Merge branch 'iov_iter' into for-next

35 files changed, 410 insertions, 260 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index dc5c77544fd6..17ea6d4a9a24 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -86,7 +86,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_CPU_PM) += cpu_pm.o
-obj-$(CONFIG_NET) += bpf/
+obj-$(CONFIG_BPF) += bpf/
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
diff --git a/kernel/audit.c b/kernel/audit.c
index 80983df92cd4..cebb11db4d34 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -739,7 +739,7 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature
 
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE);
 	audit_log_task_info(ab, current);
-	audit_log_format(ab, "feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
+	audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
 			 audit_feature_names[which], !!old_feature, !!new_feature,
 			 !!old_lock, !!new_lock, res);
 	audit_log_end(ab);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index e242e3a9864a..80f29e015570 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -154,6 +154,7 @@ static struct audit_chunk *alloc_chunk(int count)
 		chunk->owners[i].index = i;
 	}
 	fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch);
+	chunk->mark.mask = FS_IN_IGNORED;
 	return chunk;
 }
 
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 45427239f375..0daf7f6ae7df 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,5 @@
-obj-y := core.o syscall.o verifier.o
-
+obj-y := core.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o
 ifdef CONFIG_TEST_BPF
-obj-y += test_stub.o
+obj-$(CONFIG_BPF_SYSCALL) += test_stub.o
 endif
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f0c30c59b317..d6594e457a25 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -655,3 +655,12 @@ void bpf_prog_free(struct bpf_prog *fp)
 	schedule_work(&aux->work);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_free);
+
+/* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
+ * skb_copy_bits(), so provide a weak definition of it for NET-less config.
+ */
+int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
+			 int len)
+{
+	return -EFAULT;
+}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 801f5f3b9307..9f81818f2941 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1409,7 +1409,8 @@ static bool states_equal(struct verifier_state *old, struct verifier_state *cur)
 		if (memcmp(&old->regs[i], &cur->regs[i],
 			   sizeof(old->regs[0])) != 0) {
 			if (old->regs[i].type == NOT_INIT ||
-			    old->regs[i].type == UNKNOWN_VALUE)
+			    (old->regs[i].type == UNKNOWN_VALUE &&
+			     cur->regs[i].type != NOT_INIT))
 				continue;
 			return false;
 		}
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 5664985c46a0..937ecdfdf258 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -107,46 +107,6 @@ void context_tracking_user_enter(void)
 }
 NOKPROBE_SYMBOL(context_tracking_user_enter);
 
-#ifdef CONFIG_PREEMPT
-/**
- * preempt_schedule_context - preempt_schedule called by tracing
- *
- * The tracing infrastructure uses preempt_enable_notrace to prevent
- * recursion and tracing preempt enabling caused by the tracing
- * infrastructure itself. But as tracing can happen in areas coming
- * from userspace or just about to enter userspace, a preempt enable
- * can occur before user_exit() is called. This will cause the scheduler
- * to be called when the system is still in usermode.
- *
- * To prevent this, the preempt_enable_notrace will use this function
- * instead of preempt_schedule() to exit user context if needed before
- * calling the scheduler.
- */
-asmlinkage __visible void __sched notrace preempt_schedule_context(void)
-{
-	enum ctx_state prev_ctx;
-
-	if (likely(!preemptible()))
-		return;
-
-	/*
-	 * Need to disable preemption in case user_exit() is traced
-	 * and the tracer calls preempt_enable_notrace() causing
-	 * an infinite recursion.
-	 */
-	preempt_disable_notrace();
-	prev_ctx = exception_enter();
-	preempt_enable_no_resched_notrace();
-
-	preempt_schedule();
-
-	preempt_disable_notrace();
-	exception_exit(prev_ctx);
-	preempt_enable_notrace();
-}
-EXPORT_SYMBOL_GPL(preempt_schedule_context);
-#endif /* CONFIG_PREEMPT */
-
 /**
  * context_tracking_user_exit - Inform the context tracking that the CPU is
  *                              exiting userspace mode and entering the kernel.
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 356450f09c1f..90a3d017b90c 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -64,6 +64,8 @@ static struct {
 	 * an ongoing cpu hotplug operation.
 	 */
 	int refcount;
+	/* And allows lockless put_online_cpus(). */
+	atomic_t puts_pending;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
@@ -113,7 +115,11 @@ void put_online_cpus(void)
 {
 	if (cpu_hotplug.active_writer == current)
 		return;
-	mutex_lock(&cpu_hotplug.lock);
+	if (!mutex_trylock(&cpu_hotplug.lock)) {
+		atomic_inc(&cpu_hotplug.puts_pending);
+		cpuhp_lock_release();
+		return;
+	}
 
 	if (WARN_ON(!cpu_hotplug.refcount))
 		cpu_hotplug.refcount++; /* try to fix things up */
@@ -155,6 +161,12 @@ void cpu_hotplug_begin(void)
 	cpuhp_lock_acquire();
 	for (;;) {
 		mutex_lock(&cpu_hotplug.lock);
+		if (atomic_read(&cpu_hotplug.puts_pending)) {
+			int delta;
+
+			delta = atomic_xchg(&cpu_hotplug.puts_pending, 0);
+			cpu_hotplug.refcount -= delta;
+		}
 		if (likely(!cpu_hotplug.refcount))
 			break;
 		__set_current_state(TASK_UNINTERRUPTIBLE);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 446fbeefad1c..e56923026dd8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1562,8 +1562,10 @@ static void perf_remove_from_context(struct perf_event *event, bool detach_group
 
 	if (!task) {
 		/*
-		 * Per cpu events are removed via an smp call and
-		 * the removal is always successful.
+		 * Per cpu events are removed via an smp call. The removal can
+		 * fail if the CPU is currently offline, but in that case we
+		 * already called __perf_remove_from_context from
+		 * perf_event_exit_cpu.
 		 */
 		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
 		return;
@@ -6071,11 +6073,6 @@ static int perf_swevent_init(struct perf_event *event)
 	return 0;
 }
 
