Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block into for-3.18

This is to receive 0a30288da1ae ("blk-mq, percpu_ref: implement a
kludge for SCSI blk-mq stall during probe") which implements
__percpu_ref_kill_expedited() to work around SCSI blk-mq stall.  The
commit reverted and patches to implement proper fix will be added.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>

22 files changed, 403 insertions, 186 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 589b4d89a0a5..a99d504294de 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1035,6 +1035,11 @@ static void cgroup_get(struct cgroup *cgrp)
 	css_get(&cgrp->self);
 }
 
+static bool cgroup_tryget(struct cgroup *cgrp)
+{
+	return css_tryget(&cgrp->self);
+}
+
 static void cgroup_put(struct cgroup *cgrp)
 {
 	css_put(&cgrp->self);
@@ -1147,7 +1152,8 @@ static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn)
 	 * protection against removal.  Ensure @cgrp stays accessible and
 	 * break the active_ref protection.
 	 */
-	cgroup_get(cgrp);
+	if (!cgroup_tryget(cgrp))
+		return NULL;
 	kernfs_break_active_protection(kn);
 
 	mutex_lock(&cgroup_mutex);
@@ -3271,8 +3277,17 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
 	struct cftype *cft;
 
-	for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
-		cft->flags |= __CFTYPE_NOT_ON_DFL;
+	/*
+	 * If legacy_flies_on_dfl, we want to show the legacy files on the
+	 * dfl hierarchy but iff the target subsystem hasn't been updated
+	 * for the dfl hierarchy yet.
+	 */
+	if (!cgroup_legacy_files_on_dfl ||
+	    ss->dfl_cftypes != ss->legacy_cftypes) {
+		for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
+			cft->flags |= __CFTYPE_NOT_ON_DFL;
+	}
+
 	return cgroup_add_cftypes(ss, cfts);
 }
 
@@ -3970,7 +3985,6 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 
 	l = cgroup_pidlist_find_create(cgrp, type);
 	if (!l) {
-		mutex_unlock(&cgrp->pidlist_mutex);
 		pidlist_free(array);
 		return -ENOMEM;
 	}
@@ -4387,6 +4401,15 @@ static void css_release_work_fn(struct work_struct *work)
 		/* cgroup release path */
 		cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
 		cgrp->id = -1;
+
+		/*
+		 * There are two control paths which try to determine
+		 * cgroup from dentry without going through kernfs -
+		 * cgroupstats_build() and css_tryget_online_from_dir().
+		 * Those are supported by RCU protecting clearing of
+		 * cgrp->kn->priv backpointer.
+		 */
+		RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
 	}
 
 	mutex_unlock(&cgroup_mutex);
@@ -4543,6 +4566,11 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	struct cftype *base_files;
 	int ssid, ret;
 
+	/* Do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable.
+	 */
+	if (strchr(name, '\n'))
+		return -EINVAL;
+
 	parent = cgroup_kn_lock_live(parent_kn);
 	if (!parent)
 		return -ENODEV;
@@ -4820,16 +4848,6 @@ static int cgroup_rmdir(struct kernfs_node *kn)
 
 	cgroup_kn_unlock(kn);
 
-	/*
-	 * There are two control paths which try to determine cgroup from
-	 * dentry without going through kernfs - cgroupstats_build() and
-	 * css_tryget_online_from_dir().  Those are supported by RCU
-	 * protecting clearing of cgrp->kn->priv backpointer, which should
-	 * happen after all files under it have been removed.
-	 */
-	if (!ret)
-		RCU_INIT_POINTER(*(void __rcu __force **)&kn->priv, NULL);
-
 	cgroup_put(cgrp);
 	return ret;
 }
@@ -5416,7 +5434,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 	/*
 	 * This path doesn't originate from kernfs and @kn could already
 	 * have been or be removed at any point.  @kn->priv is RCU
-	 * protected for this access.  See cgroup_rmdir() for details.
+	 * protected for this access.  See css_release_work_fn() for details.
 	 */
 	cgrp = rcu_dereference(kn->priv);
 	if (cgrp)
diff --git a/kernel/compat.c b/kernel/compat.c
index 633394f442f8..ebb3c369d03d 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -226,7 +226,7 @@ static long compat_nanosleep_restart(struct restart_block *restart)
 	ret = hrtimer_nanosleep_restart(restart);
 	set_fs(oldfs);
 
-	if (ret) {
+	if (ret == -ERESTART_RESTARTBLOCK) {
 		rmtp = restart->nanosleep.compat_rmtp;
 
 		if (rmtp && compat_put_timespec(&rmt, rmtp))
@@ -256,7 +256,26 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
 				HRTIMER_MODE_REL, CLOCK_MONOTONIC);
 	set_fs(oldfs);
 
-	if (ret) {
+	/*
+	 * hrtimer_nanosleep() can only return 0 or
+	 * -ERESTART_RESTARTBLOCK here because:
+	 *
+	 * - we call it with HRTIMER_MODE_REL and therefor exclude the
+	 *   -ERESTARTNOHAND return path.
+	 *
+	 * - we supply the rmtp argument from the task stack (due to
+	 *   the necessary compat conversion. So the update cannot
+	 *   fail, which excludes the -EFAULT return path as well. If
+	 *   it fails nevertheless we have a bigger problem and wont
+	 *   reach this place anymore.
+	 *
+	 * - if the return value is 0, we do not have to update rmtp
+	 *    because there is no remaining time.
+	 *
+	 * We check for -ERESTART_RESTARTBLOCK nevertheless if the
+	 * core implementation decides to return random nonsense.
+	 */
+	if (ret == -ERESTART_RESTARTBLOCK) {
 		struct restart_block *restart
 			= &current_thread_info()->restart_block;
 
