Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates from Russell King:
 "First ARM push of this merge window, post me coming back from holiday.
  This is what has been in linux-next for the last few weeks.  Not much
  to say which isn't described by the commit summaries."

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (32 commits)
  ARM: 7463/1: topology: Update cpu_power according to DT information
  ARM: 7462/1: topology: factorize the update of sibling masks
  ARM: 7461/1: topology: Add arch_scale_freq_power function
  ARM: 7456/1: ptrace: provide separate functions for tracing syscall {entry,exit}
  ARM: 7455/1: audit: move syscall auditing until after ptrace SIGTRAP handling
  ARM: 7454/1: entry: don't bother with syscall tracing on ret_from_fork path
  ARM: 7453/1: audit: only allow syscall auditing for pure EABI userspace
  ARM: 7452/1: delay: allow timer-based delay implementation to be selected
  ARM: 7451/1: arch timer: implement read_current_timer and get_cycles
  ARM: 7450/1: dcache: select DCACHE_WORD_ACCESS for little-endian ARMv6+ CPUs
  ARM: 7449/1: use generic strnlen_user and strncpy_from_user functions
  ARM: 7448/1: perf: remove arm_perf_pmu_ids global enumeration
  ARM: 7447/1: rwlocks: remove unused branch labels from trylock routines
  ARM: 7446/1: spinlock: use ticket algorithm for ARMv6+ locking implementation
  ARM: 7445/1: mm: update CONTEXTIDR register to contain PID of current process
  ARM: 7444/1: kernel: add arch-timer C3STOP feature
  ARM: 7460/1: remove asm/locks.h
  ARM: 7439/1: head.S: simplify initial page table mapping
  ARM: 7437/1: zImage: Allow DTB command line concatenation with ATAG_CMDLINE
  ARM: 7436/1: Do not map the vectors page as write-through on UP systems
  ...

1 files changed, 25 insertions, 7 deletions

diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index b2deda181549..dc6145120de3 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -6,9 +6,22 @@
 #ifndef __ASM_ARM_DELAY_H
 #define __ASM_ARM_DELAY_H
 
+#include <asm/memory.h>
 #include <asm/param.h>  /* HZ */
 
-extern void __delay(int loops);
+#define MAX_UDELAY_MS   2
+#define UDELAY_MULT     ((UL(2199023) * HZ) >> 11)
+#define UDELAY_SHIFT    30
+
+#ifndef __ASSEMBLY__
+
+extern struct arm_delay_ops {
+        void (*delay)(unsigned long);
+        void (*const_udelay)(unsigned long);
+        void (*udelay)(unsigned long);
+} arm_delay_ops;
+
+#define __delay(n)              arm_delay_ops.delay(n)
 
 /*
  * This function intentionally does not exist; if you see references to
@@ -23,22 +36,27 @@ extern void __bad_udelay(void);
  * division by multiplication: you don't have to worry about
  * loss of precision.
  *
- * Use only for very small delays ( < 1 msec).  Should probably use a
+ * Use only for very small delays ( < 2 msec).  Should probably use a
  * lookup table, really, as the multiplications take much too long with
  * short delays.  This is a "reasonable" implementation, though (and the
  * first constant multiplications gets optimized away if the delay is
  * a constant)
  */
-extern void __udelay(unsigned long usecs);
-extern void __const_udelay(unsigned long);
-
-#define MAX_UDELAY_MS 2
+#define __udelay(n)             arm_delay_ops.udelay(n)
+#define __const_udelay(n)       arm_delay_ops.const_udelay(n)
 
 #define udelay(n)                                                       \
         (__builtin_constant_p(n) ?                                      \
           ((n) > (MAX_UDELAY_MS * 1000) ? __bad_udelay() :              \
-                        __const_udelay((n) * ((2199023U*HZ)>>11))) :    \
+                        __const_udelay((n) * UDELAY_MULT)) :            \
           __udelay(n))
 
+/* Loop-based definitions for assembly code. */
+extern void __loop_delay(unsigned long loops);
+extern void __loop_udelay(unsigned long usecs);
+extern void __loop_const_udelay(unsigned long);
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* defined(_ARM_DELAY_H) */