powerpc/vdso: Switch VDSO to generic C implementation.

With the C VDSO, the performance is slightly lower, but it is worth
it as it will ease maintenance and evolution, and also brings clocks
that are not supported with the ASM VDSO.

On an 8xx at 132 MHz, vdsotest with the ASM VDSO:
  gettimeofday:    		  vdso:  828 nsec/call
  clock-getres-realtime-coarse:   vdso:  391 nsec/call
  clock-gettime-realtime-coarse:  vdso:  614 nsec/call
  clock-getres-realtime:    	  vdso:  460 nsec/call
  clock-gettime-realtime:    	  vdso:  876 nsec/call
  clock-getres-monotonic-coarse:  vdso:  399 nsec/call
  clock-gettime-monotonic-coarse: vdso:  691 nsec/call
  clock-getres-monotonic:    	  vdso:  460 nsec/call
  clock-gettime-monotonic:    	  vdso: 1026 nsec/call

On an 8xx at 132 MHz, vdsotest with the C VDSO:
  gettimeofday:    		  vdso:  955 nsec/call
  clock-getres-realtime-coarse:   vdso:  545 nsec/call
  clock-gettime-realtime-coarse:  vdso:  592 nsec/call
  clock-getres-realtime:          vdso:  545 nsec/call
  clock-gettime-realtime:    	  vdso:  941 nsec/call
  clock-getres-monotonic-coarse:  vdso:  545 nsec/call
  clock-gettime-monotonic-coarse: vdso:  591 nsec/call
  clock-getres-monotonic:         vdso:  545 nsec/call
  clock-gettime-monotonic:        vdso:  940 nsec/call

It is even better for gettime with monotonic clocks.

Unsupported clocks with ASM VDSO:
  clock-gettime-boottime:         vdso: 3851 nsec/call
  clock-gettime-tai:      	  vdso: 3852 nsec/call
  clock-gettime-monotonic-raw:    vdso: 3396 nsec/call

Same clocks with C VDSO:
  clock-gettime-tai:              vdso:  941 nsec/call
  clock-gettime-monotonic-raw:    vdso: 1001 nsec/call
  clock-gettime-monotonic-coarse: vdso:  591 nsec/call

On an 8321E at 333 MHz, vdsotest with the ASM VDSO:
  gettimeofday:     		  vdso: 220 nsec/call
  clock-getres-realtime-coarse:   vdso: 102 nsec/call
  clock-gettime-realtime-coarse:  vdso: 178 nsec/call
  clock-getres-realtime:          vdso: 129 nsec/call
  clock-gettime-realtime:    	  vdso: 235 nsec/call
  clock-getres-monotonic-coarse:  vdso: 105 nsec/call
  clock-gettime-monotonic-coarse: vdso: 208 nsec/call
  clock-getres-monotonic:         vdso: 129 nsec/call
  clock-gettime-monotonic:        vdso: 274 nsec/call

On an 8321E at 333 MHz, vdsotest with the C VDSO:
  gettimeofday:    		  vdso: 272 nsec/call
  clock-getres-realtime-coarse:   vdso: 160 nsec/call
  clock-gettime-realtime-coarse:  vdso: 184 nsec/call
  clock-getres-realtime:          vdso: 166 nsec/call
  clock-gettime-realtime:         vdso: 281 nsec/call
  clock-getres-monotonic-coarse:  vdso: 160 nsec/call
  clock-gettime-monotonic-coarse: vdso: 184 nsec/call
  clock-getres-monotonic:         vdso: 169 nsec/call
  clock-gettime-monotonic:        vdso: 275 nsec/call

On a Power9 Nimbus DD2.2 at 3.8GHz, with the ASM VDSO:
  clock-gettime-monotonic:    	  vdso:  35 nsec/call
  clock-getres-monotonic:    	  vdso:  16 nsec/call
  clock-gettime-monotonic-coarse: vdso:  18 nsec/call
  clock-getres-monotonic-coarse:  vdso: 522 nsec/call
  clock-gettime-monotonic-raw:    vdso: 598 nsec/call
  clock-getres-monotonic-raw:     vdso: 520 nsec/call
  clock-gettime-realtime:    	  vdso:  34 nsec/call
  clock-getres-realtime:    	  vdso:  16 nsec/call
  clock-gettime-realtime-coarse:  vdso:  18 nsec/call
  clock-getres-realtime-coarse:   vdso: 517 nsec/call
  getcpu:    			  vdso:   8 nsec/call
  gettimeofday:    		  vdso:  25 nsec/call

And with the C VDSO:
  clock-gettime-monotonic:    	  vdso:  37 nsec/call
  clock-getres-monotonic:    	  vdso:  20 nsec/call
  clock-gettime-monotonic-coarse: vdso:  21 nsec/call
  clock-getres-monotonic-coarse:  vdso:  19 nsec/call
  clock-gettime-monotonic-raw:    vdso:  38 nsec/call
  clock-getres-monotonic-raw:     vdso:  20 nsec/call
  clock-gettime-realtime:    	  vdso:  37 nsec/call
  clock-getres-realtime:    	  vdso:  20 nsec/call
  clock-gettime-realtime-coarse:  vdso:  20 nsec/call
  clock-getres-realtime-coarse:   vdso:  19 nsec/call
  getcpu:    			  vdso:   8 nsec/call
  gettimeofday:    		  vdso:  28 nsec/call

