30 files changed, 419 insertions, 177 deletions

diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index d6709eb70970..0d302a87f21b 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -19,6 +19,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/file.h>
 #include <linux/kernel.h>
 #include <linux/audit.h>
 #include <linux/kthread.h>
@@ -544,10 +545,11 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark)
 	unsigned long ino;
 	dev_t dev;
 
-	rcu_read_lock();
-	exe_file = rcu_dereference(tsk->mm->exe_file);
+	exe_file = get_task_exe_file(tsk);
+	if (!exe_file)
+		return 0;
 	ino = exe_file->f_inode->i_ino;
 	dev = exe_file->f_inode->i_sb->s_dev;
-	rcu_read_unlock();
+	fput(exe_file);
 	return audit_mark_compare(mark, ino, dev);
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d1c51b7f5221..d6b729beba49 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -3446,9 +3446,28 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 	 * Except for the root, subtree_control must be zero for a cgroup
 	 * with tasks so that child cgroups don't compete against tasks.
 	 */
-	if (enable && cgroup_parent(cgrp) && !list_empty(&cgrp->cset_links)) {
-		ret = -EBUSY;
-		goto out_unlock;
+	if (enable && cgroup_parent(cgrp)) {
+		struct cgrp_cset_link *link;
+
+		/*
+		 * Because namespaces pin csets too, @cgrp->cset_links
+		 * might not be empty even when @cgrp is empty.  Walk and
+		 * verify each cset.
+		 */
+		spin_lock_irq(&css_set_lock);
+
+		ret = 0;
+		list_for_each_entry(link, &cgrp->cset_links, cset_link) {
+			if (css_set_populated(link->cset)) {
+				ret = -EBUSY;
+				break;
+			}
+		}
+
+		spin_unlock_irq(&css_set_lock);
+
+		if (ret)
+			goto out_unlock;
 	}
 
 	/* save and update control masks and prepare csses */
@@ -3899,7 +3918,9 @@ void cgroup_file_notify(struct cgroup_file *cfile)
  * cgroup_task_count - count the number of tasks in a cgroup.
  * @cgrp: the cgroup in question
  *
- * Return the number of tasks in the cgroup.
+ * Return the number of tasks in the cgroup.  The returned number can be
+ * higher than the actual number of tasks due to css_set references from
+ * namespace roots and temporary usages.
  */
 static int cgroup_task_count(const struct cgroup *cgrp)
 {
@@ -6270,6 +6291,12 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 	if (cgroup_sk_alloc_disabled)
 		return;
 
+	/* Socket clone path */
+	if (skcd->val) {
+		cgroup_get(sock_cgroup_ptr(skcd));
+		return;
+	}
+
 	rcu_read_lock();
 
 	while (true) {
diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config
index c2de56ab0fce..7fa0c4ae6394 100644
--- a/kernel/configs/tiny.config
+++ b/kernel/configs/tiny.config
@@ -1,4 +1,12 @@
+# CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE is not set
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_KERNEL_GZIP is not set
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
 CONFIG_KERNEL_XZ=y
+# CONFIG_KERNEL_LZO is not set
+# CONFIG_KERNEL_LZ4 is not set
 CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_SLAB is not set
+# CONFIG_SLUB is not set
 CONFIG_SLOB=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 341bf80f80bd..ebbf027dd4a1 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1024,12 +1024,13 @@ EXPORT_SYMBOL_GPL(cpu_up);
 #ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_var_t frozen_cpus;
 
-int disable_nonboot_cpus(void)
+int freeze_secondary_cpus(int primary)
 {
-	int cpu, first_cpu, error = 0;
+	int cpu, error = 0;
 
 	cpu_maps_update_begin();
-	first_cpu = cpumask_first(cpu_online_mask);
+	if (!cpu_online(primary))
+		primary = cpumask_first(cpu_online_mask);
 	/*
 	 * We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time
@@ -1038,7 +1039,7 @@ int disable_nonboot_cpus(void)
 
 	pr_info("Disabling non-boot CPUs ...\n");
 	for_each_online_cpu(cpu) {
-		if (cpu == first_cpu)
+		if (cpu == primary)
 			continue;
 		trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
 		error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index c7fd2778ed50..2b4c20ab5bbe 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -325,8 +325,7 @@ static struct file_system_type cpuset_fs_type = {
 /*
  * Return in pmask the portion of a cpusets's cpus_allowed that
  * are online.  If none are online, walk up the cpuset hierarchy
- * until we find one that does have some online cpus.  The top
- * cpuset always has some cpus online.
+ * until we find one that does have some online cpus.
  *
  * One way or another, we guarantee to return some non-empty subset
  * of cpu_online_mask.
@@ -335,8 +334,20 @@ static struct file_system_type cpuset_fs_type = {
  */
 static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 {
-	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask))
+	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
 		cs = parent_cs(cs);
+		if (unlikely(!cs)) {
+			/*
+			 * The top cpuset doesn't have any online cpu as a
+			 * consequence of a race between cpuset_hotplug_work
+			 * and cpu hotplug notifier.  But we know the top
+			 * cpuset's effective_cpus is on its way to to be
+			 * identical to cpu_online_mask.
+			 */
+			cpumask_copy(pmask, cpu_online_mask);
+			return;
+		}
+	}
 	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
 }
 
