linux-kernel - [PATCH v2] x86/vdso: Rearrange do_hres() to improve code generation

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:   Fri,  5 Oct 2018 11:02:43 -0700
From:   Andy Lutomirski <luto@...nel.org>
To:     x86@...nel.org
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Andy Lutomirski <luto@...nel.org>
Subject: [PATCH v2] 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@...nel.org>
---

v2: Fix the obvious race -- this doesn't appear to affect performance
    Thanks, tglx, for noticing it.

arch/x86/entry/vdso/vclock_gettime.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 18c8a78d1ec9..007b3fe9d727 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/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;
-- 
2.17.1