Merge branch 'akpm-current/current'

Conflicts:
	fs/fs-writeback.c

22 files changed, 174 insertions, 139 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index e2dbb60004d4..3d54c418bd06 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -996,7 +996,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	task_lock(tsk);
 	/*
 	 * Determine if a loop is necessary if another thread is doing
-	 * get_mems_allowed().  If at least one node remains unchanged and
+	 * read_mems_allowed_begin().  If at least one node remains unchanged and
 	 * tsk does not have a mempolicy, then an empty nodemask will not be
 	 * possible when mems_allowed is larger than a word.
 	 */
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 99982a70ddad..2956c8da1605 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -49,6 +49,7 @@
 #include <linux/pid.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/rcupdate.h>
 
 #include <asm/cacheflush.h>
@@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
 	if (!CACHE_FLUSH_IS_SAFE)
 		return;
 
-	if (current->mm && current->mm->mmap_cache) {
-		flush_cache_range(current->mm->mmap_cache,
-				  addr, addr + BREAK_INSTR_SIZE);
+	if (current->mm) {
+		int i;
+
+		for (i = 0; i < VMACACHE_SIZE; i++) {
+			if (!current->vmacache[i])
+				continue;
+			flush_cache_range(current->vmacache[i],
+					  addr, addr + BREAK_INSTR_SIZE);
+		}
 	}
+
 	/* Force flush instruction cache if it was outside the mm */
 	flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index 1e77fc645317..b4ada02fdc0f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -570,7 +570,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (same_thread_group(p->real_parent, father))
 		return;
 
-	/* We don't want people slaying init.  */
+	/* We don't want people slaying init. */
 	p->exit_signal = SIGCHLD;
 
 	/* If it has exited notify the new parent about this child's death. */
@@ -784,9 +784,10 @@ void do_exit(long code)
 	exit_shm(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
+	if (group_dead)
+		disassociate_ctty(1);
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
-	check_stack_usage();
 	exit_thread();
 
 	/*
@@ -799,19 +800,15 @@ void do_exit(long code)
 
 	cgroup_exit(tsk, 1);
 
-	if (group_dead)
-		disassociate_ctty(1);
-
 	module_put(task_thread_info(tsk)->exec_domain->module);
 
-	proc_exit_connector(tsk);
-
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
 	flush_ptrace_hw_breakpoint(tsk);
 
 	exit_notify(tsk, group_dead);
+	proc_exit_connector(tsk);
 #ifdef CONFIG_NUMA
 	task_lock(tsk);
 	mpol_put(tsk->mempolicy);
@@ -844,6 +841,7 @@ void do_exit(long code)
 
 	validate_creds_for_do_exit(tsk);
 
+	check_stack_usage();
 	preempt_disable();
 	if (tsk->nr_dirtied)
 		__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
@@ -1038,17 +1036,13 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		return wait_noreap_copyout(wo, p, pid, uid, why, status);
 	}
 
+	traced = ptrace_reparented(p);
 	/*
-	 * Try to move the task's state to DEAD
-	 * only one thread is allowed to do this:
+	 * Move the task's state to DEAD/TRACE, only one thread can do this.
 	 */
-	state = xchg(&p->exit_state, EXIT_DEAD);
-	if (state != EXIT_ZOMBIE) {
-		BUG_ON(state != EXIT_DEAD);
+	state = traced && thread_group_leader(p) ? EXIT_TRACE : EXIT_DEAD;
+	if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE)
 		return 0;
-	}
-
-	traced = ptrace_reparented(p);
 	/*
 	 * It can be ptraced but not reparented, check
 	 * thread_group_leader() to filter out sub-threads.
@@ -1109,7 +1103,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 
 	/*
 	 * Now we are sure this task is interesting, and no other
-	 * thread can reap it because we set its state to EXIT_DEAD.
+	 * thread can reap it because we its state == DEAD/TRACE.
 	 */
 	read_unlock(&tasklist_lock);
 
@@ -1146,22 +1140,19 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	if (!retval)
 		retval = pid;
 
