[PATCH v4 2/4] vdso/math64: Add and use __iter_div64_u64_rem()

[Zhan Xusheng]

The vDSO basetimes for CLOCK_MONOTONIC and CLOCK_BOOTTIME are kept in the
scaled nanoseconds of tkr_mono, so normalising them means dividing by
NSEC_PER_SEC << shift, which does not fit the u32 divisor of
__iter_div_u64_rem().  update_vdso_time_data() therefore open-codes the
iterative division twice.

Subtracting is the right shape here rather than dividing, because the
quotient is never more than one: xtime_nsec is kept below one scaled
second by accumulate_nsecs_to_secs(), and the offset added to it is a
normalised timespec64 fraction, so the dividend stays below twice the
divisor.  That holds on every architecture, which matters more than what
any one of them charges for a division.

Add __iter_div64_u64_rem(), the u64-divisor counterpart of
__iter_div_u64_rem(), and use it for both.  The remainder goes straight
into the basetime as the coarse clocks already do, which also makes the
copy of the CLOCK_MONOTONIC values for CLOCK_BOOTTIME take both of them
from the same place.

The quotient is a u32 like the u32-divisor version returns.  It keeps
32-bit from carrying the counter in a register pair: vsyscall.o loses 16
bytes of text on x86-64 and the loop drops from 36 to 28 instructions on
32-bit gcc.

No functional change.

Suggested-by: David Laight <david.laight.linux@xxxxxxxxx>
Signed-off-by: Zhan Xusheng <zhanxusheng@xxxxxxxxxx>
---
 include/vdso/math64.h  | 21 +++++++++++++++++++++
 kernel/time/vsyscall.c | 16 +++++-----------
 2 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/include/vdso/math64.h b/include/vdso/math64.h
index 83ebac2e5c1b..0c91410e5f69 100644
--- a/include/vdso/math64.h
+++ b/include/vdso/math64.h
@@ -23,6 +23,27 @@ __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
 	return ret;
 }
 
+static __always_inline u32
+__iter_div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
+{
+	u32 ret = 0;
+
+	while (dividend >= divisor) {
+		/*
+		 * Prevent the compiler from optimising this loop into a
+		 * modulo operation.
+		 */
+		OPTIMIZER_HIDE_VAR(dividend);
+
+		dividend -= divisor;
+		ret++;
+	}
+
+	*remainder = dividend;
+
+	return ret;
+}
+
 #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
 
 #ifndef mul_u64_u32_add_u64_shr
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index aa59919b8f2c..f43dd3f4744b 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -41,14 +41,12 @@ static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct ti
 
 	nsec = tk->tkr_mono.xtime_nsec;
 	nsec += ((u64)tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift);
-	while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
-		nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift);
-		vdso_ts->sec++;
-	}
-	vdso_ts->nsec	= nsec;
+	vdso_ts->sec	+= __iter_div64_u64_rem(nsec, (u64)NSEC_PER_SEC << tk->tkr_mono.shift,
+						&vdso_ts->nsec);
 
 	/* Copy MONOTONIC time for BOOTTIME */
 	sec	= vdso_ts->sec;
+	nsec	= vdso_ts->nsec;
 	/* Add the boot offset */
 	sec	+= tk->monotonic_to_boot.tv_sec;
 	nsec	+= (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift;
@@ -56,12 +54,8 @@ static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct ti
 	/* CLOCK_BOOTTIME */
 	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME];
 	vdso_ts->sec	= sec;
-
-	while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
-		nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift);
-		vdso_ts->sec++;
-	}
-	vdso_ts->nsec	= nsec;
+	vdso_ts->sec	+= __iter_div64_u64_rem(nsec, (u64)NSEC_PER_SEC << tk->tkr_mono.shift,
+						&vdso_ts->nsec);
 
 	/* CLOCK_MONOTONIC_RAW */
 	vdso_ts		= &vc[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
-- 
2.43.0