| Message ID | 20170828074440.18766-1-santosh@fossix.org (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | [resend] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE | expand |
Hi all, Any comments on the below patch? Thanks, Santosh * Santosh Sivaraj <santosh@fossix.org> wrote (on 2017-08-28 13:14:40 +0530): > 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 | 70 ++++++++++++++++++++++++++++--- > 2 files changed, 66 insertions(+), 6 deletions(-) > > diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c > index 6e95c2c19a7e..c6acaa5edd16 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 382021324883..bae197a81add 100644 > --- a/arch/powerpc/kernel/vdso64/gettimeofday.S > +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S > @@ -60,18 +60,25 @@ V_FUNCTION_END(__kernel_gettimeofday) > */ > V_FUNCTION_BEGIN(__kernel_clock_gettime) > .cfi_startproc > + mr r11,r4 /* r11 saves tp */ > + mflr r12 /* r12 saves lr */ > + lis r7,NSEC_PER_SEC@h /* want nanoseconds */ > + ori r7,r7,NSEC_PER_SEC@l > + > /* Check for supported clock IDs */ > cmpwi cr0,r3,CLOCK_REALTIME > cmpwi cr1,r3,CLOCK_MONOTONIC > cror cr0*4+eq,cr0*4+eq,cr1*4+eq > - bne cr0,99f > + beq cr0,49f > > - mflr r12 /* r12 saves lr */ > + 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 > - mr r11,r4 /* r11 saves tp */ > - bl V_LOCAL_FUNC(__get_datapage) /* get data page */ > - lis r7,NSEC_PER_SEC@h /* want nanoseconds */ > - ori r7,r7,NSEC_PER_SEC@l > +49: bl V_LOCAL_FUNC(__get_datapage) /* get data page */ > 50: bl V_LOCAL_FUNC(__do_get_tspec) /* get time from tb & kernel */ > bne cr1,80f /* if not monotonic, all done */ > > @@ -110,6 +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) --
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 6e95c2c19a7e..c6acaa5edd16 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 382021324883..bae197a81add 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -60,18 +60,25 @@ V_FUNCTION_END(__kernel_gettimeofday) */ V_FUNCTION_BEGIN(__kernel_clock_gettime) .cfi_startproc + mr r11,r4 /* r11 saves tp */ + mflr r12 /* r12 saves lr */ + lis r7,NSEC_PER_SEC@h /* want nanoseconds */ + ori r7,r7,NSEC_PER_SEC@l + /* Check for supported clock IDs */ cmpwi cr0,r3,CLOCK_REALTIME cmpwi cr1,r3,CLOCK_MONOTONIC cror cr0*4+eq,cr0*4+eq,cr1*4+eq - bne cr0,99f + beq cr0,49f - mflr r12 /* r12 saves lr */ + 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 - mr r11,r4 /* r11 saves tp */ - bl V_LOCAL_FUNC(__get_datapage) /* get data page */ - lis r7,NSEC_PER_SEC@h /* want nanoseconds */ - ori r7,r7,NSEC_PER_SEC@l +49: bl V_LOCAL_FUNC(__get_datapage) /* get data page */ 50: bl V_LOCAL_FUNC(__do_get_tspec) /* get time from tb & kernel */ bne cr1,80f /* if not monotonic, all done */ @@ -110,6 +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)
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 | 70 ++++++++++++++++++++++++++++--- 2 files changed, 66 insertions(+), 6 deletions(-)