@@ -2069,6 +2080,20 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 	mutex_unlock(&cpuset_mutex);
 }
 
+/*
+ * Make sure the new task conform to the current state of its parent,
+ * which could have been changed by cpuset just after it inherits the
+ * state from the parent and before it sits on the cgroup's task list.
+ */
+static void cpuset_fork(struct task_struct *task)
+{
+	if (task_css_is_root(task, cpuset_cgrp_id))
+		return;
+
+	set_cpus_allowed_ptr(task, &current->cpus_allowed);
+	task->mems_allowed = current->mems_allowed;
+}
+
 struct cgroup_subsys cpuset_cgrp_subsys = {
 	.css_alloc	= cpuset_css_alloc,
 	.css_online	= cpuset_css_online,
@@ -2079,6 +2104,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 	.attach		= cpuset_attach,
 	.post_attach	= cpuset_post_attach,
 	.bind		= cpuset_bind,
+	.fork		= cpuset_fork,
 	.legacy_cftypes	= files,
 	.early_init	= true,
 };
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3cfabdf7b942..fc9bb2225291 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2496,11 +2496,11 @@ static int __perf_event_stop(void *info)
 	return 0;
 }
 
-static int perf_event_restart(struct perf_event *event)
+static int perf_event_stop(struct perf_event *event, int restart)
 {
 	struct stop_event_data sd = {
 		.event		= event,
-		.restart	= 1,
+		.restart	= restart,
 	};
 	int ret = 0;
 
@@ -3549,10 +3549,18 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.group = group,
 			.ret = 0,
 		};
-		ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
-		/* The event must have been read from an online CPU: */
-		WARN_ON_ONCE(ret);
-		ret = ret ? : data.ret;
+		/*
+		 * Purposely ignore the smp_call_function_single() return
+		 * value.
+		 *
+		 * If event->oncpu isn't a valid CPU it means the event got
+		 * scheduled out and that will have updated the event count.
+		 *
+		 * Therefore, either way, we'll have an up-to-date event count
+		 * after this.
+		 */
+		(void)smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
 		unsigned long flags;
@@ -3921,7 +3929,7 @@ static void exclusive_event_destroy(struct perf_event *event)
 
 static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2)
 {
-	if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) &&
+	if ((e1->pmu == e2->pmu) &&
 	    (e1->cpu == e2->cpu ||
 	     e1->cpu == -1 ||
 	     e2->cpu == -1))
@@ -4837,6 +4845,19 @@ static void ring_buffer_attach(struct perf_event *event,
 		spin_unlock_irqrestore(&rb->event_lock, flags);
 	}
 
+	/*
+	 * Avoid racing with perf_mmap_close(AUX): stop the event
+	 * before swizzling the event::rb pointer; if it's getting
+	 * unmapped, its aux_mmap_count will be 0 and it won't
+	 * restart. See the comment in __perf_pmu_output_stop().
+	 *
+	 * Data will inevitably be lost when set_output is done in
+	 * mid-air, but then again, whoever does it like this is
+	 * not in for the data anyway.
+	 */
+	if (has_aux(event))
+		perf_event_stop(event, 0);
+
 	rcu_assign_pointer(event->rb, rb);
 
 	if (old_rb) {
@@ -6112,7 +6133,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
 	if (restart)
-		perf_event_restart(event);
+		perf_event_stop(event, 1);
 }
 
 void perf_event_exec(void)
@@ -6156,7 +6177,13 @@ static void __perf_event_output_stop(struct perf_event *event, void *data)
 
 	/*
 	 * In case of inheritance, it will be the parent that links to the
-	 * ring-buffer, but it will be the child that's actually using it:
+	 * ring-buffer, but it will be the child that's actually using it.
+	 *
+	 * We are using event::rb to determine if the event should be stopped,
+	 * however this may race with ring_buffer_attach() (through set_output),
+	 * which will make us skip the event that actually needs to be stopped.
+	 * So ring_buffer_attach() has to stop an aux event before re-assigning
+	 * its rb pointer.
 	 */
 	if (rcu_dereference(parent->rb) == rb)
 		ro->err = __perf_event_stop(&sd);
@@ -6670,7 +6697,7 @@ static void __perf_addr_filters_adjust(struct perf_event *event, void *data)
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
 	if (restart)
-		perf_event_restart(event);
+		perf_event_stop(event, 1);
 }
 
 /*
@@ -7859,7 +7886,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	mmput(mm);
 
 restart:
-	perf_event_restart(event);
+	perf_event_stop(event, 1);
 }
 
 /*
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index ae9b90dc9a5a..257fa460b846 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -330,15 +330,22 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	if (!rb)
 		return NULL;
 
