Merge branch 'for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu into for-3.11

This is to receive percpu_refcount which will replace atomic_t
reference count in cgroup_subsys_state.

Signed-off-by: Tejun Heo <tj@kernel.org>

18 files changed, 195 insertions, 213 deletions

diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 83a2970295d..6bd4a90d199 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1021,9 +1021,6 @@ static void audit_log_rule_change(char *action, struct audit_krule *rule, int re
  * @seq: netlink audit message sequence (serial) number
  * @data: payload data
  * @datasz: size of payload data
- * @loginuid: loginuid of sender
- * @sessionid: sessionid for netlink audit message
- * @sid: SE Linux Security ID of sender
  */
 int audit_receive_filter(int type, int pid, int seq, void *data, size_t datasz)
 {
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index df6814706cc..ebbfc043153 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1688,11 +1688,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		 */
 		cgroup_free_root(opts.new_root);
 
-		if (((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) &&
-		    root->flags != opts.flags) {
-			pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
-			ret = -EINVAL;
-			goto drop_new_super;
+		if (root->flags != opts.flags) {
+			if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) {
+				pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
+				ret = -EINVAL;
+				goto drop_new_super;
+			} else {
+				pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
+			}
 		}
 
 		/* no subsys rebinding, so refcounts don't change */
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index 8b86c0c68ed..d5585f5e038 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -40,11 +40,13 @@ __setup("hlt", cpu_idle_nopoll_setup);
 
 static inline int cpu_idle_poll(void)
 {
+	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
 	while (!need_resched())
 		cpu_relax();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+	rcu_idle_exit();
 	return 1;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6b41c1899a8..9dc297faf7c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4394,6 +4394,64 @@ perf_event_read_event(struct perf_event *event,
 	perf_output_end(&handle);
 }
 
+typedef int  (perf_event_aux_match_cb)(struct perf_event *event, void *data);
+typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data);
+
+static void
+perf_event_aux_ctx(struct perf_event_context *ctx,
+		   perf_event_aux_match_cb match,
+		   perf_event_aux_output_cb output,
+		   void *data)
+{
+	struct perf_event *event;
+
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+		if (event->state < PERF_EVENT_STATE_INACTIVE)
+			continue;
+		if (!event_filter_match(event))
+			continue;
+		if (match(event, data))
+			output(event, data);
+	}
+}
+
+static void
+perf_event_aux(perf_event_aux_match_cb match,
+	       perf_event_aux_output_cb output,
+	       void *data,
+	       struct perf_event_context *task_ctx)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+	int ctxn;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->unique_pmu != pmu)
+			goto next;
+		perf_event_aux_ctx(&cpuctx->ctx, match, output, data);
+		if (task_ctx)
+			goto next;
+		ctxn = pmu->task_ctx_nr;
+		if (ctxn < 0)
+			goto next;
+		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		if (ctx)
+			perf_event_aux_ctx(ctx, match, output, data);
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
+	}
+
+	if (task_ctx) {
+		preempt_disable();
+		perf_event_aux_ctx(task_ctx, match, output, data);
+		preempt_enable();
+	}
+	rcu_read_unlock();
+}
+
 /*
  * task tracking -- fork/exit
  *
@@ -4416,8 +4474,9 @@ struct perf_task_event {
 };
 
 static void perf_event_task_output(struct perf_event *event,
-				     struct perf_task_event *task_event)
+				   void *data)
 {
+	struct perf_task_event *task_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data	sample;
 	struct task_struct *task = task_event->task;
@@ -4445,62 +4504,11 @@ out:
 	task_event->event_id.header.size = size;
 }
 