-	if (traced) {
+	if (state == EXIT_TRACE) {
 		write_lock_irq(&tasklist_lock);
 		/* We dropped tasklist, ptracer could die and untrace */
 		ptrace_unlink(p);
-		/*
-		 * If this is not a sub-thread, notify the parent.
-		 * If parent wants a zombie, don't release it now.
-		 */
-		if (thread_group_leader(p) &&
-		    !do_notify_parent(p, p->exit_signal)) {
-			p->exit_state = EXIT_ZOMBIE;
-			p = NULL;
-		}
+
+		/* If parent wants a zombie, don't release it now */
+		state = EXIT_ZOMBIE;
+		if (do_notify_parent(p, p->exit_signal))
+			state = EXIT_DEAD;
+		p->exit_state = state;
 		write_unlock_irq(&tasklist_lock);
 	}
-	if (p != NULL)
+	if (state == EXIT_DEAD)
 		release_task(p);
 
 	return retval;
@@ -1338,7 +1329,12 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 static int wait_consider_task(struct wait_opts *wo, int ptrace,
 				struct task_struct *p)
 {
-	int ret = eligible_child(wo, p);
+	int ret;
+
+	if (unlikely(p->exit_state == EXIT_DEAD))
+		return 0;
+
+	ret = eligible_child(wo, p);
 	if (!ret)
 		return ret;
 
@@ -1356,33 +1352,44 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		return 0;
 	}
 
-	/* dead body doesn't have much to contribute */
-	if (unlikely(p->exit_state == EXIT_DEAD)) {
+	if (unlikely(p->exit_state == EXIT_TRACE)) {
 		/*
-		 * But do not ignore this task until the tracer does
-		 * wait_task_zombie()->do_notify_parent().
+		 * ptrace == 0 means we are the natural parent. In this case
+		 * we should clear notask_error, debugger will notify us.
 		 */
-		if (likely(!ptrace) && unlikely(ptrace_reparented(p)))
+		if (likely(!ptrace))
 			wo->notask_error = 0;
 		return 0;
 	}
 
-	/* slay zombie? */
-	if (p->exit_state == EXIT_ZOMBIE) {
+	if (likely(!ptrace) && unlikely(p->ptrace)) {
 		/*
-		 * A zombie ptracee is only visible to its ptracer.
-		 * Notification and reaping will be cascaded to the real
-		 * parent when the ptracer detaches.
+		 * If it is traced by its real parent's group, just pretend
+		 * the caller is ptrace_do_wait() and reap this child if it
+		 * is zombie.
+		 *
+		 * This also hides group stop state from real parent; otherwise
+		 * a single stop can be reported twice as group and ptrace stop.
+		 * If a ptracer wants to distinguish these two events for its
+		 * own children it should create a separate process which takes
+		 * the role of real parent.
 		 */
-		if (likely(!ptrace) && unlikely(p->ptrace)) {
-			/* it will become visible, clear notask_error */
-			wo->notask_error = 0;
-			return 0;
-		}
+		if (!ptrace_reparented(p))
+			ptrace = 1;
+	}
 
+	/* slay zombie? */
+	if (p->exit_state == EXIT_ZOMBIE) {
 		/* we don't reap group leaders with subthreads */
-		if (!delay_group_leader(p))
-			return wait_task_zombie(wo, p);
+		if (!delay_group_leader(p)) {
+			/*
+			 * A zombie ptracee is only visible to its ptracer.
+			 * Notification and reaping will be cascaded to the
+			 * real parent when the ptracer detaches.
+			 */
+			if (unlikely(ptrace) || likely(!p->ptrace))
+				return wait_task_zombie(wo, p);
+		}
 
 		/*
 		 * Allow access to stopped/continued state via zombie by
@@ -1408,19 +1415,6 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 			wo->notask_error = 0;
 	} else {
 		/*
-		 * If @p is ptraced by a task in its real parent's group,
-		 * hide group stop/continued state when looking at @p as
-		 * the real parent; otherwise, a single stop can be
-		 * reported twice as group and ptrace stops.
-		 *
-		 * If a ptracer wants to distinguish the two events for its
-		 * own children, it should create a separate process which
-		 * takes the role of real parent.
-		 */
-		if (likely(!ptrace) && p->ptrace && !ptrace_reparented(p))
-			return 0;
-
-		/*
 		 * @p is alive and it's gonna stop, continue or exit, so
 		 * there always is something to wait for.
 		 */
diff --git a/kernel/fork.c b/kernel/fork.c
index 332688e5e7b4..0b65a2b0c426 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -28,6 +28,8 @@
 #include <linux/mman.h>
 #include <linux/mmu_notifier.h>
 #include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
@@ -364,7 +366,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 
 	mm->locked_vm = 0;
 	mm->mmap = NULL;
-	mm->mmap_cache = NULL;
+	mm->vmacache_seqnum = 0;
 	mm->map_count = 0;
 	cpumask_clear(mm_cpumask(mm));
 	mm->mm_rb = RB_ROOT;
@@ -530,8 +532,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	atomic_set(&mm->mm_count, 1);
 	init_rwsem(&mm->mmap_sem);
 	INIT_LIST_HEAD(&mm->mmlist);
-	mm->flags = (current->mm) ?
-		(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
 	mm->core_state = NULL;
 	atomic_long_set(&mm->nr_ptes, 0);
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
@@ -540,8 +540,15 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	mm_init_owner(mm, p);
 	clear_tlb_flush_pending(mm);
 
-	if (likely(!mm_alloc_pgd(mm))) {
+	if (current->mm) {
+		mm->flags = current->mm->flags & MMF_INIT_MASK;
+		mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
+	} else {
+		mm->flags = default_dump_filter;
 		mm->def_flags = 0;
+	}
+
+	if (likely(!mm_alloc_pgd(mm))) {
 		mmu_notifier_mm_init(mm);
 		return mm;
 	}
@@ -877,6 +884,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	if (!oldmm)
 		return 0;
 
+	/* initialize the new vmacache entries */
+	vmacache_flush(tsk);
+
 	if (clone_flags & CLONE_VM) {
 		atomic_inc(&oldmm->mm_users);
 		mm = oldmm;
@@ -1070,15 +1080,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	return 0;
 }
 
-static void copy_flags(unsigned long clone_flags, struct task_struct *p)
-{
-	unsigned long new_flags = p->flags;
-
-	new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
-	new_flags |= PF_FORKNOEXEC;
-	p->flags = new_flags;
-}
-
 SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
 {
 	current->clear_child_tid = tidptr;
@@ -1228,7 +1229,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_count;
 
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
-	copy_flags(clone_flags, p);
+	p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
+	p->flags |= PF_FORKNOEXEC;
 	INIT_LIST_HEAD(&p->children);
 	INIT_LIST_HEAD(&p->sibling);
 	rcu_copy_process(p);
@@ -1274,7 +1276,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->mempolicy = NULL;
 		goto bad_fork_cleanup_cgroup;
 	}
-	mpol_fix_fork_child_flag(p);
 #endif
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
diff --git a/kernel/groups.c b/kernel/groups.c
index 90cf1c38c8ea..451698f86cfa 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -157,17 +157,13 @@ int groups_search(const struct group_info *group_info, kgid_t grp)
  * set_groups - Change a group subscription in a set of credentials
  * @new: The newly prepared set of credentials to alter
  * @group_info: The group list to install
- *
- * Validate a group subscription and, if valid, insert it into a set
- * of credentials.
  */
-int set_groups(struct cred *new, struct group_info *group_info)
+void set_groups(struct cred *new, struct group_info *group_info)
 {
 	put_group_info(new->group_info);
 	groups_sort(group_info);
 	get_group_info(group_info);
 	new->group_info = group_info;
-	return 0;
 }
 
 EXPORT_SYMBOL(set_groups);
@@ -182,18 +178,12 @@ EXPORT_SYMBOL(set_groups);
 int set_current_groups(struct group_info *group_info)
 {
 	struct cred *new;
-	int ret;
 
 	new = prepare_creds();
 	if (!new)
 		return -ENOMEM;
 
-	ret = set_groups(new, group_info);
-	if (ret < 0) {
-		abort_creds(new);
-		return ret;
-	}
-
+	set_groups(new, group_info);
 	return commit_creds(new);
 }
 
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 0b9c169d577f..06bb1417b063 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -246,5 +246,4 @@ static int __init hung_task_init(void)
 
 	return 0;
 }
-
-module_init(hung_task_init);
+subsys_initcall(hung_task_init);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 45601cf41bee..c0d261c7db7b 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1235,7 +1235,7 @@ static int __init crash_notes_memory_init(void)
 	}
 	return 0;
 }
-module_init(crash_notes_memory_init)
+subsys_initcall(crash_notes_memory_init);
 
 
 /*
@@ -1629,7 +1629,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	return 0;
 }
 
