60dbd66331
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> |
||
|---|---|---|
| .. | ||
| asm-offsets.c | ||
| crisksyms.c | ||
| irq.c | ||
| Makefile | ||
| module.c | ||
| process.c | ||
| profile.c | ||
| ptrace.c | ||
| setup.c | ||
| sys_cris.c | ||
| time.c | ||
| traps.c | ||
| vmlinux.lds.S | ||