Merge tag 'v4.1.35' into 4.1-2.0.x-imx

Linux 4.1.35

* tag 'v4.1.35': (98 commits)
  Linux 4.1.35
  xhci: fix usb2 resume timing and races.
  mm: remove gup_flags FOLL_WRITE games from __get_user_pages()
  timekeeping: Fix __ktime_get_fast_ns() regression
  time: Add cycles to nanoseconds translation
  Linux 4.1.34
  openrisc: fix the fix of copy_from_user()
  avr32: fix 'undefined reference to `___copy_from_user'
  fix memory leaks in tracing_buffers_splice_read()
  tracing: Move mutex to protect against resetting of seq data
  MIPS: SMP: Fix possibility of deadlock when bringing CPUs online
  MIPS: Fix pre-r6 emulation FPU initialisation
  btrfs: ensure that file descriptor used with subvol ioctls is a dir
  fix fault_in_multipages_...() on architectures with no-op access_ok()
  ocfs2: fix start offset to ocfs2_zero_range_for_truncate()
  fanotify: fix list corruption in fanotify_get_response()
  fsnotify: add a way to stop queueing events on group shutdown
  autofs: use dentry flags to block walks during expire
  autofs races
  ocfs2/dlm: fix race between convert and migration
  ...

Signed-off-by: Otavio Salvador <otavio@ossystems.com.br>

3 files changed, 64 insertions, 19 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 98e607121d09..6cb5f00696f5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1672,6 +1672,28 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
 
+	/*
+	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
+	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
+	 * in smp_cond_load_acquire() below.
+	 *
+	 * sched_ttwu_pending()                 try_to_wake_up()
+	 *   [S] p->on_rq = 1;                  [L] P->state
+	 *       UNLOCK rq->lock  -----.
+	 *                              \
+	 *				 +---   RMB
+	 * schedule()                   /
+	 *       LOCK rq->lock    -----'
+	 *       UNLOCK rq->lock
+	 *
+	 * [task p]
+	 *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+	 *
+	 * Pairs with the UNLOCK+LOCK on rq->lock from the
+	 * last wakeup of our task and the schedule that got our task
+	 * current.
+	 */
+	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
 		goto stat;
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 8fcc801fde15..d9f112bd42a7 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -309,17 +309,34 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
+static inline s64 timekeeping_delta_to_ns(struct tk_read_base *tkr,
+					  cycle_t delta)
+{
+	s64 nsec;
+
+	nsec = delta * tkr->mult + tkr->xtime_nsec;
+	nsec >>= tkr->shift;
+
+	/* If arch requires, add in get_arch_timeoffset() */
+	return nsec + arch_gettimeoffset();
+}
+
 static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
 {
 	cycle_t delta;
-	s64 nsec;
 
 	delta = timekeeping_get_delta(tkr);
+	return timekeeping_delta_to_ns(tkr, delta);
+}
 
-	nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift;
+static inline s64 timekeeping_cycles_to_ns(struct tk_read_base *tkr,
+					    cycle_t cycles)
+{
+	cycle_t delta;
 
-	/* If arch requires, add in get_arch_timeoffset() */
-	return nsec + arch_gettimeoffset();
+	/* calculate the delta since the last update_wall_time */
+	delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask);
+	return timekeeping_delta_to_ns(tkr, delta);
 }
 
 /**
@@ -421,8 +438,11 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 		tkr = tkf->base + (seq & 0x01);
 		now = ktime_to_ns(tkr->base);
 
-		now += clocksource_delta(tkr->read(tkr->clock),
-					 tkr->cycle_last, tkr->mask);
+		now += timekeeping_delta_to_ns(tkr,
+				clocksource_delta(
+					tkr->read(tkr->clock),
+					tkr->cycle_last,
+					tkr->mask));
 	} while (read_seqcount_retry(&tkf->seq, seq));
 
 	return now;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index de6ea94c41bb..61ea7e8cdde5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4694,19 +4694,20 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	struct trace_iterator *iter = filp->private_data;
 	ssize_t sret;
 
-	/* return any leftover data */
-	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
-	if (sret != -EBUSY)
-		return sret;
-
-	trace_seq_init(&iter->seq);
-
 	/*
 	 * Avoid more than one consumer on a single file descriptor
 	 * This is just a matter of traces coherency, the ring buffer itself
 	 * is protected.
 	 */
 	mutex_lock(&iter->mutex);
+
+	/* return any leftover data */
+	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+	if (sret != -EBUSY)
+		goto out;
+
+	trace_seq_init(&iter->seq);
+
 	if (iter->trace->read) {
 		sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
 		if (sret)
@@ -5731,9 +5732,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		return -EBUSY;
 #endif
 
-	if (splice_grow_spd(pipe, &spd))
-		return -ENOMEM;
-
 	if (*ppos & (PAGE_SIZE - 1))
 		return -EINVAL;
 
@@ -5743,6 +5741,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		len &= PAGE_MASK;
 	}
 
+	if (splice_grow_spd(pipe, &spd))
+		return -ENOMEM;
+
  again:
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
@@ -5800,19 +5801,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	/* did we read anything? */
 	if (!spd.nr_pages) {
 		if (ret)
-			return ret;
+			goto out;
 
+		ret = -EAGAIN;
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
-			return -EAGAIN;
+			goto out;
 
 		ret = wait_on_pipe(iter, true);
 		if (ret)
-			return ret;
+			goto out;
 
 		goto again;
 	}
 
 	ret = splice_to_pipe(pipe, &spd);
+out:
 	splice_shrink_spd(&spd);
 
 	return ret;