powerpc: Rework VDSO gettimeofday to prevent time going backwards

Currently it is possible for userspace to see the result of
gettimeofday() going backwards by 1 microsecond, assuming that
userspace is using the gettimeofday() in the VDSO.  The VDSO
gettimeofday() algorithm computes the time in "xsecs", which are
units of 2^-20 seconds, or approximately 0.954 microseconds,
using the algorithm

	now = (timebase - tb_orig_stamp) * tb_to_xs + stamp_xsec

and then converts the time in xsecs to seconds and microseconds.

The kernel updates the tb_orig_stamp and stamp_xsec values every
tick in update_vsyscall().  If the length of the tick is not an
integer number of xsecs, then some precision is lost in converting
the current time to xsecs.  For example, with CONFIG_HZ=1000, the
tick is 1ms long, which is 1048.576 xsecs.  That means that
stamp_xsec will advance by either 1048 or 1049 on each tick.
With the right conditions, it is possible for userspace to get
(timebase - tb_orig_stamp) * tb_to_xs being 1049 if the kernel is
slightly late in updating the vdso_datapage, and then for stamp_xsec
to advance by 1048 when the kernel does update it, and for userspace
to then see (timebase - tb_orig_stamp) * tb_to_xs being zero due to
integer truncation.  The result is that time appears to go backwards
by 1 microsecond.

To fix this we change the VDSO gettimeofday to use a new field in the
VDSO datapage which stores the nanoseconds part of the time as a
fractional number of seconds in a 0.32 binary fraction format.
(Or put another way, as a 32-bit number in units of 0.23283 ns.)
This is convenient because we can use the mulhwu instruction to
convert it to either microseconds or nanoseconds.

Since it turns out that computing the time of day using this new field
is simpler than either using stamp_xsec (as gettimeofday does) or
stamp_xtime.tv_nsec (as clock_gettime does), this converts both
gettimeofday and clock_gettime to use the new field.  The existing
__do_get_tspec function is converted to use the new field and take
a parameter in r7 that indicates the desired resolution, 1,000,000
for microseconds or 1,000,000,000 for nanoseconds.  The __do_get_xsec
function is then unused and is deleted.

The new algorithm is

	now = ((timebase - tb_orig_stamp) << 12) * tb_to_xs
		+ (stamp_xtime_seconds << 32) + stamp_sec_fraction

with 'now' in units of 2^-32 seconds.  That is then converted to
seconds and either microseconds or nanoseconds with

	seconds = now >> 32
	partseconds = ((now & 0xffffffff) * resolution) >> 32

The 32-bit VDSO code also makes a further simplification: it ignores
the bottom 32 bits of the tb_to_xs value, which is a 0.64 format binary
fraction.  Doing so gets rid of 4 multiply instructions.  Assuming
a timebase frequency of 1GHz or less and an update interval of no
more than 10ms, the upper 32 bits of tb_to_xs will be at least
4503599, so the error from ignoring the low 32 bits will be at most
2.2ns, which is more than an order of magnitude less than the time
taken to do gettimeofday or clock_gettime on our fastest processors,
so there is no possibility of seeing inconsistent values due to this.

This also moves update_gtod() down next to its only caller, and makes
update_vsyscall use the time passed in via the wall_time argument rather
than accessing xtime directly.  At present, wall_time always points to
xtime, but that could change in future.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 34 insertions, 27 deletions

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0441bbdadbd1..5adebaf47f13 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -423,30 +423,6 @@ void udelay(unsigned long usecs)
 }
 EXPORT_SYMBOL(udelay);
 
-static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
-			       u64 new_tb_to_xs)
-{
-	/*
-	 * tb_update_count is used to allow the userspace gettimeofday code
-	 * to assure itself that it sees a consistent view of the tb_to_xs and
-	 * stamp_xsec variables.  It reads the tb_update_count, then reads
-	 * tb_to_xs and stamp_xsec and then reads tb_update_count again.  If
-	 * the two values of tb_update_count match and are even then the
-	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
-	 * loops back and reads them again until this criteria is met.
-	 * We expect the caller to have done the first increment of
-	 * vdso_data->tb_update_count already.
-	 */
-	vdso_data->tb_orig_stamp = new_tb_stamp;
-	vdso_data->stamp_xsec = new_stamp_xsec;
-	vdso_data->tb_to_xs = new_tb_to_xs;
-	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
-	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
-	vdso_data->stamp_xtime = xtime;
-	smp_wmb();
-	++(vdso_data->tb_update_count);
-}
-
 #ifdef CONFIG_SMP
 unsigned long profile_pc(struct pt_regs *regs)
 {
@@ -873,10 +849,37 @@ static cycle_t timebase_read(struct clocksource *cs)
 	return (cycle_t)get_tb();
 }
 
+static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
+			       u64 new_tb_to_xs, struct timespec *now,
+			       u32 frac_sec)
+{
+	/*
+	 * tb_update_count is used to allow the userspace gettimeofday code
+	 * to assure itself that it sees a consistent view of the tb_to_xs and
+	 * stamp_xsec variables.  It reads the tb_update_count, then reads
+	 * tb_to_xs and stamp_xsec and then reads tb_update_count again.  If
+	 * the two values of tb_update_count match and are even then the
+	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
+	 * loops back and reads them again until this criteria is met.
+	 * We expect the caller to have done the first increment of
+	 * vdso_data->tb_update_count already.
+	 */
+	vdso_data->tb_orig_stamp = new_tb_stamp;
+	vdso_data->stamp_xsec = new_stamp_xsec;
+	vdso_data->tb_to_xs = new_tb_to_xs;
+	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
+	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
+	vdso_data->stamp_xtime = *now;
+	vdso_data->stamp_sec_fraction = frac_sec;
+	smp_wmb();
+	++(vdso_data->tb_update_count);
+}
+
 void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
 		     u32 mult)
 {
 	u64 t2x, stamp_xsec;
+	u32 frac_sec;
 
 	if (clock != &clocksource_timebase)
 		return;
@@ -888,10 +891,14 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
 	/* XXX this assumes clock->shift == 22 */
 	/* 4611686018 ~= 2^(20+64-22) / 1e9 */
 	t2x = (u64) mult * 4611686018ULL;
-	stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC;
+	stamp_xsec = (u64) wall_time->tv_nsec * XSEC_PER_SEC;
 	do_div(stamp_xsec, 1000000000);
-	stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC;
-	update_gtod(clock->cycle_last, stamp_xsec, t2x);
+	stamp_xsec += (u64) wall_time->tv_sec * XSEC_PER_SEC;
+
+	BUG_ON(wall_time->tv_nsec >= NSEC_PER_SEC);
+	/* this is tv_nsec / 1e9 as a 0.32 fraction */
+	frac_sec = ((u64) wall_time->tv_nsec * 18446744073ULL) >> 32;
+	update_gtod(clock->cycle_last, stamp_xsec, t2x, wall_time, frac_sec);
 }
 
 void update_vsyscall_tz(void)