Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "The main changes in this cycle are:

   - rwsem scalability improvements, phase #2, by Waiman Long, which are
     rather impressive:

       "On a 2-socket 40-core 80-thread Skylake system with 40 reader
        and writer locking threads, the min/mean/max locking operations
        done in a 5-second testing window before the patchset were:

         40 readers, Iterations Min/Mean/Max = 1,807/1,808/1,810
         40 writers, Iterations Min/Mean/Max = 1,807/50,344/151,255

        After the patchset, they became:

         40 readers, Iterations Min/Mean/Max = 30,057/31,359/32,741
         40 writers, Iterations Min/Mean/Max = 94,466/95,845/97,098"

     There's a lot of changes to the locking implementation that makes
     it similar to qrwlock, including owner handoff for more fair
     locking.

     Another microbenchmark shows how across the spectrum the
     improvements are:

       "With a locking microbenchmark running on 5.1 based kernel, the
        total locking rates (in kops/s) on a 2-socket Skylake system
        with equal numbers of readers and writers (mixed) before and
        after this patchset were:

        # of Threads   Before Patch      After Patch
        ------------   ------------      -----------
             2            2,618             4,193
             4            1,202             3,726
             8              802             3,622
            16              729             3,359
            32              319             2,826
            64              102             2,744"

     The changes are extensive and the patch-set has been through
     several iterations addressing various locking workloads. There
     might be more regressions, but unless they are pathological I
     believe we want to use this new implementation as the baseline
     going forward.

   - jump-label optimizations by Daniel Bristot de Oliveira: the primary
     motivation was to remove IPI disturbance of isolated RT-workload
     CPUs, which resulted in the implementation of batched jump-label
     updates. Beyond the improvement of the real-time characteristics
     kernel, in one test this patchset improved static key update
     overhead from 57 msecs to just 1.4 msecs - which is a nice speedup
     as well.

   - atomic64_t cross-arch type cleanups by Mark Rutland: over the last
     ~10 years of atomic64_t existence the various types used by the
     APIs only had to be self-consistent within each architecture -
     which means they became wildly inconsistent across architectures.
     Mark puts and end to this by reworking all the atomic64
     implementations to use 's64' as the base type for atomic64_t, and
     to ensure that this type is consistently used for parameters and
     return values in the API, avoiding further problems in this area.

   - A large set of small improvements to lockdep by Yuyang Du: type
     cleanups, output cleanups, function return type and othr cleanups
     all around the place.

   - A set of percpu ops cleanups and fixes by Peter Zijlstra.

   - Misc other changes - please see the Git log for more details"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits)
  locking/lockdep: increase size of counters for lockdep statistics
  locking/atomics: Use sed(1) instead of non-standard head(1) option
  locking/lockdep: Move mark_lock() inside CONFIG_TRACE_IRQFLAGS && CONFIG_PROVE_LOCKING
  x86/jump_label: Make tp_vec_nr static
  x86/percpu: Optimize raw_cpu_xchg()
  x86/percpu, sched/fair: Avoid local_clock()
  x86/percpu, x86/irq: Relax {set,get}_irq_regs()
  x86/percpu: Relax smp_processor_id()
  x86/percpu: Differentiate this_cpu_{}() and __this_cpu_{}()
  locking/rwsem: Guard against making count negative
  locking/rwsem: Adaptive disabling of reader optimistic spinning
  locking/rwsem: Enable time-based spinning on reader-owned rwsem
  locking/rwsem: Make rwsem->owner an atomic_long_t
  locking/rwsem: Enable readers spinning on writer
  locking/rwsem: Clarify usage of owner's nonspinaable bit
  locking/rwsem: Wake up almost all readers in wait queue
  locking/rwsem: More optimal RT task handling of null owner
  locking/rwsem: Always release wait_lock before waking up tasks
  locking/rwsem: Implement lock handoff to prevent lock starvation
  locking/rwsem: Make rwsem_spin_on_owner() return owner state
  ...