@@ -266,7 +285,6 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
 		if (rmtp && compat_put_timespec(&rmt, rmtp))
 			return -EFAULT;
 	}
-
 	return ret;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cf24b3e42ec..d640a8b4dcbc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -41,6 +41,7 @@
 #include <linux/cgroup.h>
 #include <linux/module.h>
 #include <linux/mman.h>
+#include <linux/compat.h>
 
 #include "internal.h"
 
@@ -1523,6 +1524,11 @@ retry:
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -1966,6 +1972,11 @@ retry:
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -3717,6 +3728,26 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return 0;
 }
 
+#ifdef CONFIG_COMPAT
+static long perf_compat_ioctl(struct file *file, unsigned int cmd,
+				unsigned long arg)
+{
+	switch (_IOC_NR(cmd)) {
+	case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
+	case _IOC_NR(PERF_EVENT_IOC_ID):
+		/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
+		if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
+			cmd &= ~IOCSIZE_MASK;
+			cmd |= sizeof(void *) << IOCSIZE_SHIFT;
+		}
+		break;
+	}
+	return perf_ioctl(file, cmd, arg);
+}
+#else
+# define perf_compat_ioctl NULL
+#endif
+
 int perf_event_task_enable(void)
 {
 	struct perf_event *event;
@@ -4222,7 +4253,7 @@ static const struct file_operations perf_fops = {
 	.read			= perf_read,
 	.poll			= perf_poll,
 	.unlocked_ioctl		= perf_ioctl,
-	.compat_ioctl		= perf_ioctl,
+	.compat_ioctl		= perf_compat_ioctl,
 	.mmap			= perf_mmap,
 	.fasync			= perf_fasync,
 };
diff --git a/kernel/futex.c b/kernel/futex.c
index d3a9d946d0b7..815d7af2ffe8 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2592,6 +2592,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * shared futexes. We need to compare the keys:
 	 */
 	if (match_futex(&q.key, &key2)) {
+		queue_unlock(hb);
 		ret = -EINVAL;
 		goto out_put_keys;
 	}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index a2b28a2fd7b1..6223fab9a9d2 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -517,6 +517,7 @@ out:
 		chip->irq_eoi(&desc->irq_data);
 	raw_spin_unlock(&desc->lock);
 }
+EXPORT_SYMBOL_GPL(handle_fasteoi_irq);
 
 /**
  *	handle_edge_irq - edge type IRQ handler
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index e30ac0fe61c3..0aa69ea1d8fd 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -44,11 +44,12 @@ static long kptr_obfuscate(long v, int type)
  */
 static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
 {
-	long ret;
+	long t1, t2;
 
-	ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);
+	t1 = kptr_obfuscate((long)v1, type);
+	t2 = kptr_obfuscate((long)v2, type);
 
-	return (ret < 0) | ((ret > 0) << 1);
+	return (t1 < t2) | ((t1 > t2) << 1);
 }
 
 /* The caller must have pinned the task */
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 0b49a0a58102..2bee072268d9 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -64,7 +64,9 @@ bool kexec_in_progress = false;
 char __weak kexec_purgatory[0];
 size_t __weak kexec_purgatory_size = 0;
 
+#ifdef CONFIG_KEXEC_FILE
 static int kexec_calculate_store_digests(struct kimage *image);
+#endif
 
 /* Location of the reserved area for the crash kernel */
 struct resource crashk_res = {
@@ -341,6 +343,7 @@ out_free_image:
 	return ret;
 }
 
+#ifdef CONFIG_KEXEC_FILE
 static int copy_file_from_fd(int fd, void **buf, unsigned long *buf_len)
 {
 	struct fd f = fdget(fd);
@@ -612,6 +615,9 @@ out_free_image:
 	kfree(image);
 	return ret;
 }
+#else /* CONFIG_KEXEC_FILE */
+static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
+#endif /* CONFIG_KEXEC_FILE */
 
 static int kimage_is_destination_range(struct kimage *image,
 					unsigned long start,
@@ -1375,6 +1381,7 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry,
 }
 #endif
 
+#ifdef CONFIG_KEXEC_FILE
 SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 		unsigned long, cmdline_len, const char __user *, cmdline_ptr,
 		unsigned long, flags)
@@ -1451,6 +1458,8 @@ out:
 	return ret;
 }
 
+#endif /* CONFIG_KEXEC_FILE */
+
 void crash_kexec(struct pt_regs *regs)
 {
 	/* Take the kexec_mutex here to prevent sys_kexec_load
@@ -2006,6 +2015,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 
 subsys_initcall(crash_save_vmcoreinfo_init);
 
+#ifdef CONFIG_KEXEC_FILE
 static int __kexec_add_segment(struct kimage *image, char *buf,
 			       unsigned long bufsz, unsigned long mem,
 			       unsigned long memsz)
@@ -2682,6 +2692,7 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name,
 
 	return 0;
 }
+#endif /* CONFIG_KEXEC_FILE */
 
 /*
  * Move into place and start executing a preloaded standalone
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 734e9a7d280b..3995f546d0f3 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1778,7 +1778,18 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 	unsigned long hash, flags = 0;
 	struct kretprobe_instance *ri;
 
-	/*TODO: consider to only swap the RA after the last pre_handler fired */
+	/*
+	 * To avoid deadlocks, prohibit return probing in NMI contexts,
+	 * just skip the probe and increase the (inexact) 'nmissed'
+	 * statistical counter, so that the user is informed that
+	 * something happened:
+	 */
+	if (unlikely(in_nmi())) {
+		rp->nmissed++;
+		return 0;
+	}
+
+	/* TODO: consider to only swap the RA after the last pre_handler fired */
 	hash = hash_ptr(current, KPROBE_HASH_BITS);
 	raw_spin_lock_irqsave(&rp->lock, flags);
 	if (!hlist_empty(&rp->free_instances)) {
diff --git a/kernel/module.c b/kernel/module.c
index 6f69463f0066..03214bd288e9 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3304,6 +3304,11 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	mutex_lock(&module_mutex);
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
+
+	/* we can't deallocate the module until we clear memory protection */
+	unset_module_init_ro_nx(mod);
+	unset_module_core_ro_nx(mod);
+
  ddebug_cleanup:
 	dynamic_debug_remove(info->debug);
 	synchronize_sched();
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 5d49dcac2537..2df883a9d3cb 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -179,6 +179,7 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *,
 
