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:

   - big rtmutex and futex cleanup and robustification from Thomas
     Gleixner
   - mutex optimizations and refinements from Jason Low
   - arch_mutex_cpu_relax() removal and related cleanups
   - smaller lockdep tweaks"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  arch, locking: Ciao arch_mutex_cpu_relax()
  locking/lockdep: Only ask for /proc/lock_stat output when available
  locking/mutexes: Optimize mutex trylock slowpath
  locking/mutexes: Try to acquire mutex only if it is unlocked
  locking/mutexes: Delete the MUTEX_SHOW_NO_WAITER macro
  locking/mutexes: Correct documentation on mutex optimistic spinning
  rtmutex: Make the rtmutex tester depend on BROKEN
  futex: Simplify futex_lock_pi_atomic() and make it more robust
  futex: Split out the first waiter attachment from lookup_pi_state()
  futex: Split out the waiter check from lookup_pi_state()
  futex: Use futex_top_waiter() in lookup_pi_state()
  futex: Make unlock_pi more robust
  rtmutex: Avoid pointless requeueing in the deadlock detection chain walk
  rtmutex: Cleanup deadlock detector debug logic
  rtmutex: Confine deadlock logic to futex
  rtmutex: Simplify remove_waiter()
  rtmutex: Document pi chain walk
  rtmutex: Clarify the boost/deboost part
  rtmutex: No need to keep task ref for lock owner check
  rtmutex: Simplify and document try_to_take_rtmutex()
  ...

arch/alpha/include/asm/processor.h

@@ -57,6 +57,7 @@ unsigned long get_wchan(struct task_struct *p);
   ((tsk) == current ? rdusp() : task_thread_info(tsk)->pcb.usp)
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 #define ARCH_HAS_PREFETCH
 #define ARCH_HAS_PREFETCHW

arch/arc/include/asm/processor.h

@@ -62,6 +62,8 @@ unsigned long thread_saved_pc(struct task_struct *t);
 #define cpu_relax()	do { } while (0)
 #endif
 
+#define cpu_relax_lowlatency() cpu_relax()
+
 #define copy_segments(tsk, mm)      do { } while (0)
 #define release_segments(mm)        do { } while (0)
 

arch/arm/include/asm/processor.h

@@ -82,6 +82,8 @@ unsigned long get_wchan(struct task_struct *p);
 #define cpu_relax()			barrier()
 #endif
 
+#define cpu_relax_lowlatency()                cpu_relax()
+
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 

arch/arm64/include/asm/processor.h

@@ -129,6 +129,7 @@ extern void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
 #define cpu_relax()			barrier()
+#define cpu_relax_lowlatency()                cpu_relax()
 
 /* Thread switching */
 extern struct task_struct *cpu_switch_to(struct task_struct *prev,

arch/avr32/include/asm/processor.h

@@ -92,6 +92,7 @@ extern struct avr32_cpuinfo boot_cpu_data;
 #define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))
 
 #define cpu_relax()		barrier()
+#define cpu_relax_lowlatency()        cpu_relax()
 #define cpu_sync_pipeline()	asm volatile("sub pc, -2" : : : "memory")
 
 struct cpu_context {

arch/blackfin/include/asm/processor.h

@@ -99,7 +99,7 @@ unsigned long get_wchan(struct task_struct *p);
 #define	KSTK_ESP(tsk)	((tsk) == current ? rdusp() : (tsk)->thread.usp)
 
 #define cpu_relax()    	smp_mb()
-
+#define cpu_relax_lowlatency() cpu_relax()
 
 /* Get the Silicon Revision of the chip */
 static inline uint32_t __pure bfin_revid(void)

arch/c6x/include/asm/processor.h

@@ -121,6 +121,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(task)	(task_pt_regs(task)->sp)
 
 #define cpu_relax()		do { } while (0)
+#define cpu_relax_lowlatency()        cpu_relax()
 
 extern const struct seq_operations cpuinfo_op;
 

arch/cris/include/asm/processor.h

@@ -63,6 +63,7 @@ static inline void release_thread(struct task_struct *dead_task)
 #define init_stack      (init_thread_union.stack)
 
