Linux 4.17-rc5

-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAlr4xw8eHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGNYoH/1d5zyMpVJVUKZ0K
 LuEctCGby1PjSvSOhmMuxFVagFAqfBJXmwWTeohLfLG48r/Yk0AsZQ5HH13/8baj
 k/T8UgUvKZKustndCRp+joQ3Pa1ZpcIFaWRvB8pKFCefJ/F/Lj4B4X1HYI7vLq0K
 /ZBXUdy3ry0lcVuypnaARYAb2O7l/nyZIjZ3FhiuyymWe7Jpo+G7VK922LOMSX/y
 VYFZCWa8nxN+yFhO0ao9X5k7ggIiUrEBtbfNrk19VtAn0hx+OYKW2KfJK/eHNey/
 CKrOT+KAxU8VU29AEIbYzlL3yrQmULcEoIDiqJ/6m5m6JwsEbP6EqQHs0TiuQFpq
 A0MO9rw=
 =yjUP
 -----END PGP SIGNATURE-----

Merge tag 'v4.17-rc5' into sched/core, to pick up fixes and dependencies

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

kernel/bpf/arraymap.c

@@ -476,7 +476,7 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
@@ -495,6 +495,7 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_get_ptr = prog_fd_array_get_ptr,
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
+	.map_release_uref = bpf_fd_array_map_clear,
 };
 
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,

kernel/bpf/sockmap.c

@@ -43,6 +43,7 @@
 #include <net/tcp.h>
 #include <linux/ptr_ring.h>
 #include <net/inet_common.h>
+#include <linux/sched/signal.h>
 
 #define SOCK_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
@@ -325,6 +326,9 @@ retry:
 			if (ret > 0) {
 				if (apply)
 					apply_bytes -= ret;
+
+				sg->offset += ret;
+				sg->length -= ret;
 				size -= ret;
 				offset += ret;
 				if (uncharge)
@@ -332,8 +336,6 @@ retry:
 				goto retry;
 			}
 
-			sg->length = size;
-			sg->offset = offset;
 			return ret;
 		}
 
@@ -391,7 +393,8 @@ static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 	} while (i != md->sg_end);
 }
 
-static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
+static void free_bytes_sg(struct sock *sk, int bytes,
+			  struct sk_msg_buff *md, bool charge)
 {
 	struct scatterlist *sg = md->sg_data;
 	int i = md->sg_start, free;
@@ -401,11 +404,13 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 		if (bytes < free) {
 			sg[i].length -= bytes;
 			sg[i].offset += bytes;
-			sk_mem_uncharge(sk, bytes);
+			if (charge)
+				sk_mem_uncharge(sk, bytes);
 			break;
 		}
 
-		sk_mem_uncharge(sk, sg[i].length);
+		if (charge)
+			sk_mem_uncharge(sk, sg[i].length);
 		put_page(sg_page(&sg[i]));
 		bytes -= sg[i].length;
 		sg[i].length = 0;
@@ -416,6 +421,7 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
 		if (i == MAX_SKB_FRAGS)
 			i = 0;
 	}
+	md->sg_start = i;
 }
 
 static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
@@ -523,8 +529,6 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 	i = md->sg_start;
 
 	do {
-		r->sg_data[i] = md->sg_data[i];
-
 		size = (apply && apply_bytes < md->sg_data[i].length) ?
 			apply_bytes : md->sg_data[i].length;
 
@@ -535,6 +539,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 		}
 
 		sk_mem_charge(sk, size);
+		r->sg_data[i] = md->sg_data[i];
 		r->sg_data[i].length = size;
 		md->sg_data[i].length -= size;
 		md->sg_data[i].offset += size;
@@ -575,10 +580,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 				       struct sk_msg_buff *md,
 				       int flags)
 {
+	bool ingress = !!(md->flags & BPF_F_INGRESS);
 	struct smap_psock *psock;
 	struct scatterlist *sg;
-	int i, err, free = 0;
-	bool ingress = !!(md->flags & BPF_F_INGRESS);
+	int err = 0;
 
 	sg = md->sg_data;
 
