diff mbox series

[2/2] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

Message ID 20170918092336.21912-2-santosh@fossix.org (mailing list archive)
State Superseded
Headers show
Series [1/2] powerpc/vdso64: Coarse timer support preparatory patch | expand

Commit Message

Santosh Sivaraj Sept. 18, 2017, 9:23 a.m. UTC 
Current vDSO64 implementation does not have support for coarse clocks
(CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), for which it falls back
to system call, increasing the response time, vDSO implementation reduces
the cycle time. Below is a benchmark of the difference in execution time
with and without vDSO support.

(Non-coarse clocks are also included just for completion)

Without vDSO support:
--------------------
clock-gettime-realtime: syscall: 172 nsec/call
clock-gettime-realtime:    libc: 26 nsec/call
clock-gettime-realtime:    vdso: 21 nsec/call
clock-gettime-monotonic: syscall: 170 nsec/call
clock-gettime-monotonic:    libc: 30 nsec/call
clock-gettime-monotonic:    vdso: 24 nsec/call
clock-gettime-realtime-coarse: syscall: 153 nsec/call
clock-gettime-realtime-coarse:    libc: 15 nsec/call
clock-gettime-realtime-coarse:    vdso: 9 nsec/call
clock-gettime-monotonic-coarse: syscall: 167 nsec/call
clock-gettime-monotonic-coarse:    libc: 15 nsec/call
clock-gettime-monotonic-coarse:    vdso: 11 nsec/call

CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
---
 arch/powerpc/kernel/asm-offsets.c         |  2 ++
 arch/powerpc/kernel/vdso64/gettimeofday.S | 56 +++++++++++++++++++++++++++++++
 2 files changed, 58 insertions(+)

Comments

Naveen N. Rao Oct. 6, 2017, 9:28 a.m. UTC | #1 
On 2017/09/18 09:23AM, Santosh Sivaraj wrote:
> Current vDSO64 implementation does not have support for coarse clocks
> (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), for which it falls back
> to system call, increasing the response time, vDSO implementation reduces
> the cycle time. Below is a benchmark of the difference in execution time
> with and without vDSO support.
> 
> (Non-coarse clocks are also included just for completion)
> 
> Without vDSO support:
> --------------------
> clock-gettime-realtime: syscall: 172 nsec/call
> clock-gettime-realtime:    libc: 26 nsec/call
> clock-gettime-realtime:    vdso: 21 nsec/call
> clock-gettime-monotonic: syscall: 170 nsec/call
> clock-gettime-monotonic:    libc: 30 nsec/call
> clock-gettime-monotonic:    vdso: 24 nsec/call
> clock-gettime-realtime-coarse: syscall: 153 nsec/call
> clock-gettime-realtime-coarse:    libc: 15 nsec/call
> clock-gettime-realtime-coarse:    vdso: 9 nsec/call
> clock-gettime-monotonic-coarse: syscall: 167 nsec/call
> clock-gettime-monotonic-coarse:    libc: 15 nsec/call
> clock-gettime-monotonic-coarse:    vdso: 11 nsec/call
> 
> CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
> ---
>  arch/powerpc/kernel/asm-offsets.c         |  2 ++
>  arch/powerpc/kernel/vdso64/gettimeofday.S | 56 +++++++++++++++++++++++++++++++
>  2 files changed, 58 insertions(+)
> 
> diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
> index 8cfb20e38cfe..b55c68c54dc1 100644
> --- a/arch/powerpc/kernel/asm-offsets.c
> +++ b/arch/powerpc/kernel/asm-offsets.c
> @@ -396,6 +396,8 @@ int main(void)
>  	/* Other bits used by the vdso */
>  	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
>  	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
> +	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
> +	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
>  	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
>  	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
> 
> diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
> index a0b4943811db..bae197a81add 100644
> --- a/arch/powerpc/kernel/vdso64/gettimeofday.S
> +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
> @@ -71,6 +71,11 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
>  	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
>  	beq	cr0,49f
> 
> +	cmpwi	cr0,r3,CLOCK_REALTIME_COARSE
> +	cmpwi	cr1,r3,CLOCK_MONOTONIC_COARSE
> +	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
> +	beq	cr0,65f

If you use cr5-7 here, you should be able to re-organize this to not 
have to update r4/r11/r12 if we're taking the syscall path. Not 
necessarily a huge win by itself, but can also help reuse some of the 
other code between the _COARSE and the regular variants.