 #define cpu_relax()     barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 void default_idle(void);
 

arch/hexagon/include/asm/processor.h

@@ -56,6 +56,7 @@ struct thread_struct {
 }
 
 #define cpu_relax() __vmyield()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * Decides where the kernel will search for a free chunk of vm space during

arch/ia64/include/asm/processor.h

@@ -548,6 +548,7 @@ ia64_eoi (void)
 }
 
 #define cpu_relax()	ia64_hint(ia64_hint_pause)
+#define cpu_relax_lowlatency() cpu_relax()
 
 static inline int
 ia64_get_irr(unsigned int vector)

arch/m32r/include/asm/processor.h

@@ -133,5 +133,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)  ((tsk)->thread.sp)
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 #endif /* _ASM_M32R_PROCESSOR_H */

arch/m68k/include/asm/processor.h

@@ -176,5 +176,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define task_pt_regs(tsk)	((struct pt_regs *) ((tsk)->thread.esp0))
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 #endif

arch/metag/include/asm/processor.h

@@ -155,6 +155,7 @@ unsigned long get_wchan(struct task_struct *p);
 #define user_stack_pointer(regs)        ((regs)->ctx.AX[0].U0)
 
 #define cpu_relax()     barrier()
+#define cpu_relax_lowlatency()  cpu_relax()
 
 extern void setup_priv(void);
 

arch/microblaze/include/asm/processor.h

@@ -22,6 +22,7 @@
 extern const struct seq_operations cpuinfo_op;
 
 # define cpu_relax()		barrier()
+# define cpu_relax_lowlatency()	cpu_relax()
 
 #define task_pt_regs(tsk) \
 		(((struct pt_regs *)(THREAD_SIZE + task_stack_page(tsk))) - 1)

arch/mips/include/asm/processor.h

@@ -367,6 +367,7 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * Return_address is a replacement for __builtin_return_address(count)

arch/mn10300/include/asm/processor.h

@@ -68,7 +68,9 @@ extern struct mn10300_cpuinfo cpu_data[];
 extern void identify_cpu(struct mn10300_cpuinfo *);
 extern void print_cpu_info(struct mn10300_cpuinfo *);
 extern void dodgy_tsc(void);
+
 #define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * User space process size: 1.75GB (default).

arch/openrisc/include/asm/processor.h

@@ -101,6 +101,7 @@ extern unsigned long thread_saved_pc(struct task_struct *t);
 #define init_stack      (init_thread_union.stack)
 
 #define cpu_relax()     barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_OPENRISC_PROCESSOR_H */

arch/parisc/include/asm/processor.h

@@ -338,6 +338,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)	((tsk)->thread.regs.gr[30])
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /* Used as a macro to identify the combined VIPT/PIPT cached
  * CPUs which require a guarantee of coherency (no inequivalent

arch/powerpc/include/asm/processor.h

@@ -400,6 +400,8 @@ static inline unsigned long __pack_fe01(unsigned int fpmode)
 #define cpu_relax()	barrier()
 #endif
 
+#define cpu_relax_lowlatency() cpu_relax()
+
 /* Check that a certain kernel stack pointer is valid in task_struct p */
 int validate_sp(unsigned long sp, struct task_struct *p,
                        unsigned long nbytes);

arch/s390/include/asm/processor.h

@@ -217,7 +217,7 @@ static inline void cpu_relax(void)
 	barrier();
 }
 
-#define arch_mutex_cpu_relax()  barrier()
+#define cpu_relax_lowlatency()  barrier()
 
 static inline void psw_set_key(unsigned int key)
 {

arch/score/include/asm/processor.h

@@ -24,6 +24,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define current_text_addr() ({ __label__ _l; _l: &&_l; })
 
 #define cpu_relax()		barrier()
+#define cpu_relax_lowlatency()        cpu_relax()
 #define release_thread(thread)	do {} while (0)
 
 /*

arch/sh/include/asm/processor.h

@@ -97,6 +97,7 @@ extern struct sh_cpuinfo cpu_data[];
 
 #define cpu_sleep()	__asm__ __volatile__ ("sleep" : : : "memory")
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 void default_idle(void);
 void stop_this_cpu(void *);

arch/sparc/include/asm/processor_32.h

@@ -119,6 +119,8 @@ extern struct task_struct *last_task_used_math;
 int do_mathemu(struct pt_regs *regs, struct task_struct *fpt);
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
+
 extern void (*sparc_idle)(void);
 
 #endif

arch/sparc/include/asm/processor_64.h

@@ -216,6 +216,7 @@ unsigned long get_wchan(struct task_struct *task);
 				     "nop\n\t"				\
 				     ".previous"			\
 				     ::: "memory")
+#define cpu_relax_lowlatency() cpu_relax()
 
 /* Prefetch support.  This is tuned for UltraSPARC-III and later.
  * UltraSPARC-I will treat these as nops, and UltraSPARC-II has

arch/tile/include/asm/processor.h

@@ -266,6 +266,8 @@ static inline void cpu_relax(void)
 	barrier();
 }
 
+#define cpu_relax_lowlatency() cpu_relax()
+
 /* Info on this processor (see fs/proc/cpuinfo.c) */
 struct seq_operations;
 extern const struct seq_operations cpuinfo_op;

arch/unicore32/include/asm/processor.h

@@ -71,6 +71,7 @@ extern void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
 #define cpu_relax()			barrier()
+#define cpu_relax_lowlatency()                cpu_relax()
 
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)

arch/x86/include/asm/barrier.h

@@ -99,7 +99,7 @@
 #if defined(CONFIG_X86_PPRO_FENCE)
 
 /*
- * For either of these options x86 doesn't have a strong TSO memory
+ * For this option x86 doesn't have a strong TSO memory
  * model and we should fall back to full barriers.
  */
 

arch/x86/include/asm/processor.h

@@ -696,6 +696,8 @@ static inline void cpu_relax(void)
 	rep_nop();
 }
 
+#define cpu_relax_lowlatency() cpu_relax()
+
 /* Stop speculative execution and prefetching of modified code. */
 static inline void sync_core(void)
 {

arch/x86/include/asm/qrwlock.h

@@ -3,7 +3,7 @@
 
 #include <asm-generic/qrwlock_types.h>
 
-#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+#ifndef CONFIG_X86_PPRO_FENCE
 #define queue_write_unlock queue_write_unlock
 static inline void queue_write_unlock(struct qrwlock *lock)
 {

arch/x86/um/asm/processor.h

@@ -25,7 +25,8 @@ static inline void rep_nop(void)
 	__asm__ __volatile__("rep;nop": : :"memory");
 }
 
-#define cpu_relax()	rep_nop()
+#define cpu_relax()		rep_nop()
+#define cpu_relax_lowlatency()	cpu_relax()
 
 #include <asm/processor-generic.h>
 

arch/xtensa/include/asm/processor.h

@@ -182,6 +182,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)		(task_pt_regs(tsk)->areg[1])
 
 #define cpu_relax()  barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /* Special register access. */
 

include/linux/mutex.h

@@ -176,8 +176,4 @@ extern void mutex_unlock(struct mutex *lock);
 
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
-#ifndef arch_mutex_cpu_relax
-# define arch_mutex_cpu_relax() cpu_relax()
-#endif
-
 #endif /* __LINUX_MUTEX_H */

include/linux/rtmutex.h

@@ -90,11 +90,9 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name);
 extern void rt_mutex_destroy(struct rt_mutex *lock);
 
 extern void rt_mutex_lock(struct rt_mutex *lock);
-extern int rt_mutex_lock_interruptible(struct rt_mutex *lock,
-						int detect_deadlock);
+extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
 extern int rt_mutex_timed_lock(struct rt_mutex *lock,
-					struct hrtimer_sleeper *timeout,
-					int detect_deadlock);
+			       struct hrtimer_sleeper *timeout);
 
 extern int rt_mutex_trylock(struct rt_mutex *lock);
 

include/linux/seqlock.h

@@ -164,8 +164,6 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
 static inline unsigned raw_seqcount_begin(const seqcount_t *s)
 {
 	unsigned ret = ACCESS_ONCE(s->sequence);
-
-	seqcount_lockdep_reader_access(s);
 	smp_rmb();
 	return ret & ~1;
 }

kernel/locking/lockdep.c

@@ -384,7 +384,9 @@ static void print_lockdep_off(const char *bug_msg)
 {
 	printk(KERN_DEBUG "%s\n", bug_msg);
 	printk(KERN_DEBUG "turning off the locking correctness validator.\n");
+#ifdef CONFIG_LOCK_STAT
 	printk(KERN_DEBUG "Please attach the output of /proc/lock_stat to the bug report\n");
+#endif
 }
 
 static int save_trace(struct stack_trace *trace)

kernel/locking/mcs_spinlock.c

-
 #include <linux/percpu.h>
-#include <linux/mutex.h>
 #include <linux/sched.h>
 #include "mcs_spinlock.h"
 
@@ -79,7 +77,7 @@ osq_wait_next(struct optimistic_spin_queue *lock,
 				break;
 		}
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 
 	return next;
@@ -120,7 +118,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 		if (need_resched())
 			goto unqueue;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	return true;
 
