Merge branch 'akpm' (patches from Andrew)

Merge first patchbomb from Andrew Morton:

 - a few misc things

 - ocfs2 udpates

 - kernel/watchdog.c feature work (took ages to get right)

 - most of MM.  A few tricky bits are held up and probably won't make 4.2.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (91 commits)
  mm: kmemleak_alloc_percpu() should follow the gfp from per_alloc()
  mm, thp: respect MPOL_PREFERRED policy with non-local node
  tmpfs: truncate prealloc blocks past i_size
  mm/memory hotplug: print the last vmemmap region at the end of hot add memory
  mm/mmap.c: optimization of do_mmap_pgoff function
  mm: kmemleak: optimise kmemleak_lock acquiring during kmemleak_scan
  mm: kmemleak: avoid deadlock on the kmemleak object insertion error path
  mm: kmemleak: do not acquire scan_mutex in kmemleak_do_cleanup()
  mm: kmemleak: fix delete_object_*() race when called on the same memory block
  mm: kmemleak: allow safe memory scanning during kmemleak disabling
  memcg: convert mem_cgroup->under_oom from atomic_t to int
  memcg: remove unused mem_cgroup->oom_wakeups
  frontswap: allow multiple backends
  x86, mirror: x86 enabling - find mirrored memory ranges
  mm/memblock: allocate boot time data structures from mirrored memory
  mm/memblock: add extra "flags" to memblock to allow selection of memory based on attribute
  mm: do not ignore mapping_gfp_mask in page cache allocation paths
  mm/cma.c: fix typos in comments
  mm/oom_kill.c: print points as unsigned int
  mm/hugetlb: handle races in alloc_huge_page and hugetlb_reserve_pages
  ...

4 files changed, 129 insertions, 7 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 22fcc05dec40..185752a729f6 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -436,7 +436,7 @@ static void exit_mm(struct task_struct *tsk)
 	mm_update_next_owner(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))
-		unmark_oom_victim();
+		exit_oom_victim();
 }
 
 static struct task_struct *find_alive_thread(struct task_struct *p)
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index c697f73d82d6..7c434c39f02a 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -232,7 +232,8 @@ void smpboot_unpark_threads(unsigned int cpu)
 
 	mutex_lock(&smpboot_threads_lock);
 	list_for_each_entry(cur, &hotplug_threads, list)
-		smpboot_unpark_thread(cur, cpu);
+		if (cpumask_test_cpu(cpu, cur->cpumask))
+			smpboot_unpark_thread(cur, cpu);
 	mutex_unlock(&smpboot_threads_lock);
 }
 
@@ -258,6 +259,15 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
 {
 	unsigned int cpu;
 
+	/* Unpark any threads that were voluntarily parked. */
+	for_each_cpu_not(cpu, ht->cpumask) {
+		if (cpu_online(cpu)) {
+			struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+			if (tsk)
+				kthread_unpark(tsk);
+		}
+	}
+
 	/* We need to destroy also the parked threads of offline cpus */
 	for_each_possible_cpu(cpu) {
 		struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
@@ -281,6 +291,10 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	unsigned int cpu;
 	int ret = 0;
 
+	if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL))
+		return -ENOMEM;
+	cpumask_copy(plug_thread->cpumask, cpu_possible_mask);
+
 	get_online_cpus();
 	mutex_lock(&smpboot_threads_lock);
 	for_each_online_cpu(cpu) {
@@ -313,9 +327,53 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	smpboot_destroy_threads(plug_thread);
 	mutex_unlock(&smpboot_threads_lock);
 	put_online_cpus();
+	free_cpumask_var(plug_thread->cpumask);
 }
 EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
 
+/**
+ * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked
+ * @plug_thread:	Hotplug thread descriptor
+ * @new:		Revised mask to use
+ *
+ * The cpumask field in the smp_hotplug_thread must not be updated directly
+ * by the client, but only by calling this function.
+ * This function can only be called on a registered smp_hotplug_thread.
+ */
+int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
+					 const struct cpumask *new)
+{
+	struct cpumask *old = plug_thread->cpumask;
+	cpumask_var_t tmp;
+	unsigned int cpu;
+
+	if (!alloc_cpumask_var(&tmp, GFP_KERNEL))
+		return -ENOMEM;
+
+	get_online_cpus();
+	mutex_lock(&smpboot_threads_lock);
+
+	/* Park threads that were exclusively enabled on the old mask. */
+	cpumask_andnot(tmp, old, new);
+	for_each_cpu_and(cpu, tmp, cpu_online_mask)
+		smpboot_park_thread(plug_thread, cpu);
+
+	/* Unpark threads that are exclusively enabled on the new mask. */
+	cpumask_andnot(tmp, new, old);
+	for_each_cpu_and(cpu, tmp, cpu_online_mask)
+		smpboot_unpark_thread(plug_thread, cpu);
+
+	cpumask_copy(old, new);
+
+	mutex_unlock(&smpboot_threads_lock);
+	put_online_cpus();
+
+	free_cpumask_var(tmp);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread);
+
 static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b13e9d2de302..812fcc3fd390 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -872,6 +872,13 @@ static struct ctl_table kern_table[] = {
 		.extra2		= &one,
 	},
 	{
+		.procname	= "watchdog_cpumask",
+		.data		= &watchdog_cpumask_bits,
+		.maxlen		= NR_CPUS,
+		.mode		= 0644,
+		.proc_handler	= proc_watchdog_cpumask,
+	},
+	{
 		.procname	= "softlockup_panic",
 		.data		= &softlockup_panic,
 		.maxlen		= sizeof(int),
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 581a68a04c64..a6ffa43f2993 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -19,6 +19,7 @@
 #include <linux/sysctl.h>
 #include <linux/smpboot.h>
 #include <linux/sched/rt.h>
+#include <linux/tick.h>
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
@@ -58,6 +59,12 @@ int __read_mostly sysctl_softlockup_all_cpu_backtrace;
 #else
 #define sysctl_softlockup_all_cpu_backtrace 0
 #endif
+static struct cpumask watchdog_cpumask __read_mostly;
+unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
+
+/* Helper for online, unparked cpus. */
+#define for_each_watchdog_cpu(cpu) \
+	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
 