@@ -606,16 +611,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 out_rcu:
 	rcu_read_unlock();
 out:
-	i = md->sg_start;
-	while (sg[i].length) {
-		free += sg[i].length;
-		put_page(sg_page(&sg[i]));
-		sg[i].length = 0;
-		i++;
-		if (i == MAX_SKB_FRAGS)
-			i = 0;
-	}
-	return free;
+	free_bytes_sg(NULL, send, md, false);
+	return err;
 }
 
 static inline void bpf_md_init(struct smap_psock *psock)
@@ -700,19 +697,26 @@ more_data:
 		err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags);
 		lock_sock(sk);
 
+		if (unlikely(err < 0)) {
+			free_start_sg(sk, m);
+			psock->sg_size = 0;
+			if (!cork)
+				*copied -= send;
+		} else {
+			psock->sg_size -= send;
+		}
+
 		if (cork) {
 			free_start_sg(sk, m);
+			psock->sg_size = 0;
 			kfree(m);
 			m = NULL;
+			err = 0;
 		}
-		if (unlikely(err))
-			*copied -= err;
-		else
-			psock->sg_size -= send;
 		break;
 	case __SK_DROP:
 	default:
-		free_bytes_sg(sk, send, m);
+		free_bytes_sg(sk, send, m, true);
 		apply_bytes_dec(psock, send);
 		*copied -= send;
 		psock->sg_size -= send;
@@ -732,6 +736,26 @@ out_err:
 	return err;
 }
 
+static int bpf_wait_data(struct sock *sk,
+			 struct smap_psock *psk, int flags,
+			 long timeo, int *err)
+{
+	int rc;
+
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	rc = sk_wait_event(sk, &timeo,
+			   !list_empty(&psk->ingress) ||
+			   !skb_queue_empty(&sk->sk_receive_queue),
+			   &wait);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+
+	return rc;
+}
+
 static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			   int nonblock, int flags, int *addr_len)
 {
@@ -755,6 +779,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	lock_sock(sk);
+bytes_ready:
 	while (copied != len) {
 		struct scatterlist *sg;
 		struct sk_msg_buff *md;
@@ -809,6 +834,28 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 	}
 
+	if (!copied) {
+		long timeo;
+		int data;
+		int err = 0;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = bpf_wait_data(sk, psock, flags, timeo, &err);
+
+		if (data) {
+			if (!skb_queue_empty(&sk->sk_receive_queue)) {
+				release_sock(sk);
+				smap_release_sock(psock, sk);
+				copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+				return copied;
+			}
+			goto bytes_ready;
+		}
+
+		if (err)
+			copied = err;
+	}
+
 	release_sock(sk);
 	smap_release_sock(psock, sk);
 	return copied;
@@ -1831,7 +1878,7 @@ static int sock_map_update_elem(struct bpf_map *map,
 	return err;
 }
 
-static void sock_map_release(struct bpf_map *map, struct file *map_file)
+static void sock_map_release(struct bpf_map *map)
 {
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
 	struct bpf_prog *orig;
@@ -1855,7 +1902,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_get_next_key = sock_map_get_next_key,
 	.map_update_elem = sock_map_update_elem,
 	.map_delete_elem = sock_map_delete_elem,
-	.map_release = sock_map_release,
+	.map_release_uref = sock_map_release,
 };
 
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,

kernel/bpf/syscall.c

@@ -26,6 +26,7 @@
 #include <linux/cred.h>
 #include <linux/timekeeping.h>
 #include <linux/ctype.h>
+#include <linux/nospec.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
 			   (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -102,12 +103,14 @@ const struct bpf_map_ops bpf_map_offload_ops = {
 static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 {
 	const struct bpf_map_ops *ops;
+	u32 type = attr->map_type;
 	struct bpf_map *map;
 	int err;
 
-	if (attr->map_type >= ARRAY_SIZE(bpf_map_types))
+	if (type >= ARRAY_SIZE(bpf_map_types))
 		return ERR_PTR(-EINVAL);
-	ops = bpf_map_types[attr->map_type];
+	type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types));
+	ops = bpf_map_types[type];
 	if (!ops)
 		return ERR_PTR(-EINVAL);
 
