| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 26 Nov 2012 13:15:24 +0100
From: Robert Richter <rric@...nel.org>
To: Jacob Shin <jacob.shin@....com>
Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Paul Mackerras <paulus@...ba.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...stprotocols.net>,
Thomas Gleixner <tglx@...utronix.de>,
"H. Peter Anvin" <hpa@...or.com>,
Stephane Eranian <eranian@...gle.com>, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH 4/4] perf, amd: Enable northbridge performance counters
on AMD family 15h
Jacob,
On 16.11.12 15:57:18, Jacob Shin wrote:
> > It looks like the paths should be defined more clearly.
>
> Per comments above the function, I was logically going down the cases,
> 1. is this a legacy counter?
> 2. is this a perfctr_core counter?
> 3. is this a perfctr_nb counter?
>
> To me it seems clear ..
See below...
> So here is v3, how does this look? If okay, could you add Reviewed-by or
> Acked-by ? After that, I'll send out the patchbomb again with review/ack
> on patch [3/4] and [4/4]
I will ack your resent patches if they are looking good to me and we
leave it at the maintainers to add my acked-by after your
signed-off-by.
The direction looks good to me know, but see my comments below.
> diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
> index 4fabcdf..df97186 100644
> --- a/arch/x86/include/asm/perf_event.h
> +++ b/arch/x86/include/asm/perf_event.h
> @@ -29,9 +29,14 @@
> #define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23)
> #define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL
>
> +#define AMD_PERFMON_EVENTSEL_INT_CORE_ENABLE (1ULL << 36)
> #define AMD_PERFMON_EVENTSEL_GUESTONLY (1ULL << 40)
> #define AMD_PERFMON_EVENTSEL_HOSTONLY (1ULL << 41)
>
> +#define AMD_PERFMON_EVENTSEL_INT_CORE_SEL_SHIFT 37
> +#define AMD_PERFMON_EVENTSEL_INT_CORE_SEL_MASK \
> + (0xFULL << AMD_PERFMON_EVENTSEL_INT_CORE_SEL_SHIFT)
> +
This is a bit shorter:
AMD64_EVENTSEL_INT_CORE_SEL_*
AMD64_* refers to AMD architectural definitions in the AMD64 manuals.
AMD_PERFMON_* is actually not consistent here. Arghh, Joerg.
> #define AMD64_EVENTSEL_EVENT \
> (ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
> #define INTEL_ARCH_EVENT_MASK \
> @@ -46,8 +51,12 @@
> #define AMD64_RAW_EVENT_MASK \
> (X86_RAW_EVENT_MASK | \
> AMD64_EVENTSEL_EVENT)
> +#define AMD64_NB_EVENT_MASK \
> + (AMD64_EVENTSEL_EVENT | \
> + ARCH_PERFMON_EVENTSEL_UMASK)
Since this is equivalent to AMD64_RAW_EVENT_MASK a better name would
be AMD64_RAW_EVENT_MASK_NB.
> #define AMD64_NUM_COUNTERS 4
> #define AMD64_NUM_COUNTERS_CORE 6
> +#define AMD64_NUM_COUNTERS_NB 4
>
> #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c
> #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
> static inline int amd_pmu_addr_offset(int index)
> {
> int offset;
> + int ncore;
>
> if (!index)
> return index;
> @@ -156,31 +163,27 @@ static inline int amd_pmu_addr_offset(int index)
> if (offset)
> return offset;
>
> - if (!cpu_has_perfctr_core)
> + if (!cpu_has_perfctr_core) {
> offset = index;
> - else
> + ncore = AMD64_NUM_COUNTERS;
> + } else {
> offset = index << 1;
> + ncore = AMD64_NUM_COUNTERS_CORE;
> + }
We still go in a block above even if we have a nb counter. See
solution below.
> +
> + /* find offset of NB counters with respect to x86_pmu.eventsel */
> + if (amd_nb_event_constraint &&
> + test_bit(index, amd_nb_event_constraint->idxmsk))
> + offset = (MSR_F15H_NB_PERF_CTL - x86_pmu.eventsel) +
> + ((index - ncore) << 1);
I prefer the following paths:
if (amd_nb_event_constraint && ...) {
/* nb counter */
...
} else if (!cpu_has_perfctr_core) {
/* core counter */
...
} else {
/* legacy counter */
...
}
>
> addr_offsets[index] = offset;
>
> return offset;
> }
>
> -static int amd_pmu_hw_config(struct perf_event *event)
> +static int __amd_core_hw_config(struct perf_event *event)
No need for underscores...
> +/*
> + * NB counters do not support the following event select bits:
> + * Host/Guest only
> + * Counter mask
> + * Invert counter mask
> + * Edge detect
> + * OS/User mode
> + */
> +static int __amd_nb_hw_config(struct perf_event *event)
No need for underscores...
> +{
> + if (event->attr.exclude_user || event->attr.exclude_kernel ||
> + event->attr.exclude_host || event->attr.exclude_guest)
> + return -EINVAL;
> +
> + /* set up interrupts to be delivered only to this core */
> + if (cpu_has_perfctr_nb) {
> + struct cpuinfo_x86 *c = &cpu_data(event->cpu);
> +
> + event->hw.config |= AMD_PERFMON_EVENTSEL_INT_CORE_ENABLE;
> + event->hw.config &= ~AMD_PERFMON_EVENTSEL_INT_CORE_SEL_MASK;
> + event->hw.config |= (0ULL | (c->cpu_core_id)) <<
Better make the cast visible:
(u64)(c->cpu_core_id) << AMD_PERFMON_EVENTSEL_INT_CORE_SEL_SHIFT
> + AMD_PERFMON_EVENTSEL_INT_CORE_SEL_SHIFT;
> + }
> +
> + event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
> + ARCH_PERFMON_EVENTSEL_OS);
>
> - event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
Since this is calculated before ...
> + if (event->hw.config & ~(AMD64_NB_EVENT_MASK |
> + ARCH_PERFMON_EVENTSEL_INT |
> + AMD_PERFMON_EVENTSEL_INT_CORE_ENABLE |
> + AMD_PERFMON_EVENTSEL_INT_CORE_SEL_MASK))
... we can check:
if (event->hw.config & ~AMD64_NB_EVENT_MASK)
if we move core_sel setup after the check.
Move comment from above here too.
> + return -EINVAL;
>
> return 0;
> @@ -422,7 +485,10 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
> if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw)))
> return &unconstrained;
>
> - return __amd_get_nb_event_constraints(cpuc, event, &unconstrained);
> + return __amd_get_nb_event_constraints(cpuc, event,
> + amd_nb_event_constraint ?
> + amd_nb_event_constraint :
> + &unconstrained);
An option would be to always set amd_nb_event_constraint to
&unconstrained per default. Or, move the check to
__amd_get_nb_event_constraints().
-Robert
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists