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 tree got pretty big in this development cycle, but the net effect
  is pretty good:

    115 files changed, 673 insertions(+), 1522 deletions(-)

  The main changes were:

   - Rework and generalize the mutex code to remove per arch mutex
     primitives. (Peter Zijlstra)

   - Add vCPU preemption support: add an interface to query the
     preemption status of vCPUs and use it in locking primitives - this
     optimizes paravirt performance. (Pan Xinhui, Juergen Gross,
     Christian Borntraeger)

   - Introduce cpu_relax_yield() and remov cpu_relax_lowlatency() to
     clean up and improve the s390 lock yielding machinery and its core
     kernel impact. (Christian Borntraeger)

   - Micro-optimize mutexes some more. (Waiman Long)

   - Reluctantly add the to-be-deprecated mutex_trylock_recursive()
     interface on a temporary basis, to give the DRM code more time to
     get rid of its locking hacks. Any other users will be NAK-ed on
     sight. (We turned off the deprecation warning for the time being to
     not pollute the build log.) (Peter Zijlstra)

   - Improve the rtmutex code a bit, in light of recent long lived
     bugs/races. (Thomas Gleixner)

   - Misc fixes, cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  x86/paravirt: Fix bool return type for PVOP_CALL()
  x86/paravirt: Fix native_patch()
  locking/ww_mutex: Use relaxed atomics
  locking/rtmutex: Explain locking rules for rt_mutex_proxy_unlock()/init_proxy_locked()
  locking/rtmutex: Get rid of RT_MUTEX_OWNER_MASKALL
  x86/paravirt: Optimize native pv_lock_ops.vcpu_is_preempted()
  locking/mutex: Break out of expensive busy-loop on {mutex,rwsem}_spin_on_owner() when owner vCPU is preempted
  locking/osq: Break out of spin-wait busy waiting loop for a preempted vCPU in osq_lock()
  Documentation/virtual/kvm: Support the vCPU preemption check
  x86/xen: Support the vCPU preemption check
  x86/kvm: Support the vCPU preemption check
  x86/kvm: Support the vCPU preemption check
  kvm: Introduce kvm_write_guest_offset_cached()
  locking/core, x86/paravirt: Implement vcpu_is_preempted(cpu) for KVM and Xen guests
  locking/spinlocks, s390: Implement vcpu_is_preempted(cpu)
  locking/core, powerpc: Implement vcpu_is_preempted(cpu)
  sched/core: Introduce the vcpu_is_preempted(cpu) interface
  sched/wake_q: Rename WAKE_Q to DEFINE_WAKE_Q
  locking/core: Provide common cpu_relax_yield() definition
  locking/mutex: Don't mark mutex_trylock_recursive() as deprecated, temporarily
  ...

4 files changed, 23 insertions, 40 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 8832f8ec1583..383d13416442 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -723,7 +723,7 @@ bool __i915_spin_request(const struct drm_i915_gem_request *req,
 		if (busywait_stop(timeout_us, cpu))
 			break;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	} while (!need_resched());
 
 	return false;
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 1c237d02f30b..c450076d2f9b 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -35,19 +35,6 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 
-static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
-{
-	if (!mutex_is_locked(mutex))
-		return false;
-
-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
-	return mutex->owner == task;
-#else
-	/* Since UP may be pre-empted, we cannot assume that we own the lock */
-	return false;
-#endif
-}
-
 static bool any_vma_pinned(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
@@ -240,15 +227,20 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 
 static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
 {
-	if (!mutex_trylock(&dev->struct_mutex)) {
-		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return false;
+	switch (mutex_trylock_recursive(&dev->struct_mutex)) {
+	case MUTEX_TRYLOCK_FAILED:
+		return false;
 
-		*unlock = false;
-	} else
+	case MUTEX_TRYLOCK_SUCCESS:
 		*unlock = true;
+		return true;
 
-	return true;
+	case MUTEX_TRYLOCK_RECURSIVE:
+		*unlock = false;
+		return true;
+	}
+
+	BUG();
 }
 
 static unsigned long
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
index 192b2d3a79cb..ab1dd020eb04 100644
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -18,33 +18,24 @@
 #include "msm_drv.h"
 #include "msm_gem.h"
 
-static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
+static bool msm_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
 {
-	if (!mutex_is_locked(mutex))
+	switch (mutex_trylock_recursive(&dev->struct_mutex)) {
+	case MUTEX_TRYLOCK_FAILED:
 		return false;
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
-	return mutex->owner == task;
-#else
-	/* Since UP may be pre-empted, we cannot assume that we own the lock */
-	return false;
-#endif
-}
+	case MUTEX_TRYLOCK_SUCCESS:
+		*unlock = true;
+		return true;
 
-static bool msm_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
-{
-	if (!mutex_trylock(&dev->struct_mutex)) {
-		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return false;
+	case MUTEX_TRYLOCK_RECURSIVE:
 		*unlock = false;
-	} else {
-		*unlock = true;
+		return true;
 	}
 
-	return true;
+	BUG();
 }
 
-
 static unsigned long
 msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 {
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 5dc128a8da83..5dc34653274a 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -342,7 +342,7 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 		endtime = busy_clock() + vq->busyloop_timeout;
 		while (vhost_can_busy_poll(vq->dev, endtime) &&
 		       vhost_vq_avail_empty(vq->dev, vq))
-			cpu_relax_lowlatency();
+			cpu_relax();
 		preempt_enable();
 		r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
 				      out_num, in_num, NULL, NULL);
@@ -533,7 +533,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 		while (vhost_can_busy_poll(&net->dev, endtime) &&
 		       !sk_has_rx_data(sk) &&
 		       vhost_vq_avail_empty(&net->dev, vq))
-			cpu_relax_lowlatency();
+			cpu_relax();
 
 		preempt_enable();