-static int perf_swevent_event_idx(struct perf_event *event)
-{
-	return 0;
-}
-
 static struct pmu perf_swevent = {
 	.task_ctx_nr	= perf_sw_context,
 
@@ -6085,8 +6082,6 @@ static struct pmu perf_swevent = {
 	.start		= perf_swevent_start,
 	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
-
-	.event_idx	= perf_swevent_event_idx,
 };
 
 #ifdef CONFIG_EVENT_TRACING
@@ -6204,8 +6199,6 @@ static struct pmu perf_tracepoint = {
 	.start		= perf_swevent_start,
 	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
-
-	.event_idx	= perf_swevent_event_idx,
 };
 
 static inline void perf_tp_register(void)
@@ -6431,8 +6424,6 @@ static struct pmu perf_cpu_clock = {
 	.start		= cpu_clock_event_start,
 	.stop		= cpu_clock_event_stop,
 	.read		= cpu_clock_event_read,
-
-	.event_idx	= perf_swevent_event_idx,
 };
 
 /*
@@ -6511,8 +6502,6 @@ static struct pmu perf_task_clock = {
 	.start		= task_clock_event_start,
 	.stop		= task_clock_event_stop,
 	.read		= task_clock_event_read,
-
-	.event_idx	= perf_swevent_event_idx,
 };
 
 static void perf_pmu_nop_void(struct pmu *pmu)
@@ -6542,7 +6531,7 @@ static void perf_pmu_cancel_txn(struct pmu *pmu)
 
 static int perf_event_idx_default(struct perf_event *event)
 {
-	return event->hw.idx + 1;
+	return 0;
 }
 
 /*
@@ -8130,7 +8119,7 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 
 static void __perf_event_exit_context(void *__info)
 {
-	struct remove_event re = { .detach_group = false };
+	struct remove_event re = { .detach_group = true };
 	struct perf_event_context *ctx = __info;
 
 	perf_pmu_rotate_stop(ctx->pmu);
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 1559fb0b9296..9803a6600d49 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -605,11 +605,6 @@ static void hw_breakpoint_stop(struct perf_event *bp, int flags)
 	bp->hw.state = PERF_HES_STOPPED;
 }
 
-static int hw_breakpoint_event_idx(struct perf_event *bp)
-{
-	return 0;
-}
-
 static struct pmu perf_breakpoint = {
 	.task_ctx_nr	= perf_sw_context, /* could eventually get its own */
 
@@ -619,8 +614,6 @@ static struct pmu perf_breakpoint = {
 	.start		= hw_breakpoint_start,
 	.stop		= hw_breakpoint_stop,
 	.read		= hw_breakpoint_pmu_read,
-
-	.event_idx	= hw_breakpoint_event_idx,
 };
 
 int __init init_hw_breakpoint(void)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 1d0af8a2c646..ed8f2cde34c5 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1640,7 +1640,6 @@ bool uprobe_deny_signal(void)
 		if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
 			utask->state = UTASK_SSTEP_TRAPPED;
 			set_tsk_thread_flag(t, TIF_UPROBE);
-			set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
 		}
 	}
 
diff --git a/kernel/futex.c b/kernel/futex.c
index f3a3a071283c..63678b573d61 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -143,9 +143,8 @@
  *
  * Where (A) orders the waiters increment and the futex value read through
  * atomic operations (see hb_waiters_inc) and where (B) orders the write
- * to futex and the waiters read -- this is done by the barriers in
- * get_futex_key_refs(), through either ihold or atomic_inc, depending on the
- * futex type.
+ * to futex and the waiters read -- this is done by the barriers for both
+ * shared and private futexes in get_futex_key_refs().
  *
  * This yields the following case (where X:=waiters, Y:=futex):
  *
@@ -344,13 +343,20 @@ static void get_futex_key_refs(union futex_key *key)
 		futex_get_mm(key); /* implies MB (B) */
 		break;
 	default:
+		/*
+		 * Private futexes do not hold reference on an inode or
+		 * mm, therefore the only purpose of calling get_futex_key_refs
+		 * is because we need the barrier for the lockless waiter check.
+		 */
 		smp_mb(); /* explicit MB (B) */
 	}
 }
 
 /*
  * Drop a reference to the resource addressed by a key.
- * The hash bucket spinlock must not be held.
+ * The hash bucket spinlock must not be held. This is
+ * a no-op for private futexes, see comment in the get
+ * counterpart.
  */
 static void drop_futex_key_refs(union futex_key *key)
 {
@@ -641,8 +647,14 @@ static struct futex_pi_state * alloc_pi_state(void)
 	return pi_state;
 }
 
+/*
+ * Must be called with the hb lock held.
+ */
 static void free_pi_state(struct futex_pi_state *pi_state)
 {
+	if (!pi_state)
+		return;
+
 	if (!atomic_dec_and_test(&pi_state->refcount))
 		return;
 
