Merge branch 'sched/urgent' into sched/core, to pick up fixes before applying more changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

24 files changed, 224 insertions, 153 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index dc5c775..17ea6d4 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/bpf/Makefile b/kernel/bpf/Makefile
index 4542723..0daf7f6 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 f0c30c5..d6594e4 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 801f5f3..9f81818 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/cpu.c b/kernel/cpu.c
index 356450f..90a3d01 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 1425d07..2b02c9f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6071,11 +6071,6 @@ 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 +6080,6 @@ 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 +6197,6 @@ 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 +6422,6 @@ 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 +6500,6 @@ 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 +6529,7 @@ 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;
 }
 
 /*
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 1559fb0..9803a66 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/futex.c b/kernel/futex.c
index f3a3a07..63678b5 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 cf66c5c..3b74087 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 8637e04..80f7a6d 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/power/hibernate.c b/kernel/power/hibernate.c
index a9dfa79..1f35a34 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/rcu/tree.c b/kernel/rcu/tree.c
index 133e472..9815447 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 d037646..bbdc45d 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 387dd45..c1d7f27 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 72d9d92..960f704 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2457,44 +2457,6 @@ 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.
@@ -2503,7 +2465,7 @@ 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)
 	/*
@@ -2522,7 +2484,16 @@ 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;
@@ -6470,6 +6441,10 @@ 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).
@@ -7568,8 +7543,12 @@ 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;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f3d7776..b091179 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1747,6 +1747,8 @@ 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,
 };
 
 #ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 826fdf3..cf80643 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)
 {
@@ -1268,6 +1273,13 @@ static void task_numa_compare(struct task_numa_env *env,
 	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
 	 * source and destination node. Calculate the total differential for
 	 * the source task and potential destination task. The more negative
@@ -8137,6 +8149,8 @@ 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/rt.c b/kernel/sched/rt.c
index 3d14312..f1bb92f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2134,6 +2134,8 @@ 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 31f1e4d..9a2a45c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1177,6 +1177,8 @@ 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/time/clockevents.c b/kernel/time/clockevents.c
index 9c94c19..5544990 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 492b986..a16b678 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 42b463a..31ea01f 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 fb186b9..31c90fe 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/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 4dc8b79..29228c4 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;