 #ifdef CONFIG_SUSPEND
 /* kernel/power/suspend.c */
+extern const char *pm_labels[];
 extern const char *pm_states[];
 
 extern int suspend_devices_and_enter(suspend_state_t state);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6dadb25cb0d8..18c62195660f 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -31,7 +31,7 @@
 
 #include "power.h"
 
-static const char *pm_labels[] = { "mem", "standby", "freeze", };
+const char *pm_labels[] = { "mem", "standby", "freeze", NULL };
 const char *pm_states[PM_SUSPEND_MAX];
 
 static const struct platform_suspend_ops *suspend_ops;
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 2f524928b6aa..bd91bc177c93 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -129,20 +129,20 @@ static int __init has_wakealarm(struct device *dev, const void *data)
  * at startup time.  They're normally disabled, for faster boot and because
  * we can't know which states really work on this particular system.
  */
-static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
+static const char *test_state_label __initdata;
 
 static char warn_bad_state[] __initdata =
 	KERN_WARNING "PM: can't test '%s' suspend state\n";
 
 static int __init setup_test_suspend(char *value)
 {
-	suspend_state_t i;
+	int i;
 
 	/* "=mem" ==> "mem" */
 	value++;
-	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
-		if (!strcmp(pm_states[i], value)) {
-			test_state = i;
+	for (i = 0; pm_labels[i]; i++)
+		if (!strcmp(pm_labels[i], value)) {
+			test_state_label = pm_labels[i];
 			return 0;
 		}
 
@@ -158,13 +158,21 @@ static int __init test_suspend(void)
 
 	struct rtc_device	*rtc = NULL;
 	struct device		*dev;
+	suspend_state_t test_state;
 
 	/* PM is initialized by now; is that state testable? */
-	if (test_state == PM_SUSPEND_ON)
-		goto done;
-	if (!pm_states[test_state]) {
-		printk(warn_bad_state, pm_states[test_state]);
-		goto done;
+	if (!test_state_label)
+		return 0;
+
+	for (test_state = PM_SUSPEND_MIN; test_state < PM_SUSPEND_MAX; test_state++) {
+		const char *state_label = pm_states[test_state];
+
+		if (state_label && !strcmp(test_state_label, state_label))
+			break;
+	}
+	if (test_state == PM_SUSPEND_MAX) {
+		printk(warn_bad_state, test_state_label);
+		return 0;
 	}
 
 	/* RTCs have initialized by now too ... can we use one? */
@@ -173,13 +181,12 @@ static int __init test_suspend(void)
 		rtc = rtc_class_open(dev_name(dev));
 	if (!rtc) {
 		printk(warn_no_rtc);
-		goto done;
+		return 0;
 	}
 
 	/* go for it */
 	test_wakealarm(rtc, test_state);
 	rtc_class_close(rtc);
-done:
 	return 0;
 }
 late_initcall(test_suspend);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index e04c455a0e38..1ce770687ea8 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1665,15 +1665,15 @@ asmlinkage int vprintk_emit(int facility, int level,
 	raw_spin_lock(&logbuf_lock);
 	logbuf_cpu = this_cpu;
 
-	if (recursion_bug) {
+	if (unlikely(recursion_bug)) {
 		static const char recursion_msg[] =
 			"BUG: recent printk recursion!";
 
 		recursion_bug = 0;
-		text_len = strlen(recursion_msg);
 		/* emit KERN_CRIT message */
 		printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0,
-					 NULL, 0, recursion_msg, text_len);
+					 NULL, 0, recursion_msg,
+					 strlen(recursion_msg));
 	}
 
 	/*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 71e64c718f75..6a86eb7bac45 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -358,7 +358,7 @@ struct rcu_data {
 	struct rcu_head **nocb_gp_tail;
 	long nocb_gp_count;
 	long nocb_gp_count_lazy;
-	bool nocb_leader_wake;		/* Is the nocb leader thread awake? */
+	bool nocb_leader_sleep;		/* Is the nocb leader thread asleep? */
 	struct rcu_data *nocb_next_follower;
 					/* Next follower in wakeup chain. */
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 00dc411e9676..a7997e272564 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2074,9 +2074,9 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
 
 	if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
 		return;
-	if (!ACCESS_ONCE(rdp_leader->nocb_leader_wake) || force) {
+	if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
 		/* Prior xchg orders against prior callback enqueue. */
-		ACCESS_ONCE(rdp_leader->nocb_leader_wake) = true;
+		ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
 		wake_up(&rdp_leader->nocb_wq);
 	}
 }
@@ -2253,7 +2253,7 @@ wait_again:
 	if (!rcu_nocb_poll) {
 		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
 		wait_event_interruptible(my_rdp->nocb_wq,
-					 ACCESS_ONCE(my_rdp->nocb_leader_wake));
+				!ACCESS_ONCE(my_rdp->nocb_leader_sleep));
 		/* Memory barrier handled by smp_mb() calls below and repoll. */
 	} else if (firsttime) {
 		firsttime = false; /* Don't drown trace log with "Poll"! */
@@ -2292,12 +2292,12 @@ wait_again:
 		schedule_timeout_interruptible(1);
 