@@ -1521,15 +1533,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	}
 
 retry:
-	if (pi_state != NULL) {
-		/*
-		 * We will have to lookup the pi_state again, so free this one
-		 * to keep the accounting correct.
-		 */
-		free_pi_state(pi_state);
-		pi_state = NULL;
-	}
-
 	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
@@ -1619,6 +1622,8 @@ retry_private:
 		case 0:
 			break;
 		case -EFAULT:
+			free_pi_state(pi_state);
+			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
@@ -1634,6 +1639,8 @@ retry_private:
 			 *   exit to complete.
 			 * - The user space value changed.
 			 */
+			free_pi_state(pi_state);
+			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
@@ -1710,6 +1717,7 @@ retry_private:
 	}
 
 out_unlock:
+	free_pi_state(pi_state);
 	double_unlock_hb(hb1, hb2);
 	hb_waiters_dec(hb2);
 
@@ -1727,8 +1735,6 @@ out_put_keys:
 out_put_key1:
 	put_futex_key(&key1);
 out:
-	if (pi_state != NULL)
-		free_pi_state(pi_state);
 	return ret ? ret : task_count;
 }
 
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index cf66c5c8458e..3b7408759bdf 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -35,7 +35,7 @@ config GCOV_KERNEL
 config GCOV_PROFILE_ALL
 	bool "Profile entire Kernel"
 	depends on GCOV_KERNEL
-	depends on SUPERH || S390 || X86 || PPC || MICROBLAZE || ARM
+	depends on SUPERH || S390 || X86 || PPC || MICROBLAZE || ARM || ARM64
 	default n
 	---help---
 	This options activates profiling for the entire kernel.
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 8637e041a247..80f7a6d00519 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -196,12 +196,34 @@ int __request_module(bool wait, const char *fmt, ...)
 EXPORT_SYMBOL(__request_module);
 #endif /* CONFIG_MODULES */
 
+static void call_usermodehelper_freeinfo(struct subprocess_info *info)
+{
+	if (info->cleanup)
+		(*info->cleanup)(info);
+	kfree(info);
+}
+
+static void umh_complete(struct subprocess_info *sub_info)
+{
+	struct completion *comp = xchg(&sub_info->complete, NULL);
+	/*
+	 * See call_usermodehelper_exec(). If xchg() returns NULL
+	 * we own sub_info, the UMH_KILLABLE caller has gone away
+	 * or the caller used UMH_NO_WAIT.
+	 */
+	if (comp)
+		complete(comp);
+	else
+		call_usermodehelper_freeinfo(sub_info);
+}
+
 /*
  * This is the task which runs the usermode application
  */
 static int ____call_usermodehelper(void *data)
 {
 	struct subprocess_info *sub_info = data;
+	int wait = sub_info->wait & ~UMH_KILLABLE;
 	struct cred *new;
 	int retval;
 
@@ -221,7 +243,7 @@ static int ____call_usermodehelper(void *data)
 	retval = -ENOMEM;
 	new = prepare_kernel_cred(current);
 	if (!new)
-		goto fail;
+		goto out;
 
 	spin_lock(&umh_sysctl_lock);
 	new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset);
@@ -233,7 +255,7 @@ static int ____call_usermodehelper(void *data)
 		retval = sub_info->init(sub_info, new);
 		if (retval) {
 			abort_creds(new);
-			goto fail;
+			goto out;
 		}
 	}
 
@@ -242,12 +264,13 @@ static int ____call_usermodehelper(void *data)
 	retval = do_execve(getname_kernel(sub_info->path),
 			   (const char __user *const __user *)sub_info->argv,
 			   (const char __user *const __user *)sub_info->envp);
+out:
+	sub_info->retval = retval;
+	/* wait_for_helper() will call umh_complete if UHM_WAIT_PROC. */
+	if (wait != UMH_WAIT_PROC)
+		umh_complete(sub_info);
 	if (!retval)
 		return 0;
-
-	/* Exec failed? */
-fail:
-	sub_info->retval = retval;
 	do_exit(0);
 }
 
@@ -258,26 +281,6 @@ static int call_helper(void *data)
 	return ____call_usermodehelper(data);
 }
 
-static void call_usermodehelper_freeinfo(struct subprocess_info *info)
-{
-	if (info->cleanup)
-		(*info->cleanup)(info);
-	kfree(info);
-}
-
-static void umh_complete(struct subprocess_info *sub_info)
-{
-	struct completion *comp = xchg(&sub_info->complete, NULL);
-	/*
-	 * See call_usermodehelper_exec(). If xchg() returns NULL
-	 * we own sub_info, the UMH_KILLABLE caller has gone away.
-	 */
-	if (comp)
-		complete(comp);
-	else
-		call_usermodehelper_freeinfo(sub_info);
-}
-
 /* Keventd can't block, but this (a child) can. */
 static int wait_for_helper(void *data)
 {
@@ -336,18 +339,8 @@ static void __call_usermodehelper(struct work_struct *work)
 		kmod_thread_locker = NULL;
 	}
 
-	switch (wait) {
-	case UMH_NO_WAIT:
-		call_usermodehelper_freeinfo(sub_info);
-		break;
-
-	case UMH_WAIT_PROC:
-		if (pid > 0)
-			break;
-		/* FALLTHROUGH */
-	case UMH_WAIT_EXEC:
-		if (pid < 0)
-			sub_info->retval = pid;
+	if (pid < 0) {
+		sub_info->retval = pid;
 		umh_complete(sub_info);
 	}
 }
@@ -588,7 +581,12 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 		goto out;
 	}
 
