Messages in this thread Patch in this message | | | Subject | [PATCH 05/43] MN10300: Prevent cnt32_to_63() from being preempted in sched_clock() | From | David Howells <> | Date | Tue, 26 Oct 2010 03:53:28 +0100 |
| |
Prevent cnt32_to_63() from being preempted in sched_clock() because it may read its internal counter, get preempted, get delayed for more than the half period of the 'TSC' and then write the internal counter, thus corrupting it.
Whilst some callers of sched_clock() have interrupts disabled or hold spinlocks, not all do, and so preemption must be held here.
Note that sched_clock() is called from lockdep, but that shouldn't be a problem because although preempt_disable() calls into lockdep, lockdep has a recursion counter to deal with this.
Signed-off-by: David Howells <dhowells@redhat.com> ---
arch/mn10300/kernel/time.c | 5 +++++ 1 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/arch/mn10300/kernel/time.c b/arch/mn10300/kernel/time.c index 8f7f6d2..0b5c856 100644 --- a/arch/mn10300/kernel/time.c +++ b/arch/mn10300/kernel/time.c @@ -54,6 +54,9 @@ unsigned long long sched_clock(void) unsigned long tsc, tmp; unsigned product[3]; /* 96-bit intermediate value */ + /* cnt32_to_63() is not safe with preemption */ + preempt_disable(); + /* read the TSC value */ tsc = 0 - get_cycles(); /* get_cycles() counts down */ @@ -64,6 +67,8 @@ unsigned long long sched_clock(void) */ tsc64.ll = cnt32_to_63(tsc) & 0x7fffffffffffffffULL; + preempt_enable(); + /* scale the 64-bit TSC value to a nanosecond value via a 96-bit * intermediate */
| |