-	if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount))
+	if (!rb_has_aux(rb))
 		goto err;
 
 	/*
-	 * If rb::aux_mmap_count is zero (and rb_has_aux() above went through),
-	 * the aux buffer is in perf_mmap_close(), about to get freed.
+	 * If aux_mmap_count is zero, the aux buffer is in perf_mmap_close(),
+	 * about to get freed, so we leave immediately.
+	 *
+	 * Checking rb::aux_mmap_count and rb::refcount has to be done in
+	 * the same order, see perf_mmap_close. Otherwise we end up freeing
+	 * aux pages in this path, which is a bug, because in_atomic().
 	 */
 	if (!atomic_read(&rb->aux_mmap_count))
-		goto err_put;
+		goto err;
+
+	if (!atomic_inc_not_zero(&rb->aux_refcount))
+		goto err;
 
 	/*
 	 * Nesting is not supported for AUX area, make sure nested
diff --git a/kernel/exit.c b/kernel/exit.c
index 2f974ae042a6..091a78be3b09 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -848,12 +848,7 @@ void do_exit(long code)
 	TASKS_RCU(preempt_enable());
 	exit_notify(tsk, group_dead);
 	proc_exit_connector(tsk);
-#ifdef CONFIG_NUMA
-	task_lock(tsk);
-	mpol_put(tsk->mempolicy);
-	tsk->mempolicy = NULL;
-	task_unlock(tsk);
-#endif
+	mpol_put_task_policy(tsk);
 #ifdef CONFIG_FUTEX
 	if (unlikely(current->pi_state_cache))
 		kfree(current->pi_state_cache);
diff --git a/kernel/fork.c b/kernel/fork.c
index 52e725d4a866..beb31725f7e2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -799,6 +799,29 @@ struct file *get_mm_exe_file(struct mm_struct *mm)
 EXPORT_SYMBOL(get_mm_exe_file);
 
 /**
+ * get_task_exe_file - acquire a reference to the task's executable file
+ *
+ * Returns %NULL if task's mm (if any) has no associated executable file or
+ * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
+ * User must release file via fput().
+ */
+struct file *get_task_exe_file(struct task_struct *task)
+{
+	struct file *exe_file = NULL;
+	struct mm_struct *mm;
+
+	task_lock(task);
+	mm = task->mm;
+	if (mm) {
+		if (!(task->flags & PF_KTHREAD))
+			exe_file = get_mm_exe_file(mm);
+	}
+	task_unlock(task);
+	return exe_file;
+}
+EXPORT_SYMBOL(get_task_exe_file);
+
+/**
  * get_task_mm - acquire a reference to the task's mm
  *
  * Returns %NULL if the task has no mm.  Checks PF_KTHREAD (meaning
@@ -913,14 +936,12 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	deactivate_mm(tsk, mm);
 
 	/*
-	 * If we're exiting normally, clear a user-space tid field if
-	 * requested.  We leave this alone when dying by signal, to leave
-	 * the value intact in a core dump, and to save the unnecessary
-	 * trouble, say, a killed vfork parent shouldn't touch this mm.
-	 * Userland only wants this done for a sys_exit.
+	 * Signal userspace if we're not exiting with a core dump
+	 * because we want to leave the value intact for debugging
+	 * purposes.
 	 */
 	if (tsk->clear_child_tid) {
-		if (!(tsk->flags & PF_SIGNALED) &&
+		if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
 		    atomic_read(&mm->mm_users) > 1) {
 			/*
 			 * We don't check the error code - if userspace has
@@ -1404,7 +1425,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->real_start_time = ktime_get_boot_ns();
 	p->io_context = NULL;
 	p->audit_context = NULL;
-	threadgroup_change_begin(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1556,6 +1576,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
+	threadgroup_change_begin(current);
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
@@ -1656,6 +1677,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p);
 bad_fork_free_pid:
+	threadgroup_change_end(current);
 	if (pid != &init_struct_pid)
 		free_pid(pid);
 bad_fork_cleanup_thread:
@@ -1688,7 +1710,6 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-	threadgroup_change_end(current);
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 637389088b3f..26ba5654d9d5 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -820,6 +820,8 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 	desc->name = name;
 
 	if (handle != handle_bad_irq && is_chained) {
+		unsigned int type = irqd_get_trigger_type(&desc->irq_data);
+
 		/*
 		 * We're about to start this interrupt immediately,
 		 * hence the need to set the trigger configuration.
@@ -828,8 +830,10 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 		 * chained interrupt. Reset it immediately because we
 		 * do know better.
 		 */
-		__irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data));
-		desc->handle_irq = handle;
+		if (type != IRQ_TYPE_NONE) {
+			__irq_set_trigger(desc, type);
+			desc->handle_irq = handle;
+		}
 
 		irq_settings_set_noprobe(desc);
 		irq_settings_set_norequest(desc);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 503bc2d348e5..037c321c5618 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -887,7 +887,10 @@ int kexec_load_purgatory(struct kimage *image, unsigned long min,
 	return 0;
 out:
 	vfree(pi->sechdrs);
+	pi->sechdrs = NULL;
+
 	vfree(pi->purgatory_buf);
+	pi->purgatory_buf = NULL;
 	return ret;
 }
 
