Re: [PATCH] x86, msr: Allow read access to /dev/cpu/X/msr

[Ingo Molnar <mingo@kernel.org>]

* Ingo Molnar <mingo@kernel.org> wrote:

> So what's wrong with exposing them as a simplified PMU driver?
> 
> That way we only expose the ones we want to - plus tooling can use all the rich 
> perf features that can be used around this. (sampling, counting, call chains, 
> etc.)

See below code from Andy that exposes a single MSR via perf. At the core of the 
PMU driver is a single rdmsrl():

+static void aperfmperf_event_start(struct perf_event *event, int flags)
+{
+	u64 now;
+
+	rdmsrl(event->hw.event_base, now);
+	local64_set(&event->hw.prev_count, now);
+}

Now I think what we really want is to expose not a single MSR but multiple MSRs in 
a single driver, i.e. don't have one PMU driver per MSR, but have a driver that 
allows the exposure of select MSRs as counters.

There should also be a maker/family/model filter mechanism, so that certain MSRs 
are only exposed on models that are known to support them, etc.

Thanks,

	Ingo

----- Forwarded message from Andy Lutomirski <luto@kernel.org> -----

Date: Tue, 28 Apr 2015 14:25:37 -0700
From: Andy Lutomirski <luto@kernel.org>
To: Len Brown <len.brown@intel.com>, Peter Zijlstra <peterz@infradead.org>, "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Cc: Paul Mackerras <paulus@samba.org>, Ingo Molnar <mingo@redhat.com>, Arnaldo Carvalho de Melo <acme@kernel.org>, Andy Lutomirski <luto@kernel.org>
Subject: [RFC] x86, perf: Add an aperfmperf driver

Signed-off-by: Andy Lutomirski <luto@kernel.org>
---

This driver seems a little bit silly, but I can imagine it being useful.  For
example, I think that turbostat could do some of its work without being
root if we had a driver like this.

Thoughts?  Would it make sense at all?  Did I wire it up right?  This is
the only PMU driver I've ever written, and it could have any number of
issues.

 arch/x86/kernel/cpu/Makefile                |   2 +
 arch/x86/kernel/cpu/perf_event_aperfmperf.c | 119 ++++++++++++++++++++++++++++
 2 files changed, 121 insertions(+)
 create mode 100644 arch/x86/kernel/cpu/perf_event_aperfmperf.c

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 80091ae54c2b..fadc822efc90 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -45,6 +45,8 @@ obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= perf_event_intel_uncore.o \
 					   perf_event_intel_uncore_snb.o \
 					   perf_event_intel_uncore_snbep.o \
 					   perf_event_intel_uncore_nhmex.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_aperf_mperf.o
+obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_aperf_mperf.o
 endif
 
 
diff --git a/arch/x86/kernel/cpu/perf_event_aperfmperf.c b/arch/x86/kernel/cpu/perf_event_aperfmperf.c
new file mode 100644
index 000000000000..6e6d113bd9ce
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_aperfmperf.c
@@ -0,0 +1,119 @@
+#include <linux/perf_event.h>
+
+#define APERFMPERF_EVENT_APERF 0
+#define APERFMPERF_EVENT_MPERF 1
+
+PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x00");
+PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x01");
+static struct attribute *events_attrs[] = {
+	&evattr_aperf.attr.attr,
+	&evattr_mperf.attr.attr,
+	NULL,
+};
+static struct attribute_group events_attr_group = {
+	.name = "events",
+	.attrs = events_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+static struct attribute *format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+static struct attribute_group format_attr_group = {
+	.name = "format",
+	.attrs = format_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+	&events_attr_group,
+	&format_attr_group,
+	NULL,
+};
+
+static int aperfmperf_event_init(struct perf_event *event)
+{
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (event->attr.config != APERFMPERF_EVENT_APERF &&
+	    event->attr.config != APERFMPERF_EVENT_MPERF)
+		return -ENOENT;
+
+	if (event->attr.config1 != 0)
+		return -ENOENT;
+
+	/* no sampling */
+	if (event->hw.sample_period)
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest  ||
+	    event->attr.freq           ||
+	    event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
+	event->hw.idx = -1;
+	event->hw.event_base = (event->attr.config == APERFMPERF_EVENT_APERF ?
+				MSR_IA32_APERF : MSR_IA32_MPERF);
+
+	return 0;
+}
+
+static void aperfmperf_event_update(struct perf_event *event)
+{
+	u64 prev;
+	u64 now;
+
+	rdmsrl(event->hw.event_base, now);
+	prev = local64_xchg(&event->hw.prev_count, now);
+	local64_add(now - prev, &event->count);
+}
+
+static void aperfmperf_event_start(struct perf_event *event, int flags)
+{
+	u64 now;
+
+	rdmsrl(event->hw.event_base, now);
+	local64_set(&event->hw.prev_count, now);
+}
+
+static void aperfmperf_event_stop_or_del(struct perf_event *event, int flags)
+{
+	aperfmperf_event_update(event);
+}
+
+static int aperfmperf_event_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		aperfmperf_event_start(event, flags);
+
+	return 0;
+}
+
+static struct pmu pmu_aperfmperf = {
+        .task_ctx_nr    = perf_invalid_context,
+	.attr_groups	= attr_groups,
+        .event_init     = aperfmperf_event_init,
+        .add            = aperfmperf_event_add,
+        .del            = aperfmperf_event_stop_or_del,
+        .start          = aperfmperf_event_start,
+        .stop           = aperfmperf_event_stop_or_del,
+        .read           = aperfmperf_event_update,
+};
+
+static int __init aperfmperf_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
+		return -ENODEV;
+
+	perf_pmu_register(&pmu_aperfmperf, "aperfmperf", -1);
+
+	return 0;
+}
+device_initcall(aperfmperf_init);
-- 
2.3.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

----- End forwarded message -----