-	sub_info->complete = &done;
+	/*
+	 * Set the completion pointer only if there is a waiter.
+	 * This makes it possible to use umh_complete to free
+	 * the data structure in case of UMH_NO_WAIT.
+	 */
+	sub_info->complete = (wait == UMH_NO_WAIT) ? NULL : &done;
 	sub_info->wait = wait;
 
 	queue_work(khelper_wq, &sub_info->work);
diff --git a/kernel/panic.c b/kernel/panic.c
index d09dc5c32c67..cf80672b7924 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -244,6 +244,7 @@ static const struct tnt tnts[] = {
  *  'I' - Working around severe firmware bug.
  *  'O' - Out-of-tree module has been loaded.
  *  'E' - Unsigned module has been loaded.
+ *  'L' - A soft lockup has previously occurred.
  *
  *	The string is overwritten by the next call to print_tainted().
  */
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index a9dfa79b6bab..1f35a3478f3c 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -502,8 +502,14 @@ int hibernation_restore(int platform_mode)
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
-		dpm_resume_end(PMSG_RECOVER);
+		/*
+		 * The above should either succeed and jump to the new kernel,
+		 * or return with an error. Otherwise things are just
+		 * undefined, so let's be paranoid.
+		 */
+		BUG_ON(!error);
 	}
+	dpm_resume_end(PMSG_RECOVER);
 	pm_restore_gfp_mask();
 	resume_console();
 	pm_restore_console();
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 4ca9a33ff620..c347e3ce3a55 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -146,7 +146,7 @@ static int platform_suspend_prepare(suspend_state_t state)
 
 static int platform_suspend_prepare_late(suspend_state_t state)
 {
-	return state == PM_SUSPEND_FREEZE && freeze_ops->prepare ?
+	return state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->prepare ?
 		freeze_ops->prepare() : 0;
 }
 
@@ -164,7 +164,7 @@ static void platform_resume_noirq(suspend_state_t state)
 
 static void platform_resume_early(suspend_state_t state)
 {
-	if (state == PM_SUSPEND_FREEZE && freeze_ops->restore)
+	if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->restore)
 		freeze_ops->restore();
 }
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 133e47223095..9815447d22e0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3299,11 +3299,16 @@ static void _rcu_barrier(struct rcu_state *rsp)
 			continue;
 		rdp = per_cpu_ptr(rsp->rda, cpu);
 		if (rcu_is_nocb_cpu(cpu)) {
-			_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
-					   rsp->n_barrier_done);
-			atomic_inc(&rsp->barrier_cpu_count);
-			__call_rcu(&rdp->barrier_head, rcu_barrier_callback,
-				   rsp, cpu, 0);
+			if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
+				_rcu_barrier_trace(rsp, "OfflineNoCB", cpu,
+						   rsp->n_barrier_done);
+			} else {
+				_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
+						   rsp->n_barrier_done);
+				atomic_inc(&rsp->barrier_cpu_count);
+				__call_rcu(&rdp->barrier_head,
+					   rcu_barrier_callback, rsp, cpu, 0);
+			}
 		} else if (ACCESS_ONCE(rdp->qlen)) {
 			_rcu_barrier_trace(rsp, "OnlineQ", cpu,
 					   rsp->n_barrier_done);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index d03764652d91..bbdc45d8d74f 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -587,6 +587,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
+static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
 static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
 static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 387dd4599344..c1d7f27bd38f 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2050,6 +2050,33 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
 }
 
 /*
+ * Does the specified CPU need an RCU callback for the specified flavor
+ * of rcu_barrier()?
+ */
+static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+	struct rcu_head *rhp;
+
+	/* No-CBs CPUs might have callbacks on any of three lists. */
+	rhp = ACCESS_ONCE(rdp->nocb_head);
+	if (!rhp)
+		rhp = ACCESS_ONCE(rdp->nocb_gp_head);
+	if (!rhp)
+		rhp = ACCESS_ONCE(rdp->nocb_follower_head);
+
+	/* Having no rcuo kthread but CBs after scheduler starts is bad! */
+	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp) {
+		/* RCU callback enqueued before CPU first came online??? */
+		pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
+		       cpu, rhp->func);
+		WARN_ON_ONCE(1);
+	}
+
+	return !!rhp;
+}
+
+/*
  * Enqueue the specified string of rcu_head structures onto the specified
  * CPU's no-CBs lists.  The CPU is specified by rdp, the head of the
  * string by rhp, and the tail of the string by rhtp.  The non-lazy/lazy
@@ -2642,6 +2669,12 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 
+static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
+{
+	WARN_ON_ONCE(1); /* Should be dead code. */
+	return false;
+}
+
 static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 44999505e1bf..24beb9bb4c3e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2475,44 +2475,6 @@ EXPORT_PER_CPU_SYMBOL(kstat);
 EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
 
 /*
- * Return any ns on the sched_clock that have not yet been accounted in
- * @p in case that task is currently running.
- *
- * Called with task_rq_lock() held on @rq.
- */
-static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
-{
-	u64 ns = 0;
-
-	/*
-	 * Must be ->curr _and_ ->on_rq.  If dequeued, we would
-	 * project cycles that may never be accounted to this
-	 * thread, breaking clock_gettime().
-	 */
-	if (task_current(rq, p) && task_on_rq_queued(p)) {
-		update_rq_clock(rq);
-		ns = rq_clock_task(rq) - p->se.exec_start;
-		if ((s64)ns < 0)
-			ns = 0;
-	}
-
-	return ns;
-}
-
-unsigned long long task_delta_exec(struct task_struct *p)
-{
-	unsigned long flags;
-	struct rq *rq;
-	u64 ns = 0;
-
-	rq = task_rq_lock(p, &flags);
-	ns = do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, p, &flags);
-
-	return ns;
-}
-
-/*
  * Return accounted runtime for the task.
  * In case the task is currently running, return the runtime plus current's
  * pending runtime that have not been accounted yet.
@@ -2521,7 +2483,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 {
 	unsigned long flags;
 	struct rq *rq;
-	u64 ns = 0;
+	u64 ns;
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
 	/*
@@ -2540,7 +2502,16 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 #endif
 