 		/* Rescan in case we were a victim of memory ordering. */
-		my_rdp->nocb_leader_wake = false;
-		smp_mb();  /* Ensure _wake false before scan. */
+		my_rdp->nocb_leader_sleep = true;
+		smp_mb();  /* Ensure _sleep true before scan. */
 		for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
 			if (ACCESS_ONCE(rdp->nocb_head)) {
 				/* Found CB, so short-circuit next wait. */
-				my_rdp->nocb_leader_wake = true;
+				my_rdp->nocb_leader_sleep = false;
 				break;
 			}
 		goto wait_again;
@@ -2307,17 +2307,17 @@ wait_again:
 	rcu_nocb_wait_gp(my_rdp);
 
 	/*
-	 * We left ->nocb_leader_wake set to reduce cache thrashing.
-	 * We clear it now, but recheck for new callbacks while
+	 * We left ->nocb_leader_sleep unset to reduce cache thrashing.
+	 * We set it now, but recheck for new callbacks while
 	 * traversing our follower list.
 	 */
-	my_rdp->nocb_leader_wake = false;
-	smp_mb(); /* Ensure _wake false before scan of ->nocb_head. */
+	my_rdp->nocb_leader_sleep = true;
+	smp_mb(); /* Ensure _sleep true before scan of ->nocb_head. */
 
 	/* Each pass through the following loop wakes a follower, if needed. */
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
 		if (ACCESS_ONCE(rdp->nocb_head))
-			my_rdp->nocb_leader_wake = true; /* No need to wait. */
+			my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/
 		if (!rdp->nocb_gp_head)
 			continue; /* No CBs, so no need to wake follower. */
 
diff --git a/kernel/resource.c b/kernel/resource.c
index da14b8d09296..60c5a3856ab7 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -351,15 +351,12 @@ static int find_next_iomem_res(struct resource *res, char *name,
 	end = res->end;
 	BUG_ON(start >= end);
 
-	read_lock(&resource_lock);
-
-	if (first_level_children_only) {
-		p = iomem_resource.child;
+	if (first_level_children_only)
 		sibling_only = true;
-	} else
-		p = &iomem_resource;
 
-	while ((p = next_resource(p, sibling_only))) {
+	read_lock(&resource_lock);
+
+	for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) {
 		if (p->flags != res->flags)
 			continue;
 		if (name && strcmp(p->name, name))
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 4aec4a457431..a7077d3ae52f 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -464,18 +464,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid)
 static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
 							ktime_t now)
 {
+	unsigned long flags;
 	struct k_itimer *ptr = container_of(alarm, struct k_itimer,
 						it.alarm.alarmtimer);
-	if (posix_timer_event(ptr, 0) != 0)
-		ptr->it_overrun++;
+	enum alarmtimer_restart result = ALARMTIMER_NORESTART;
+
+	spin_lock_irqsave(&ptr->it_lock, flags);
+	if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) {
+		if (posix_timer_event(ptr, 0) != 0)
+			ptr->it_overrun++;
+	}
 
 	/* Re-add periodic timers */
 	if (ptr->it.alarm.interval.tv64) {
 		ptr->it_overrun += alarm_forward(alarm, now,
 						ptr->it.alarm.interval);
-		return ALARMTIMER_RESTART;
+		result = ALARMTIMER_RESTART;
 	}
-	return ALARMTIMER_NORESTART;
+	spin_unlock_irqrestore(&ptr->it_lock, flags);
+
+	return result;
 }
 
 /**
@@ -541,18 +549,22 @@ static int alarm_timer_create(struct k_itimer *new_timer)
  * @new_timer: k_itimer pointer
  * @cur_setting: itimerspec data to fill
  *
- * Copies the itimerspec data out from the k_itimer
+ * Copies out the current itimerspec data
  */
 static void alarm_timer_get(struct k_itimer *timr,
 				struct itimerspec *cur_setting)
 {
-	memset(cur_setting, 0, sizeof(struct itimerspec));
+	ktime_t relative_expiry_time =
+		alarm_expires_remaining(&(timr->it.alarm.alarmtimer));
+
+	if (ktime_to_ns(relative_expiry_time) > 0) {
+		cur_setting->it_value = ktime_to_timespec(relative_expiry_time);
+	} else {
+		cur_setting->it_value.tv_sec = 0;
+		cur_setting->it_value.tv_nsec = 0;
+	}
 
-	cur_setting->it_interval =
-			ktime_to_timespec(timr->it.alarm.interval);
-	cur_setting->it_value =
-		ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires);
-	return;
+	cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval);
 }
 
 /**
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 99aa6ee3908f..f654a8a298fa 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -225,6 +225,20 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
 };
 
 /*
+ * Kick this CPU if it's full dynticks in order to force it to
+ * re-evaluate its dependency on the tick and restart it if necessary.
+ * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(),
+ * is NMI safe.
+ */
+void tick_nohz_full_kick(void)
+{
+	if (!tick_nohz_full_cpu(smp_processor_id()))
+		return;
+
+	irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
+}
+
+/*
  * Kick the CPU if it's full dynticks in order to force it to
  * re-evaluate its dependency on the tick and restart it if necessary.
  */
diff --git a/kernel/time/time.c b/kernel/time/time.c
index f0294ba14634..a9ae20fb0b11 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -559,17 +559,20 @@ EXPORT_SYMBOL(usecs_to_jiffies);
  * that a remainder subtract here would not do the right thing as the
  * resolution values don't fall on second boundries.  I.e. the line:
  * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
  *
  * Rather, we just shift the bits off the right.
  *
  * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
  * value to a scaled second value.
  */
-unsigned long
-timespec_to_jiffies(const struct timespec *value)
+static unsigned long
+__timespec_to_jiffies(unsigned long sec, long nsec)
 {
-	unsigned long sec = value->tv_sec;
-	long nsec = value->tv_nsec + TICK_NSEC - 1;
+	nsec = nsec + TICK_NSEC - 1;
 
 	if (sec >= MAX_SEC_IN_JIFFIES){
 		sec = MAX_SEC_IN_JIFFIES;
@@ -580,6 +583,13 @@ timespec_to_jiffies(const struct timespec *value)
 		 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 
 }
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+	return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
 EXPORT_SYMBOL(timespec_to_jiffies);
 
 void
@@ -596,31 +606,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
-/* Same for "timeval"
- *
- * Well, almost.  The problem here is that the real system resolution is
- * in nanoseconds and the value being converted is in micro seconds.
- * Also for some machines (those that use HZ = 1024, in-particular),
- * there is a LARGE error in the tick size in microseconds.
-
- * The solution we use is to do the rounding AFTER we convert the
- * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
- * Instruction wise, this should cost only an additional add with carry
- * instruction above the way it was done above.
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
+ *
+ * We could instead round in the intermediate scaled representation
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
+ * perilous: the scaling introduces a small positive error, which
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
+ * units to the intermediate before shifting) leads to accidental
+ * overflow and overestimates.
+ *
+ * At the cost of one additional multiplication by a constant, just
+ * use the timespec implementation.
  */
 unsigned long
 timeval_to_jiffies(const struct timeval *value)
 {
-	unsigned long sec = value->tv_sec;
-	long usec = value->tv_usec;
-
-	if (sec >= MAX_SEC_IN_JIFFIES){
-		sec = MAX_SEC_IN_JIFFIES;
-		usec = 0;
-	}
-	return (((u64)sec * SEC_CONVERSION) +
-		(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
-		 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+	return __timespec_to_jiffies(value->tv_sec,
+				     value->tv_usec * NSEC_PER_USEC);
 }
 EXPORT_SYMBOL(timeval_to_jiffies);
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index fb4a9c2cf8d9..ec1791fae965 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -442,11 +442,12 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
 		tk->ntp_error = 0;
 		ntp_clear();
 	}
-	update_vsyscall(tk);
-	update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
 
 	tk_update_ktime_data(tk);
 
+	update_vsyscall(tk);
+	update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
+
 	if (action & TK_MIRROR)
 		memcpy(&shadow_timekeeper, &tk_core.timekeeper,
 		       sizeof(tk_core.timekeeper));
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1654b12c891a..5916a8e59e87 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -65,15 +65,21 @@
 #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_CONTROL)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-#define INIT_REGEX_LOCK(opsname)	\
-	.regex_lock	= __MUTEX_INITIALIZER(opsname.regex_lock),
+#define INIT_OPS_HASH(opsname)	\
+	.func_hash		= &opsname.local_hash,			\
+	.local_hash.regex_lock	= __MUTEX_INITIALIZER(opsname.local_hash.regex_lock),
+#define ASSIGN_OPS_HASH(opsname, val) \
+	.func_hash		= val, \
+	.local_hash.regex_lock	= __MUTEX_INITIALIZER(opsname.local_hash.regex_lock),
 #else
-#define INIT_REGEX_LOCK(opsname)
+#define INIT_OPS_HASH(opsname)
+#define ASSIGN_OPS_HASH(opsname, val)
 #endif
 
 static struct ftrace_ops ftrace_list_end __read_mostly = {
 	.func		= ftrace_stub,
 	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB,
+	INIT_OPS_HASH(ftrace_list_end)
 };
 
 /* ftrace_enabled is a method to turn ftrace on or off */
@@ -140,7 +146,8 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops)
 {
 #ifdef CONFIG_DYNAMIC_FTRACE
 	if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) {
-		mutex_init(&ops->regex_lock);
+		mutex_init(&ops->local_hash.regex_lock);
+		ops->func_hash = &ops->local_hash;
 		ops->flags |= FTRACE_OPS_FL_INITIALIZED;
 	}
 #endif
@@ -899,7 +906,7 @@ static void unregister_ftrace_profiler(void)
 static struct ftrace_ops ftrace_profile_ops __read_mostly = {
 	.func		= function_profile_call,
 	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(ftrace_profile_ops)
+	INIT_OPS_HASH(ftrace_profile_ops)
 };
 
 static int register_ftrace_profiler(void)
@@ -1081,11 +1088,12 @@ static const struct ftrace_hash empty_hash = {
 #define EMPTY_HASH	((struct ftrace_hash *)&empty_hash)
 
 static struct ftrace_ops global_ops = {
-	.func			= ftrace_stub,
-	.notrace_hash		= EMPTY_HASH,
-	.filter_hash		= EMPTY_HASH,
-	.flags			= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(global_ops)
+	.func				= ftrace_stub,
+	.local_hash.notrace_hash	= EMPTY_HASH,
+	.local_hash.filter_hash		= EMPTY_HASH,
+	INIT_OPS_HASH(global_ops)
+	.flags				= FTRACE_OPS_FL_RECURSION_SAFE |
+					  FTRACE_OPS_FL_INITIALIZED,
 };
 
 struct ftrace_page {
@@ -1226,8 +1234,8 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
 void ftrace_free_filter(struct ftrace_ops *ops)
 {
 	ftrace_ops_init(ops);
-	free_ftrace_hash(ops->filter_hash);
-	free_ftrace_hash(ops->notrace_hash);
+	free_ftrace_hash(ops->func_hash->filter_hash);
+	free_ftrace_hash(ops->func_hash->notrace_hash);
 }
 
 static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
@@ -1288,9 +1296,9 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 }
 
 static void
-ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash);
+ftrace_hash_rec_disable_modify(struct ftrace_ops *ops, int filter_hash);
 static void
-ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash);
+ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, int filter_hash);
 
 static int
 ftrace_hash_move(struct ftrace_ops *ops, int enable,
@@ -1342,13 +1350,13 @@ update:
 	 * Remove the current set, update the hash and add
 	 * them back.
 	 */
-	ftrace_hash_rec_disable(ops, enable);
+	ftrace_hash_rec_disable_modify(ops, enable);
 
 	old_hash = *dst;
 	rcu_assign_pointer(*dst, new_hash);
 	free_ftrace_hash_rcu(old_hash);
 
