[POWERPC] Fix gettimeofday inaccuracies
There are two problems in the powerpc gettimeofday code which can
cause incorrect results to be returned.
The first is that there is a race between do_gettimeofday and the
timer interrupt:
1. do_gettimeofday does get_tb()
2. decrementer exception on boot cpu which runs timer_recalc_offset,
which also samples the timebase and updates the do_gtod structure
with a greater timebase value.
3. do_gettimeofday calls __do_gettimeofday, which leads to the
negative result from tb_val - temp_varp->tb_orig_stamp.
The second is caused by taking the boot cpu offline, which can cause
the value of tb_last_jiffy to be increased past the currently
available timebase, causing the same underflow as above.
[paulus@samba.org - define and use data_barrier() instead of mb().]
Signed-off-by: Nathan Lynch <ntl@pobox.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 774c0a3..18e59e4 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -417,7 +417,7 @@
/*
* This version of gettimeofday has microsecond resolution.
*/
-static inline void __do_gettimeofday(struct timeval *tv, u64 tb_val)
+static inline void __do_gettimeofday(struct timeval *tv)
{
unsigned long sec, usec;
u64 tb_ticks, xsec;
@@ -431,7 +431,12 @@
* without a divide (and in fact, without a multiply)
*/
temp_varp = do_gtod.varp;
- tb_ticks = tb_val - temp_varp->tb_orig_stamp;
+
+ /* Sampling the time base must be done after loading
+ * do_gtod.varp in order to avoid racing with update_gtod.
+ */
+ data_barrier(temp_varp);
+ tb_ticks = get_tb() - temp_varp->tb_orig_stamp;
temp_tb_to_xs = temp_varp->tb_to_xs;
temp_stamp_xsec = temp_varp->stamp_xsec;
xsec = temp_stamp_xsec + mulhdu(tb_ticks, temp_tb_to_xs);
@@ -464,7 +469,7 @@
tv->tv_usec = usec;
return;
}
- __do_gettimeofday(tv, get_tb());
+ __do_gettimeofday(tv);
}
EXPORT_SYMBOL(do_gettimeofday);
@@ -650,6 +655,7 @@
int next_dec;
int cpu = smp_processor_id();
unsigned long ticks;
+ u64 tb_next_jiffy;
#ifdef CONFIG_PPC32
if (atomic_read(&ppc_n_lost_interrupts) != 0)
@@ -691,11 +697,14 @@
continue;
write_seqlock(&xtime_lock);
- tb_last_jiffy += tb_ticks_per_jiffy;
- tb_last_stamp = per_cpu(last_jiffy, cpu);
- do_timer(regs);
- timer_recalc_offset(tb_last_jiffy);
- timer_check_rtc();
+ tb_next_jiffy = tb_last_jiffy + tb_ticks_per_jiffy;
+ if (per_cpu(last_jiffy, cpu) >= tb_next_jiffy) {
+ tb_last_jiffy = tb_next_jiffy;
+ tb_last_stamp = per_cpu(last_jiffy, cpu);
+ do_timer(regs);
+ timer_recalc_offset(tb_last_jiffy);
+ timer_check_rtc();
+ }
write_sequnlock(&xtime_lock);
}
diff --git a/include/asm-powerpc/system.h b/include/asm-powerpc/system.h
index 7307aa7..4c9f522 100644
--- a/include/asm-powerpc/system.h
+++ b/include/asm-powerpc/system.h
@@ -53,6 +53,15 @@
#define smp_read_barrier_depends() do { } while(0)
#endif /* CONFIG_SMP */
+/*
+ * This is a barrier which prevents following instructions from being
+ * started until the value of the argument x is known. For example, if
+ * x is a variable loaded from memory, this prevents following
+ * instructions from being executed until the load has been performed.
+ */
+#define data_barrier(x) \
+ asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
+
struct task_struct;
struct pt_regs;