perf/x86: Fix time_shift in perf_event_mmap_page
Subsystems (2)
Adrian Hunter
reviewercover perf/x86: Fix time_shift in perf_event_mmap_page
Hi
There is a problem with my patch:
commit b20112edeadf ("perf/x86: Improve accuracy of perf/sched clock") which is in tip at the moment.
The problem is that userspace does not expect time_shift in perf_event_mmap_page to be as much as 32. Here is a proposed fix.
Adrian Hunter (1):
perf/x86: Fix time_shift in perf_event_mmap_page
arch/x86/kernel/tsc.c | 11 +++++++++++ include/uapi/linux/perf_event.h | 4 ++-- 2 files changed, 13 insertions(+), 2 deletions(-)
Regards
Adrian
Adrian Hunter
reviewerPATCH 1/1 perf/x86: Fix time_shift in perf_event_mmap_page
Commit b20112edeadf ("perf/x86: Improve accuracy of perf/sched clock") allowed the time_shift value in perf_event_mmap_page to be as much as 32. Unfortunately the documented algorithms for using time_shift have it shifting an integer, whereas to work correctly with the value 32, the type must be u64.
Fix by limiting the shift to 31 and adjusting the multiplier accordingly.
Also update the documentation of perf_event_mmap_page so that new code based on it will be more future-proof.
--- arch/x86/kernel/tsc.c | 11 +++++++++++ include/uapi/linux/perf_event.h | 4 ++-- 2 files changed, 13 insertions(+), 2 deletions(-)
arch/x86/kernel/tsc.c +11 -0
@@ -259,6 +259,17 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)clocks_calc_mult_shift (&data->cyc2ns_mul, &data->cyc2ns_shift, cpu_khz,NSEC_PER_MSEC ,0 ); +/* +* cyc2ns_shift is exported via arch_perf_update_userpage() where it is +* not expected to be greater than 31 due to the original published +* conversion algorithm shifting a 32-bit value (now specifies a 64-bit +* value) - refer perf_event_mmap_page documentation in perf_event.h. +*/ +if (data->cyc2ns_shift ==32 ) { + data->cyc2ns_shift =31 ; + data->cyc2ns_mul >>=1 ; + } + data->cyc2ns_offset = ns_now -mul_u64_u32_shr (tsc_now, data->cyc2ns_mul, data->cyc2ns_shift);
include/uapi/linux/perf_event.h +2 -2
@@ -476,7 +476,7 @@ struct perf_event_mmap_page {* u64 delta; * * quot = (cyc >> time_shift); -* rem = cyc & ((1 << time_shift) - 1); +* rem = cyc & (((u64)1 << time_shift) - 1); * delta = time_offset + quot * time_mult + * ((rem * time_mult) >> time_shift); *
@@ -507,7 +507,7 @@ struct perf_event_mmap_page {* And vice versa: * * quot = cyc >> time_shift; -* rem = cyc & ((1 << time_shift) - 1); +* rem = cyc & (((u64)1 << time_shift) - 1); * timestamp = time_zero + quot * time_mult + * ((rem * time_mult) >> time_shift); */
Signature · 1 line
1.9.1
Quoted 6 lines · Adrian Hunter
Commit
b20112edeadf("perf/x86: Improve accuracy of perf/sched clock") allowed thetime_shiftvalue inperf_event_mmap_pageto be as much as 32. Unfortunately the documented algorithms for usingtime_shifthave it shifting an integer, whereas to work correctly with the value 32, the type must be u64.
Quoted 7 lines
Fix by limiting the shift to 31 and adjusting the multiplier accordingly.
Also update the documentation of
perf_event_mmap_pageso that new code based on it will be more future-proof.Fixes b20112edeadf ("perf/x86: Improve accuracy of perf/sched clock")Signed-off-by Adrian Hunter <[email protected]>
Would be nice to point out via what symptoms the code misbehaves and how users notice.
Thanks,
Ingo
Adrian Hunter
reviewerQuoted 11 lines · Ingo Molnar
Quoted 8 lines · Adrian Hunter
Commit
b20112edeadf("perf/x86: Improve accuracy of perf/sched clock") allowed thetime_shiftvalue inperf_event_mmap_pageto be as much as 32. Unfortunately the documented algorithms for usingtime_shifthave it shifting an integer, whereas to work correctly with the value 32, the type must be u64.Fix by limiting the shift to 31 and adjusting the multiplier accordingly.
Quoted 8 lines
Quoted 5 lines
Also update the documentation of
perf_event_mmap_pageso that new code based on it will be more future-proof.Fixes b20112edeadf ("perf/x86: Improve accuracy of perf/sched clock")Signed-off-by Adrian Hunter <[email protected]>Would be nice to point out via what symptoms the code misbehaves and how users notice.
In the case of perf tools, Intel PT decodes correctly but the timestamps that are output (for example by perf script) have lost 32-bits of granularity so they look like they are not changing at all.
Quoted 18 lines · Adrian Hunter
Quoted 17 lines · Ingo Molnar
Quoted 13 lines · Adrian Hunter
Commit
b20112edeadf("perf/x86: Improve accuracy of perf/sched clock") allowed thetime_shiftvalue inperf_event_mmap_pageto be as much as 32. Unfortunately the documented algorithms for usingtime_shifthave it shifting an integer, whereas to work correctly with the value 32, the type must be u64.Fix by limiting the shift to 31 and adjusting the multiplier accordingly.
Also update the documentation of
perf_event_mmap_pageso that new code based on it will be more future-proof.Fixes b20112edeadf ("perf/x86: Improve accuracy of perf/sched clock")Signed-off-by Adrian Hunter <[email protected]>
Quoted 6 lines
Quoted 2 lines
Would be nice to point out via what symptoms the code misbehaves and how users notice.
In the case of perf tools, Intel PT decodes correctly but the timestamps that are output (for example by perf script) have lost 32-bits of granularity so they look like they are not changing at all.
Sounds like a nice and very informative paragraph to add to the changelog! :-)
Thanks,
Ingo
Adrian Hunter
reviewerPATCH v2 1/1 perf/x86: Fix time_shift in perf_event_mmap_page
Quoted 1 line
From
96bb79ce53b9373f5b6a212fcc2cd4d364d708afMon Sep 17 00:00:00 2001
From: Adrian Hunter <[email protected]>
Date: Fri, 16 Oct 2015 11:41:56 +0300
Subject: [PATCH 1/1] perf/x86: Fix time_shift in perf_event_mmap_page
Commit b20112edeadf ("perf/x86: Improve accuracy of perf/sched clock") allowed the time_shift value in perf_event_mmap_page to be as much as 32. Unfortunately the documented algorithms for using time_shift have it shifting an integer, whereas to work correctly with the value 32, the type must be u64.
In the case of perf tools, Intel PT decodes correctly but the timestamps that are output (for example by perf script) have lost 32-bits of granularity so they look like they are not changing at all.
Fix by limiting the shift to 31 and adjusting the multiplier accordingly.
Also update the documentation of perf_event_mmap_page so that new code based on it will be more future-proof.
---
Changes in V2:
Add to the commit message symptoms of the code misbehaviour and how users notice.