-	ftrace_hash_rec_enable(ops, enable);
+	ftrace_hash_rec_enable_modify(ops, enable);
 
 	return 0;
 }
@@ -1382,8 +1390,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 		return 0;
 #endif
 
-	filter_hash = rcu_dereference_raw_notrace(ops->filter_hash);
-	notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash);
+	filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash);
+	notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash);
 
 	if ((ftrace_hash_empty(filter_hash) ||
 	     ftrace_lookup_ip(filter_hash, ip)) &&
@@ -1503,25 +1511,38 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
 static void ftrace_remove_tramp(struct ftrace_ops *ops,
 				struct dyn_ftrace *rec)
 {
-	struct ftrace_func_entry *entry;
-
-	entry = ftrace_lookup_ip(ops->tramp_hash, rec->ip);
-	if (!entry)
+	/* If TRAMP is not set, no ops should have a trampoline for this */
+	if (!(rec->flags & FTRACE_FL_TRAMP))
 		return;
 
+	rec->flags &= ~FTRACE_FL_TRAMP;
+
+	if ((!ftrace_hash_empty(ops->func_hash->filter_hash) &&
+	     !ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip)) ||
+	    ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip))
+		return;
 	/*
 	 * The tramp_hash entry will be removed at time
 	 * of update.
 	 */
 	ops->nr_trampolines--;
-	rec->flags &= ~FTRACE_FL_TRAMP;
 }
 
-static void ftrace_clear_tramps(struct dyn_ftrace *rec)
+static void ftrace_clear_tramps(struct dyn_ftrace *rec, struct ftrace_ops *ops)
 {
 	struct ftrace_ops *op;
 
+	/* If TRAMP is not set, no ops should have a trampoline for this */
+	if (!(rec->flags & FTRACE_FL_TRAMP))
+		return;
+
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		/*
+		 * This function is called to clear other tramps
+		 * not the one that is being updated.
+		 */
+		if (op == ops)
+			continue;
 		if (op->nr_trampolines)
 			ftrace_remove_tramp(op, rec);
 	} while_for_each_ftrace_op(op);
@@ -1554,14 +1575,14 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 	 *   gets inversed.
 	 */
 	if (filter_hash) {
-		hash = ops->filter_hash;
-		other_hash = ops->notrace_hash;
+		hash = ops->func_hash->filter_hash;
+		other_hash = ops->func_hash->notrace_hash;
 		if (ftrace_hash_empty(hash))
 			all = 1;
 	} else {
 		inc = !inc;
-		hash = ops->notrace_hash;
-		other_hash = ops->filter_hash;
+		hash = ops->func_hash->notrace_hash;
+		other_hash = ops->func_hash->filter_hash;
 		/*
 		 * If the notrace hash has no items,
 		 * then there's nothing to do.
@@ -1622,13 +1643,10 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				/*
 				 * If we are adding another function callback
 				 * to this function, and the previous had a
-				 * trampoline used, then we need to go back to
-				 * the default trampoline.
+				 * custom trampoline in use, then we need to go
+				 * back to the default trampoline.
 				 */
-				rec->flags &= ~FTRACE_FL_TRAMP;
-
-				/* remove trampolines from any ops for this rec */
-				ftrace_clear_tramps(rec);
+				ftrace_clear_tramps(rec, ops);
 			}
 
 			/*
@@ -1682,6 +1700,41 @@ static void ftrace_hash_rec_enable(struct ftrace_ops *ops,
 	__ftrace_hash_rec_update(ops, filter_hash, 1);
 }
 
+static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops,
+					  int filter_hash, int inc)
+{
+	struct ftrace_ops *op;
+
+	__ftrace_hash_rec_update(ops, filter_hash, inc);
+
+	if (ops->func_hash != &global_ops.local_hash)
+		return;
+
+	/*
+	 * If the ops shares the global_ops hash, then we need to update
+	 * all ops that are enabled and use this hash.
+	 */
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		/* Already done */
+		if (op == ops)
+			continue;
+		if (op->func_hash == &global_ops.local_hash)
+			__ftrace_hash_rec_update(op, filter_hash, inc);
+	} while_for_each_ftrace_op(op);
+}
+
+static void ftrace_hash_rec_disable_modify(struct ftrace_ops *ops,
+					   int filter_hash)
+{
+	ftrace_hash_rec_update_modify(ops, filter_hash, 0);
+}
+
+static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops,
+					  int filter_hash)
+{
+	ftrace_hash_rec_update_modify(ops, filter_hash, 1);
+}
+
 static void print_ip_ins(const char *fmt, unsigned char *p)
 {
 	int i;
@@ -1896,8 +1949,8 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec)
 	if (rec->flags & FTRACE_FL_TRAMP) {
 		ops = ftrace_find_tramp_ops_new(rec);
 		if (FTRACE_WARN_ON(!ops || !ops->trampoline)) {
-			pr_warning("Bad trampoline accounting at: %p (%pS)\n",
-				    (void *)rec->ip, (void *)rec->ip);
+			pr_warn("Bad trampoline accounting at: %p (%pS) (%lx)\n",
+				(void *)rec->ip, (void *)rec->ip, rec->flags);
 			/* Ftrace is shutting down, return anything */
 			return (unsigned long)FTRACE_ADDR;
 		}
@@ -1964,7 +2017,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 		return ftrace_make_call(rec, ftrace_addr);
 
 	case FTRACE_UPDATE_MAKE_NOP:
-		return ftrace_make_nop(NULL, rec, ftrace_addr);
+		return ftrace_make_nop(NULL, rec, ftrace_old_addr);
 
 	case FTRACE_UPDATE_MODIFY_CALL:
 		return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr);
@@ -2227,7 +2280,10 @@ static int ftrace_save_ops_tramp_hash(struct ftrace_ops *ops)
 	} while_for_each_ftrace_rec();
 