- Naveen

> +
>  	b	99f		/* Fallback to syscall */
>    .cfi_register lr,r12
>  49:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
> @@ -112,6 +117,57 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
>  1:	bge	cr1,80f
>  	addi	r4,r4,-1
>  	add	r5,r5,r7
> +	b	80f
> +
> +	/*
> +	 * For coarse clocks we get data directly from the vdso data page, so
> +	 * we don't need to call __do_get_tspec, but we still need to do the
> +	 * counter trick.
> +	 */
> +65:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
> +70:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
> +	andi.	r0,r8,1			/* pending update ? loop */
> +	bne-	70b
> +	xor	r0,r8,r8		/* create dependency */
> +	add	r3,r3,r0
> +
> +	/*
> +	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
> +	 * too
> +	 */
> +	ld	r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
> +	ld	r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
> +	bne	cr1,78f
> +
> +	/* CLOCK_MONOTONIC_COARSE */
> +	lwa	r6,WTOM_CLOCK_SEC(r3)
> +	lwa	r9,WTOM_CLOCK_NSEC(r3)
> +
> +	/* check if counter has updated */
> +78:	or	r0,r6,r9
> +	xor	r0,r0,r0
> +	add	r3,r3,r0
> +	ld	r0,CFG_TB_UPDATE_COUNT(r3)
> +	cmpld	cr0,r0,r8		/* check if updated */
> +	bne-	70b
> +
> +	/* Counter has not updated, so continue calculating proper values for
> +	 * sec and nsec if monotonic coarse, or just return with the proper
> +	 * values for realtime.
> +	 */
> +	bne	cr1,80f
> +
> +	/* Add wall->monotonic offset and check for overflow or underflow */
> +	add	r4,r4,r6
> +	add	r5,r5,r9
> +	cmpd	cr0,r5,r7
> +	cmpdi	cr1,r5,0
> +	blt	79f
> +	subf	r5,r7,r5
> +	addi	r4,r4,1
> +79:	bge	cr1,80f
> +	addi	r4,r4,-1
> +	add	r5,r5,r7
> 
>  80:	std	r4,TSPC64_TV_SEC(r11)
>  	std	r5,TSPC64_TV_NSEC(r11)
> -- 
> 2.13.5
>
Naveen N. Rao Oct. 6, 2017, 11:25 a.m. UTC | #2 
On 2017/09/18 09:23AM, Santosh Sivaraj wrote:
> Current vDSO64 implementation does not have support for coarse clocks
> (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), for which it falls back
> to system call, increasing the response time, vDSO implementation reduces
> the cycle time. Below is a benchmark of the difference in execution time
> with and without vDSO support.
> 
> (Non-coarse clocks are also included just for completion)
> 
> Without vDSO support:
> --------------------
> clock-gettime-realtime: syscall: 172 nsec/call
> clock-gettime-realtime:    libc: 26 nsec/call
> clock-gettime-realtime:    vdso: 21 nsec/call
> clock-gettime-monotonic: syscall: 170 nsec/call
> clock-gettime-monotonic:    libc: 30 nsec/call
> clock-gettime-monotonic:    vdso: 24 nsec/call
> clock-gettime-realtime-coarse: syscall: 153 nsec/call
> clock-gettime-realtime-coarse:    libc: 15 nsec/call
> clock-gettime-realtime-coarse:    vdso: 9 nsec/call
> clock-gettime-monotonic-coarse: syscall: 167 nsec/call
> clock-gettime-monotonic-coarse:    libc: 15 nsec/call
> clock-gettime-monotonic-coarse:    vdso: 11 nsec/call
> 
> CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
> ---
>  arch/powerpc/kernel/asm-offsets.c         |  2 ++
>  arch/powerpc/kernel/vdso64/gettimeofday.S | 56 +++++++++++++++++++++++++++++++
>  2 files changed, 58 insertions(+)
> 
> diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
> index 8cfb20e38cfe..b55c68c54dc1 100644
> --- a/arch/powerpc/kernel/asm-offsets.c
> +++ b/arch/powerpc/kernel/asm-offsets.c
> @@ -396,6 +396,8 @@ int main(void)
>  	/* Other bits used by the vdso */
>  	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
>  	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
> +	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
> +	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
>  	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
>  	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
> 
> diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
> index a0b4943811db..bae197a81add 100644
> --- a/arch/powerpc/kernel/vdso64/gettimeofday.S
> +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
> @@ -71,6 +71,11 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
>  	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
>  	beq	cr0,49f
> 
> +	cmpwi	cr0,r3,CLOCK_REALTIME_COARSE
> +	cmpwi	cr1,r3,CLOCK_MONOTONIC_COARSE
> +	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
> +	beq	cr0,65f
> +
>  	b	99f		/* Fallback to syscall */
>    .cfi_register lr,r12
>  49:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
> @@ -112,6 +117,57 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
>  1:	bge	cr1,80f
>  	addi	r4,r4,-1
>  	add	r5,r5,r7
> +	b	80f
> +
> +	/*
> +	 * For coarse clocks we get data directly from the vdso data page, so
> +	 * we don't need to call __do_get_tspec, but we still need to do the
> +	 * counter trick.
> +	 */
> +65:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
> +70:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
> +	andi.	r0,r8,1			/* pending update ? loop */
> +	bne-	70b
> +	xor	r0,r8,r8		/* create dependency */
> +	add	r3,r3,r0
> +
> +	/*
> +	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
> +	 * too
> +	 */
> +	ld	r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
> +	ld	r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
> +	bne	cr1,78f
> +
> +	/* CLOCK_MONOTONIC_COARSE */
> +	lwa	r6,WTOM_CLOCK_SEC(r3)
> +	lwa	r9,WTOM_CLOCK_NSEC(r3)
> +
> +	/* check if counter has updated */
> +78:	or	r0,r6,r9
> +	xor	r0,r0,r0
> +	add	r3,r3,r0
> +	ld	r0,CFG_TB_UPDATE_COUNT(r3)
> +	cmpld	cr0,r0,r8		/* check if updated */
> +	bne-	70b

Don't you need a dependency on r4/r5 here for REALTIME_COARSE?
Something like:

	/* check if counter has updated */
	or	r0,r6,r9
78:	or	r0,r4,r5
	xor	r0,r0,r0

> +
> +	/* Counter has not updated, so continue calculating proper values for
> +	 * sec and nsec if monotonic coarse, or just return with the proper
> +	 * values for realtime.
> +	 */
> +	bne	cr1,80f
> +

I think the below hunk can surely be shared across the _COARSE and 
regular clocks, if not more.

- Naveen

> +	/* Add wall->monotonic offset and check for overflow or underflow */
> +	add	r4,r4,r6
> +	add	r5,r5,r9
> +	cmpd	cr0,r5,r7
> +	cmpdi	cr1,r5,0
> +	blt	79f
> +	subf	r5,r7,r5
> +	addi	r4,r4,1
> +79:	bge	cr1,80f
> +	addi	r4,r4,-1
> +	add	r5,r5,r7
> 
>  80:	std	r4,TSPC64_TV_SEC(r11)
>  	std	r5,TSPC64_TV_NSEC(r11)
> -- 
> 2.13.5
>
Santosh Sivaraj Oct. 9, 2017, 6:23 a.m. UTC | #3 
* Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> wrote (on 2017-10-06 11:25:28 +0000):

> On 2017/09/18 09:23AM, Santosh Sivaraj wrote:
> > Current vDSO64 implementation does not have support for coarse clocks
> > (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), for which it falls back
> > to system call, increasing the response time, vDSO implementation reduces
> > the cycle time. Below is a benchmark of the difference in execution time
> > with and without vDSO support.
> > 
> > (Non-coarse clocks are also included just for completion)
> > 
> > Without vDSO support:
> > --------------------
> > clock-gettime-realtime: syscall: 172 nsec/call
> > clock-gettime-realtime:    libc: 26 nsec/call
> > clock-gettime-realtime:    vdso: 21 nsec/call
> > clock-gettime-monotonic: syscall: 170 nsec/call
> > clock-gettime-monotonic:    libc: 30 nsec/call
> > clock-gettime-monotonic:    vdso: 24 nsec/call
> > clock-gettime-realtime-coarse: syscall: 153 nsec/call
> > clock-gettime-realtime-coarse:    libc: 15 nsec/call
> > clock-gettime-realtime-coarse:    vdso: 9 nsec/call
> > clock-gettime-monotonic-coarse: syscall: 167 nsec/call
> > clock-gettime-monotonic-coarse:    libc: 15 nsec/call
> > clock-gettime-monotonic-coarse:    vdso: 11 nsec/call
> > 
> > CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> > Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
> > ---
> >  arch/powerpc/kernel/asm-offsets.c         |  2 ++
> >  arch/powerpc/kernel/vdso64/gettimeofday.S | 56 +++++++++++++++++++++++++++++++
> >  2 files changed, 58 insertions(+)
> > 
> > diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
> > index 8cfb20e38cfe..b55c68c54dc1 100644
> > --- a/arch/powerpc/kernel/asm-offsets.c
> > +++ b/arch/powerpc/kernel/asm-offsets.c
> > @@ -396,6 +396,8 @@ int main(void)
> >  	/* Other bits used by the vdso */
> >  	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
> >  	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
> > +	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
> > +	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
> >  	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
> >  	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
> > 
> > diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
> > index a0b4943811db..bae197a81add 100644
> > --- a/arch/powerpc/kernel/vdso64/gettimeofday.S
> > +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
> > @@ -71,6 +71,11 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
> >  	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
> >  	beq	cr0,49f
> > 
> > +	cmpwi	cr0,r3,CLOCK_REALTIME_COARSE
> > +	cmpwi	cr1,r3,CLOCK_MONOTONIC_COARSE
> > +	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
> > +	beq	cr0,65f
> > +
> >  	b	99f		/* Fallback to syscall */
> >    .cfi_register lr,r12
> >  49:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
> > @@ -112,6 +117,57 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
> >  1:	bge	cr1,80f
> >  	addi	r4,r4,-1
> >  	add	r5,r5,r7
> > +	b	80f
> > +
> > +	/*
> > +	 * For coarse clocks we get data directly from the vdso data page, so
> > +	 * we don't need to call __do_get_tspec, but we still need to do the
> > +	 * counter trick.
> > +	 */
> > +65:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
> > +70:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
> > +	andi.	r0,r8,1			/* pending update ? loop */
> > +	bne-	70b
> > +	xor	r0,r8,r8		/* create dependency */
> > +	add	r3,r3,r0
> > +
> > +	/*
> > +	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
> > +	 * too
> > +	 */
> > +	ld	r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
> > +	ld	r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
> > +	bne	cr1,78f
> > +
> > +	/* CLOCK_MONOTONIC_COARSE */
> > +	lwa	r6,WTOM_CLOCK_SEC(r3)
> > +	lwa	r9,WTOM_CLOCK_NSEC(r3)
> > +
> > +	/* check if counter has updated */
> > +78:	or	r0,r6,r9
> > +	xor	r0,r0,r0
> > +	add	r3,r3,r0
> > +	ld	r0,CFG_TB_UPDATE_COUNT(r3)
> > +	cmpld	cr0,r0,r8		/* check if updated */
> > +	bne-	70b
> 
> Don't you need a dependency on r4/r5 here for REALTIME_COARSE?
> Something like:
> 
> 	/* check if counter has updated */
> 	or	r0,r6,r9
> 78:	or	r0,r4,r5
> 	xor	r0,r0,r0
>

Yes, we would need it. Will update in v2.
> > +
> > +	/* Counter has not updated, so continue calculating proper values for
> > +	 * sec and nsec if monotonic coarse, or just return with the proper
> > +	 * values for realtime.
> > +	 */
> > +	bne	cr1,80f
> > +
> 
> I think the below hunk can surely be shared across the _COARSE and 
> regular clocks, if not more.

Yes, except for the label its the same for both monotonic and
monotonic_coarse, will update in the next set.