 	rq = task_rq_lock(p, &flags);
-	ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
+	/*
+	 * Must be ->curr _and_ ->on_rq.  If dequeued, we would
+	 * project cycles that may never be accounted to this
+	 * thread, breaking clock_gettime().
+	 */
+	if (task_current(rq, p) && task_on_rq_queued(p)) {
+		update_rq_clock(rq);
+		p->sched_class->update_curr(rq);
+	}
+	ns = p->se.sum_exec_runtime;
 	task_rq_unlock(rq, p, &flags);
 
 	return ns;
@@ -2951,6 +2922,47 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 }
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
+
+#ifdef CONFIG_CONTEXT_TRACKING
+/**
+ * preempt_schedule_context - preempt_schedule called by tracing
+ *
+ * The tracing infrastructure uses preempt_enable_notrace to prevent
+ * recursion and tracing preempt enabling caused by the tracing
+ * infrastructure itself. But as tracing can happen in areas coming
+ * from userspace or just about to enter userspace, a preempt enable
+ * can occur before user_exit() is called. This will cause the scheduler
+ * to be called when the system is still in usermode.
+ *
+ * To prevent this, the preempt_enable_notrace will use this function
+ * instead of preempt_schedule() to exit user context if needed before
+ * calling the scheduler.
+ */
+asmlinkage __visible void __sched notrace preempt_schedule_context(void)
+{
+	enum ctx_state prev_ctx;
+
+	if (likely(!preemptible()))
+		return;
+
+	do {
+		__preempt_count_add(PREEMPT_ACTIVE);
+		/*
+		 * Needs preempt disabled in case user_exit() is traced
+		 * and the tracer calls preempt_enable_notrace() causing
+		 * an infinite recursion.
+		 */
+		prev_ctx = exception_enter();
+		__schedule();
+		exception_exit(prev_ctx);
+
+		__preempt_count_sub(PREEMPT_ACTIVE);
+		barrier();
+	} while (need_resched());
+}
+EXPORT_SYMBOL_GPL(preempt_schedule_context);
+#endif /* CONFIG_CONTEXT_TRACKING */
+
 #endif /* CONFIG_PREEMPT */
 
 /*
@@ -6327,6 +6339,10 @@ static void sched_init_numa(void)
 		if (!sched_debug())
 			break;
 	}
+
+	if (!level)
+		return;
+
 	/*
 	 * 'level' contains the number of unique distances, excluding the
 	 * identity distance node_distance(i,i).
@@ -7403,8 +7419,12 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		put_prev_task(rq, tsk);
 
-	tg = container_of(task_css_check(tsk, cpu_cgrp_id,
-				lockdep_is_held(&tsk->sighand->siglock)),
+	/*
+	 * All callers are synchronized by task_rq_lock(); we do not use RCU
+	 * which is pointless here. Thus, we pass "true" to task_css_check()
+	 * to prevent lockdep warnings.
+	 */
+	tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
 			  struct task_group, css);
 	tg = autogroup_task_group(tsk, tg);
 	tsk->sched_task_group = tg;
@@ -7833,6 +7853,11 @@ static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
 	sched_offline_group(tg);
 }
 
+static void cpu_cgroup_fork(struct task_struct *task)
+{
+	sched_move_task(task);
+}
+
 static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
 				 struct cgroup_taskset *tset)
 {
@@ -8205,6 +8230,7 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_free	= cpu_cgroup_css_free,
 	.css_online	= cpu_cgroup_css_online,
 	.css_offline	= cpu_cgroup_css_offline,
+	.fork		= cpu_cgroup_fork,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 256e577faf1b..28fa9d9e9201 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -518,12 +518,20 @@ again:
 	}
 
 	/*
-	 * We need to take care of a possible races here. In fact, the
-	 * task might have changed its scheduling policy to something
-	 * different from SCHED_DEADLINE or changed its reservation
-	 * parameters (through sched_setattr()).
+	 * We need to take care of several possible races here:
+	 *
+	 *   - the task might have changed its scheduling policy
+	 *     to something different than SCHED_DEADLINE
+	 *   - the task might have changed its reservation parameters
+	 *     (through sched_setattr())
+	 *   - the task might have been boosted by someone else and
+	 *     might be in the boosting/deboosting path
+	 *
+	 * In all this cases we bail out, as the task is already
+	 * in the runqueue or is going to be enqueued back anyway.
 	 */
-	if (!dl_task(p) || dl_se->dl_new)
+	if (!dl_task(p) || dl_se->dl_new ||
+	    dl_se->dl_boosted || !dl_se->dl_throttled)
 		goto unlock;
 
 	sched_clock_tick();
@@ -532,7 +540,7 @@ again:
 	dl_se->dl_yielded = 0;
 	if (task_on_rq_queued(p)) {
 		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
-		if (task_has_dl_policy(rq->curr))
+		if (dl_task(rq->curr))
 			check_preempt_curr_dl(rq, p, 0);
 		else
 			resched_curr(rq);
@@ -847,8 +855,19 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	 * smaller than our one... OTW we keep our runtime and
 	 * deadline.
 	 */
-	if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio))
+	if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio)) {
 		pi_se = &pi_task->dl;
+	} else if (!dl_prio(p->normal_prio)) {
+		/*
+		 * Special case in which we have a !SCHED_DEADLINE task
+		 * that is going to be deboosted, but exceedes its
+		 * runtime while doing so. No point in replenishing
+		 * it, as it's going to return back to its original
+		 * scheduling class after this.
+		 */
+		BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
+		return;
+	}
 
