linux/arch/cris
Jesper Nilsson 60dbd66331 CRIS: GENERIC_TIME fixes
GENERIC_TIME was not functional for CRIS, giving random backward
time jumps.

For CRISv32 implement a new clocksource using the free running counter
and ditch the arch_gettimeoffset.

The random time jumps still existed, but turned out to be the write_seqlock
which was missing around our do_timer() call.

So switch over to GENERIC_TIME using the clocksource for CRISv32.

CRISv10 doesn't have the free running counter needed for the
clocksource trick, but we can still use GENERIC_TIME with
arch_gettimeoffset.

Unfortunately, there were problems in using the prescaler register
to timer0 for the gettimeoffset calculation, so it is now ignored,
making our resolution worse by the tune of 40usec (0.4%) worst case.

At the same time, clean up some formatting and use NSEC_PER_SEC
instead of 1000000000.

Signed-off-by: Jesper Nilsson <jesper.nilsson@axis.com>
2010-08-04 12:58:55 +02:00
..
arch-v10 CRIS: GENERIC_TIME fixes 2010-08-04 12:58:55 +02:00
arch-v32 CRIS: GENERIC_TIME fixes 2010-08-04 12:58:55 +02:00
boot CRIS: Merge machine dependent boot/compressed and boot/rescue 2009-04-21 11:44:57 +02:00
configs CRIS: proper defconfig setup 2008-10-13 21:34:55 +02:00
include Merge branch 'for-linus' of git://www.jni.nu/cris 2010-06-01 08:51:25 -07:00
kernel CRIS: GENERIC_TIME fixes 2010-08-04 12:58:55 +02:00
mm include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 2010-03-30 22:02:32 +09:00
Kconfig CRIS: GENERIC_TIME fixes 2010-08-04 12:58:55 +02:00
Kconfig.debug [PATCH] arch/cris/Kconfig.debug: use lib/Kconfig.debug 2005-09-05 00:06:19 -07:00
Makefile arm, cris, mips, sparc, powerpc, um, xtensa: fix build with bash 4.0 2009-09-20 12:28:22 +02:00