ARM: 7452/1: delay: allow timer-based delay implementation to be selected

This patch allows a timer-based delay implementation to be selected by
switching the delay routines over to use get_cycles, which is
implemented in terms of read_current_timer. This further allows us to
skip the loop calibration and have a consistent delay function in the
face of core frequency scaling.

To avoid the pain of dealing with memory-mapped counters, this
implementation uses the co-processor interface to the architected timers
when they are available. The previous loop-based implementation is
kept around for CPUs without the architected timers and we retain both
the maximum delay (2ms) and the corresponding conversion factors for
determining the number of loops required for a given interval. Since the
indirection of the timer routines will only work when called from C,
the sa1100 sleep routines are modified to branch to the loop-based delay
functions directly.

Tested-by: Shinya Kuribayashi <shinya.kuribayashi.px@renesas.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

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) */