Thanks,
Santosh
> 
> - Naveen
> 
> > +	/* Add wall->monotonic offset and check for overflow or underflow */
> > +	add	r4,r4,r6
> > +	add	r5,r5,r9
> > +	cmpd	cr0,r5,r7
> > +	cmpdi	cr1,r5,0
> > +	blt	79f
> > +	subf	r5,r7,r5
> > +	addi	r4,r4,1
> > +79:	bge	cr1,80f
> > +	addi	r4,r4,-1
> > +	add	r5,r5,r7
> > 
> >  80:	std	r4,TSPC64_TV_SEC(r11)
> >  	std	r5,TSPC64_TV_NSEC(r11)
> > -- 
> > 2.13.5
> > 
> 

--
Santosh Sivaraj Oct. 9, 2017, 6:27 a.m. UTC | #4 
* Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> wrote (on 2017-10-06 09:28:30 +0000):

> On 2017/09/18 09:23AM, Santosh Sivaraj wrote:
> > Current vDSO64 implementation does not have support for coarse clocks
> > (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), for which it falls back
> > to system call, increasing the response time, vDSO implementation reduces
> > the cycle time. Below is a benchmark of the difference in execution time
> > with and without vDSO support.
> > 
> > (Non-coarse clocks are also included just for completion)
> > 
> > Without vDSO support:
> > --------------------
> > clock-gettime-realtime: syscall: 172 nsec/call
> > clock-gettime-realtime:    libc: 26 nsec/call
> > clock-gettime-realtime:    vdso: 21 nsec/call
> > clock-gettime-monotonic: syscall: 170 nsec/call
> > clock-gettime-monotonic:    libc: 30 nsec/call
> > clock-gettime-monotonic:    vdso: 24 nsec/call
> > clock-gettime-realtime-coarse: syscall: 153 nsec/call
> > clock-gettime-realtime-coarse:    libc: 15 nsec/call
> > clock-gettime-realtime-coarse:    vdso: 9 nsec/call
> > clock-gettime-monotonic-coarse: syscall: 167 nsec/call
> > clock-gettime-monotonic-coarse:    libc: 15 nsec/call
> > clock-gettime-monotonic-coarse:    vdso: 11 nsec/call
> > 
> > CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> > Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
> > ---
> >  arch/powerpc/kernel/asm-offsets.c         |  2 ++
> >  arch/powerpc/kernel/vdso64/gettimeofday.S | 56 +++++++++++++++++++++++++++++++
> >  2 files changed, 58 insertions(+)
> > 
> > diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
> > index 8cfb20e38cfe..b55c68c54dc1 100644
> > --- a/arch/powerpc/kernel/asm-offsets.c
> > +++ b/arch/powerpc/kernel/asm-offsets.c
> > @@ -396,6 +396,8 @@ int main(void)
> >  	/* Other bits used by the vdso */
> >  	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
> >  	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
> > +	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
> > +	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
> >  	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
> >  	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
> > 
> > diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
> > index a0b4943811db..bae197a81add 100644
> > --- a/arch/powerpc/kernel/vdso64/gettimeofday.S
> > +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
> > @@ -71,6 +71,11 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
> >  	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
> >  	beq	cr0,49f
> > 
> > +	cmpwi	cr0,r3,CLOCK_REALTIME_COARSE
> > +	cmpwi	cr1,r3,CLOCK_MONOTONIC_COARSE
> > +	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
> > +	beq	cr0,65f
> 
> If you use cr5-7 here, you should be able to re-organize this to not 
> have to update r4/r11/r12 if we're taking the syscall path. Not 
> necessarily a huge win by itself, but can also help reuse some of the 
> other code between the _COARSE and the regular variants.
>

If we are going to use cr5-7, then the first patch is no longer required, we
don't have to do a re-org of the intial clock_id checks. I will send the
updated patch.