@@ -122,7 +125,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return map;
 	map->ops = ops;
-	map->map_type = attr->map_type;
+	map->map_type = type;
 	return map;
 }
 
@@ -257,8 +260,8 @@ static void bpf_map_free_deferred(struct work_struct *work)
 static void bpf_map_put_uref(struct bpf_map *map)
 {
 	if (atomic_dec_and_test(&map->usercnt)) {
-		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
-			bpf_fd_array_map_clear(map);
+		if (map->ops->map_release_uref)
+			map->ops->map_release_uref(map);
 	}
 }
 
@@ -871,11 +874,17 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = {
 
 static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
 {
-	if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
+	const struct bpf_prog_ops *ops;
+
+	if (type >= ARRAY_SIZE(bpf_prog_types))
+		return -EINVAL;
+	type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types));
+	ops = bpf_prog_types[type];
+	if (!ops)
 		return -EINVAL;
 
 	if (!bpf_prog_is_dev_bound(prog->aux))
-		prog->aux->ops = bpf_prog_types[type];
+		prog->aux->ops = ops;
 	else
 		prog->aux->ops = &bpf_offload_prog_ops;
 	prog->type = type;

kernel/compat.c

@@ -34,6 +34,7 @@ int compat_get_timex(struct timex *txc, const struct compat_timex __user *utp)
 {
 	struct compat_timex tx32;
 
+	memset(txc, 0, sizeof(struct timex));
 	if (copy_from_user(&tx32, utp, sizeof(struct compat_timex)))
 		return -EFAULT;
 

kernel/events/ring_buffer.c

@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/circ_buf.h>
 #include <linux/poll.h>
+#include <linux/nospec.h>
 
 #include "internal.h"
 
@@ -867,8 +868,10 @@ perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
 			return NULL;
 
 		/* AUX space */
-		if (pgoff >= rb->aux_pgoff)
-			return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]);
+		if (pgoff >= rb->aux_pgoff) {
+			int aux_pgoff = array_index_nospec(pgoff - rb->aux_pgoff, rb->aux_nr_pages);
+			return virt_to_page(rb->aux_pages[aux_pgoff]);
+		}
 	}
 
 	return __perf_mmap_to_page(rb, pgoff);

kernel/module.c

@@ -3517,6 +3517,11 @@ static noinline int do_init_module(struct module *mod)
 	 * walking this with preempt disabled.  In all the failure paths, we
 	 * call synchronize_sched(), but we don't want to slow down the success
 	 * path, so use actual RCU here.
+	 * Note that module_alloc() on most architectures creates W+X page
+	 * mappings which won't be cleaned up until do_free_init() runs.  Any
+	 * code such as mark_rodata_ro() which depends on those mappings to
+	 * be cleaned up needs to sync with the queued work - ie
+	 * rcu_barrier_sched()
 	 */
 	call_rcu_sched(&freeinit->rcu, do_free_init);
 	mutex_unlock(&module_mutex);

kernel/sched/autogroup.c

@@ -2,6 +2,7 @@
 /*
  * Auto-group scheduling implementation:
  */
+#include <linux/nospec.h>
 #include "sched.h"
 
 unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
@@ -209,7 +210,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 	static unsigned long next = INITIAL_JIFFIES;
 	struct autogroup *ag;
 	unsigned long shares;
-	int err;
+	int err, idx;
 
 	if (nice < MIN_NICE || nice > MAX_NICE)
 		return -EINVAL;
@@ -227,7 +228,9 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 
 	next = HZ / 10 + jiffies;
 	ag = autogroup_task_get(p);
-	shares = scale_load(sched_prio_to_weight[nice + 20]);
+
+	idx = array_index_nospec(nice + 20, 40);
+	shares = scale_load(sched_prio_to_weight[idx]);
 
 	down_write(&ag->lock);
 	err = sched_group_set_shares(ag->tg, shares);

kernel/sched/core.c

@@ -8,6 +8,7 @@
 #include "sched.h"
 
