From 8c071b0f19dfa230335d22ce56a8fab5bd20cedc Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Thu, 17 Oct 2013 12:38:17 +0200 Subject: s390/time: correct use of store clock fast The result of the store-clock-fast (STCKF) instruction is a bit fuzzy. It can happen that the value stored on one CPU is smaller than the value stored on another CPU, although the order of the stores is the other way around. This can cause deltas of get_tod_clock() values to become negative when they should not be. We need to be more careful with store-clock-fast, this patch partially reverts git commit e4b7b4238e666682555461fa52eecd74652f36bb "time: always use stckf instead of stck if available". The get_tod_clock() function now uses the store-clock-extended (STCKE) instruction. get_tod_clock_fast() can be used if the fuzziness of store-clock-fast is acceptable e.g. for wait loops local to a CPU. Signed-off-by: Martin Schwidefsky --- drivers/s390/cio/cio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/s390/cio/cio.c') diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index d7da67a31c77..88e35d85d205 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -878,9 +878,9 @@ static void css_reset(void) atomic_inc(&chpid_reset_count); } /* Wait for machine check for all channel paths. */ - timeout = get_tod_clock() + (RCHP_TIMEOUT << 12); + timeout = get_tod_clock_fast() + (RCHP_TIMEOUT << 12); while (atomic_read(&chpid_reset_count) != 0) { - if (get_tod_clock() > timeout) + if (get_tod_clock_fast() > timeout) break; cpu_relax(); } -- cgit v1.2.3