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 251d16b4cb41..b501e390bb34 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -247,6 +247,7 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 	arch_remove_memory(align_start, align_size);
+	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
 	pgmap_radix_release(res);
 	dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
 			"%s: failed to free all reserved pages\n", __func__);
@@ -282,6 +283,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 		struct percpu_ref *ref, struct vmem_altmap *altmap)
 {
 	resource_size_t key, align_start, align_size, align_end;
+	pgprot_t pgprot = PAGE_KERNEL;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
 	int error, nid, is_ram;
@@ -351,6 +353,11 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (nid < 0)
 		nid = numa_mem_id();
 
+	error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
+			align_size);
+	if (error)
+		goto err_pfn_remap;
+
 	error = arch_add_memory(nid, align_start, align_size, true);
 	if (error)
 		goto err_add_memory;
@@ -371,6 +378,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	return __va(res->start);
 
  err_add_memory:
+	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
+ err_pfn_remap:
  err_radix:
 	pgmap_radix_release(res);
 	devres_free(page_map);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 68d3ebc12601..e8517b63eb37 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -186,7 +186,7 @@ config PM_SLEEP_DEBUG
 
 config DPM_WATCHDOG
 	bool "Device suspend/resume watchdog"
-	depends on PM_DEBUG && PSTORE
+	depends on PM_DEBUG && PSTORE && EXPERT
 	---help---
 	  Sets up a watchdog timer to capture drivers that are
 	  locked up attempting to suspend/resume a device.
@@ -197,7 +197,7 @@ config DPM_WATCHDOG
 config DPM_WATCHDOG_TIMEOUT
 	int "Watchdog timeout in seconds"
 	range 1 120
-	default 60
+	default 120
 	depends on DPM_WATCHDOG
 
 config PM_TRACE
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 33c79b6105c5..b26dbc48c75b 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -306,8 +306,10 @@ static int create_image(int platform_mode)
 	if (error)
 		printk(KERN_ERR "PM: Error %d creating hibernation image\n",
 			error);
-	if (!in_suspend)
+	if (!in_suspend) {
 		events_check_enabled = false;
+		clear_free_pages();
+	}
 
 	platform_leave(platform_mode);
 
@@ -1189,22 +1191,6 @@ static int __init nohibernate_setup(char *str)
 	return 1;
 }
 
-static int __init page_poison_nohibernate_setup(char *str)
-{
-#ifdef CONFIG_PAGE_POISONING_ZERO
-	/*
-	 * The zeroing option for page poison skips the checks on alloc.
-	 * since hibernation doesn't save free pages there's no way to
-	 * guarantee the pages will still be zeroed.
-	 */
-	if (!strcmp(str, "on")) {
-		pr_info("Disabling hibernation due to page poisoning\n");
-		return nohibernate_setup(str);
-	}
-#endif
-	return 1;
-}
-
 __setup("noresume", noresume_setup);
 __setup("resume_offset=", resume_offset_setup);
 __setup("resume=", resume_setup);
@@ -1212,4 +1198,3 @@ __setup("hibernate=", hibernate_setup);
 __setup("resumewait", resumewait_setup);
 __setup("resumedelay=", resumedelay_setup);
 __setup("nohibernate", nohibernate_setup);
-__setup("page_poison=", page_poison_nohibernate_setup);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 5ea50b1b7595..281a697fd458 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -644,6 +644,7 @@ static int __init pm_init(void)
 		return error;
 	hibernate_image_size_init();
 	hibernate_reserved_size_init();
+	pm_states_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 242d8b827dd5..56d1d0dedf76 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -110,6 +110,8 @@ extern int create_basic_memory_bitmaps(void);
 extern void free_basic_memory_bitmaps(void);
 extern int hibernate_preallocate_memory(void);
 
+extern void clear_free_pages(void);
+
 /**
  *	Auxiliary structure used for reading the snapshot image data and
  *	metadata from and writing them to the list of page backup entries
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 97b0df71303e..168ff442ebde 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -482,7 +482,16 @@ void pm_qos_update_request(struct pm_qos_request *req,
 		return;
 	}
 
-	cancel_delayed_work_sync(&req->work);
+	/*
+	 * This function may be called very early during boot, for example,
+	 * from of_clk_init(), where irq needs to stay disabled.
+	 * cancel_delayed_work_sync() assumes that irq is enabled on
+	 * invocation and re-enables it on return.  Avoid calling it until
+	 * workqueue is initialized.
+	 */
+	if (keventd_up())
+		cancel_delayed_work_sync(&req->work);
+
 	__pm_qos_update_request(req, new_value);
 }
 EXPORT_SYMBOL_GPL(pm_qos_update_request);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index b02228411d57..4f0f0604f1c4 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1132,6 +1132,28 @@ void free_basic_memory_bitmaps(void)
 	pr_debug("PM: Basic memory bitmaps freed\n");
 }
 