-module_init(crash_save_vmcoreinfo_init)
+subsys_initcall(crash_save_vmcoreinfo_init);
 
 /*
  * Move into place and start executing a preloaded standalone
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 6b375af4958d..55a36537fef4 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -40,6 +40,7 @@
 #include <linux/ptrace.h>
 #include <linux/async.h>
 #include <asm/uaccess.h>
+#include <linux/kthread.h>
 
 #include <trace/events/module.h>
 
@@ -209,8 +210,14 @@ static int ____call_usermodehelper(void *data)
 	flush_signal_handlers(current, 1);
 	spin_unlock_irq(&current->sighand->siglock);
 
-	/* We can run anywhere, unlike our parent keventd(). */
-	set_cpus_allowed_ptr(current, cpu_all_mask);
+	/*
+	 * Kthreadd can be restricted to a set of processors if the user wants
+	 * to protect other processors from OS latencies. If that has happened
+	 * then we do not want to disturb the other processors here either so we
+	 * start the usermode helper threads only on the processors allowed for
+	 * kthreadd.
+	 */
+	set_kthreadd_affinity();
 
 	/*
 	 * Our parent is keventd, which runs with elevated scheduling priority.
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b5ae3ee860a9..2c355bf2f094 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -136,6 +136,15 @@ void *kthread_data(struct task_struct *task)
 	return to_kthread(task)->data;
 }
 
+/*
+ * Set the affinity of the calling task to be the same
+ * as the kthreadd affinities.
+ */
+void set_kthreadd_affinity(void)
+{
+	set_cpus_allowed_ptr(current, &kthreadd_task->cpus_allowed);
+}
+
 /**
  * probe_kthread_data - speculative version of kthread_data()
  * @task: possible kthread task in question
@@ -217,7 +226,7 @@ int tsk_fork_get_node(struct task_struct *tsk)
 	if (tsk == kthreadd_task)
 		return tsk->pref_node_fork;
 #endif
-	return numa_node_id();
+	return NUMA_NO_NODE;
 }
 
 static void create_kthread(struct kthread_create_info *create)
@@ -369,7 +378,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 {
 	struct task_struct *p;
 
-	p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
+	p = kthread_create_on_node(threadfn, data, cpu_to_mem(cpu), namefmt,
 				   cpu);
 	if (IS_ERR(p))
 		return p;
diff --git a/kernel/panic.c b/kernel/panic.c
index 4b85f51e3570..cb007f37170a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -100,7 +100,7 @@ void panic(const char *fmt, ...)
 	va_start(args, fmt);
 	vsnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
-	printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
+	pr_emerg("Kernel panic - not syncing: %s\n", buf);
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 	/*
 	 * Avoid nested stack-dumping if a panic occurs during oops processing
@@ -141,7 +141,7 @@ void panic(const char *fmt, ...)
 		 * Delay timeout seconds before rebooting the machine.
 		 * We can't use the "normal" timers since we just panicked.
 		 */
-		printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout);
+		pr_emerg("Rebooting in %d seconds..", panic_timeout);
 
 		for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
 			touch_nmi_watchdog();
@@ -165,7 +165,7 @@ void panic(const char *fmt, ...)
 		extern int stop_a_enabled;
 		/* Make sure the user can actually press Stop-A (L1-A) */
 		stop_a_enabled = 1;
-		printk(KERN_EMERG "Press Stop-A (L1-A) to return to the boot prom\n");
+		pr_emerg("Press Stop-A (L1-A) to return to the boot prom\n");
 	}
 #endif
 #if defined(CONFIG_S390)
@@ -176,6 +176,7 @@ void panic(const char *fmt, ...)
 		disabled_wait(caller);
 	}
 #endif
+	pr_emerg("---[ end Kernel panic - not syncing: %s\n", buf);
 	local_irq_enable();
 	for (i = 0; ; i += PANIC_TIMER_STEP) {
 		touch_softlockup_watchdog();
@@ -276,8 +277,7 @@ unsigned long get_taint(void)
 void add_taint(unsigned flag, enum lockdep_ok lockdep_ok)
 {
 	if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off())
-		printk(KERN_WARNING
-		       "Disabling lock debugging due to kernel taint\n");
+		pr_warn("Disabling lock debugging due to kernel taint\n");
 
 	set_bit(flag, &tainted_mask);
 }
@@ -382,8 +382,7 @@ late_initcall(init_oops_id);
 void print_oops_end_marker(void)
 {
 	init_oops_id();
-	printk(KERN_WARNING "---[ end trace %016llx ]---\n",
-		(unsigned long long)oops_id);
+	pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);
 }
 