 #include <linux/kthread.h>
+#include <linux/nospec.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -6926,11 +6927,15 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
 				     struct cftype *cft, s64 nice)
 {
 	unsigned long weight;
+	int idx;
 
 	if (nice < MIN_NICE || nice > MAX_NICE)
 		return -ERANGE;
 
-	weight = sched_prio_to_weight[NICE_TO_PRIO(nice) - MAX_RT_PRIO];
+	idx = NICE_TO_PRIO(nice) - MAX_RT_PRIO;
+	idx = array_index_nospec(idx, 40);
+	weight = sched_prio_to_weight[idx];
+
 	return sched_group_set_shares(css_tg(css), scale_load(weight));
 }
 #endif

kernel/sched/cpufreq_schedutil.c

@@ -305,7 +305,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
 	 */
-	if (busy && next_f < sg_policy->next_freq) {
+	if (busy && next_f < sg_policy->next_freq &&
+	    sg_policy->next_freq != UINT_MAX) {
 		next_f = sg_policy->next_freq;
 
 		/* Reset cached freq as next_freq has changed */
@@ -396,19 +397,6 @@ static void sugov_irq_work(struct irq_work *irq_work)
 
 	sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
 
-	/*
-	 * For RT tasks, the schedutil governor shoots the frequency to maximum.
-	 * Special care must be taken to ensure that this kthread doesn't result
-	 * in the same behavior.
-	 *
-	 * This is (mostly) guaranteed by the work_in_progress flag. The flag is
-	 * updated only at the end of the sugov_work() function and before that
-	 * the schedutil governor rejects all other frequency scaling requests.
-	 *
-	 * There is a very rare case though, where the RT thread yields right
-	 * after the work_in_progress flag is cleared. The effects of that are
-	 * neglected for now.
-	 */
 	kthread_queue_work(&sg_policy->worker, &sg_policy->work);
 }
 

kernel/sched/fair.c

@@ -1854,7 +1854,6 @@ static int task_numa_migrate(struct task_struct *p)
 static void numa_migrate_preferred(struct task_struct *p)
 {
 	unsigned long interval = HZ;
-	unsigned long numa_migrate_retry;
 
 	/* This task has no NUMA fault statistics yet */
 	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
@@ -1862,18 +1861,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 
 	/* Periodically retry migrating the task to the preferred node */
 	interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16);
-	numa_migrate_retry = jiffies + interval;
-
-	/*
-	 * Check that the new retry threshold is after the current one. If
-	 * the retry is in the future, it implies that wake_affine has
-	 * temporarily asked NUMA balancing to backoff from placement.
-	 */
-	if (numa_migrate_retry > p->numa_migrate_retry)
-		return;
-
-	/* Safe to try placing the task on the preferred node */
-	p->numa_migrate_retry = numa_migrate_retry;
+	p->numa_migrate_retry = jiffies + interval;
 
 	/* Success if task is already running on preferred CPU */
 	if (task_node(p) == p->numa_preferred_nid)
@@ -5922,48 +5910,6 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
 	return this_eff_load < prev_eff_load ? this_cpu : nr_cpumask_bits;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
-	unsigned long interval;
-
-	if (!static_branch_likely(&sched_numa_balancing))
-		return;
-
-	/* If balancing has no preference then continue gathering data */
-	if (p->numa_preferred_nid == -1)
-		return;
-
-	/*
-	 * If the wakeup is not affecting locality then it is neutral from
-	 * the perspective of NUMA balacing so continue gathering data.
-	 */
-	if (cpu_to_node(prev_cpu) == cpu_to_node(target))
-		return;
-
-	/*
-	 * Temporarily prevent NUMA balancing trying to place waker/wakee after
-	 * wakee has been moved by wake_affine. This will potentially allow
-	 * related tasks to converge and update their data placement. The
-	 * 4 * numa_scan_period is to allow the two-pass filter to migrate
-	 * hot data to the wakers node.
-	 */
-	interval = max(sysctl_numa_balancing_scan_delay,
-			 p->numa_scan_period << 2);
-	p->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-
-	interval = max(sysctl_numa_balancing_scan_delay,
-			 current->numa_scan_period << 2);
-	current->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-}
-#else
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
-}
-#endif
-
 static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		       int this_cpu, int prev_cpu, int sync)
 {
@@ -5979,7 +5925,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	if (target == nr_cpumask_bits)
 		return prev_cpu;
 