+void clear_free_pages(void)
+{
+#ifdef CONFIG_PAGE_POISONING_ZERO
+	struct memory_bitmap *bm = free_pages_map;
+	unsigned long pfn;
+
+	if (WARN_ON(!(free_pages_map)))
+		return;
+
+	memory_bm_position_reset(bm);
+	pfn = memory_bm_next_pfn(bm);
+	while (pfn != BM_END_OF_MAP) {
+		if (pfn_valid(pfn))
+			clear_highpage(pfn_to_page(pfn));
+
+		pfn = memory_bm_next_pfn(bm);
+	}
+	memory_bm_position_reset(bm);
+	pr_info("PM: free pages cleared after restore\n");
+#endif /* PAGE_POISONING_ZERO */
+}
+
 /**
  * snapshot_additional_pages - Estimate the number of extra pages needed.
  * @zone: Memory zone to carry out the computation for.
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 0acab9d7f96f..1e7f5da648d9 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -118,10 +118,18 @@ static bool valid_state(suspend_state_t state)
  */
 static bool relative_states;
 
+void __init pm_states_init(void)
+{
+	/*
+	 * freeze state should be supported even without any suspend_ops,
+	 * initialize pm_states accordingly here
+	 */
+	pm_states[PM_SUSPEND_FREEZE] = pm_labels[relative_states ? 0 : 2];
+}
+
 static int __init sleep_states_setup(char *str)
 {
 	relative_states = !strncmp(str, "1", 1);
-	pm_states[PM_SUSPEND_FREEZE] = pm_labels[relative_states ? 0 : 2];
 	return 1;
 }
 
@@ -211,7 +219,7 @@ static int platform_suspend_begin(suspend_state_t state)
 {
 	if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->begin)
 		return freeze_ops->begin();
-	else if (suspend_ops->begin)
+	else if (suspend_ops && suspend_ops->begin)
 		return suspend_ops->begin(state);
 	else
 		return 0;
@@ -221,7 +229,7 @@ static void platform_resume_end(suspend_state_t state)
 {
 	if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end)
 		freeze_ops->end();
-	else if (suspend_ops->end)
+	else if (suspend_ops && suspend_ops->end)
 		suspend_ops->end();
 }
 
diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c
index b69eb8a2876f..16bab471c7e2 100644
--- a/kernel/printk/nmi.c
+++ b/kernel/printk/nmi.c
@@ -99,27 +99,33 @@ again:
 	return add;
 }
 
-/*
- * printk one line from the temporary buffer from @start index until
- * and including the @end index.
- */
-static void print_nmi_seq_line(struct nmi_seq_buf *s, int start, int end)
+static void printk_nmi_flush_line(const char *text, int len)
 {
-	const char *buf = s->buffer + start;
-
 	/*
 	 * The buffers are flushed in NMI only on panic.  The messages must
 	 * go only into the ring buffer at this stage.  Consoles will get
 	 * explicitly called later when a crashdump is not generated.
 	 */
 	if (in_nmi())
-		printk_deferred("%.*s", (end - start) + 1, buf);
+		printk_deferred("%.*s", len, text);
 	else
-		printk("%.*s", (end - start) + 1, buf);
+		printk("%.*s", len, text);
 
 }
 
 /*
+ * printk one line from the temporary buffer from @start index until
+ * and including the @end index.
+ */
+static void printk_nmi_flush_seq_line(struct nmi_seq_buf *s,
+					int start, int end)
+{
+	const char *buf = s->buffer + start;
+
+	printk_nmi_flush_line(buf, (end - start) + 1);
+}
+
+/*
  * Flush data from the associated per_CPU buffer. The function
  * can be called either via IRQ work or independently.
  */
@@ -150,9 +156,11 @@ more:
 	 * the buffer an unexpected way. If we printed something then
 	 * @len must only increase.
 	 */
-	if (i && i >= len)
-		pr_err("printk_nmi_flush: internal error: i=%d >= len=%zu\n",
-		       i, len);
+	if (i && i >= len) {
+		const char *msg = "printk_nmi_flush: internal error\n";
+
+		printk_nmi_flush_line(msg, strlen(msg));
+	}
 
 	if (!len)
 		goto out; /* Someone else has already flushed the buffer. */
@@ -166,14 +174,14 @@ more:
 	/* Print line by line. */
 	for (; i < size; i++) {
 		if (s->buffer[i] == '\n') {
-			print_nmi_seq_line(s, last_i, i);
+			printk_nmi_flush_seq_line(s, last_i, i);
 			last_i = i + 1;
 		}
 	}
 	/* Check if there was a partial line. */
 	if (last_i < size) {
-		print_nmi_seq_line(s, last_i, size - 1);
-		pr_cont("\n");
+		printk_nmi_flush_seq_line(s, last_i, size - 1);
+		printk_nmi_flush_line("\n", strlen("\n"));
 	}
 
