Merge "Merge remote-tracking branch 'origin/tmp-917a9a9133a6' into lsk"

15 files changed, 126 insertions, 72 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d1d3e8f57de9..2e7f7ab739e4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2082,7 +2082,7 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
 		/* adjust offset of jmps if necessary */
 		if (i < pos && i + insn->off + 1 > pos)
 			insn->off += delta;
-		else if (i > pos && i + insn->off + 1 < pos)
+		else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
 			insn->off -= delta;
 	}
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 359d881f7ffe..d5512e1e7138 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -57,7 +57,7 @@
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 #include <linux/kthread.h>
 #include <linux/delay.h>
-
+#include <linux/cpuset.h>
 #include <linux/atomic.h>
 
 /*
@@ -2819,6 +2819,7 @@ out_unlock_rcu:
 out_unlock_threadgroup:
 	percpu_up_write(&cgroup_threadgroup_rwsem);
 	cgroup_kn_unlock(of->kn);
+	cpuset_post_attach_flush();
 	return ret ?: nbytes;
 }
 
@@ -4838,6 +4839,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
 	css->serial_nr = css_serial_nr_next++;
+	atomic_set(&css->online_cnt, 0);
 
 	if (cgroup_parent(cgrp)) {
 		css->parent = cgroup_css(cgroup_parent(cgrp), ss);
@@ -4860,6 +4862,10 @@ static int online_css(struct cgroup_subsys_state *css)
 	if (!ret) {
 		css->flags |= CSS_ONLINE;
 		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
+
+		atomic_inc(&css->online_cnt);
+		if (css->parent)
+			atomic_inc(&css->parent->online_cnt);
 	}
 	return ret;
 }
@@ -5091,10 +5097,15 @@ static void css_killed_work_fn(struct work_struct *work)
 		container_of(work, struct cgroup_subsys_state, destroy_work);
 
 	mutex_lock(&cgroup_mutex);
-	offline_css(css);
-	mutex_unlock(&cgroup_mutex);
 
-	css_put(css);
+	do {
+		offline_css(css);
+		css_put(css);
+		/* @css can't go away while we're holding cgroup_mutex */
+		css = css->parent;
+	} while (css && atomic_dec_and_test(&css->online_cnt));
+
+	mutex_unlock(&cgroup_mutex);
 }
 
 /* css kill confirmation processing requires process context, bounce */
@@ -5103,8 +5114,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
-	INIT_WORK(&css->destroy_work, css_killed_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	if (atomic_dec_and_test(&css->online_cnt)) {
+		INIT_WORK(&css->destroy_work, css_killed_work_fn);
+		queue_work(cgroup_destroy_wq, &css->destroy_work);
+	}
 }
 
 /**
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 02a8ea5c9963..2ade632197d5 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -286,6 +286,8 @@ static struct cpuset top_cpuset = {
 static DEFINE_MUTEX(cpuset_mutex);
 static DEFINE_SPINLOCK(callback_lock);
 
+static struct workqueue_struct *cpuset_migrate_mm_wq;
+
 /*
  * CPU / memory hotplug is handled asynchronously.
  */
@@ -971,31 +973,51 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 }
 
 /*
- * cpuset_migrate_mm
- *
- *    Migrate memory region from one set of nodes to another.
- *
- *    Temporarilly set tasks mems_allowed to target nodes of migration,
- *    so that the migration code can allocate pages on these nodes.
- *
- *    While the mm_struct we are migrating is typically from some
- *    other task, the task_struct mems_allowed that we are hacking
- *    is for our current task, which must allocate new pages for that
- *    migrating memory region.
+ * Migrate memory region from one set of nodes to another.  This is
+ * performed asynchronously as it can be called from process migration path
+ * holding locks involved in process management.  All mm migrations are
+ * performed in the queued order and can be waited for by flushing
+ * cpuset_migrate_mm_wq.
  */
 
+struct cpuset_migrate_mm_work {
+	struct work_struct	work;
+	struct mm_struct	*mm;
+	nodemask_t		from;
+	nodemask_t		to;
+};
+
+static void cpuset_migrate_mm_workfn(struct work_struct *work)
+{
+	struct cpuset_migrate_mm_work *mwork =
+		container_of(work, struct cpuset_migrate_mm_work, work);
+
+	/* on a wq worker, no need to worry about %current's mems_allowed */
+	do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
+	mmput(mwork->mm);
+	kfree(mwork);
+}
+
 static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 							const nodemask_t *to)
 {
-	struct task_struct *tsk = current;
-
-	tsk->mems_allowed = *to;
+	struct cpuset_migrate_mm_work *mwork;
 
-	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+	mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
+	if (mwork) {
+		mwork->mm = mm;
+		mwork->from = *from;
+		mwork->to = *to;
+		INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
+		queue_work(cpuset_migrate_mm_wq, &mwork->work);
+	} else {
+		mmput(mm);
+	}
+}
 
-	rcu_read_lock();
-	guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
-	rcu_read_unlock();
+void cpuset_post_attach_flush(void)
+{
+	flush_workqueue(cpuset_migrate_mm_wq);
 }
 