 /*
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 4dae9cbe9259..ff9faf4e3cd5 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -319,7 +319,7 @@ static void log_store(int facility, int level,
 		else
 			free = log_first_idx - log_next_idx;
 
-		if (free > size + sizeof(struct printk_log))
+		if (free >= size + sizeof(struct printk_log))
 			break;
 
 		/* drop old messages until we have enough contiuous space */
@@ -327,7 +327,7 @@ static void log_store(int facility, int level,
 		log_first_seq++;
 	}
 
-	if (log_next_idx + size + sizeof(struct printk_log) >= log_buf_len) {
+	if (log_next_idx + size + sizeof(struct printk_log) > log_buf_len) {
 		/*
 		 * This message + an additional empty header does not fit
 		 * at the end of the buffer. Add an empty header with len == 0
@@ -351,7 +351,7 @@ static void log_store(int facility, int level,
 	else
 		msg->ts_nsec = local_clock();
 	memset(log_dict(msg) + dict_len, 0, pad_len);
-	msg->len = sizeof(struct printk_log) + text_len + dict_len + pad_len;
+	msg->len = size;
 
 	/* insert message */
 	log_next_idx += msg->len;
@@ -1560,9 +1560,12 @@ asmlinkage int vprintk_emit(int facility, int level,
 					level = kern_level - '0';
 			case 'd':	/* KERN_DEFAULT */
 				lflags |= LOG_PREFIX;
-			case 'c':	/* KERN_CONT */
-				break;
 			}
+			/*
+			 * No need to check length here because vscnprintf
+			 * put '\0' at the end of the string. Only valid and
+			 * newly printed level is detected.
+			 */
 			text_len -= end_of_header - text;
 			text = (char *)end_of_header;
 		}
diff --git a/kernel/profile.c b/kernel/profile.c
index 93b2a3fe0a64..cb980f0c731b 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -614,5 +614,5 @@ out:
 	cpu_notifier_register_done();
 	return err;
 }
-module_init(create_proc_profile);
+subsys_initcall(create_proc_profile);
 #endif /* CONFIG_PROC_FS */
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 4aa8a305aede..51dbac6a3633 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -22,8 +22,18 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 	counter->parent = parent;
 }
 
-int res_counter_charge_locked(struct res_counter *counter, unsigned long val,
-			      bool force)
+static u64 res_counter_uncharge_locked(struct res_counter *counter,
+				       unsigned long val)
+{
+	if (WARN_ON(counter->usage < val))
+		val = counter->usage;
+
+	counter->usage -= val;
+	return counter->usage;
+}
+
+static int res_counter_charge_locked(struct res_counter *counter,
+				     unsigned long val, bool force)
 {
 	int ret = 0;
 
@@ -86,15 +96,6 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
 	return __res_counter_charge(counter, val, limit_fail_at, true);
 }
 
