalp;
-		switch(op) {
-		case OP_SET:	*valp = val; break;
-		case OP_AND:	*valp &= val; break;
-		case OP_OR:	*valp |= val; break;
-		}
-	} else {
-		int val = *valp;
-		if (val < 0) {
-			*negp = -1;
-			*lvalp = (unsigned long)-val;
-		} else {
-			*negp = 0;
-			*lvalp = (unsigned long)val;
-		}
-	}
-	return 0;
-}
-
 /*
- *	Taint values can only be increased
+ * Taint values can only be increased
+ * This means we can safely use a temporary.
  */
-static int proc_dointvec_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write, struct file *filp,
 			       void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int op;
+	struct ctl_table t;
+	unsigned long tmptaint = get_taint();
+	int err;
 
 	if (write && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	op = OP_OR;
-	return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
-				do_proc_dointvec_bset_conv,&op);
+	t = *table;
+	t.data = &tmptaint;
+	err = proc_doulongvec_minmax(&t, write, filp, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+
+	if (write) {
+		/*
+		 * Poor man's atomic or. Not worth adding a primitive
+		 * to everyone's atomic.h for this
+		 */
+		int i;
+		for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) {
+			if ((tmptaint >> i) & 1)
+				add_taint(i);
+		}
+	}
+
+	return err;
 }
 
 struct do_proc_dointvec_minmax_conv_param {
@@ -2725,7 +2706,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
  */
 
 /* The generic sysctl data routine (used if no strategy routine supplied) */
-int sysctl_data(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_data(struct ctl_table *table,
 		void __user *oldval, size_t __user *oldlenp,
 		void __user *newval, size_t newlen)
 {
@@ -2759,7 +2740,7 @@ int sysctl_data(struct ctl_table *table, int __user *name, int nlen,
 }
 
 /* The generic string strategy routine: */
-int sysctl_string(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_string(struct ctl_table *table,
 		  void __user *oldval, size_t __user *oldlenp,
 		  void __user *newval, size_t newlen)
 {
@@ -2805,7 +2786,7 @@ int sysctl_string(struct ctl_table *table, int __user *name, int nlen,
  * are between the minimum and maximum values given in the arrays
  * table->extra1 and table->extra2, respectively.
  */
-int sysctl_intvec(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_intvec(struct ctl_table *table,
 		void __user *oldval, size_t __user *oldlenp,
 		void __user *newval, size_t newlen)
 {
@@ -2841,7 +2822,7 @@ int sysctl_intvec(struct ctl_table *table, int __user *name, int nlen,
 }
 
 /* Strategy function to convert jiffies to seconds */ 
-int sysctl_jiffies(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_jiffies(struct ctl_table *table,
 		void __user *oldval, size_t __user *oldlenp,
 		void __user *newval, size_t newlen)
 {
@@ -2875,7 +2856,7 @@ int sysctl_jiffies(struct ctl_table *table, int __user *name, int nlen,
 }
 
 /* Strategy function to convert jiffies to seconds */ 
-int sysctl_ms_jiffies(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_ms_jiffies(struct ctl_table *table,
 		void __user *oldval, size_t __user *oldlenp,
 		void __user *newval, size_t newlen)
 {
@@ -2930,35 +2911,35 @@ asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
 	return error;
 }
 
-int sysctl_data(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_data(struct ctl_table *table,
 		  void __user *oldval, size_t __user *oldlenp,
 		  void __user *newval, size_t newlen)
 {
 	return -ENOSYS;
 }
 
-int sysctl_string(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_string(struct ctl_table *table,
 		  void __user *oldval, size_t __user *oldlenp,
 		  void __user *newval, size_t newlen)
 {
 	return -ENOSYS;
 }
 
-int sysctl_intvec(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_intvec(struct ctl_table *table,
 		void __user *oldval, size_t __user *oldlenp,
 		void __user *newval, size_t newlen)
 {
 	return -ENOSYS;
 }
 
-int sysctl_jiffies(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_jiffies(struct ctl_table *table,
 		void __user *oldval, size_t __user *oldlenp,
 		void __user *newval, size_t newlen)
 {
 	return -ENOSYS;
 }
 
-int sysctl_ms_jiffies(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_ms_jiffies(struct ctl_table *table,
 		void __user *oldval, size_t __user *oldlenp,
 		void __user *newval, size_t newlen)
 {
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 8d53106a0a92..95ed42951e0a 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -3,7 +3,6 @@
 #
 config TICK_ONESHOT
 	bool
-	default n
 
 config NO_HZ
 	bool "Tickless System (Dynamic Ticks)"
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a4d219398167..b711ffcb106c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -270,7 +270,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 	next_jiffies = get_next_timer_interrupt(last_jiffies);
 	delta_jiffies = next_jiffies - last_jiffies;
 
-	if (rcu_needs_cpu(cpu))
+	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu))
 		delta_jiffies = 1;
 	/*
 	 * Do not stop the tick, if we are only one off
diff --git a/kernel/timer.c b/kernel/timer.c
index 03bc7f1f1593..510fe69351ca 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -978,6 +978,7 @@ void update_process_times(int user_tick)
 	run_local_timers();
 	if (rcu_pending(cpu))
 		rcu_check_callbacks(cpu, user_tick);
+	printk_tick();
 	scheduler_tick();
 	run_posix_cpu_timers(p);
 }
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 4ab9659d269e..3b34b3545936 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -60,7 +60,7 @@ static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
 
 #ifdef CONFIG_SYSCTL_SYSCALL
 /* The generic string strategy routine: */
-static int sysctl_uts_string(ctl_table *table, int __user *name, int nlen,
+static int sysctl_uts_string(ctl_table *table,
 		  void __user *oldval, size_t __user *oldlenp,
 		  void __user *newval, size_t newlen)
 {
@@ -69,8 +69,7 @@ static int sysctl_uts_string(ctl_table *table, int __user *name, int nlen,
 	write = newval && newlen;
 	memcpy(&uts_table, table, sizeof(uts_table));
 	uts_table.data = get_uts(table, write);
-	r = sysctl_string(&uts_table, name, nlen,
-		oldval, oldlenp, newval, newlen);
+	r = sysctl_string(&uts_table, oldval, oldlenp, newval, newlen);
 	put_uts(table, write, uts_table.data);
 	return r;
 }
diff --git a/kernel/wait.c b/kernel/wait.c
index c275c56cf2d3..cd87131f2fc2 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -72,12 +72,7 @@ prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
 	spin_lock_irqsave(&q->lock, flags);
 	if (list_empty(&wait->task_list))
 		__add_wait_queue(q, wait);
-	/*
-	 * don't alter the task state if this is just going to
-	 * queue an async wait queue callback
-	 */
-	if (is_sync_wait(wait))
-		set_current_state(state);
+	set_current_state(state);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(prepare_to_wait);
@@ -91,12 +86,7 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
 	spin_lock_irqsave(&q->lock, flags);
 	if (list_empty(&wait->task_list))
 		__add_wait_queue_tail(q, wait);
-	/*
-	 * don't alter the task state if this is just going to
- 	 * queue an async wait queue callback
-	 */
-	if (is_sync_wait(wait))
-		set_current_state(state);
+	set_current_state(state);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4048e92aa04f..714afad46539 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -9,7 +9,7 @@
  * Derived from the taskqueue/keventd code by:
  *
  *   David Woodhouse <dwmw2@infradead.org>
- *   Andrew Morton <andrewm@uow.edu.au>
+ *   Andrew Morton
  *   Kai Petzke <wpp@marie.physik.tu-berlin.de>
  *   Theodore Ts'o <tytso@mit.edu>
  *