@@ -146,7 +144,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 		if (smp_load_acquire(&node->locked))
 			return true;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 
 		/*
 		 * Or we race against a concurrent unqueue()'s step-B, in which

kernel/locking/mcs_spinlock.h

@@ -27,7 +27,7 @@ struct mcs_spinlock {
 #define arch_mcs_spin_lock_contended(l)					\
 do {									\
 	while (!(smp_load_acquire(l)))					\
-		arch_mutex_cpu_relax();					\
+		cpu_relax_lowlatency();					\
 } while (0)
 #endif
 
@@ -104,7 +104,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 			return;
 		/* Wait until the next pointer is set */
 		while (!(next = ACCESS_ONCE(node->next)))
-			arch_mutex_cpu_relax();
+			cpu_relax_lowlatency();
 	}
 
 	/* Pass lock to next waiter. */

kernel/locking/mutex.c

@@ -46,12 +46,6 @@
 # include <asm/mutex.h>
 #endif
 
-/*
- * A negative mutex count indicates that waiters are sleeping waiting for the
- * mutex.
- */
-#define	MUTEX_SHOW_NO_WAITER(mutex)	(atomic_read(&(mutex)->count) >= 0)
-
 void
 __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 {
@@ -152,7 +146,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 		if (need_resched())
 			break;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	rcu_read_unlock();
 
@@ -388,12 +382,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	/*
 	 * Optimistic spinning.
 	 *
-	 * We try to spin for acquisition when we find that there are no
-	 * pending waiters and the lock owner is currently running on a
-	 * (different) CPU.
-	 *
-	 * The rationale is that if the lock owner is running, it is likely to
-	 * release the lock soon.
+	 * We try to spin for acquisition when we find that the lock owner
+	 * is currently running on a (different) CPU and while we don't
+	 * need to reschedule. The rationale is that if the lock owner is
+	 * running, it is likely to release the lock soon.
 	 *
 	 * Since this needs the lock owner, and this mutex implementation
 	 * doesn't track the owner atomically in the lock field, we need to
@@ -440,7 +432,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		if (owner && !mutex_spin_on_owner(lock, owner))
 			break;
 
-		if ((atomic_read(&lock->count) == 1) &&
+		/* Try to acquire the mutex if it is unlocked. */
+		if (!mutex_is_locked(lock) &&
 		    (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
 			lock_acquired(&lock->dep_map, ip);
 			if (use_ww_ctx) {
@@ -471,7 +464,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	osq_unlock(&lock->osq);
 slowpath:
@@ -485,8 +478,11 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);
 
-	/* once more, can we acquire the lock? */
-	if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, 0) == 1))
+	/*
+	 * Once more, try to acquire the lock. Only try-lock the mutex if
+	 * it is unlocked to reduce unnecessary xchg() operations.
+	 */
+	if (!mutex_is_locked(lock) && (atomic_xchg(&lock->count, 0) == 1))
 		goto skip_wait;
 
 	debug_mutex_lock_common(lock, &waiter);
@@ -506,9 +502,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * it's unlocked. Later on, if we sleep, this is the
 		 * operation that gives us the lock. We xchg it to -1, so
 		 * that when we release the lock, we properly wake up the
-		 * other waiters:
+		 * other waiters. We only attempt the xchg if the count is
+		 * non-negative in order to avoid unnecessary xchg operations:
 		 */
-		if (MUTEX_SHOW_NO_WAITER(lock) &&
+		if (atomic_read(&lock->count) >= 0 &&
 		    (atomic_xchg(&lock->count, -1) == 1))
 			break;
 
@@ -823,6 +820,10 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
 	unsigned long flags;
 	int prev;
 
+	/* No need to trylock if the mutex is locked. */
+	if (mutex_is_locked(lock))
+		return 0;
+
 	spin_lock_mutex(&lock->wait_lock, flags);
 
 	prev = atomic_xchg(&lock->count, -1);

kernel/locking/qrwlock.c

@@ -20,7 +20,6 @@
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
-#include <linux/mutex.h>
 #include <asm/qrwlock.h>
 
 /**
@@ -35,7 +34,7 @@ static __always_inline void
 rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts)
 {
 	while ((cnts & _QW_WMASK) == _QW_LOCKED) {
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 		cnts = smp_load_acquire((u32 *)&lock->cnts);
 	}
 }
@@ -75,7 +74,7 @@ void queue_read_lock_slowpath(struct qrwlock *lock)
 	 * to make sure that the write lock isn't taken.
 	 */
 	while (atomic_read(&lock->cnts) & _QW_WMASK)
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 
 	cnts = atomic_add_return(_QR_BIAS, &lock->cnts) - _QR_BIAS;
 	rspin_until_writer_unlock(lock, cnts);
@@ -114,7 +113,7 @@ void queue_write_lock_slowpath(struct qrwlock *lock)
 				    cnts | _QW_WAITING) == cnts))
 			break;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 
 	/* When no more readers, set the locked flag */
@@ -125,7 +124,7 @@ void queue_write_lock_slowpath(struct qrwlock *lock)
 				    _QW_LOCKED) == _QW_WAITING))
 			break;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 unlock:
 	arch_spin_unlock(&lock->lock);