 	/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2a906f20fba7..44817c640e99 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2016,6 +2016,28 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
 
+	/*
+	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
+	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
+	 * in smp_cond_load_acquire() below.
+	 *
+	 * sched_ttwu_pending()                 try_to_wake_up()
+	 *   [S] p->on_rq = 1;                  [L] P->state
+	 *       UNLOCK rq->lock  -----.
+	 *                              \
+	 *				 +---   RMB
+	 * schedule()                   /
+	 *       LOCK rq->lock    -----'
+	 *       UNLOCK rq->lock
+	 *
+	 * [task p]
+	 *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+	 *
+	 * Pairs with the UNLOCK+LOCK on rq->lock from the
+	 * last wakeup of our task and the schedule that got our task
+	 * current.
+	 */
+	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
 		goto stat;
 
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 1141954e73b4..dbc51442ecbc 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
  */
 void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
 			void (*func)(struct update_util_data *data, u64 time,
-				     unsigned long util, unsigned long max))
+				     unsigned int flags))
 {
 	if (WARN_ON(!data || !func))
 		return;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index a84641b222c1..69e06898997d 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -12,7 +12,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/cpufreq.h>
-#include <linux/module.h>
 #include <linux/slab.h>
 #include <trace/events/power.h>
 
@@ -48,11 +47,14 @@ struct sugov_cpu {
 	struct sugov_policy *sg_policy;
 
 	unsigned int cached_raw_freq;
+	unsigned long iowait_boost;
+	unsigned long iowait_boost_max;
+	u64 last_update;
 
 	/* The fields below are only needed when sharing a policy. */
 	unsigned long util;
 	unsigned long max;
-	u64 last_update;
+	unsigned int flags;
 };
 
 static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
@@ -144,24 +146,75 @@ static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
+static void sugov_get_util(unsigned long *util, unsigned long *max)
+{
+	struct rq *rq = this_rq();
+	unsigned long cfs_max;
+
+	cfs_max = arch_scale_cpu_capacity(NULL, smp_processor_id());
+
+	*util = min(rq->cfs.avg.util_avg, cfs_max);
+	*max = cfs_max;
+}
+
+static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
+				   unsigned int flags)
+{
+	if (flags & SCHED_CPUFREQ_IOWAIT) {
+		sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+	} else if (sg_cpu->iowait_boost) {
+		s64 delta_ns = time - sg_cpu->last_update;
+
+		/* Clear iowait_boost if the CPU apprears to have been idle. */
+		if (delta_ns > TICK_NSEC)
+			sg_cpu->iowait_boost = 0;
+	}
+}
+
+static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
+			       unsigned long *max)
+{
+	unsigned long boost_util = sg_cpu->iowait_boost;
+	unsigned long boost_max = sg_cpu->iowait_boost_max;
+
+	if (!boost_util)
+		return;
+
+	if (*util * boost_max < *max * boost_util) {
+		*util = boost_util;
+		*max = boost_max;
+	}
+	sg_cpu->iowait_boost >>= 1;
+}
+
 static void sugov_update_single(struct update_util_data *hook, u64 time,
-				unsigned long util, unsigned long max)
+				unsigned int flags)
 {
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
+	unsigned long util, max;
 	unsigned int next_f;
 
+	sugov_set_iowait_boost(sg_cpu, time, flags);
+	sg_cpu->last_update = time;
+
 	if (!sugov_should_update_freq(sg_policy, time))
 		return;
 
-	next_f = util == ULONG_MAX ? policy->cpuinfo.max_freq :
-			get_next_freq(sg_cpu, util, max);
+	if (flags & SCHED_CPUFREQ_RT_DL) {
+		next_f = policy->cpuinfo.max_freq;
+	} else {
+		sugov_get_util(&util, &max);
+		sugov_iowait_boost(sg_cpu, &util, &max);
+		next_f = get_next_freq(sg_cpu, util, max);
+	}
 	sugov_update_commit(sg_policy, time, next_f);
 }
 
 static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
-					   unsigned long util, unsigned long max)
+					   unsigned long util, unsigned long max,
+					   unsigned int flags)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
@@ -169,9 +222,11 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
 	u64 last_freq_update_time = sg_policy->last_freq_update_time;
 	unsigned int j;
 
-	if (util == ULONG_MAX)
+	if (flags & SCHED_CPUFREQ_RT_DL)
 		return max_f;
 
+	sugov_iowait_boost(sg_cpu, &util, &max);
+
 	for_each_cpu(j, policy->cpus) {
 		struct sugov_cpu *j_sg_cpu;
 		unsigned long j_util, j_max;
@@ -186,41 +241,50 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
 		 * frequency update and the time elapsed between the last update
 		 * of the CPU utilization and the last frequency update is long
 		 * enough, don't take the CPU into account as it probably is
-		 * idle now.
+		 * idle now (and clear iowait_boost for it).
 		 */
 		delta_ns = last_freq_update_time - j_sg_cpu->last_update;
-		if (delta_ns > TICK_NSEC)
+		if (delta_ns > TICK_NSEC) {
+			j_sg_cpu->iowait_boost = 0;
 			continue;
-
-		j_util = j_sg_cpu->util;
-		if (j_util == ULONG_MAX)
+		}
+		if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
 			return max_f;
 