 	/*
 	 * If p is throttled, we do nothing. In fact, if it exhausted
@@ -1607,8 +1626,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 			/* Only reschedule if pushing failed */
 			check_resched = 0;
 #endif /* CONFIG_SMP */
-		if (check_resched && task_has_dl_policy(rq->curr))
-			check_preempt_curr_dl(rq, p, 0);
+		if (check_resched) {
+			if (dl_task(rq->curr))
+				check_preempt_curr_dl(rq, p, 0);
+			else
+				resched_curr(rq);
+		}
 	}
 }
 
@@ -1678,4 +1701,6 @@ const struct sched_class dl_sched_class = {
 	.prio_changed           = prio_changed_dl,
 	.switched_from		= switched_from_dl,
 	.switched_to		= switched_to_dl,
+
+	.update_curr		= update_curr_dl,
 };
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b069bf3e708..ef2b104b254c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -726,6 +726,11 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	account_cfs_rq_runtime(cfs_rq, delta_exec);
 }
 
+static void update_curr_fair(struct rq *rq)
+{
+	update_curr(cfs_rq_of(&rq->curr->se));
+}
+
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -828,11 +833,12 @@ static unsigned int task_nr_scan_windows(struct task_struct *p)
 
 static unsigned int task_scan_min(struct task_struct *p)
 {
+	unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size);
 	unsigned int scan, floor;
 	unsigned int windows = 1;
 
-	if (sysctl_numa_balancing_scan_size < MAX_SCAN_WINDOW)
-		windows = MAX_SCAN_WINDOW / sysctl_numa_balancing_scan_size;
+	if (scan_size < MAX_SCAN_WINDOW)
+		windows = MAX_SCAN_WINDOW / scan_size;
 	floor = 1000 / windows;
 
 	scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
@@ -1164,9 +1170,26 @@ static void task_numa_compare(struct task_numa_env *env,
 	long moveimp = imp;
 
 	rcu_read_lock();
-	cur = ACCESS_ONCE(dst_rq->curr);
-	if (cur->pid == 0) /* idle */
+
+	raw_spin_lock_irq(&dst_rq->lock);
+	cur = dst_rq->curr;
+	/*
+	 * No need to move the exiting task, and this ensures that ->curr
+	 * wasn't reaped and thus get_task_struct() in task_numa_assign()
+	 * is safe under RCU read lock.
+	 * Note that rcu_read_lock() itself can't protect from the final
+	 * put_task_struct() after the last schedule().
+	 */
+	if ((cur->flags & PF_EXITING) || is_idle_task(cur))
 		cur = NULL;
+	raw_spin_unlock_irq(&dst_rq->lock);
+
+	/*
+	 * Because we have preemption enabled we can get migrated around and
+	 * end try selecting ourselves (current == env->p) as a swap candidate.
+	 */
+	if (cur == env->p)
+		goto unlock;
 
 	/*
 	 * "imp" is the fault differential for the source task between the
@@ -1520,7 +1543,7 @@ static void update_task_scan_period(struct task_struct *p,
 		 * scanning faster if shared accesses dominate as it may
 		 * simply bounce migrations uselessly
 		 */
-		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
+		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared + 1));
 		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
 	}
 
@@ -7938,6 +7961,8 @@ const struct sched_class fair_sched_class = {
 
 	.get_rr_interval	= get_rr_interval_fair,
 
+	.update_curr		= update_curr_fair,
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	.task_move_group	= task_move_group_fair,
 #endif
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 67ad4e7f506a..c65dac8c97cd 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -75,6 +75,10 @@ static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task
 	return 0;
 }
 
+static void update_curr_idle(struct rq *rq)
+{
+}
+
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
@@ -101,4 +105,5 @@ const struct sched_class idle_sched_class = {
 
 	.prio_changed		= prio_changed_idle,
 	.switched_to		= switched_to_idle,
+	.update_curr		= update_curr_idle,
 };
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d024e6ce30ba..20bca398084a 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2128,6 +2128,8 @@ const struct sched_class rt_sched_class = {
 
 	.prio_changed		= prio_changed_rt,
 	.switched_to		= switched_to_rt,
+
+	.update_curr		= update_curr_rt,
 };
 
 #ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 24156c8434d1..2df8ef067cc5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1135,6 +1135,8 @@ struct sched_class {
 	unsigned int (*get_rr_interval) (struct rq *rq,
 					 struct task_struct *task);
 
+	void (*update_curr) (struct rq *rq);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	void (*task_move_group) (struct task_struct *p, int on_rq);
 #endif
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 67426e529f59..79ffec45a6ac 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -102,6 +102,10 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task)
 	return 0;
 }
 
+static void update_curr_stop(struct rq *rq)
+{
+}
+
 /*
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
@@ -128,4 +132,5 @@ const struct sched_class stop_sched_class = {
 