-	update_wa_numa_placement(p, prev_cpu, target);
 	schedstat_inc(sd->ttwu_move_affine);
 	schedstat_inc(p->se.statistics.nr_wakeups_affine);
 	return target;

kernel/time/clocksource.c

@@ -119,6 +119,16 @@ static DEFINE_SPINLOCK(watchdog_lock);
 static int watchdog_running;
 static atomic_t watchdog_reset_pending;
 
+static void inline clocksource_watchdog_lock(unsigned long *flags)
+{
+	spin_lock_irqsave(&watchdog_lock, *flags);
+}
+
+static void inline clocksource_watchdog_unlock(unsigned long *flags)
+{
+	spin_unlock_irqrestore(&watchdog_lock, *flags);
+}
+
 static int clocksource_watchdog_kthread(void *data);
 static void __clocksource_change_rating(struct clocksource *cs, int rating);
 
@@ -142,9 +152,19 @@ static void __clocksource_unstable(struct clocksource *cs)
 	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
 	cs->flags |= CLOCK_SOURCE_UNSTABLE;
 
+	/*
+	 * If the clocksource is registered clocksource_watchdog_kthread() will
+	 * re-rate and re-select.
+	 */
+	if (list_empty(&cs->list)) {
+		cs->rating = 0;
+		return;
+	}
+
 	if (cs->mark_unstable)
 		cs->mark_unstable(cs);
 
+	/* kick clocksource_watchdog_kthread() */
 	if (finished_booting)
 		schedule_work(&watchdog_work);
 }
@@ -153,10 +173,8 @@ static void __clocksource_unstable(struct clocksource *cs)
  * clocksource_mark_unstable - mark clocksource unstable via watchdog
  * @cs:		clocksource to be marked unstable
  *
- * This function is called instead of clocksource_change_rating from
- * cpu hotplug code to avoid a deadlock between the clocksource mutex
- * and the cpu hotplug mutex. It defers the update of the clocksource
- * to the watchdog thread.
+ * This function is called by the x86 TSC code to mark clocksources as unstable;
+ * it defers demotion and re-selection to a kthread.
  */
 void clocksource_mark_unstable(struct clocksource *cs)
 {
@@ -164,7 +182,7 @@ void clocksource_mark_unstable(struct clocksource *cs)
 
 	spin_lock_irqsave(&watchdog_lock, flags);
 	if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
-		if (list_empty(&cs->wd_list))
+		if (!list_empty(&cs->list) && list_empty(&cs->wd_list))
 			list_add(&cs->wd_list, &watchdog_list);
 		__clocksource_unstable(cs);
 	}
@@ -319,9 +337,8 @@ static void clocksource_resume_watchdog(void)
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)
 {
-	unsigned long flags;
+	INIT_LIST_HEAD(&cs->wd_list);
 
-	spin_lock_irqsave(&watchdog_lock, flags);
 	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
 		/* cs is a clocksource to be watched. */
 		list_add(&cs->wd_list, &watchdog_list);
@@ -331,7 +348,6 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 	}
-	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
 static void clocksource_select_watchdog(bool fallback)
@@ -373,9 +389,6 @@ static void clocksource_select_watchdog(bool fallback)
 
 static void clocksource_dequeue_watchdog(struct clocksource *cs)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&watchdog_lock, flags);
 	if (cs != watchdog) {
 		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
 			/* cs is a watched clocksource. */
@@ -384,21 +397,19 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs)
 			clocksource_stop_watchdog();
 		}
 	}
-	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
 static int __clocksource_watchdog_kthread(void)
 {
 	struct clocksource *cs, *tmp;
 	unsigned long flags;
-	LIST_HEAD(unstable);
 	int select = 0;
 