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201126131006.2431205-8-mpe@ellerman.id.au

1 files changed, 1 insertions, 90 deletions

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 74efe46f5532..92481463f9dc 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -82,6 +82,7 @@ static struct clocksource clocksource_timebase = {
 	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,
 	.mask         = CLOCKSOURCE_MASK(64),
 	.read         = timebase_read,
+	.vdso_clock_mode	= VDSO_CLOCKMODE_ARCHTIMER,
 };
 
 #define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
@@ -831,95 +832,6 @@ static notrace u64 timebase_read(struct clocksource *cs)
 	return (u64)get_tb();
 }
 
-
-void update_vsyscall(struct timekeeper *tk)
-{
-	struct timespec64 xt;
-	struct clocksource *clock = tk->tkr_mono.clock;
-	u32 mult = tk->tkr_mono.mult;
-	u32 shift = tk->tkr_mono.shift;
-	u64 cycle_last = tk->tkr_mono.cycle_last;
-	u64 new_tb_to_xs, new_stamp_xsec;
-	u64 frac_sec;
-
-	if (clock != &clocksource_timebase)
-		return;
-
-	xt.tv_sec = tk->xtime_sec;
-	xt.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
-
-	/* Make userspace gettimeofday spin until we're done. */
-	++vdso_data->tb_update_count;
-	smp_mb();
-
-	/*
-	 * This computes ((2^20 / 1e9) * mult) >> shift as a
-	 * 0.64 fixed-point fraction.
-	 * The computation in the else clause below won't overflow
-	 * (as long as the timebase frequency is >= 1.049 MHz)
-	 * but loses precision because we lose the low bits of the constant
-	 * in the shift.  Note that 19342813113834067 ~= 2^(20+64) / 1e9.
-	 * For a shift of 24 the error is about 0.5e-9, or about 0.5ns
-	 * over a second.  (Shift values are usually 22, 23 or 24.)
-	 * For high frequency clocks such as the 512MHz timebase clock
-	 * on POWER[6789], the mult value is small (e.g. 32768000)
-	 * and so we can shift the constant by 16 initially
-	 * (295147905179 ~= 2^(20+64-16) / 1e9) and then do the
-	 * remaining shifts after the multiplication, which gives a
-	 * more accurate result (e.g. with mult = 32768000, shift = 24,
-	 * the error is only about 1.2e-12, or 0.7ns over 10 minutes).
-	 */
-	if (mult <= 62500000 && clock->shift >= 16)
-		new_tb_to_xs = ((u64) mult * 295147905179ULL) >> (clock->shift - 16);
-	else
-		new_tb_to_xs = (u64) mult * (19342813113834067ULL >> clock->shift);
-
-	/*
-	 * Compute the fractional second in units of 2^-32 seconds.
-	 * The fractional second is tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift
-	 * in nanoseconds, so multiplying that by 2^32 / 1e9 gives
-	 * it in units of 2^-32 seconds.
-	 * We assume shift <= 32 because clocks_calc_mult_shift()
-	 * generates shift values in the range 0 - 32.
-	 */
-	frac_sec = tk->tkr_mono.xtime_nsec << (32 - shift);
-	do_div(frac_sec, NSEC_PER_SEC);
-
-	/*
-	 * Work out new stamp_xsec value for any legacy users of systemcfg.
-	 * stamp_xsec is in units of 2^-20 seconds.
-	 */
-	new_stamp_xsec = frac_sec >> 12;
-	new_stamp_xsec += tk->xtime_sec * XSEC_PER_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.
-	 */
-	vdso_data->tb_orig_stamp = cycle_last;
-	vdso_data->stamp_xsec = new_stamp_xsec;
-	vdso_data->tb_to_xs = new_tb_to_xs;
-	vdso_data->wtom_clock_sec = tk->wall_to_monotonic.tv_sec;
-	vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec;
-	vdso_data->stamp_xtime_sec = xt.tv_sec;
-	vdso_data->stamp_xtime_nsec = xt.tv_nsec;
-	vdso_data->stamp_sec_fraction = frac_sec;
-	vdso_data->hrtimer_res = hrtimer_resolution;
-	smp_wmb();
-	++(vdso_data->tb_update_count);
-}
-
-void update_vsyscall_tz(void)
-{
-	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
-	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
-}
-
 static void __init clocksource_init(void)
 {
 	struct clocksource *clock = &clocksource_timebase;
@@ -1079,7 +991,6 @@ void __init time_init(void)
 		sys_tz.tz_dsttime = 0;
 	}
 
-	vdso_data->tb_update_count = 0;
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
 
 	/* initialise and enable the large decrementer (if we have one) */