 /*
@@ -1096,7 +1118,8 @@ static void update_tasks_nodemask(struct cpuset *cs)
 		mpol_rebind_mm(mm, &cs->mems_allowed);
 		if (migrate)
 			cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
-		mmput(mm);
+		else
+			mmput(mm);
 	}
 	css_task_iter_end(&it);
 
@@ -1541,11 +1564,11 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 			 * @old_mems_allowed is the right nodesets that we
 			 * migrate mm from.
 			 */
-			if (is_memory_migrate(cs)) {
+			if (is_memory_migrate(cs))
 				cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
 						  &cpuset_attach_nodemask_to);
-			}
-			mmput(mm);
+			else
+				mmput(mm);
 		}
 	}
 
@@ -1710,6 +1733,7 @@ out_unlock:
 	mutex_unlock(&cpuset_mutex);
 	kernfs_unbreak_active_protection(of->kn);
 	css_put(&cs->css);
+	flush_workqueue(cpuset_migrate_mm_wq);
 	return retval ?: nbytes;
 }
 
@@ -2355,6 +2379,9 @@ void __init cpuset_init_smp(void)
 	top_cpuset.effective_mems = node_states[N_MEMORY];
 
 	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
+
+	cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0);
+	BUG_ON(!cpuset_migrate_mm_wq);
 }
 
 /**
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index e1dbf4a2c69e..90ff129c88a2 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -153,13 +153,11 @@ static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp)
 	} else {
 		kdb_printf("%s: failed to set breakpoint at 0x%lx\n",
 			   __func__, bp->bp_addr);
-#ifdef CONFIG_DEBUG_RODATA
 		if (!bp->bp_type) {
 			kdb_printf("Software breakpoints are unavailable.\n"
-				   "  Change the kernel CONFIG_DEBUG_RODATA=n\n"
+				   "  Boot the kernel with rodata=off\n"
 				   "  OR use hw breaks: help bph\n");
 		}
-#endif
 		return 1;
 	}
 	return 0;
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a302cf9a2126..57bff7857e87 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -138,7 +138,8 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 	unsigned int flags = 0, irq = desc->irq_data.irq;
 	struct irqaction *action = desc->action;
 
-	do {
+	/* action might have become NULL since we dropped the lock */
+	while (action) {
 		irqreturn_t res;
 
 		trace_irq_handler_entry(irq, action);
@@ -173,7 +174,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 
 		retval |= res;
 		action = action->next;
-	} while (action);
+	}
 
 	add_interrupt_randomness(irq, flags);
 
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 7a4e473cea4d..25ced161ebeb 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -133,8 +133,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset,
 	if (addr) {
 		*ptr = addr;
 		devres_add(dev, ptr);
-	} else
+	} else {
 		devres_free(ptr);
+		return ERR_PTR(-ENXIO);
+	}
 
 	return addr;
 }
diff --git a/kernel/module.c b/kernel/module.c
index 2ec4df630677..fe5248ab3378 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2495,7 +2495,6 @@ static void layout_symtab(struct module *mod, struct load_info *info)
 	strsect->sh_flags |= SHF_ALLOC;
 	strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect,
 					 info->index.str) | INIT_OFFSET_MASK;
-	mod->init_size = debug_align(mod->init_size);
 	pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
 
 	/* We'll tack temporary mod_kallsyms on the end. */
diff --git a/kernel/resource.c b/kernel/resource.c
index 035b989b582b..4c9835c09dcd 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1083,9 +1083,10 @@ struct resource * __request_region(struct resource *parent,
 		if (!conflict)
 			break;
 		if (conflict != parent) {
-			parent = conflict;
-			if (!(conflict->flags & IORESOURCE_BUSY))
+			if (!(conflict->flags & IORESOURCE_BUSY)) {
+				parent = conflict;
 				continue;
+			}
 		}
 		if (conflict->flags & flags & IORESOURCE_MUXED) {
 			add_wait_queue(&muxed_resource_wait, &wait);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 580ac2d4024f..15a1795bbba1 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -316,24 +316,24 @@ static inline void seccomp_sync_threads(void)
 		put_seccomp_filter(thread);
 		smp_store_release(&thread->seccomp.filter,
 				  caller->seccomp.filter);
+
+		/*
+		 * Don't let an unprivileged task work around
+		 * the no_new_privs restriction by creating
+		 * a thread that sets it up, enters seccomp,
+		 * then dies.
+		 */
+		if (task_no_new_privs(caller))
+			task_set_no_new_privs(thread);
+
 		/*
 		 * Opt the other thread into seccomp if needed.
 		 * As threads are considered to be trust-realm
 		 * equivalent (see ptrace_may_access), it is safe to
 		 * allow one thread to transition the other.
 		 */
-		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) {
-			/*
-			 * Don't let an unprivileged task work around
-			 * the no_new_privs restriction by creating
-			 * a thread that sets it up, enters seccomp,
-			 * then dies.
-			 */
-			if (task_no_new_privs(caller))
-				task_set_no_new_privs(thread);
-
+		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
 			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
-		}
 	}
 }
 