+		j_util = j_sg_cpu->util;
 		j_max = j_sg_cpu->max;
 		if (j_util * max > j_max * util) {
 			util = j_util;
 			max = j_max;
 		}
+
+		sugov_iowait_boost(j_sg_cpu, &util, &max);
 	}
 
 	return get_next_freq(sg_cpu, util, max);
 }
 
 static void sugov_update_shared(struct update_util_data *hook, u64 time,
-				unsigned long util, unsigned long max)
+				unsigned int flags)
 {
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	unsigned long util, max;
 	unsigned int next_f;
 
+	sugov_get_util(&util, &max);
+
 	raw_spin_lock(&sg_policy->update_lock);
 
 	sg_cpu->util = util;
 	sg_cpu->max = max;
+	sg_cpu->flags = flags;
+
+	sugov_set_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
 
 	if (sugov_should_update_freq(sg_policy, time)) {
-		next_f = sugov_next_freq_shared(sg_cpu, util, max);
+		next_f = sugov_next_freq_shared(sg_cpu, util, max, flags);
 		sugov_update_commit(sg_policy, time, next_f);
 	}
 
@@ -444,10 +508,13 @@ static int sugov_start(struct cpufreq_policy *policy)
 
 		sg_cpu->sg_policy = sg_policy;
 		if (policy_is_shared(policy)) {
-			sg_cpu->util = ULONG_MAX;
+			sg_cpu->util = 0;
 			sg_cpu->max = 0;
+			sg_cpu->flags = SCHED_CPUFREQ_RT;
 			sg_cpu->last_update = 0;
 			sg_cpu->cached_raw_freq = 0;
+			sg_cpu->iowait_boost = 0;
+			sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
 			cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
 						     sugov_update_shared);
 		} else {
@@ -495,28 +562,15 @@ static struct cpufreq_governor schedutil_gov = {
 	.limits = sugov_limits,
 };
 
-static int __init sugov_module_init(void)
-{
-	return cpufreq_register_governor(&schedutil_gov);
-}
-
-static void __exit sugov_module_exit(void)
-{
-	cpufreq_unregister_governor(&schedutil_gov);
-}
-
-MODULE_AUTHOR("Rafael J. Wysocki <rafael.j.wysocki@intel.com>");
-MODULE_DESCRIPTION("Utilization-based CPU frequency selection");
-MODULE_LICENSE("GPL");
-
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
 	return &schedutil_gov;
 }
-
-fs_initcall(sugov_module_init);
-#else
-module_init(sugov_module_init);
 #endif
-module_exit(sugov_module_exit);
+
+static int __init sugov_register(void)
+{
+	return cpufreq_register_governor(&schedutil_gov);
+}
+fs_initcall(sugov_register);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 1ce8867283dc..974779656999 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -735,9 +735,8 @@ static void update_curr_dl(struct rq *rq)
 		return;
 	}
 
-	/* kick cpufreq (see the comment in linux/cpufreq.h). */
-	if (cpu_of(rq) == smp_processor_id())
-		cpufreq_trigger_update(rq_clock(rq));
+	/* kick cpufreq (see the comment in kernel/sched/sched.h). */
+	cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_DL);
 
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 039de34f1521..a5cd07b25aa1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2875,12 +2875,7 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 
 static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 {
-	struct rq *rq = rq_of(cfs_rq);
-	int cpu = cpu_of(rq);
-
-	if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
-		unsigned long max = rq->cpu_capacity_orig;
-
+	if (&this_rq()->cfs == cfs_rq) {
 		/*
 		 * There are a few boundary cases this might miss but it should
 		 * get called often enough that that should (hopefully) not be
@@ -2897,8 +2892,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 		 *
 		 * See cpu_util().
 		 */
-		cpufreq_update_util(rq_clock(rq),
-				    min(cfs_rq->avg.util_avg, max), max);
+		cpufreq_update_util(rq_of(cfs_rq), 0);
 	}
 }
 
@@ -3159,10 +3153,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 
 static inline void update_load_avg(struct sched_entity *se, int not_used)
 {
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	struct rq *rq = rq_of(cfs_rq);
-
-	cpufreq_trigger_update(rq_clock(rq));
+	cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
 }
 
 static inline void
@@ -4509,6 +4500,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 
+	/*
+	 * If in_iowait is set, the code below may not trigger any cpufreq
+	 * utilization updates, so do it here explicitly with the IOWAIT flag
+	 * passed.
+	 */
+	if (p->in_iowait)
+		cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
+
 	for_each_sched_entity(se) {
 		if (se->on_rq)
 			break;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d5690b722691..2516b8df6dbb 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -957,9 +957,8 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely((s64)delta_exec <= 0))
 		return;
 
