Commit f06b0a9e authored by David Mosberger's avatar David Mosberger

ia64: Two more minor cleanups for 2.5.72.

parent ebb2aef5
......@@ -4,7 +4,7 @@
/*
* IA-64 specific AGP definitions.
*
* Copyright (C) 2002 Hewlett-Packard Co
* Copyright (C) 2002-2003 Hewlett-Packard Co
* David Mosberger-Tang <davidm@hpl.hp.com>
*/
......@@ -18,7 +18,4 @@
#define flush_agp_mappings() /* nothing */
#define flush_agp_cache() mb()
/* Page-protection value to be used for AGP memory mapped into kernel space. */
#define PAGE_AGP PAGE_KERNEL
#endif /* _ASM_IA64_AGP_H */
......@@ -15,8 +15,15 @@
typedef unsigned long cycles_t;
/*
* Something low processor frequency like 100Mhz but
* yet multiple of HZ to avoid truncation in some formulas.
* For performance reasons, we don't want to define CLOCK_TICK_TRATE as
* local_cpu_data->itc_rate. Fortunately, we don't have to, either: according to George
* Anzinger, 1/CLOCK_TICK_RATE is taken as the resolution of the timer clock. The time
* calculation assumes that you will use enough of these so that your tick size <= 1/HZ.
* If the calculation shows that your CLOCK_TICK_RATE can not supply exactly 1/HZ ticks,
* the actual value is calculated and used to update the wall clock each jiffie. Setting
* the CLOCK_TICK_RATE to x*HZ insures that the calculation will find no errors. Hence we
* pick a multiple of HZ which gives us a (totally virtual) CLOCK_TICK_RATE of about
* 100MHz.
*/
#define CLOCK_TICK_RATE (HZ * 100000UL)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment