* Michael Ellerman [off-list ref] wrote (on 2017-07-20 23:18:26 +1000=
):

Santosh Sivaraj [off-list ref] writes:
=20

quoted

Current vDSO64 implementation does not have support for coarse
clocks (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), for which it fa=

lls

quoted

back to system call. Below is a benchmark of the difference in execution
time with and without vDSO support.

=20
Hi Santosh,
=20
Great patch! Always good to see asm replaced with C.
=20

quoted

diff --git a/arch/powerpc/kernel/vdso64/gettime.c b/arch/powerpc/kernel=

/vdso64/gettime.c

quoted

new file mode 100644
index 0000000..01f411f

--- /dev/null
+++ b/arch/powerpc/kernel/vdso64/gettime.c

@@ -0,0 +1,162 @@

...

quoted

+static notrace int gettime_syscall_fallback(clockid_t clk_id,
+					     struct timespec *tp)
+{
+	register clockid_t id asm("r3") =3D clk_id;
+	register struct timespec *t asm("r4") =3D tp;
+	register int nr asm("r0") =3D __NR_clock_gettime;
+	register int ret asm("r3");

=20
I guess this works. I've always been a bit nervous about register
variables TBH.

Yes, this works. It falls back to syscall in the case of CLOCK_BOOTTIME.

=20

quoted

+	asm volatile("sc"
+		     : "=3Dr" (ret)
+		     : "r"(nr), "r"(id), "r"(t)
+		     : "memory");

=20
Not sure we need the memory clobber?
=20
It can clobber more registers than that though.
=20
See: Documentation/powerpc/syscall64-abi.txt
=20

quoted

diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/k=

ernel/vdso64/gettimeofday.S

quoted

index 3820213..1258009 100644

--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S

@@ -51,85 +53,21 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)

...

quoted

+	stwu	r1,-112(r1)
+  .cfi_register lr,r6
+	std	r6,24(r1)
+	bl	V_LOCAL_FUNC(kernel_clock_gettime)
 	crclr	cr0*4+so

=20
Clearing CR0[SO] says that the syscall always succeeded.
=20
What happens if you call this with a completely bogus clock id?

In case of a bogus clock id, the default case sets 'ret' to -1, which force=
s it
to fallback to the syscall.

I think the solution is probably to do the syscall fallback in asm, and
everything else in C.

Ok. That's what Sergey also sugested. I will send a v2.

Thanks,
Santosh

=20
cheers

--=20