On Thu, Mar 21, 2019 at 09:15:22PM +0000, Phillips, Kim wrote:
> From: Kim Phillips <kim.phill...@amd.com>
>
> Family 17h differs from prior families by:
> - not supporting an L2 cache miss event
> - having re-enumerated PMC counters for:
> - L2 cache references
> - front & back end stalled cycles
>
> So we add a new amd_f17h_perfmon_event_map so that the generic
> perf event names will resolve to the correct h/w events on
> family 17h and above processors.
>
> Reference sections 2.1.13.3.3 (stalls) and 2.1.13.3.6 (L2):
> https://www.amd.com/system/files/TechDocs/54945_PPR_Family_17h_Models_00h-0Fh.pdf
>
> Fixes: e40ed1542dd7 ("perf/x86: Add perf support for AMD family-17h
> processors")
> Signed-off-by: Kim Phillips <kim.phill...@amd.com>
> Cc: Janakarajan Natarajan <janakarajan.natara...@amd.com>
> Cc: Suravee Suthikulpanit <suravee.suthikulpa...@amd.com>
> Cc: Martin Liška <mli...@suse.cz>
> Cc: Peter Zijlstra <pet...@infradead.org>
> Cc: Ingo Molnar <mi...@redhat.com>
> Cc: Arnaldo Carvalho de Melo <a...@kernel.org>
> Cc: Alexander Shishkin <alexander.shish...@linux.intel.com>
> Cc: Jiri Olsa <jo...@redhat.com>
> Cc: Namhyung Kim <namhy...@kernel.org>
> Cc: Thomas Gleixner <t...@linutronix.de>
> Cc: Borislav Petkov <b...@alien8.de>
> Cc: "H. Peter Anvin" <h...@zytor.com>
> Cc: Pu Wen <pu...@hygon.cn>
> Cc: x...@kernel.org
> Cc: linux-kernel@vger.kernel.org
> ---
> arch/x86/events/amd/core.c | 17 +++++++++++++++++
> 1 file changed, 17 insertions(+)
>
> diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
> index 7d2d7c801dba..764d181afa18 100644
> --- a/arch/x86/events/amd/core.c
> +++ b/arch/x86/events/amd/core.c
> @@ -127,8 +127,25 @@ static const u64
> amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
> [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls"
> event */
> };
>
> +/*
> + * AMD Performance Monitor Family 17h
> + */
> +static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
> +{
> + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
> + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
> + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60,
> + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
> + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
> + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287,
> + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187,
> +};
> +
> static u64 amd_pmu_event_map(int hw_event)
> {
> + if (boot_cpu_data.x86 >= 0x17)
> + return amd_f17h_perfmon_event_map[hw_event];
> +
> return amd_perfmon_event_map[hw_event];
> }
>
> --
Your patch has some style problems, see below. Please run it through
checkpatch before submitting.
And yeah, that amd_perfmon_event_map in that file has some wrong
formatting too - preceding whitespace instead of tabs - so you can
submit a cleanup patch ontop to fix that up too.
Thx.
---
ERROR: that open brace { should be on the previous line
#70: FILE: arch/x86/events/amd/core.c:134:
+static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
WARNING: please, no spaces at the start of a line
#71: FILE: arch/x86/events/amd/core.c:135:
+ [PERF_COUNT_HW_CPU_CYCLES]^I^I^I= 0x0076,$
WARNING: please, no spaces at the start of a line
#72: FILE: arch/x86/events/amd/core.c:136:
+ [PERF_COUNT_HW_INSTRUCTIONS]^I^I^I= 0x00c0,$
WARNING: please, no spaces at the start of a line
#73: FILE: arch/x86/events/amd/core.c:137:
+ [PERF_COUNT_HW_CACHE_REFERENCES]^I^I= 0xff60,$
WARNING: please, no spaces at the start of a line
#74: FILE: arch/x86/events/amd/core.c:138:
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]^I^I= 0x00c2,$
WARNING: please, no spaces at the start of a line
#75: FILE: arch/x86/events/amd/core.c:139:
+ [PERF_COUNT_HW_BRANCH_MISSES]^I^I^I= 0x00c3,$
WARNING: please, no spaces at the start of a line
#76: FILE: arch/x86/events/amd/core.c:140:
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]^I= 0x0287,$
WARNING: please, no spaces at the start of a line
#77: FILE: arch/x86/events/amd/core.c:141:
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND]^I= 0x0187,$
total: 1 errors, 8 warnings, 25 lines checked
NOTE: For some of the reported defects, checkpatch may be able to
mechanically convert to the typical style using --fix or --fix-inplace.
Your patch has style problems, please review.
NOTE: If any of the errors are false positives, please report
them to the maintainer, see CHECKPATCH in MAINTAINERS.
--
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.