-static int perf_event_task_match(struct perf_event *event)
-{
-	if (event->state < PERF_EVENT_STATE_INACTIVE)
-		return 0;
-
-	if (!event_filter_match(event))
-		return 0;
-
-	if (event->attr.comm || event->attr.mmap ||
-	    event->attr.mmap_data || event->attr.task)
-		return 1;
-
-	return 0;
-}
-
-static void perf_event_task_ctx(struct perf_event_context *ctx,
-				  struct perf_task_event *task_event)
+static int perf_event_task_match(struct perf_event *event,
+				 void *data __maybe_unused)
 {
-	struct perf_event *event;
-
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-		if (perf_event_task_match(event))
-			perf_event_task_output(event, task_event);
-	}
-}
-
-static void perf_event_task_event(struct perf_task_event *task_event)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
-	struct pmu *pmu;
-	int ctxn;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->unique_pmu != pmu)
-			goto next;
-		perf_event_task_ctx(&cpuctx->ctx, task_event);
-
-		ctx = task_event->task_ctx;
-		if (!ctx) {
-			ctxn = pmu->task_ctx_nr;
-			if (ctxn < 0)
-				goto next;
-			ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
-			if (ctx)
-				perf_event_task_ctx(ctx, task_event);
-		}
-next:
-		put_cpu_ptr(pmu->pmu_cpu_context);
-	}
-	if (task_event->task_ctx)
-		perf_event_task_ctx(task_event->task_ctx, task_event);
-
-	rcu_read_unlock();
+	return event->attr.comm || event->attr.mmap ||
+	       event->attr.mmap_data || event->attr.task;
 }
 
 static void perf_event_task(struct task_struct *task,
@@ -4531,7 +4539,10 @@ static void perf_event_task(struct task_struct *task,
 		},
 	};
 
-	perf_event_task_event(&task_event);
+	perf_event_aux(perf_event_task_match,
+		       perf_event_task_output,
+		       &task_event,
+		       task_ctx);
 }
 
 void perf_event_fork(struct task_struct *task)
@@ -4557,8 +4568,9 @@ struct perf_comm_event {
 };
 
 static void perf_event_comm_output(struct perf_event *event,
-				     struct perf_comm_event *comm_event)
+				   void *data)
 {
+	struct perf_comm_event *comm_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
 	int size = comm_event->event_id.header.size;
@@ -4585,39 +4597,16 @@ out:
 	comm_event->event_id.header.size = size;
 }
 
-static int perf_event_comm_match(struct perf_event *event)
-{
-	if (event->state < PERF_EVENT_STATE_INACTIVE)
-		return 0;
-
-	if (!event_filter_match(event))
-		return 0;
-
-	if (event->attr.comm)
-		return 1;
-
-	return 0;
-}
-
-static void perf_event_comm_ctx(struct perf_event_context *ctx,
-				  struct perf_comm_event *comm_event)
+static int perf_event_comm_match(struct perf_event *event,
+				 void *data __maybe_unused)
 {
-	struct perf_event *event;
-
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-		if (perf_event_comm_match(event))
-			perf_event_comm_output(event, comm_event);
-	}
+	return event->attr.comm;
 }
 
 static void perf_event_comm_event(struct perf_comm_event *comm_event)
 {
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
 	char comm[TASK_COMM_LEN];
 	unsigned int size;
-	struct pmu *pmu;
-	int ctxn;
 
 	memset(comm, 0, sizeof(comm));
 	strlcpy(comm, comm_event->task->comm, sizeof(comm));
@@ -4627,24 +4616,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	comm_event->comm_size = size;
 
 	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
-	rcu_read_lock();
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->unique_pmu != pmu)
-			goto next;
-		perf_event_comm_ctx(&cpuctx->ctx, comm_event);
 
-		ctxn = pmu->task_ctx_nr;
-		if (ctxn < 0)
-			goto next;
-
-		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
-		if (ctx)
-			perf_event_comm_ctx(ctx, comm_event);
-next:
-		put_cpu_ptr(pmu->pmu_cpu_context);
-	}
-	rcu_read_unlock();
+	perf_event_aux(perf_event_comm_match,
+		       perf_event_comm_output,
+		       comm_event,
+		       NULL);
 }
 
 void perf_event_comm(struct task_struct *task)
@@ -4706,8 +4682,9 @@ struct perf_mmap_event {
 };
 
 static void perf_event_mmap_output(struct perf_event *event,
-				     struct perf_mmap_event *mmap_event)
+				   void *data)
 {
+	struct perf_mmap_event *mmap_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
 	int size = mmap_event->event_id.header.size;
@@ -4734,46 +4711,24 @@ out:
 }
 
 static int perf_event_mmap_match(struct perf_event *event,
-				   struct perf_mmap_event *mmap_event,
-				   int executable)
-{
-	if (event->state < PERF_EVENT_STATE_INACTIVE)
-		return 0;
-
-	if (!event_filter_match(event))
-		return 0;
-
-	if ((!executable && event->attr.mmap_data) ||
-	    (executable && event->attr.mmap))
-		return 1;
-
-	return 0;
-}
-
-static void perf_event_mmap_ctx(struct perf_event_context *ctx,
-				  struct perf_mmap_event *mmap_event,
-				  int executable)
+				 void *data)
 {
-	struct perf_event *event;
+	struct perf_mmap_event *mmap_event = data;
+	struct vm_area_struct *vma = mmap_event->vma;
+	int executable = vma->vm_flags & VM_EXEC;
 
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-		if (perf_event_mmap_match(event, mmap_event, executable))
-			perf_event_mmap_output(event, mmap_event);
-	}
+	return (!executable && event->attr.mmap_data) ||
+	       (executable && event->attr.mmap);
 }
 
 static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 {
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
 	struct vm_area_struct *vma = mmap_event->vma;
 	struct file *file = vma->vm_file;
 	unsigned int size;
 	char tmp[16];
 	char *buf = NULL;
 	const char *name;
-	struct pmu *pmu;
-	int ctxn;
 
 	memset(tmp, 0, sizeof(tmp));
 
@@ -4829,27 +4784,10 @@ got_name:
 
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->unique_pmu != pmu)
-			goto next;
-		perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
-					vma->vm_flags & VM_EXEC);
-
-		ctxn = pmu->task_ctx_nr;
-		if (ctxn < 0)
-			goto next;
-
-		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
-		if (ctx) {
-			perf_event_mmap_ctx(ctx, mmap_event,
-					vma->vm_flags & VM_EXEC);
-		}
-next:
-		put_cpu_ptr(pmu->pmu_cpu_context);
-	}
-	rcu_read_unlock();
+	perf_event_aux(perf_event_mmap_match,
+		       perf_event_mmap_output,
+		       mmap_event,
+		       NULL);
 
 	kfree(buf);
 }
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 1296e72e416..8241906c4b6 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -569,6 +569,11 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 	int retval = 0;
 
 	helper_lock();
+	if (!sub_info->path) {
+		retval = -EINVAL;
+		goto out;
+	}
+
 	if (sub_info->path[0] == '\0')
 		goto out;
 
diff --git a/kernel/module.c b/kernel/module.c
index b049939177f..cab4bce49c2 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2431,10 +2431,10 @@ static void kmemleak_load_module(const struct module *mod,
 	kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL);
 
 	for (i = 1; i < info->hdr->e_shnum; i++) {
-		const char *name = info->secstrings + info->sechdrs[i].sh_name;
-		if (!(info->sechdrs[i].sh_flags & SHF_ALLOC))
-			continue;
-		if (!strstarts(name, ".data") && !strstarts(name, ".bss"))
+		/* Scan all writable sections that's not executable */
+		if (!(info->sechdrs[i].sh_flags & SHF_ALLOC) ||
+		    !(info->sechdrs[i].sh_flags & SHF_WRITE) ||
+		    (info->sechdrs[i].sh_flags & SHF_EXECINSTR))
 			continue;
 
 		kmemleak_scan_area((void *)info->sechdrs[i].sh_addr,
@@ -2769,24 +2769,11 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 	mod->trace_events = section_objs(info, "_ftrace_events",
 					 sizeof(*mod->trace_events),
 					 &mod->num_trace_events);
-	/*
-	 * This section contains pointers to allocated objects in the trace
-	 * code and not scanning it leads to false positives.
-	 */
-	kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) *
-			   mod->num_trace_events, GFP_KERNEL);
 #endif
 #ifdef CONFIG_TRACING
 	mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt",
 					 sizeof(*mod->trace_bprintk_fmt_start),
 					 &mod->num_trace_bprintk_fmt);
-	/*
-	 * This section contains pointers to allocated objects in the trace
-	 * code and not scanning it leads to false positives.
-	 */
-	kmemleak_scan_area(mod->trace_bprintk_fmt_start,
-			   sizeof(*mod->trace_bprintk_fmt_start) *
-			   mod->num_trace_bprintk_fmt, GFP_KERNEL);
 #endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 	/* sechdrs[0].sh_size is always zero */
diff --git a/kernel/range.c b/kernel/range.c
index 071b0ab455c..eb911dbce26 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -48,9 +48,11 @@ int add_range_with_merge(struct range *range, int az, int nr_range,
 		final_start = min(range[i].start, start);
 		final_end = max(range[i].end, end);
 
