timers, sched/clock: Match scope of read and write seqcounts

Currently the scope of the raw_write_seqcount_begin/end() in
sched_clock_register() far exceeds the scope of the read section
in sched_clock(). This gives the impression of safety during
cursory review but achieves little.

Note that this is likely to be a latent issue at present because
sched_clock_register() is typically called before we enable
interrupts, however the issue does risk bugs being needlessly
introduced as the code evolves.

This patch fixes the problem by increasing the scope of the read
locking performed by sched_clock() to cover all data modified by
sched_clock_register.

We also improve clarity by moving writes to struct clock_data
that do not impact sched_clock() outside of the critical
section.

Signed-off-by: Daniel Thompson <[email protected]>
[ Reworked it slightly to apply to tip/timers/core]
Signed-off-by: John Stultz <[email protected]>
Reviewed-by: Stephen Boyd <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Russell King <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Will Deacon <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

kernel/time/sched_clock.c

@@ -58,23 +58,21 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 
 unsigned long long notrace sched_clock(void)
 {
-	u64 epoch_ns;
-	u64 epoch_cyc;
-	u64 cyc;
+	u64 cyc, res;
 	unsigned long seq;
 
-	if (cd.suspended)
-		return cd.epoch_ns;
-
 	do {
 		seq = raw_read_seqcount_begin(&cd.seq);
-		epoch_cyc = cd.epoch_cyc;
-		epoch_ns = cd.epoch_ns;
+
+		res = cd.epoch_ns;
+		if (!cd.suspended) {
+			cyc = read_sched_clock();
+			cyc = (cyc - cd.epoch_cyc) & sched_clock_mask;
+			res += cyc_to_ns(cyc, cd.mult, cd.shift);
+		}
 	} while (read_seqcount_retry(&cd.seq, seq));
 
-	cyc = read_sched_clock();
-	cyc = (cyc - epoch_cyc) & sched_clock_mask;
-	return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift);
+	return res;
 }
 
 /*
@@ -111,7 +109,6 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
 {
 	u64 res, wrap, new_mask, new_epoch, cyc, ns;
 	u32 new_mult, new_shift;
-	ktime_t new_wrap_kt;
 	unsigned long r;
 	char r_unit;
 
@@ -124,10 +121,11 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
 	clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
 
 	new_mask = CLOCKSOURCE_MASK(bits);
+	cd.rate = rate;
 
 	/* calculate how many nanosecs until we risk wrapping */
 	wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL);
-	new_wrap_kt = ns_to_ktime(wrap);
+	cd.wrap_kt = ns_to_ktime(wrap);
 
 	/* update epoch for new counter and update epoch_ns from old counter*/
 	new_epoch = read();
@@ -138,8 +136,6 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
 	raw_write_seqcount_begin(&cd.seq);
 	read_sched_clock = read;
 	sched_clock_mask = new_mask;
-	cd.rate = rate;
-	cd.wrap_kt = new_wrap_kt;
 	cd.mult = new_mult;
 	cd.shift = new_shift;
 	cd.epoch_cyc = new_epoch;