 	spin_lock_irqsave(&watchdog_lock, flags);
 	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
 		if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
 			list_del_init(&cs->wd_list);
-			list_add(&cs->wd_list, &unstable);
+			__clocksource_change_rating(cs, 0);
 			select = 1;
 		}
 		if (cs->flags & CLOCK_SOURCE_RESELECT) {
@@ -410,11 +421,6 @@ static int __clocksource_watchdog_kthread(void)
 	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 
-	/* Needs to be done outside of watchdog lock */
-	list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
-		list_del_init(&cs->wd_list);
-		__clocksource_change_rating(cs, 0);
-	}
 	return select;
 }
 
@@ -447,6 +453,9 @@ static inline int __clocksource_watchdog_kthread(void) { return 0; }
 static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
 void clocksource_mark_unstable(struct clocksource *cs) { }
 
+static void inline clocksource_watchdog_lock(unsigned long *flags) { }
+static void inline clocksource_watchdog_unlock(unsigned long *flags) { }
+
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
 /**
@@ -779,14 +788,19 @@ EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
  */
 int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
+	unsigned long flags;
 
 	/* Initialize mult/shift and max_idle_ns */
 	__clocksource_update_freq_scale(cs, scale, freq);
 
 	/* Add clocksource to the clocksource list */
 	mutex_lock(&clocksource_mutex);
+
+	clocksource_watchdog_lock(&flags);
 	clocksource_enqueue(cs);
 	clocksource_enqueue_watchdog(cs);
+	clocksource_watchdog_unlock(&flags);
+
 	clocksource_select();
 	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
@@ -808,8 +822,13 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating)
  */
 void clocksource_change_rating(struct clocksource *cs, int rating)
 {
+	unsigned long flags;
+
 	mutex_lock(&clocksource_mutex);
+	clocksource_watchdog_lock(&flags);
 	__clocksource_change_rating(cs, rating);
+	clocksource_watchdog_unlock(&flags);
+
 	clocksource_select();
 	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
@@ -821,6 +840,8 @@ EXPORT_SYMBOL(clocksource_change_rating);
  */
 static int clocksource_unbind(struct clocksource *cs)
 {
+	unsigned long flags;
+
 	if (clocksource_is_watchdog(cs)) {
 		/* Select and try to install a replacement watchdog. */
 		clocksource_select_watchdog(true);
@@ -834,8 +855,12 @@ static int clocksource_unbind(struct clocksource *cs)
 		if (curr_clocksource == cs)
 			return -EBUSY;
 	}
+
+	clocksource_watchdog_lock(&flags);
 	clocksource_dequeue_watchdog(cs);
 	list_del_init(&cs->list);
+	clocksource_watchdog_unlock(&flags);
+
 	return 0;
 }
 

kernel/trace/ftrace.c

@@ -5514,10 +5514,10 @@ static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer)
 	ftrace_create_filter_files(&global_ops, d_tracer);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	trace_create_file("set_graph_function", 0444, d_tracer,
+	trace_create_file("set_graph_function", 0644, d_tracer,
 				    NULL,
 				    &ftrace_graph_fops);
-	trace_create_file("set_graph_notrace", 0444, d_tracer,
+	trace_create_file("set_graph_notrace", 0644, d_tracer,
 				    NULL,
 				    &ftrace_graph_notrace_fops);
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */

kernel/trace/trace_events_filter.c

@@ -762,6 +762,9 @@ static int regex_match_full(char *str, struct regex *r, int len)
 
 static int regex_match_front(char *str, struct regex *r, int len)
 {
+	if (len < r->len)
+		return 0;
+
 	if (strncmp(str, r->pattern, r->len) == 0)
 		return 1;
 	return 0;

kernel/trace/trace_stack.c

@@ -472,7 +472,7 @@ static __init int stack_trace_init(void)
 			NULL, &stack_trace_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-	trace_create_file("stack_trace_filter", 0444, d_tracer,
+	trace_create_file("stack_trace_filter", 0644, d_tracer,
 			  &trace_ops, &stack_trace_filter_fops);
 #endif