kernel/locking/rtmutex-debug.c

@@ -66,12 +66,13 @@ void rt_mutex_debug_task_free(struct task_struct *task)
  * the deadlock. We print when we return. act_waiter can be NULL in
  * case of a remove waiter operation.
  */
-void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter,
+void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+			     struct rt_mutex_waiter *act_waiter,
 			     struct rt_mutex *lock)
 {
 	struct task_struct *task;
 
-	if (!debug_locks || detect || !act_waiter)
+	if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter)
 		return;
 
 	task = rt_mutex_owner(act_waiter->lock);

kernel/locking/rtmutex-debug.h

@@ -20,14 +20,15 @@ extern void debug_rt_mutex_unlock(struct rt_mutex *lock);
 extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock,
 				      struct task_struct *powner);
 extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock);
-extern void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *waiter,
+extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+				    struct rt_mutex_waiter *waiter,
 				    struct rt_mutex *lock);
 extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter);
 # define debug_rt_mutex_reset_waiter(w)			\
 	do { (w)->deadlock_lock = NULL; } while (0)
 
-static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
-						 int detect)
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
+						  enum rtmutex_chainwalk walk)
 {
 	return (waiter != NULL);
 }

kernel/locking/rtmutex.h

@@ -22,10 +22,15 @@
 #define debug_rt_mutex_init(m, n)			do { } while (0)
 #define debug_rt_mutex_deadlock(d, a ,l)		do { } while (0)
 #define debug_rt_mutex_print_deadlock(w)		do { } while (0)
-#define debug_rt_mutex_detect_deadlock(w,d)		(d)
 #define debug_rt_mutex_reset_waiter(w)			do { } while (0)
 
 static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
 {
 	WARN(1, "rtmutex deadlock detected\n");
 }
+
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w,
+						  enum rtmutex_chainwalk walk)
+{
+	return walk == RT_MUTEX_FULL_CHAINWALK;
+}

kernel/locking/rtmutex_common.h

@@ -101,6 +101,21 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 		((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
 }
 
+/*
+ * Constants for rt mutex functions which have a selectable deadlock
+ * detection.
+ *
+ * RT_MUTEX_MIN_CHAINWALK:	Stops the lock chain walk when there are
+ *				no further PI adjustments to be made.
+ *
+ * RT_MUTEX_FULL_CHAINWALK:	Invoke deadlock detection with a full
+ *				walk of the lock chain.
+ */
+enum rtmutex_chainwalk {
+	RT_MUTEX_MIN_CHAINWALK,
+	RT_MUTEX_FULL_CHAINWALK,
+};
+
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
@@ -111,12 +126,11 @@ extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
-				     struct task_struct *task,
-				     int detect_deadlock);
+				     struct task_struct *task);
 extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 				      struct hrtimer_sleeper *to,
-				      struct rt_mutex_waiter *waiter,
-				      int detect_deadlock);
+				      struct rt_mutex_waiter *waiter);
+extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"

kernel/locking/rwsem-xadd.c

@@ -329,7 +329,7 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
 		if (need_resched())
 			break;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	rcu_read_unlock();
 
@@ -381,7 +381,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	osq_unlock(&sem->osq);
 done:

lib/Kconfig.debug

@@ -835,7 +835,7 @@ config DEBUG_RT_MUTEXES
 
 config RT_MUTEX_TESTER
 	bool "Built-in scriptable tester for rt-mutexes"
-	depends on DEBUG_KERNEL && RT_MUTEXES
+	depends on DEBUG_KERNEL && RT_MUTEXES && BROKEN
 	help
 	  This option enables a rt-mutex tester.
 

lib/lockref.c

 #include <linux/export.h>
 #include <linux/lockref.h>
-#include <linux/mutex.h>
 
 #if USE_CMPXCHG_LOCKREF
 
@@ -29,7 +28,7 @@
 		if (likely(old.lock_count == prev.lock_count)) {		\
 			SUCCESS;						\
 		}								\
-		arch_mutex_cpu_relax();						\
+		cpu_relax_lowlatency();						\
 	}									\
 } while (0)