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index ce033c7aa2e8..9cff0ab82b63 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -69,10 +69,10 @@ static ssize_t posix_clock_read(struct file *fp, char __user *buf,
 static unsigned int posix_clock_poll(struct file *fp, poll_table *wait)
 {
 	struct posix_clock *clk = get_posix_clock(fp);
-	int result = 0;
+	unsigned int result = 0;
 
 	if (!clk)
-		return -ENODEV;
+		return POLLERR;
 
 	if (clk->ops.poll)
 		result = clk->ops.poll(clk, fp, wait);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7f0f1d8d46b0..651ff1a3a306 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -997,9 +997,9 @@ static void tick_nohz_switch_to_nohz(void)
 	/* Get the next period */
 	next = tick_init_jiffy_update();
 
-	hrtimer_forward_now(&ts->sched_timer, tick_period);
 	hrtimer_set_expires(&ts->sched_timer, next);
-	tick_program_event(next, 1);
+	hrtimer_forward_now(&ts->sched_timer, tick_period);
+	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
 	tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
 }
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d563c1960302..99188ee5d9d0 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -305,8 +305,7 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
 
 	delta = timekeeping_get_delta(tkr);
 
-	nsec = delta * tkr->mult + tkr->xtime_nsec;
-	nsec >>= tkr->shift;
+	nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift;
 
 	/* If arch requires, add in get_arch_timeoffset() */
 	return nsec + arch_gettimeoffset();
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 52bb846af3d6..fda3b6e1b3a0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name)
 	struct ftrace_event_field *field;
 	struct list_head *head;
 
-	field = __find_event_field(&ftrace_generic_fields, name);
+	head = trace_get_fields(call);
+	field = __find_event_field(head, name);
 	if (field)
 		return field;
 
-	field = __find_event_field(&ftrace_common_fields, name);
+	field = __find_event_field(&ftrace_generic_fields, name);
 	if (field)
 		return field;
 
-	head = trace_get_fields(call);
-	return __find_event_field(head, name);
+	return __find_event_field(&ftrace_common_fields, name);
 }
 
 static int __trace_define_field(struct list_head *head, const char *type,
@@ -171,8 +171,10 @@ static int trace_define_generic_fields(void)
 {
 	int ret;
 
-	__generic_field(int, cpu, FILTER_OTHER);
-	__generic_field(char *, comm, FILTER_PTR_STRING);
+	__generic_field(int, CPU, FILTER_CPU);
+	__generic_field(int, cpu, FILTER_CPU);
+	__generic_field(char *, COMM, FILTER_COMM);
+	__generic_field(char *, comm, FILTER_COMM);
 
 	return ret;
 }
@@ -870,7 +872,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
 		 */
-		if (call->class && call->class->reg)
+		if (call->class && call->class->reg &&
+		    !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
 			return file;
 	}
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index f93a219b18da..6816302542b2 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps,
 		return -EINVAL;
 	}
 
-	if (is_string_field(field)) {
+	if (field->filter_type == FILTER_COMM) {
+		filter_build_regex(pred);
+		fn = filter_pred_comm;
+		pred->regex.field_len = TASK_COMM_LEN;
+	} else if (is_string_field(field)) {
 		filter_build_regex(pred);
 
-		if (!strcmp(field->name, "comm")) {
-			fn = filter_pred_comm;
-			pred->regex.field_len = TASK_COMM_LEN;
-		} else if (field->filter_type == FILTER_STATIC_STRING) {
+		if (field->filter_type == FILTER_STATIC_STRING) {
 			fn = filter_pred_string;
 			pred->regex.field_len = field->size;
 		} else if (field->filter_type == FILTER_DYN_STRING)
@@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps,
 		}
 		pred->val = val;
 
-		if (!strcmp(field->name, "cpu"))
+		if (field->filter_type == FILTER_CPU)
 			fn = filter_pred_cpu;
 		else
 			fn = select_comparison_fn(pred->op, field->size,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 58fe79122a61..ef84d9874d03 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -571,6 +571,16 @@ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
 						  int node)
 {
 	assert_rcu_or_wq_mutex_or_pool_mutex(wq);
+
+	/*
+	 * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a
+	 * delayed item is pending.  The plan is to keep CPU -> NODE
+	 * mapping valid and stable across CPU on/offlines.  Once that
+	 * happens, this workaround can be removed.
+	 */
+	if (unlikely(node == NUMA_NO_NODE))
+		return wq->dfl_pwq;
+
 	return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
 }
 
@@ -1465,13 +1475,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	timer_stats_timer_set_start_info(&dwork->timer);
 
 	dwork->wq = wq;
-	/* timer isn't guaranteed to run in this cpu, record earlier */
-	if (cpu == WORK_CPU_UNBOUND)
-		cpu = raw_smp_processor_id();
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
 
-	add_timer_on(timer, cpu);
+	if (unlikely(cpu != WORK_CPU_UNBOUND))
+		add_timer_on(timer, cpu);
+	else
+		add_timer(timer);
 }
 
 /**