 static int __read_mostly watchdog_running;
 static u64 __read_mostly sample_period;
@@ -207,7 +214,7 @@ void touch_all_softlockup_watchdogs(void)
 	 * do we care if a 0 races with a timestamp?
 	 * all it means is the softlock check starts one cycle later
 	 */
-	for_each_online_cpu(cpu)
+	for_each_watchdog_cpu(cpu)
 		per_cpu(watchdog_touch_ts, cpu) = 0;
 }
 
@@ -616,7 +623,7 @@ void watchdog_nmi_enable_all(void)
 		goto unlock;
 
 	get_online_cpus();
-	for_each_online_cpu(cpu)
+	for_each_watchdog_cpu(cpu)
 		watchdog_nmi_enable(cpu);
 	put_online_cpus();
 
@@ -634,7 +641,7 @@ void watchdog_nmi_disable_all(void)
 		goto unlock;
 
 	get_online_cpus();
-	for_each_online_cpu(cpu)
+	for_each_watchdog_cpu(cpu)
 		watchdog_nmi_disable(cpu);
 	put_online_cpus();
 
@@ -696,7 +703,7 @@ static void update_watchdog_all_cpus(void)
 	int cpu;
 
 	get_online_cpus();
-	for_each_online_cpu(cpu)
+	for_each_watchdog_cpu(cpu)
 		update_watchdog(cpu);
 	put_online_cpus();
 }
@@ -709,8 +716,12 @@ static int watchdog_enable_all_cpus(void)
 		err = smpboot_register_percpu_thread(&watchdog_threads);
 		if (err)
 			pr_err("Failed to create watchdog threads, disabled\n");
-		else
+		else {
+			if (smpboot_update_cpumask_percpu_thread(
+				    &watchdog_threads, &watchdog_cpumask))
+				pr_err("Failed to set cpumask for watchdog threads\n");
 			watchdog_running = 1;
+		}
 	} else {
 		/*
 		 * Enable/disable the lockup detectors or
@@ -879,12 +890,58 @@ out:
 	mutex_unlock(&watchdog_proc_mutex);
 	return err;
 }
+
+/*
+ * The cpumask is the mask of possible cpus that the watchdog can run
+ * on, not the mask of cpus it is actually running on.  This allows the
+ * user to specify a mask that will include cpus that have not yet
+ * been brought online, if desired.
+ */
+int proc_watchdog_cpumask(struct ctl_table *table, int write,
+			  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int err;
+
+	mutex_lock(&watchdog_proc_mutex);
+	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
+	if (!err && write) {
+		/* Remove impossible cpus to keep sysctl output cleaner. */
+		cpumask_and(&watchdog_cpumask, &watchdog_cpumask,
+			    cpu_possible_mask);
+
+		if (watchdog_running) {
+			/*
+			 * Failure would be due to being unable to allocate
+			 * a temporary cpumask, so we are likely not in a
+			 * position to do much else to make things better.
+			 */
+			if (smpboot_update_cpumask_percpu_thread(
+				    &watchdog_threads, &watchdog_cpumask) != 0)
+				pr_err("cpumask update failed\n");
+		}
+	}
+	mutex_unlock(&watchdog_proc_mutex);
+	return err;
+}
+
 #endif /* CONFIG_SYSCTL */
 
 void __init lockup_detector_init(void)
 {
 	set_sample_period();
 
+#ifdef CONFIG_NO_HZ_FULL
+	if (tick_nohz_full_enabled()) {
+		if (!cpumask_empty(tick_nohz_full_mask))
+			pr_info("Disabling watchdog on nohz_full cores by default\n");
+		cpumask_andnot(&watchdog_cpumask, cpu_possible_mask,
+			       tick_nohz_full_mask);
+	} else
+		cpumask_copy(&watchdog_cpumask, cpu_possible_mask);
+#else
+	cpumask_copy(&watchdog_cpumask, cpu_possible_mask);
+#endif
+
 	if (watchdog_enabled)
 		watchdog_enable_all_cpus();
 }