-	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
-	if (cpu_of(rq) == smp_processor_id())
-		cpufreq_trigger_update(rq_clock(rq));
+	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+	cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
 
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c64fc5114004..b7fc1ced4380 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1763,27 +1763,13 @@ DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
 
 /**
  * cpufreq_update_util - Take a note about CPU utilization changes.
- * @time: Current time.
- * @util: Current utilization.
- * @max: Utilization ceiling.
+ * @rq: Runqueue to carry out the update for.
+ * @flags: Update reason flags.
  *
- * This function is called by the scheduler on every invocation of
- * update_load_avg() on the CPU whose utilization is being updated.
+ * This function is called by the scheduler on the CPU whose utilization is
+ * being updated.
  *
  * It can only be called from RCU-sched read-side critical sections.
- */
-static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
-{
-       struct update_util_data *data;
-
-       data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
-       if (data)
-               data->func(data, time, util, max);
-}
-
-/**
- * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed.
- * @time: Current time.
  *
  * The way cpufreq is currently arranged requires it to evaluate the CPU
  * performance state (frequency/voltage) on a regular basis to prevent it from
@@ -1797,13 +1783,23 @@ static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned lo
  * but that really is a band-aid.  Going forward it should be replaced with
  * solutions targeted more specifically at RT and DL tasks.
  */
-static inline void cpufreq_trigger_update(u64 time)
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
+{
+	struct update_util_data *data;
+
+	data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+	if (data)
+		data->func(data, rq_clock(rq), flags);
+}
+
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags)
 {
-	cpufreq_update_util(time, ULONG_MAX, 0);
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_update_util(rq, flags);
 }
 #else
-static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
-static inline void cpufreq_trigger_update(u64 time) {}
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
 #ifdef arch_scale_freq_capacity
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index ef6c6c3f9d8a..0db7c8a2afe2 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -605,12 +605,16 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		ptrace_event(PTRACE_EVENT_SECCOMP, data);
 		/*
 		 * The delivery of a fatal signal during event
-		 * notification may silently skip tracer notification.
-		 * Terminating the task now avoids executing a system
-		 * call that may not be intended.
+		 * notification may silently skip tracer notification,
+		 * which could leave us with a potentially unmodified
+		 * syscall that the tracer would have liked to have
+		 * changed. Since the process is about to die, we just
+		 * force the syscall to be skipped and let the signal
+		 * kill the process and correctly handle any tracer exit
+		 * notifications.
 		 */
 		if (fatal_signal_pending(current))
-			do_exit(SIGSYS);
+			goto skip;
 		/* Check if the tracer forced the syscall to be skipped. */
 		this_syscall = syscall_get_nr(current, task_pt_regs(current));
 		if (this_syscall < 0)
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 204fdc86863d..2ec7c00228f3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -908,10 +908,11 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
 	ktime_t now, expires;
 	int cpu = smp_processor_id();
 
+	now = tick_nohz_start_idle(ts);
+
 	if (can_stop_idle_tick(cpu, ts)) {
 		int was_stopped = ts->tick_stopped;
 
-		now = tick_nohz_start_idle(ts);
 		ts->idle_calls++;
 
 		expires = tick_nohz_stop_sched_tick(ts, now, cpu);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dade4c9559cc..7bc56762ca35 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5124,19 +5124,20 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	struct trace_iterator *iter = filp->private_data;
 	ssize_t sret;
 
-	/* return any leftover data */
-	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
-	if (sret != -EBUSY)
-		return sret;
-
-	trace_seq_init(&iter->seq);
-
 	/*
 	 * Avoid more than one consumer on a single file descriptor
 	 * This is just a matter of traces coherency, the ring buffer itself
 	 * is protected.
 	 */
 	mutex_lock(&iter->mutex);
+
+	/* return any leftover data */
+	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+	if (sret != -EBUSY)
+		goto out;
+
+	trace_seq_init(&iter->seq);
+
 	if (iter->trace->read) {
 		sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
 		if (sret)
@@ -6163,9 +6164,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		return -EBUSY;
 #endif
 
-	if (splice_grow_spd(pipe, &spd))
-		return -ENOMEM;
-
 	if (*ppos & (PAGE_SIZE - 1))
 		return -EINVAL;
 
@@ -6175,6 +6173,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		len &= PAGE_MASK;
 	}
 
+	if (splice_grow_spd(pipe, &spd))
+		return -ENOMEM;
+
  again:
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
@@ -6232,19 +6233,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	/* did we read anything? */
 	if (!spd.nr_pages) {
 		if (ret)
-			return ret;
+			goto out;
 
+		ret = -EAGAIN;
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
-			return -EAGAIN;
+			goto out;
 
 		ret = wait_on_pipe(iter, true);
 		if (ret)
-			return ret;
+			goto out;
 
 		goto again;
 	}
 
 	ret = splice_to_pipe(pipe, &spd);
+out:
 	splice_shrink_spd(&spd);
 
 	return ret;