 	.prio_changed		= prio_changed_stop,
 	.switched_to		= switched_to_stop,
+	.update_curr		= update_curr_stop,
 };
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4aada6d9fe74..15f2511a1b7c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -387,7 +387,8 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_numa_balancing_scan_size,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
 	},
 	{
 		.procname	= "numa_balancing",
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 9c94c19f1305..55449909f114 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -72,7 +72,7 @@ static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
 	 * Also omit the add if it would overflow the u64 boundary.
 	 */
 	if ((~0ULL - clc > rnd) &&
-	    (!ismax || evt->mult <= (1U << evt->shift)))
+	    (!ismax || evt->mult <= (1ULL << evt->shift)))
 		clc += rnd;
 
 	do_div(clc, evt->mult);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 492b986195d5..a16b67859e2a 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -553,7 +553,7 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
 		*sample = cputime_to_expires(cputime.utime);
 		break;
 	case CPUCLOCK_SCHED:
-		*sample = cputime.sum_exec_runtime + task_delta_exec(p);
+		*sample = cputime.sum_exec_runtime;
 		break;
 	}
 	return 0;
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 42b463ad90f2..31ea01f42e1f 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -636,6 +636,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 			goto out;
 		}
 	} else {
+		memset(&event.sigev_value, 0, sizeof(event.sigev_value));
 		event.sigev_notify = SIGEV_SIGNAL;
 		event.sigev_signo = SIGALRM;
 		event.sigev_value.sival_int = new_timer->it_id;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index fb186b9ddf51..31c90fec4158 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1925,8 +1925,16 @@ ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec)
 	 * when we are adding another op to the rec or removing the
 	 * current one. Thus, if the op is being added, we can
 	 * ignore it because it hasn't attached itself to the rec
-	 * yet. That means we just need to find the op that has a
-	 * trampoline and is not beeing added.
+	 * yet.
+	 *
+	 * If an ops is being modified (hooking to different functions)
+	 * then we don't care about the new functions that are being
+	 * added, just the old ones (that are probably being removed).
+	 *
+	 * If we are adding an ops to a function that already is using
+	 * a trampoline, it needs to be removed (trampolines are only
+	 * for single ops connected), then an ops that is not being
+	 * modified also needs to be checked.
 	 */
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
 
@@ -1940,17 +1948,23 @@ ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec)
 		if (op->flags & FTRACE_OPS_FL_ADDING)
 			continue;
 
+
 		/*
-		 * If the ops is not being added and has a trampoline,
-		 * then it must be the one that we want!
+		 * If the ops is being modified and is in the old
+		 * hash, then it is probably being removed from this
+		 * function.
 		 */
-		if (hash_contains_ip(ip, op->func_hash))
-			return op;
-
-		/* If the ops is being modified, it may be in the old hash. */
 		if ((op->flags & FTRACE_OPS_FL_MODIFYING) &&
 		    hash_contains_ip(ip, &op->old_hash))
 			return op;
+		/*
+		 * If the ops is not being added or modified, and it's
+		 * in its normal filter hash, then this must be the one
+		 * we want!
+		 */
+		if (!(op->flags & FTRACE_OPS_FL_MODIFYING) &&
+		    hash_contains_ip(ip, op->func_hash))
+			return op;
 
 	} while_for_each_ftrace_op(op);
 
@@ -2293,10 +2307,13 @@ static void ftrace_run_update_code(int command)
 	FTRACE_WARN_ON(ret);
 }
 
-static void ftrace_run_modify_code(struct ftrace_ops *ops, int command)
+static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
+				   struct ftrace_hash *old_hash)
 {
 	ops->flags |= FTRACE_OPS_FL_MODIFYING;
+	ops->old_hash.filter_hash = old_hash;
 	ftrace_run_update_code(command);
+	ops->old_hash.filter_hash = NULL;
 	ops->flags &= ~FTRACE_OPS_FL_MODIFYING;
 }
 
@@ -3340,7 +3357,7 @@ static struct ftrace_ops trace_probe_ops __read_mostly =
 
 static int ftrace_probe_registered;
 
-static void __enable_ftrace_function_probe(void)
+static void __enable_ftrace_function_probe(struct ftrace_hash *old_hash)
 {
 	int ret;
 	int i;
@@ -3348,7 +3365,8 @@ static void __enable_ftrace_function_probe(void)
 	if (ftrace_probe_registered) {
 		/* still need to update the function call sites */
 		if (ftrace_enabled)
-			ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS);
+			ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
+					       old_hash);
 		return;
 	}
 
@@ -3477,13 +3495,14 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	} while_for_each_ftrace_rec();
 
 	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+
+	__enable_ftrace_function_probe(old_hash);
+
 	if (!ret)
 		free_ftrace_hash_rcu(old_hash);
 	else
 		count = ret;
 
-	__enable_ftrace_function_probe();
-
  out_unlock:
 	mutex_unlock(&ftrace_lock);
  out:
@@ -3764,10 +3783,11 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 	return add_hash_entry(hash, ip);
 }
 
-static void ftrace_ops_update_code(struct ftrace_ops *ops)
+static void ftrace_ops_update_code(struct ftrace_ops *ops,
+				   struct ftrace_hash *old_hash)
 {
 	if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled)
-		ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS);
+		ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash);
 }
 
 static int
@@ -3813,7 +3833,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 	old_hash = *orig_hash;
 	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
 	if (!ret) {
-		ftrace_ops_update_code(ops);
+		ftrace_ops_update_code(ops, old_hash);
 		free_ftrace_hash_rcu(old_hash);
 	}
 	mutex_unlock(&ftrace_lock);
@@ -4058,7 +4078,7 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 		ret = ftrace_hash_move(iter->ops, filter_hash,
 				       orig_hash, iter->hash);
 		if (!ret) {
-			ftrace_ops_update_code(iter->ops);
+			ftrace_ops_update_code(iter->ops, old_hash);
 			free_ftrace_hash_rcu(old_hash);
 		}
 		mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 2d75c94ae87d..a56e07c8d15b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -538,16 +538,18 @@ static void rb_wake_up_waiters(struct irq_work *work)
  * ring_buffer_wait - wait for input to the ring buffer
  * @buffer: buffer to wait on
  * @cpu: the cpu buffer to wait on
+ * @full: wait until a full page is available, if @cpu != RING_BUFFER_ALL_CPUS
  *
  * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
  * as data is added to any of the @buffer's cpu buffers. Otherwise
  * it will wait for data to be added to a specific cpu buffer.
  */
-int ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
 {
-	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer);
 	DEFINE_WAIT(wait);
 	struct rb_irq_work *work;
+	int ret = 0;
 
