x86/vdso: Rearrange do_hres() to improve code generation

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 <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/3c05644d010b72216aa286a6d20b5078d5fae5cd.1538762487.git.luto@kernel.org

arch/x86/entry/vdso/vclock_gettime.c

@@ -142,23 +142,27 @@ notrace static inline u64 vgetcyc(int mode)
 notrace static int do_hres(clockid_t clk, struct timespec *ts)
 {
 	struct vgtod_ts *base = &gtod->basetime[clk];
-	u64 cycles, last, ns;
+	u64 cycles, last, sec, ns;
 	unsigned int seq;
 
 	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)
 			ns += (cycles - last) * gtod->mult;
 		ns >>= gtod->shift;
+		sec = base->sec;
 	} while (unlikely(gtod_read_retry(gtod, seq)));
 
-	ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+	/*
+	 * Do this outside the loop: a race inside the loop could result
+	 * in __iter_div_u64_rem() being extremely slow.
+	 */
+	ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
 	ts->tv_nsec = ns;
 
 	return 0;