[PATCH] x86/vdso: implement clock_gettime(CLOCK_MONOTONIC_RAW, ...)

["Sverdlin, Alexander (Nokia - DE/Ulm)" <alexander.sverdlin@nokia.com>]

From: Alexander Sverdlin <alexander.sverdlin@nokia.com>

Add CLOCK_MONOTONIC_RAW to the existing clock_gettime() vDSO
implementation. This is based on the ideas of Jason Vas Dias and comments
of Thomas Gleixner.

---- Test code ----
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <time.h>
 #include <unistd.h>

 #define CLOCK_TYPE CLOCK_MONOTONIC_RAW
 #define DURATION_SEC 10

int main(int argc, char **argv)
{
	struct timespec t, end;
	unsigned long long cnt = 0;

	clock_gettime(CLOCK_TYPE, &end);
	end.tv_sec += DURATION_SEC;

	do {
		clock_gettime(CLOCK_TYPE, &t);
		++cnt;
	} while (t.tv_sec < end.tv_sec || t.tv_nsec < end.tv_nsec);

	dprintf(STDOUT_FILENO, "%llu", cnt);

	return EXIT_SUCCESS;
}
-------------------

The results from the above test program:

Clock			Before		After		Diff
-----			------		-----		----
CLOCK_MONOTONIC		355531720	338039373	-5%
CLOCK_MONOTONIC_RAW	44831738	336064912	+650%
CLOCK_REALTIME		347665133	338102907	-3%

Link: https://lore.kernel.org/patchwork/patch/933583/
Link: https://bugzilla.kernel.org/show_bug.cgi?id=198961
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jason Vas Dias <jason.vas.dias@gmail.com>
Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
---
 arch/x86/entry/vdso/vclock_gettime.c    | 11 +++++++++--
 arch/x86/entry/vsyscall/vsyscall_gtod.c |  6 ++++++
 arch/x86/include/asm/vgtod.h            |  5 ++++-
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 98c7d12..7c9db26 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -144,6 +144,13 @@ notrace static int do_hres(clockid_t clk, struct timespec *ts)
 	struct vgtod_ts *base = &gtod->basetime[clk];
 	u64 cycles, last, sec, ns;
 	unsigned int seq;
+	u32 mult = gtod->mult;
+	u32 shift = gtod->shift;
+
+	if (clk == CLOCK_MONOTONIC_RAW) {
+		mult = gtod->raw_mult;
+		shift = gtod->raw_shift;
+	}
 
 	do {
 		seq = gtod_read_begin(gtod);
@@ -153,8 +160,8 @@ notrace static int do_hres(clockid_t clk, struct timespec *ts)
 		if (unlikely((s64)cycles < 0))
 			return vdso_fallback_gettime(clk, ts);
 		if (cycles > last)
-			ns += (cycles - last) * gtod->mult;
-		ns >>= gtod->shift;
+			ns += (cycles - last) * mult;
+		ns >>= shift;
 		sec = base->sec;
 	} while (unlikely(gtod_read_retry(gtod, seq)));
 
diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
index cfcdba0..a967f02 100644
--- a/arch/x86/entry/vsyscall/vsyscall_gtod.c
+++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c
@@ -46,11 +46,17 @@ void update_vsyscall(struct timekeeper *tk)
 	vdata->mask		= tk->tkr_mono.mask;
 	vdata->mult		= tk->tkr_mono.mult;
 	vdata->shift		= tk->tkr_mono.shift;
+	vdata->raw_mult		= tk->tkr_raw.mult;
+	vdata->raw_shift	= tk->tkr_raw.shift;
 
 	base = &vdata->basetime[CLOCK_REALTIME];
 	base->sec = tk->xtime_sec;
 	base->nsec = tk->tkr_mono.xtime_nsec;
 
+	base = &vdata->basetime[CLOCK_MONOTONIC_RAW];
+	base->sec = tk->raw_sec;
+	base->nsec = tk->tkr_raw.xtime_nsec;
+
 	base = &vdata->basetime[CLOCK_TAI];
 	base->sec = tk->xtime_sec + (s64)tk->tai_offset;
 	base->nsec = tk->tkr_mono.xtime_nsec;
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 913a133..f65c42b 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -28,7 +28,8 @@ struct vgtod_ts {
 };
 
 #define VGTOD_BASES	(CLOCK_TAI + 1)
-#define VGTOD_HRES	(BIT(CLOCK_REALTIME) | BIT(CLOCK_MONOTONIC) | BIT(CLOCK_TAI))
+#define VGTOD_HRES	(BIT(CLOCK_REALTIME) | BIT(CLOCK_MONOTONIC) | \
+			 BIT(CLOCK_MONOTONIC_RAW) | BIT(CLOCK_TAI))
 #define VGTOD_COARSE	(BIT(CLOCK_REALTIME_COARSE) | BIT(CLOCK_MONOTONIC_COARSE))
 
 /*
@@ -43,6 +44,8 @@ struct vsyscall_gtod_data {
 	u64		mask;
 	u32		mult;
 	u32		shift;
+	u32		raw_mult;
+	u32		raw_shift;
 
 	struct vgtod_ts	basetime[VGTOD_BASES];
 
-- 
2.4.6