 	/*
 	 * Depending on what the caller is waiting for, either any
@@ -564,36 +566,61 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 	}
 
 
-	prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
+	while (true) {
+		prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
 
-	/*
-	 * The events can happen in critical sections where
-	 * checking a work queue can cause deadlocks.
-	 * After adding a task to the queue, this flag is set
-	 * only to notify events to try to wake up the queue
-	 * using irq_work.
-	 *
-	 * We don't clear it even if the buffer is no longer
-	 * empty. The flag only causes the next event to run
-	 * irq_work to do the work queue wake up. The worse
-	 * that can happen if we race with !trace_empty() is that
-	 * an event will cause an irq_work to try to wake up
-	 * an empty queue.
-	 *
-	 * There's no reason to protect this flag either, as
-	 * the work queue and irq_work logic will do the necessary
-	 * synchronization for the wake ups. The only thing
-	 * that is necessary is that the wake up happens after
-	 * a task has been queued. It's OK for spurious wake ups.
-	 */
-	work->waiters_pending = true;
+		/*
+		 * The events can happen in critical sections where
+		 * checking a work queue can cause deadlocks.
+		 * After adding a task to the queue, this flag is set
+		 * only to notify events to try to wake up the queue
+		 * using irq_work.
+		 *
+		 * We don't clear it even if the buffer is no longer
+		 * empty. The flag only causes the next event to run
+		 * irq_work to do the work queue wake up. The worse
+		 * that can happen if we race with !trace_empty() is that
+		 * an event will cause an irq_work to try to wake up
+		 * an empty queue.
+		 *
+		 * There's no reason to protect this flag either, as
+		 * the work queue and irq_work logic will do the necessary
+		 * synchronization for the wake ups. The only thing
+		 * that is necessary is that the wake up happens after
+		 * a task has been queued. It's OK for spurious wake ups.
+		 */
+		work->waiters_pending = true;
+
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+
+		if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer))
+			break;
+
+		if (cpu != RING_BUFFER_ALL_CPUS &&
+		    !ring_buffer_empty_cpu(buffer, cpu)) {
+			unsigned long flags;
+			bool pagebusy;
+
+			if (!full)
+				break;
+
+			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+			if (!pagebusy)
+				break;
+		}
 
-	if ((cpu == RING_BUFFER_ALL_CPUS && ring_buffer_empty(buffer)) ||
-	    (cpu != RING_BUFFER_ALL_CPUS && ring_buffer_empty_cpu(buffer, cpu)))
 		schedule();
+	}
 
 	finish_wait(&work->waiters, &wait);
-	return 0;
+
+	return ret;
 }
 
 /**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 459a7b1251e5..426962b04183 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1076,13 +1076,14 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-static int wait_on_pipe(struct trace_iterator *iter)
+static int wait_on_pipe(struct trace_iterator *iter, bool full)
 {
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
 		return 0;
 
-	return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+	return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file,
+				full);
 }
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -4434,15 +4435,12 @@ static int tracing_wait_pipe(struct file *filp)
 
 		mutex_unlock(&iter->mutex);
 
-		ret = wait_on_pipe(iter);
+		ret = wait_on_pipe(iter, false);
 
 		mutex_lock(&iter->mutex);
 
 		if (ret)
 			return ret;
-
-		if (signal_pending(current))
-			return -EINTR;
 	}
 
 	return 1;
@@ -5372,16 +5370,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 				goto out_unlock;
 			}
 			mutex_unlock(&trace_types_lock);
-			ret = wait_on_pipe(iter);
+			ret = wait_on_pipe(iter, false);
 			mutex_lock(&trace_types_lock);
 			if (ret) {
 				size = ret;
 				goto out_unlock;
 			}
-			if (signal_pending(current)) {
-				size = -EINTR;
-				goto out_unlock;
-			}
 			goto again;
 		}
 		size = 0;
@@ -5500,7 +5494,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	};
 	struct buffer_ref *ref;
 	int entries, size, i;
-	ssize_t ret;
+	ssize_t ret = 0;
 
 	mutex_lock(&trace_types_lock);
 
@@ -5538,13 +5532,16 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		int r;
 
 		ref = kzalloc(sizeof(*ref), GFP_KERNEL);
-		if (!ref)
+		if (!ref) {
+			ret = -ENOMEM;
 			break;
+		}
 
 		ref->ref = 1;
 		ref->buffer = iter->trace_buffer->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
 		if (!ref->page) {
+			ret = -ENOMEM;
 			kfree(ref);
 			break;
 		}
@@ -5582,19 +5579,19 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 
 	/* did we read anything? */
 	if (!spd.nr_pages) {
+		if (ret)
+			goto out;
+
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) {
 			ret = -EAGAIN;
 			goto out;
 		}
 		mutex_unlock(&trace_types_lock);
-		ret = wait_on_pipe(iter);
+		ret = wait_on_pipe(iter, true);
 		mutex_lock(&trace_types_lock);
 		if (ret)
 			goto out;
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			goto out;
-		}
+
 		goto again;
 	}
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 4dc8b79c5f75..29228c4d5696 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -313,7 +313,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 
 	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
@@ -360,7 +360,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	int syscall_nr;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 
 	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
@@ -567,7 +567,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
 		return;
@@ -641,7 +641,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
 		return;