36 files changed, 51 insertions, 25 deletions

diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h
index 6cb7fe85c4b5..b4cf03690394 100644
--- a/arch/alpha/include/asm/processor.h
+++ b/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
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index d99f9b37cd15..82588f3ba77f 100644
--- a/arch/arc/include/asm/processor.h
+++ b/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)
 
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index c3d5fc124a05..8a1e8e995dae 100644
--- a/arch/arm/include/asm/processor.h
+++ b/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)
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 34de2a8f7d93..4610b0daf1bf 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/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,
diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h
index 972adcc1e8f4..941593c7d9f3 100644
--- a/arch/avr32/include/asm/processor.h
+++ b/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 {
diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h
index d0e72e9475a6..7acd46653df3 100644
--- a/arch/blackfin/include/asm/processor.h
+++ b/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)
diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h
index b9eb3da7f278..f2ef31be2f8b 100644
--- a/arch/c6x/include/asm/processor.h
+++ b/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;
 
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index 15b815df29c1..862126b58116 100644
--- a/arch/cris/include/asm/processor.h
+++ b/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);
 
diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h
index 45a825402f63..d8501137c8d0 100644
--- a/arch/hexagon/include/asm/processor.h
+++ b/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
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index efd1b927ccb7..c7367130ab14 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/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)
diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h
index 5767367550c6..9f8fd9bef70f 100644
--- a/arch/m32r/include/asm/processor.h
+++ b/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 */
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index b0768a657920..20dda1d4b860 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/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
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index a8a37477c66e..881071c07942 100644
--- a/arch/metag/include/asm/processor.h
+++ b/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);
 
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 9d31b057c355..497a988d79c2 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/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)
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index ad70cba8daff..d5098bc554f4 100644
--- a/arch/mips/include/asm/processor.h
+++ b/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)
diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h
index 8b80b19d0c8a..769d5ed8e992 100644
--- a/arch/mn10300/include/asm/processor.h
+++ b/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).
diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h
index cab746fa9e87..4d235e3d2534 100644
--- a/arch/openrisc/include/asm/processor.h
+++ b/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 */
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index d951c9681ab3..689a8ade3606 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/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
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 6d59072e13a7..dda7ac4c80bd 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/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);
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 6f02d452bbee..e568fc8a7250 100644
--- a/arch/s390/include/asm/processor.h
+++ b/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)
 {
diff --git a/arch/score/include/asm/processor.h b/arch/score/include/asm/processor.h
index d9a922d8711b..851f441991d2 100644
--- a/arch/score/include/asm/processor.h
+++ b/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)
 
 /*
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index 5448f9bbf4ab..1506897648aa 100644
--- a/arch/sh/include/asm/processor.h
+++ b/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 *);
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index a564817bbc2e..812fd08f3e62 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/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
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 7028fe1a7c04..6924bdefe148 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/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
diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h
index 42323636c459..dd4f9f17e30a 100644
--- a/arch/tile/include/asm/processor.h
+++ b/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;
diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h
index 4eaa42167667..8d21b7adf26b 100644
--- a/arch/unicore32/include/asm/processor.h
+++ b/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)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a4ea02351f4d..32cc237f8e20 100644
--- a/arch/x86/include/asm/processor.h
+++ b/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)
 {
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 04f82e020f2b..2a206d2b14ab 100644
--- a/arch/x86/um/asm/processor.h
+++ b/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>
 
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index abb59708a3b7..b61bdf0eea25 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/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. */
 
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 42aa9b9ecd5f..8d5535c58cc2 100644
--- a/include/linux/mutex.h
+++ b/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 */
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
index be9ee1559fca..9887a905a762 100644
--- a/kernel/locking/mcs_spinlock.c
+++ b/kernel/locking/mcs_spinlock.c
@@ -1,6 +1,4 @@
-
 #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 @@ unqueue:
                 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
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 74356dc0ce29..23e89c5930e9 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/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. */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index d3100521388c..ae712b25e492 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -146,7 +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();
 
@@ -464,7 +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:
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index fb5b8ac411a5..f956ede7f90d 100644
--- a/kernel/locking/qrwlock.c
+++ b/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);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index a2391ac135c8..d6203faf2eb1 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/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:
diff --git a/lib/lockref.c b/lib/lockref.c
index f07a40d33871..d2233de9a86e 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -1,6 +1,5 @@
 #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)