arch/x86/kernel/tsc.c | 11 +++++++++++ include/uapi/linux/perf_event.h | 4 ++-- 2 files changed, 13 insertions(+), 2 deletions(-)
arch/x86/kernel/tsc.c +11 -0
@@ -259,6 +259,17 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)clocks_calc_mult_shift (&data->cyc2ns_mul, &data->cyc2ns_shift, cpu_khz,NSEC_PER_MSEC ,0 ); +/* +* cyc2ns_shift is exported via arch_perf_update_userpage() where it is +* not expected to be greater than 31 due to the original published +* conversion algorithm shifting a 32-bit value (now specifies a 64-bit +* value) - refer perf_event_mmap_page documentation in perf_event.h. +*/ +if (data->cyc2ns_shift ==32 ) { + data->cyc2ns_shift =31 ; + data->cyc2ns_mul >>=1 ; + } + data->cyc2ns_offset = ns_now -mul_u64_u32_shr (tsc_now, data->cyc2ns_mul, data->cyc2ns_shift);
include/uapi/linux/perf_event.h +2 -2
@@ -476,7 +476,7 @@ struct perf_event_mmap_page {* u64 delta; * * quot = (cyc >> time_shift); -* rem = cyc & ((1 << time_shift) - 1); +* rem = cyc & (((u64)1 << time_shift) - 1); * delta = time_offset + quot * time_mult + * ((rem * time_mult) >> time_shift); *
@@ -507,7 +507,7 @@ struct perf_event_mmap_page {* And vice versa: * * quot = cyc >> time_shift; -* rem = cyc & ((1 << time_shift) - 1); +* rem = cyc & (((u64)1 << time_shift) - 1); * timestamp = time_zero + quot * time_mult + * ((rem * time_mult) >> time_shift); */
Signature · 1 line
1.9.1
tip-bot for Adrian Hunter
merge botperf/x86: Fix time_shift in perf_event_mmap_page
Commit-ID: b9511cd761faafca7a1acc059e792c1399f9d7c6 Gitweb: http://git.kernel.org/tip/b9511cd761faafca7a1acc059e792c1399f9d7c6 Author: Adrian Hunter <[email protected]> AuthorDate: Fri, 16 Oct 2015 16:24:05 +0300 Committer: Ingo Molnar <[email protected]> CommitDate: Tue, 20 Oct 2015 10:30:52 +0200
perf/x86: Fix time_shift in perf_event_mmap_page
Commit:
b20112edeadf ("perf/x86: Improve accuracy of perf/sched clock")
allowed the time_shift value in perf_event_mmap_page to be as much as 32. Unfortunately the documented algorithms for using time_shift have it shifting an integer, whereas to work correctly with the value 32, the type must be u64.
In the case of perf tools, Intel PT decodes correctly but the timestamps that are output (for example by perf script) have lost 32-bits of granularity so they look like they are not changing at all.
Fix by limiting the shift to 31 and adjusting the multiplier accordingly.
Also update the documentation of perf_event_mmap_page so that new code based on it will be more future-proof.
--- arch/x86/kernel/tsc.c | 11 +++++++++++ include/uapi/linux/perf_event.h | 4 ++-- 2 files changed, 13 insertions(+), 2 deletions(-)
arch/x86/kernel/tsc.c +11 -0
@@ -259,6 +259,17 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)clocks_calc_mult_shift (&data->cyc2ns_mul, &data->cyc2ns_shift, cpu_khz,NSEC_PER_MSEC ,0 ); +/* +* cyc2ns_shift is exported via arch_perf_update_userpage() where it is +* not expected to be greater than 31 due to the original published +* conversion algorithm shifting a 32-bit value (now specifies a 64-bit +* value) - refer perf_event_mmap_page documentation in perf_event.h. +*/ +if (data->cyc2ns_shift ==32 ) { + data->cyc2ns_shift =31 ; + data->cyc2ns_mul >>=1 ; + } + data->cyc2ns_offset = ns_now -mul_u64_u32_shr (tsc_now, data->cyc2ns_mul, data->cyc2ns_shift);
include/uapi/linux/perf_event.h +2 -2
@@ -476,7 +476,7 @@ struct perf_event_mmap_page {* u64 delta; * * quot = (cyc >> time_shift); -* rem = cyc & ((1 << time_shift) - 1); +* rem = cyc & (((u64)1 << time_shift) - 1); * delta = time_offset + quot * time_mult + * ((rem * time_mult) >> time_shift); *
@@ -507,7 +507,7 @@ struct perf_event_mmap_page {* And vice versa: * * quot = cyc >> time_shift; -* rem = cyc & ((1 << time_shift) - 1); +* rem = cyc & (((u64)1 << time_shift) - 1); * timestamp = time_zero + quot * time_mult + * ((rem * time_mult) >> time_shift); */