 	/* The number of recs in the hash must match nr_trampolines */
-	FTRACE_WARN_ON(ops->tramp_hash->count != ops->nr_trampolines);
+	if (FTRACE_WARN_ON(ops->tramp_hash->count != ops->nr_trampolines))
+		pr_warn("count=%ld trampolines=%d\n",
+			ops->tramp_hash->count,
+			ops->nr_trampolines);
 
 	return 0;
 }
@@ -2436,8 +2492,8 @@ static inline int ops_traces_mod(struct ftrace_ops *ops)
 	 * Filter_hash being empty will default to trace module.
 	 * But notrace hash requires a test of individual module functions.
 	 */
-	return ftrace_hash_empty(ops->filter_hash) &&
-		ftrace_hash_empty(ops->notrace_hash);
+	return ftrace_hash_empty(ops->func_hash->filter_hash) &&
+		ftrace_hash_empty(ops->func_hash->notrace_hash);
 }
 
 /*
@@ -2459,12 +2515,12 @@ ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
 		return 0;
 
 	/* The function must be in the filter */
-	if (!ftrace_hash_empty(ops->filter_hash) &&
-	    !ftrace_lookup_ip(ops->filter_hash, rec->ip))
+	if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
+	    !ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))
 		return 0;
 
 	/* If in notrace hash, we ignore it too */
-	if (ftrace_lookup_ip(ops->notrace_hash, rec->ip))
+	if (ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip))
 		return 0;
 
 	return 1;
@@ -2785,10 +2841,10 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 	} else {
 		rec = &iter->pg->records[iter->idx++];
 		if (((iter->flags & FTRACE_ITER_FILTER) &&
-		     !(ftrace_lookup_ip(ops->filter_hash, rec->ip))) ||
+		     !(ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))) ||
 
 		    ((iter->flags & FTRACE_ITER_NOTRACE) &&
-		     !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) ||
+		     !ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) ||
 
 		    ((iter->flags & FTRACE_ITER_ENABLED) &&
 		     !(rec->flags & FTRACE_FL_ENABLED))) {
@@ -2837,9 +2893,9 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 	 * functions are enabled.
 	 */
 	if ((iter->flags & FTRACE_ITER_FILTER &&
-	     ftrace_hash_empty(ops->filter_hash)) ||
+	     ftrace_hash_empty(ops->func_hash->filter_hash)) ||
 	    (iter->flags & FTRACE_ITER_NOTRACE &&
-	     ftrace_hash_empty(ops->notrace_hash))) {
+	     ftrace_hash_empty(ops->func_hash->notrace_hash))) {
 		if (*pos > 0)
 			return t_hash_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
@@ -3001,12 +3057,12 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 	iter->ops = ops;
 	iter->flags = flag;
 
-	mutex_lock(&ops->regex_lock);
+	mutex_lock(&ops->func_hash->regex_lock);
 
 	if (flag & FTRACE_ITER_NOTRACE)
-		hash = ops->notrace_hash;
+		hash = ops->func_hash->notrace_hash;
 	else
-		hash = ops->filter_hash;
+		hash = ops->func_hash->filter_hash;
 
 	if (file->f_mode & FMODE_WRITE) {
 		const int size_bits = FTRACE_HASH_DEFAULT_BITS;
@@ -3041,7 +3097,7 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 		file->private_data = iter;
 
  out_unlock:
-	mutex_unlock(&ops->regex_lock);
+	mutex_unlock(&ops->func_hash->regex_lock);
 
 	return ret;
 }
@@ -3279,7 +3335,7 @@ static struct ftrace_ops trace_probe_ops __read_mostly =
 {
 	.func		= function_trace_probe_call,
 	.flags		= FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(trace_probe_ops)
+	INIT_OPS_HASH(trace_probe_ops)
 };
 
 static int ftrace_probe_registered;
@@ -3342,7 +3398,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 			      void *data)
 {
 	struct ftrace_func_probe *entry;
-	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
 	struct ftrace_hash *hash;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
@@ -3359,7 +3415,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	if (WARN_ON(not))
 		return -EINVAL;
 
-	mutex_lock(&trace_probe_ops.regex_lock);
+	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
 	if (!hash) {
@@ -3428,7 +3484,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
  out_unlock:
 	mutex_unlock(&ftrace_lock);
  out:
-	mutex_unlock(&trace_probe_ops.regex_lock);
+	mutex_unlock(&trace_probe_ops.func_hash->regex_lock);
 	free_ftrace_hash(hash);
 
 	return count;
@@ -3446,7 +3502,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	struct ftrace_func_entry *rec_entry;
 	struct ftrace_func_probe *entry;
 	struct ftrace_func_probe *p;
-	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
 	struct list_head free_list;
 	struct ftrace_hash *hash;
 	struct hlist_node *tmp;
@@ -3468,7 +3524,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 			return;
 	}
 
-	mutex_lock(&trace_probe_ops.regex_lock);
+	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
 	if (!hash)
@@ -3521,7 +3577,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	mutex_unlock(&ftrace_lock);
 		
  out_unlock:
-	mutex_unlock(&trace_probe_ops.regex_lock);
+	mutex_unlock(&trace_probe_ops.func_hash->regex_lock);
 	free_ftrace_hash(hash);
 }
 
