vgetcyc() is full of barriers, so fetching values out of the vvar
page before vgetcyc() for use after vgetcyc() results in poor code
generation. Put vgetcyc() first to avoid this problem.
Also, pull the tv_sec division into the loop and put all the ts
writes together. The old code wrote ts->tv_sec on each iteration
before the syscall fallback check and then added in the offset
afterwards, which forced the compiler to pointlessly copy base->sec
to ts->tv_sec on each iteration. The new version seems to generate
sensible code.
Saves several cycles. With this patch applied, the result is faster
than before the clock_gettime() rewrite.
Signed-off-by: Andy Lutomirski <l...@kernel.org>
---
arch/x86/entry/vdso/vclock_gettime.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/arch/x86/entry/vdso/vclock_gettime.c
b/arch/x86/entry/vdso/vclock_gettime.c
index 18c8a78d1ec9..419de7552c2f 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -147,10 +147,9 @@ notrace static int do_hres(clockid_t clk, struct timespec
*ts)
do {
seq = gtod_read_begin(gtod);
- ts->tv_sec = base->sec;
+ cycles = vgetcyc(gtod->vclock_mode);
ns = base->nsec;
last = gtod->cycle_last;
- cycles = vgetcyc(gtod->vclock_mode);
if (unlikely((s64)cycles < 0))
return vdso_fallback_gettime(clk, ts);
if (cycles > last)
@@ -158,7 +157,7 @@ notrace static int do_hres(clockid_t clk, struct timespec
*ts)
ns >>= gtod->shift;
} while (unlikely(gtod_read_retry(gtod, seq)));
- ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_sec = base->sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
ts->tv_nsec = ns;
return 0;
--
2.17.1