-u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
-{
-	if (WARN_ON(counter->usage < val))
-		val = counter->usage;
-
-	counter->usage -= val;
-	return counter->usage;
-}
-
 u64 res_counter_uncharge_until(struct res_counter *counter,
 			       struct res_counter *top,
 			       unsigned long val)
diff --git a/kernel/resource.c b/kernel/resource.c
index 673061c06da1..8957d686e29b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -511,7 +511,7 @@ static int find_resource(struct resource *root, struct resource *new,
  * @newsize: new size of the resource descriptor
  * @constraint: the size and alignment constraints to be met.
  */
-int reallocate_resource(struct resource *root, struct resource *old,
+static int reallocate_resource(struct resource *root, struct resource *old,
 			resource_size_t newsize,
 			struct resource_constraint  *constraint)
 {
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index da98af347e8b..a476bea17fbc 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -142,4 +142,4 @@ static int __init proc_schedstat_init(void)
 	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
 	return 0;
 }
-module_init(proc_schedstat_init);
+subsys_initcall(proc_schedstat_init);
diff --git a/kernel/sys.c b/kernel/sys.c
index adaeab6f7a87..fba0f29401ea 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1996,6 +1996,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
 		return current->no_new_privs ? 1 : 0;
+	case PR_GET_THP_DISABLE:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = !!(me->mm->def_flags & VM_NOHUGEPAGE);
+		break;
+	case PR_SET_THP_DISABLE:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		down_write(&me->mm->mmap_sem);
+		if (arg2)
+			me->mm->def_flags |= VM_NOHUGEPAGE;
+		else
+			me->mm->def_flags &= ~VM_NOHUGEPAGE;
+		up_write(&me->mm->mmap_sem);
+		break;
 	default:
 		error = -EINVAL;
 		break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 7078052284fd..bc8d1b74a6b9 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -146,11 +146,13 @@ cond_syscall(sys_io_destroy);
 cond_syscall(sys_io_submit);
 cond_syscall(sys_io_cancel);
 cond_syscall(sys_io_getevents);
+cond_syscall(sys_sysfs);
 cond_syscall(sys_syslog);
 cond_syscall(sys_process_vm_readv);
 cond_syscall(sys_process_vm_writev);
 cond_syscall(compat_sys_process_vm_readv);
 cond_syscall(compat_sys_process_vm_writev);
+cond_syscall(sys_uselib);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 09d2e2413605..5c14b547882e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -123,7 +123,7 @@ static int __maybe_unused neg_one = -1;
 static int zero;
 static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
-static int __maybe_unused three = 3;
+static int __maybe_unused four = 4;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
 #ifdef CONFIG_PRINTK
@@ -1264,7 +1264,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= drop_caches_sysctl_handler,
 		.extra1		= &one,
-		.extra2		= &three,
+		.extra2		= &four,
 	},
 #ifdef CONFIG_COMPACTION
 	{
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 4d23dc4d8139..5038b4d3b76d 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -154,6 +154,10 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
 	raw_write_seqcount_end(&cd.seq);
 
 	r = rate;
+	/*
+	 * Use 4MHz instead of 1MHz so that things like 1.832Mhz show as
+	 * 1832Khz
+	 */
 	if (r >= 4000000) {
 		r /= 1000000;
 		r_unit = 'M';
diff --git a/kernel/user.c b/kernel/user.c
index c006131beb77..294fc6a94168 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -222,5 +222,4 @@ static int __init uid_cache_init(void)
 
 	return 0;
 }
-
-module_init(uid_cache_init);
+subsys_initcall(uid_cache_init);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index dd06439b9c84..0d8f6023fd8d 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -902,4 +902,4 @@ static __init int user_namespaces_init(void)
 	user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC);
 	return 0;
 }
-module_init(user_namespaces_init);
+subsys_initcall(user_namespaces_init);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 01c6f979486f..18bc5c2a26df 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -158,14 +158,14 @@ void touch_all_softlockup_watchdogs(void)
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 void touch_nmi_watchdog(void)
 {
-	if (watchdog_user_enabled) {
-		unsigned cpu;
-
-		for_each_present_cpu(cpu) {
-			if (per_cpu(watchdog_nmi_touch, cpu) != true)
-				per_cpu(watchdog_nmi_touch, cpu) = true;
-		}
-	}
+	/*
+	 * Using __raw here because some code paths have
+	 * preemption enabled.  If preemption is enabled
+	 * then interrupts should be enabled too, in which
+	 * case we shouldn't have to worry about the watchdog
+	 * going off.
+	 */
+	__raw_get_cpu_var(watchdog_nmi_touch) = true;
 	touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL(touch_nmi_watchdog);
@@ -239,10 +239,12 @@ static void watchdog_overflow_callback(struct perf_event *event,
 		if (__this_cpu_read(hard_watchdog_warn) == true)
 			return;
 
-		if (hardlockup_panic)
+		if (hardlockup_panic) {
+			trigger_all_cpu_backtrace();
 			panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
-		else
+		} else {
 			WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+		}
 
 		__this_cpu_write(hard_watchdog_warn, true);
 		return;
@@ -323,8 +325,10 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		else
 			dump_stack();
 
-		if (softlockup_panic)
+		if (softlockup_panic) {
+			trigger_all_cpu_backtrace();
 			panic("softlockup: hung tasks");
+		}
 		__this_cpu_write(soft_watchdog_warn, true);
 	} else
 		__this_cpu_write(soft_watchdog_warn, false);