Thanks,
Santosh
> - Naveen
> 
> > +
> >  	b	99f		/* Fallback to syscall */
> >    .cfi_register lr,r12
> >  49:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
> > @@ -112,6 +117,57 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
> >  1:	bge	cr1,80f
> >  	addi	r4,r4,-1
> >  	add	r5,r5,r7
> > +	b	80f
> > +
> > +	/*
> > +	 * For coarse clocks we get data directly from the vdso data page, so
> > +	 * we don't need to call __do_get_tspec, but we still need to do the
> > +	 * counter trick.
> > +	 */
> > +65:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
> > +70:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
> > +	andi.	r0,r8,1			/* pending update ? loop */
> > +	bne-	70b
> > +	xor	r0,r8,r8		/* create dependency */
> > +	add	r3,r3,r0
> > +
> > +	/*
> > +	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
> > +	 * too
> > +	 */
> > +	ld	r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
> > +	ld	r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
> > +	bne	cr1,78f
> > +
> > +	/* CLOCK_MONOTONIC_COARSE */
> > +	lwa	r6,WTOM_CLOCK_SEC(r3)
> > +	lwa	r9,WTOM_CLOCK_NSEC(r3)
> > +
> > +	/* check if counter has updated */
> > +78:	or	r0,r6,r9
> > +	xor	r0,r0,r0
> > +	add	r3,r3,r0
> > +	ld	r0,CFG_TB_UPDATE_COUNT(r3)
> > +	cmpld	cr0,r0,r8		/* check if updated */
> > +	bne-	70b
> > +
> > +	/* Counter has not updated, so continue calculating proper values for
> > +	 * sec and nsec if monotonic coarse, or just return with the proper
> > +	 * values for realtime.
> > +	 */
> > +	bne	cr1,80f
> > +
> > +	/* Add wall->monotonic offset and check for overflow or underflow */
> > +	add	r4,r4,r6
> > +	add	r5,r5,r9
> > +	cmpd	cr0,r5,r7
> > +	cmpdi	cr1,r5,0
> > +	blt	79f
> > +	subf	r5,r7,r5
> > +	addi	r4,r4,1
> > +79:	bge	cr1,80f
> > +	addi	r4,r4,-1
> > +	add	r5,r5,r7
> > 
> >  80:	std	r4,TSPC64_TV_SEC(r11)
> >  	std	r5,TSPC64_TV_NSEC(r11)
> > -- 
> > 2.13.5
> > 
> 

--
diff mbox series

Patch

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8cfb20e38cfe..b55c68c54dc1 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -396,6 +396,8 @@  int main(void)
 	/* Other bits used by the vdso */
 	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
 	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
+	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
+	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
 	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
 	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
 
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index a0b4943811db..bae197a81add 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -71,6 +71,11 @@  V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
 	beq	cr0,49f
 
+	cmpwi	cr0,r3,CLOCK_REALTIME_COARSE
+	cmpwi	cr1,r3,CLOCK_MONOTONIC_COARSE
+	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
+	beq	cr0,65f
+
 	b	99f		/* Fallback to syscall */
   .cfi_register lr,r12
 49:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
@@ -112,6 +117,57 @@  V_FUNCTION_BEGIN(__kernel_clock_gettime)
 1:	bge	cr1,80f
 	addi	r4,r4,-1
 	add	r5,r5,r7
+	b	80f
+
+	/*
+	 * For coarse clocks we get data directly from the vdso data page, so
+	 * we don't need to call __do_get_tspec, but we still need to do the
+	 * counter trick.
+	 */
+65:	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
+70:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
+	andi.	r0,r8,1			/* pending update ? loop */
+	bne-	70b
+	xor	r0,r8,r8		/* create dependency */
+	add	r3,r3,r0
+
+	/*
+	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
+	 * too
+	 */
+	ld	r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
+	ld	r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
+	bne	cr1,78f
+
+	/* CLOCK_MONOTONIC_COARSE */
+	lwa	r6,WTOM_CLOCK_SEC(r3)
+	lwa	r9,WTOM_CLOCK_NSEC(r3)
+
+	/* check if counter has updated */
+78:	or	r0,r6,r9
+	xor	r0,r0,r0
+	add	r3,r3,r0
+	ld	r0,CFG_TB_UPDATE_COUNT(r3)
+	cmpld	cr0,r0,r8		/* check if updated */
+	bne-	70b
+
+	/* Counter has not updated, so continue calculating proper values for
+	 * sec and nsec if monotonic coarse, or just return with the proper
+	 * values for realtime.
+	 */
+	bne	cr1,80f
+
+	/* Add wall->monotonic offset and check for overflow or underflow */
+	add	r4,r4,r6
+	add	r5,r5,r9
+	cmpd	cr0,r5,r7
+	cmpdi	cr1,r5,0
+	blt	79f
+	subf	r5,r7,r5
+	addi	r4,r4,1
+79:	bge	cr1,80f
+	addi	r4,r4,-1
+	add	r5,r5,r7
 
 80:	std	r4,TSPC64_TV_SEC(r11)
 	std	r5,TSPC64_TV_NSEC(r11)