-		range[i].start = final_start;
-		range[i].end =  final_end;
-		return nr_range;
+		/* clear it and add it back for further merge */
+		range[i].start = 0;
+		range[i].end =  0;
+		return add_range_with_merge(range, az, nr_range,
+			final_start, final_end);
 	}
 
 	/* Need to add it: */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 170814dc418..3db5a375d8d 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -88,7 +88,7 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_RCU_NOCB_CPU
 #ifndef CONFIG_RCU_NOCB_CPU_NONE
 	if (!have_rcu_nocb_mask) {
-		alloc_bootmem_cpumask_var(&rcu_nocb_mask);
+		zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL);
 		have_rcu_nocb_mask = true;
 	}
 #ifdef CONFIG_RCU_NOCB_CPU_ZERO
@@ -1667,7 +1667,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj)
 	rdtp->last_accelerate = jiffies;
 
 	/* Request timer delay depending on laziness, and round. */
-	if (rdtp->all_lazy) {
+	if (!rdtp->all_lazy) {
 		*dj = round_up(rcu_idle_gp_delay + jiffies,
 			       rcu_idle_gp_delay) - jiffies;
 	} else {
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index e4c07b0692b..70f27e89012 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -12,11 +12,6 @@ config CLOCKSOURCE_WATCHDOG
 config ARCH_CLOCKSOURCE_DATA
 	bool
 
-# Platforms has a persistent clock
-config ALWAYS_USE_PERSISTENT_CLOCK
-	bool
-	default n
-
 # Timekeeping vsyscall support
 config GENERIC_TIME_VSYSCALL
 	bool
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 206bbfb34e0..24938d57766 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -786,11 +786,11 @@ bool tick_broadcast_oneshot_available(void)
 
 void __init tick_broadcast_init(void)
 {
-	alloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
-	alloc_cpumask_var(&tmpmask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tmpmask, GFP_NOWAIT);
 #ifdef CONFIG_TICK_ONESHOT
-	alloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
-	alloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT);
-	alloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT);
 #endif
 }
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index bc67d4245e1..f4208138fbf 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -717,6 +717,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	if (unlikely(!cpu_online(cpu))) {
 		if (cpu == tick_do_timer_cpu)
 			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+		return false;
 	}
 
 	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
@@ -1168,7 +1169,7 @@ void tick_cancel_sched_timer(int cpu)
 		hrtimer_cancel(&ts->sched_timer);
 # endif
 
-	ts->nohz_mode = NOHZ_MODE_INACTIVE;
+	memset(ts, 0, sizeof(*ts));
 }
 #endif
 
diff --git a/kernel/timer.c b/kernel/timer.c
index a860bba3441..15ffdb3f194 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1539,12 +1539,12 @@ static int __cpuinit init_timers_cpu(int cpu)
 			boot_done = 1;
 			base = &boot_tvec_bases;
 		}
+		spin_lock_init(&base->lock);
 		tvec_base_done[cpu] = 1;
 	} else {
 		base = per_cpu(tvec_bases, cpu);
 	}
 
-	spin_lock_init(&base->lock);
 
 	for (j = 0; j < TVN_SIZE; j++) {
 		INIT_LIST_HEAD(base->tv5.vec + j);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b59aea2c48c..e444ff88f0a 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -620,6 +620,9 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 	if (cpu == RING_BUFFER_ALL_CPUS)
 		work = &buffer->irq_work;
 	else {
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			return -EINVAL;
+
 		cpu_buffer = buffer->buffers[cpu];
 		work = &cpu_buffer->irq_work;
 	}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ae6fa2d1cdf..4d79485b323 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6216,10 +6216,15 @@ __init static int tracer_alloc_buffers(void)
 
 	trace_init_cmdlines();
 