3 files changed, 8 insertions, 8 deletions

diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index 5c4aa606208c..2de5e3672e42 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -856,7 +856,7 @@ static ssize_t nx842_##_name##_show(struct device *dev,		\
 	rcu_read_lock();						\
 	local_devdata = rcu_dereference(devdata);			\
 	if (local_devdata)						\
-		p = snprintf(buf, PAGE_SIZE, "%ld\n",			\
+		p = snprintf(buf, PAGE_SIZE, "%lld\n",			\
 		       atomic64_read(&local_devdata->counters->_name));	\
 	rcu_read_unlock();						\
 	return p;							\
@@ -909,7 +909,7 @@ static ssize_t nx842_timehist_show(struct device *dev,
 	}
 
 	for (i = 0; i < (NX842_HIST_SLOTS - 2); i++) {
-		bytes = snprintf(p, bytes_remain, "%u-%uus:\t%ld\n",
+		bytes = snprintf(p, bytes_remain, "%u-%uus:\t%lld\n",
 			       i ? (2<<(i-1)) : 0, (2<<i)-1,
 			       atomic64_read(&times[i]));
 		bytes_remain -= bytes;
@@ -917,7 +917,7 @@ static ssize_t nx842_timehist_show(struct device *dev,
 	}
 	/* The last bucket holds everything over
 	 * 2<<(NX842_HIST_SLOTS - 2) us */
-	bytes = snprintf(p, bytes_remain, "%uus - :\t%ld\n",
+	bytes = snprintf(p, bytes_remain, "%uus - :\t%lld\n",
 			2<<(NX842_HIST_SLOTS - 2),
 			atomic64_read(&times[(NX842_HIST_SLOTS - 1)]));
 	p += bytes;
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 29f7b15c81d9..d020bb4d03d5 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -457,7 +457,7 @@ static int alloc_name(struct ib_device *ibdev, const char *name)
 	int rc;
 	int i;
 
-	lockdep_assert_held_exclusive(&devices_rwsem);
+	lockdep_assert_held_write(&devices_rwsem);
 	ida_init(&inuse);
 	xa_for_each (&devices, index, device) {
 		char buf[IB_DEVICE_NAME_MAX];
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index e38f104db174..fde8d4073e74 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -487,7 +487,7 @@ static int tty_ldisc_open(struct tty_struct *tty, struct tty_ldisc *ld)
 
 static void tty_ldisc_close(struct tty_struct *tty, struct tty_ldisc *ld)
 {
-	lockdep_assert_held_exclusive(&tty->ldisc_sem);
+	lockdep_assert_held_write(&tty->ldisc_sem);
 	WARN_ON(!test_bit(TTY_LDISC_OPEN, &tty->flags));
 	clear_bit(TTY_LDISC_OPEN, &tty->flags);
 	if (ld->ops->close)
@@ -509,7 +509,7 @@ static int tty_ldisc_failto(struct tty_struct *tty, int ld)
 	struct tty_ldisc *disc = tty_ldisc_get(tty, ld);
 	int r;
 
-	lockdep_assert_held_exclusive(&tty->ldisc_sem);
+	lockdep_assert_held_write(&tty->ldisc_sem);
 	if (IS_ERR(disc))
 		return PTR_ERR(disc);
 	tty->ldisc = disc;
@@ -633,7 +633,7 @@ EXPORT_SYMBOL_GPL(tty_set_ldisc);
  */
 static void tty_ldisc_kill(struct tty_struct *tty)
 {
-	lockdep_assert_held_exclusive(&tty->ldisc_sem);
+	lockdep_assert_held_write(&tty->ldisc_sem);
 	if (!tty->ldisc)
 		return;
 	/*
@@ -681,7 +681,7 @@ int tty_ldisc_reinit(struct tty_struct *tty, int disc)
 	struct tty_ldisc *ld;
 	int retval;
 
-	lockdep_assert_held_exclusive(&tty->ldisc_sem);
+	lockdep_assert_held_write(&tty->ldisc_sem);
 	ld = tty_ldisc_get(tty, disc);
 	if (IS_ERR(ld)) {
 		BUG_ON(disc == N_TTY);