@@ -3717,12 +3773,12 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
-	mutex_lock(&ops->regex_lock);
+	mutex_lock(&ops->func_hash->regex_lock);
 
 	if (enable)
-		orig_hash = &ops->filter_hash;
+		orig_hash = &ops->func_hash->filter_hash;
 	else
-		orig_hash = &ops->notrace_hash;
+		orig_hash = &ops->func_hash->notrace_hash;
 
 	if (reset)
 		hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
@@ -3752,7 +3808,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 	mutex_unlock(&ftrace_lock);
 
  out_regex_unlock:
-	mutex_unlock(&ops->regex_lock);
+	mutex_unlock(&ops->func_hash->regex_lock);
 
 	free_ftrace_hash(hash);
 	return ret;
@@ -3975,15 +4031,15 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 
 	trace_parser_put(parser);
 
-	mutex_lock(&iter->ops->regex_lock);
+	mutex_lock(&iter->ops->func_hash->regex_lock);
 
 	if (file->f_mode & FMODE_WRITE) {
 		filter_hash = !!(iter->flags & FTRACE_ITER_FILTER);
 
 		if (filter_hash)
-			orig_hash = &iter->ops->filter_hash;
+			orig_hash = &iter->ops->func_hash->filter_hash;
 		else
-			orig_hash = &iter->ops->notrace_hash;
+			orig_hash = &iter->ops->func_hash->notrace_hash;
 
 		mutex_lock(&ftrace_lock);
 		ret = ftrace_hash_move(iter->ops, filter_hash,
@@ -3994,7 +4050,7 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 		mutex_unlock(&ftrace_lock);
 	}
 
-	mutex_unlock(&iter->ops->regex_lock);
+	mutex_unlock(&iter->ops->func_hash->regex_lock);
 	free_ftrace_hash(iter->hash);
 	kfree(iter);
 
@@ -4611,7 +4667,6 @@ void __init ftrace_init(void)
 static struct ftrace_ops global_ops = {
 	.func			= ftrace_stub,
 	.flags			= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(global_ops)
 };
 
 static int __init ftrace_nodyn_init(void)
@@ -4713,7 +4768,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops control_ops = {
 	.func	= ftrace_ops_control_func,
 	.flags	= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(control_ops)
+	INIT_OPS_HASH(control_ops)
 };
 
 static inline void
@@ -5145,6 +5200,17 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
+static struct ftrace_ops graph_ops = {
+	.func			= ftrace_stub,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE |
+				   FTRACE_OPS_FL_INITIALIZED |
+				   FTRACE_OPS_FL_STUB,
+#ifdef FTRACE_GRAPH_TRAMP_ADDR
+	.trampoline		= FTRACE_GRAPH_TRAMP_ADDR,
+#endif
+	ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash)
+};
+
 static int ftrace_graph_active;
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
@@ -5307,12 +5373,28 @@ static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
  */
 static void update_function_graph_func(void)
 {
-	if (ftrace_ops_list == &ftrace_list_end ||
-	    (ftrace_ops_list == &global_ops &&
-	     global_ops.next == &ftrace_list_end))
-		ftrace_graph_entry = __ftrace_graph_entry;
-	else
+	struct ftrace_ops *op;
+	bool do_test = false;
+
+	/*
+	 * The graph and global ops share the same set of functions
+	 * to test. If any other ops is on the list, then
+	 * the graph tracing needs to test if its the function
+	 * it should call.
+	 */
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		if (op != &global_ops && op != &graph_ops &&
+		    op != &ftrace_list_end) {
+			do_test = true;
+			/* in double loop, break out with goto */
+			goto out;
+		}
+	} while_for_each_ftrace_op(op);
+ out:
+	if (do_test)
 		ftrace_graph_entry = ftrace_graph_entry_test;
+	else
+		ftrace_graph_entry = __ftrace_graph_entry;
 }
 
 static struct notifier_block ftrace_suspend_notifier = {
@@ -5353,16 +5435,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_graph_entry = ftrace_graph_entry_test;
 	update_function_graph_func();
 
-	/* Function graph doesn't use the .func field of global_ops */
-	global_ops.flags |= FTRACE_OPS_FL_STUB;
-
-#ifdef CONFIG_DYNAMIC_FTRACE
-	/* Optimize function graph calling (if implemented by arch) */
-	if (FTRACE_GRAPH_TRAMP_ADDR != 0)
-		global_ops.trampoline = FTRACE_GRAPH_TRAMP_ADDR;
-#endif
-
-	ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+	ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_lock);
@@ -5380,12 +5453,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	__ftrace_graph_entry = ftrace_graph_entry_stub;
-	ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET);
-	global_ops.flags &= ~FTRACE_OPS_FL_STUB;
-#ifdef CONFIG_DYNAMIC_FTRACE
-	if (FTRACE_GRAPH_TRAMP_ADDR != 0)
-		global_ops.trampoline = 0;
-#endif
+	ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET);
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index afb04b9b818a..b38fb2b9e237 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -626,8 +626,22 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 		work = &cpu_buffer->irq_work;
 	}
 
-	work->waiters_pending = true;
 	poll_wait(filp, &work->waiters, poll_table);
+	work->waiters_pending = true;
+	/*
+	 * There's a tight race between setting the waiters_pending and
+	 * checking if the ring buffer is empty.  Once the waiters_pending bit
+	 * is set, the next event will wake the task up, but we can get stuck
+	 * if there's only a single event in.
+	 *
+	 * FIXME: Ideally, we need a memory barrier on the writer side as well,
+	 * but adding a memory barrier to all events will cause too much of a
+	 * performance hit in the fast path.  We only need a memory barrier when
+	 * the buffer goes from empty to having content.  But as this race is
+	 * extremely small, and it's not a problem if another event comes in, we
+	 * will fix it later.
+	 */
+	smp_mb();
 
 	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
 	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))