-	register_tracer(&nop_trace);
-
+	/*
+	 * register_tracer() might reference current_trace, so it
+	 * needs to be set before we register anything. This is
+	 * just a bootstrap of current_trace anyway.
+	 */
 	global_trace.current_trace = &nop_trace;
 
+	register_tracer(&nop_trace);
+
 	/* All seems OK, enable tracing */
 	tracing_disabled = 0;
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7a0cf68027c..27963e2bf4b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2072,8 +2072,10 @@ event_enable_func(struct ftrace_hash *hash,
  out_reg:
 	/* Don't let event modules unload while probe registered */
 	ret = try_module_get(file->event_call->mod);
-	if (!ret)
+	if (!ret) {
+		ret = -EBUSY;
 		goto out_free;
+	}
 
 	ret = __ftrace_event_enable_disable(file, 1, 1);
 	if (ret < 0)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index a6361178de5..e1b653f7e1c 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -750,7 +750,11 @@ static int filter_set_pred(struct event_filter *filter,
 
 static void __free_preds(struct event_filter *filter)
 {
+	int i;
+
 	if (filter->preds) {
+		for (i = 0; i < filter->n_preds; i++)
+			kfree(filter->preds[i].ops);
 		kfree(filter->preds);
 		filter->preds = NULL;
 	}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 636d45fe69b..9f46e98ba8f 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -35,7 +35,7 @@ struct trace_probe {
 	const char		*symbol;	/* symbol name */
 	struct ftrace_event_class	class;
 	struct ftrace_event_call	call;
-	struct ftrace_event_file	**files;
+	struct ftrace_event_file * __rcu *files;
 	ssize_t			size;		/* trace entry size */
 	unsigned int		nr_args;
 	struct probe_arg	args[];
@@ -185,9 +185,14 @@ static struct trace_probe *find_trace_probe(const char *event,
 
 static int trace_probe_nr_files(struct trace_probe *tp)
 {
-	struct ftrace_event_file **file = tp->files;
+	struct ftrace_event_file **file;
 	int ret = 0;
 
+	/*
+	 * Since all tp->files updater is protected by probe_enable_lock,
+	 * we don't need to lock an rcu_read_lock.
+	 */
+	file = rcu_dereference_raw(tp->files);
 	if (file)
 		while (*(file++))
 			ret++;
@@ -209,9 +214,10 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 	mutex_lock(&probe_enable_lock);
 
 	if (file) {
-		struct ftrace_event_file **new, **old = tp->files;
+		struct ftrace_event_file **new, **old;
 		int n = trace_probe_nr_files(tp);
 
+		old = rcu_dereference_raw(tp->files);
 		/* 1 is for new one and 1 is for stopper */
 		new = kzalloc((n + 2) * sizeof(struct ftrace_event_file *),
 			      GFP_KERNEL);
@@ -251,11 +257,17 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 static int
 trace_probe_file_index(struct trace_probe *tp, struct ftrace_event_file *file)
 {
+	struct ftrace_event_file **files;
 	int i;
 
-	if (tp->files) {
-		for (i = 0; tp->files[i]; i++)
-			if (tp->files[i] == file)
+	/*
+	 * Since all tp->files updater is protected by probe_enable_lock,
+	 * we don't need to lock an rcu_read_lock.
+	 */
+	files = rcu_dereference_raw(tp->files);
+	if (files) {
+		for (i = 0; files[i]; i++)
+			if (files[i] == file)
 				return i;
 	}
 
@@ -274,10 +286,11 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 	mutex_lock(&probe_enable_lock);
 
 	if (file) {
-		struct ftrace_event_file **new, **old = tp->files;
+		struct ftrace_event_file **new, **old;
 		int n = trace_probe_nr_files(tp);
 		int i, j;
 
+		old = rcu_dereference_raw(tp->files);
 		if (n == 0 || trace_probe_file_index(tp, file) < 0) {
 			ret = -EINVAL;
 			goto out_unlock;
@@ -872,9 +885,16 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
 static __kprobes void
 kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs)
 {
-	struct ftrace_event_file **file = tp->files;
+	/*
+	 * Note: preempt is already disabled around the kprobe handler.
+	 * However, we still need an smp_read_barrier_depends() corresponding
+	 * to smp_wmb() in rcu_assign_pointer() to access the pointer.
+	 */
+	struct ftrace_event_file **file = rcu_dereference_raw(tp->files);
+
+	if (unlikely(!file))
+		return;
 
-	/* Note: preempt is already disabled around the kprobe handler */
 	while (*file) {
 		__kprobe_trace_func(tp, regs, *file);
 		file++;
@@ -925,9 +945,16 @@ static __kprobes void
 kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 		     struct pt_regs *regs)
 {
-	struct ftrace_event_file **file = tp->files;
+	/*
+	 * Note: preempt is already disabled around the kprobe handler.
+	 * However, we still need an smp_read_barrier_depends() corresponding
+	 * to smp_wmb() in rcu_assign_pointer() to access the pointer.
+	 */
+	struct ftrace_event_file **file = rcu_dereference_raw(tp->files);
+
+	if (unlikely(!file))
+		return;
 
-	/* Note: preempt is already disabled around the kprobe handler */
 	while (*file) {
 		__kretprobe_trace_func(tp, ri, regs, *file);
 		file++;
@@ -935,7 +962,7 @@ kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 }
 
 /* Event entry printers */
-enum print_line_t
+static enum print_line_t
 print_kprobe_event(struct trace_iterator *iter, int flags,
 		   struct trace_event *event)
 {
@@ -971,7 +998,7 @@ partial:
 	return TRACE_TYPE_PARTIAL_LINE;
 }
 
-enum print_line_t
+static enum print_line_t
 print_kretprobe_event(struct trace_iterator *iter, int flags,
 		      struct trace_event *event)
 {
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4aa9f5bc6b2..ee8e29a2320 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -296,7 +296,7 @@ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER);
 static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
 
 struct workqueue_struct *system_wq __read_mostly;
-EXPORT_SYMBOL_GPL(system_wq);
+EXPORT_SYMBOL(system_wq);
 struct workqueue_struct *system_highpri_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_highpri_wq);
 struct workqueue_struct *system_long_wq __read_mostly;
@@ -1411,7 +1411,7 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq,
 	local_irq_restore(flags);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(queue_work_on);
+EXPORT_SYMBOL(queue_work_on);
 
 void delayed_work_timer_fn(unsigned long __data)
 {
@@ -1485,7 +1485,7 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 	local_irq_restore(flags);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(queue_delayed_work_on);
+EXPORT_SYMBOL(queue_delayed_work_on);
 
 /**
  * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU
@@ -2059,6 +2059,7 @@ static bool manage_workers(struct worker *worker)
 	if (unlikely(!mutex_trylock(&pool->manager_mutex))) {
 		spin_unlock_irq(&pool->lock);
 		mutex_lock(&pool->manager_mutex);
+		spin_lock_irq(&pool->lock);
 		ret = true;
 	}
 
@@ -4311,6 +4312,12 @@ bool current_is_workqueue_rescuer(void)
  * no synchronization around this function and the test result is
  * unreliable and only useful as advisory hints or for debugging.
  *
+ * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU.
+ * Note that both per-cpu and unbound workqueues may be associated with
+ * multiple pool_workqueues which have separate congested states.  A
+ * workqueue being congested on one CPU doesn't mean the workqueue is also
+ * contested on other CPUs / NUMA nodes.
+ *
  * RETURNS:
  * %true if congested, %false otherwise.
  */
@@ -4321,6 +4328,9 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
 
 	rcu_read_lock_sched();
 
+	if (cpu == WORK_CPU_UNBOUND)
+		cpu = smp_processor_id();
+
 	if (!(wq->flags & WQ_UNBOUND))
 		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
 	else
@@ -4895,7 +4905,8 @@ static void __init wq_numa_init(void)
 	BUG_ON(!tbl);
 
 	for_each_node(node)
-		BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node));
+		BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
+				node_online(node) ? node : NUMA_NO_NODE));
 
 	for_each_possible_cpu(cpu) {
 		node = cpu_to_node(cpu);