From: kan.liang@linux.intel.com
To: peterz@infradead.org, acme@kernel.org, mingo@redhat.com,
linux-kernel@vger.kernel.org
Cc: tglx@linutronix.de, jolsa@kernel.org, eranian@google.com,
alexander.shishkin@linux.intel.com, ak@linux.intel.com,
Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH V3 19/23] perf/x86/intel: Support CPUID 10.ECX to disable fixed counters
Date: Fri, 22 Mar 2019 09:37:14 -0700 [thread overview]
Message-ID: <20190322163718.2191-20-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20190322163718.2191-1-kan.liang@linux.intel.com>
From: Andi Kleen <ak@linux.intel.com>
Icelake supports a new CPUID 10.ECX cpu leaf to indicate some fixed
counters are not supported. This extends the previous count to a bitmap
which allows to disable even lower counters.
It's a nop on Icelake (all fixed counters are supported), but let's
implement it here. This adds the necessary checks. In theory it could
be used today by a Hypervisor.
For disabled counters disable any constraint events. I reuse the
existing intel_ctrl variable to remember which counters are disabled.
All code that reads all counters is fixed to check this extra bitmask.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
No changes since V2.
arch/x86/events/core.c | 8 +++++++-
arch/x86/events/intel/core.c | 22 +++++++++++++++-------
arch/x86/events/perf_event.h | 6 ++++++
3 files changed, 28 insertions(+), 8 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index b9bee53e53d8..12d7d591843e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -225,6 +225,8 @@ static bool check_hw_exists(void)
if (ret)
goto msr_fail;
for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
+ if (fixed_counter_disabled(i))
+ continue;
if (val & (0x03 << i*4)) {
bios_fail = 1;
val_fail = val;
@@ -1372,6 +1374,8 @@ void perf_event_print_debug(void)
cpu, idx, prev_left);
}
for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
+ if (fixed_counter_disabled(idx))
+ continue;
rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
@@ -1887,7 +1891,9 @@ static int __init init_hw_perf_events(void)
pr_info("... generic registers: %d\n", x86_pmu.num_counters);
pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask);
pr_info("... max period: %016Lx\n", x86_pmu.max_period);
- pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed);
+ pr_info("... fixed-purpose events: %lu\n",
+ hweight64((((1ULL << x86_pmu.num_counters_fixed) - 1)
+ << INTEL_PMC_IDX_FIXED) & x86_pmu.intel_ctrl));
pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl);
/*
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ef6045544628..a4b7711ef0ee 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2311,8 +2311,11 @@ static void intel_pmu_reset(void)
wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
wrmsrl_safe(x86_pmu_event_addr(idx), 0ull);
}
- for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
+ for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
+ if (fixed_counter_disabled(idx))
+ continue;
wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+ }
if (ds)
ds->bts_index = ds->bts_buffer_base;
@@ -4551,7 +4554,7 @@ __init int intel_pmu_init(void)
union cpuid10_eax eax;
union cpuid10_ebx ebx;
struct event_constraint *c;
- unsigned int unused;
+ unsigned int fixed_mask;
struct extra_reg *er;
int version, i;
char *name;
@@ -4572,9 +4575,11 @@ __init int intel_pmu_init(void)
* Check whether the Architectural PerfMon supports
* Branch Misses Retired hw_event or not.
*/
- cpuid(10, &eax.full, &ebx.full, &unused, &edx.full);
+ cpuid(10, &eax.full, &ebx.full, &fixed_mask, &edx.full);
if (eax.split.mask_length < ARCH_PERFMON_EVENTS_COUNT)
return -ENODEV;
+ if (!fixed_mask)
+ fixed_mask = -1;
version = eax.split.version_id;
if (version < 2)
@@ -5104,7 +5109,8 @@ __init int intel_pmu_init(void)
}
x86_pmu.intel_ctrl |=
- ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+ (((1LL << x86_pmu.num_counters_fixed)-1) & (u64)fixed_mask)
+ << INTEL_PMC_IDX_FIXED;
if (x86_pmu.event_constraints) {
/*
@@ -5121,9 +5127,11 @@ __init int intel_pmu_init(void)
c->weight = hweight64(c->idxmsk64);
continue;
}
- if (c->cmask == FIXED_EVENT_FLAGS
- && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
- c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+ if (c->cmask == FIXED_EVENT_FLAGS) {
+ if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES)
+ c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+ /* Disabled fixed counters which are not in CPUID */
+ c->idxmsk64 &= x86_pmu.intel_ctrl;
}
c->idxmsk64 &=
~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 077d44a96d31..fff8868f92a8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -925,6 +925,12 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
+static inline bool fixed_counter_disabled(int i)
+{
+ return x86_pmu.intel_ctrl &&
+ ((1ULL << (i + INTEL_PMC_IDX_FIXED)) & x86_pmu.intel_ctrl);
+}
+
#ifdef CONFIG_CPU_SUP_AMD
int amd_pmu_init(void);
--
2.17.1
next prev parent reply other threads:[~2019-03-22 16:40 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-22 16:36 [PATCH V3 00/23] perf: Add Icelake support kan.liang
2019-03-22 16:36 ` [PATCH V3 01/23] perf/x86: Support outputting XMM registers kan.liang
2019-03-22 17:08 ` Peter Zijlstra
2019-03-22 17:22 ` Andi Kleen
2019-03-23 9:56 ` Peter Zijlstra
2019-03-25 20:35 ` Liang, Kan
2019-03-26 0:02 ` Thomas Gleixner
2019-03-26 0:11 ` Thomas Gleixner
2019-03-26 13:14 ` Liang, Kan
2019-03-26 13:47 ` Thomas Gleixner
2019-03-26 13:55 ` Liang, Kan
2019-03-22 16:36 ` [PATCH V3 02/23] perf/x86/intel: Extract memory code PEBS parser for reuse kan.liang
2019-03-22 16:36 ` [PATCH V3 03/23] perf/x86/intel/ds: Extract code of event update in short period kan.liang
2019-03-22 16:36 ` [PATCH V3 04/23] perf/x86/intel: Support adaptive PEBSv4 kan.liang
2019-03-22 16:37 ` [PATCH V3 05/23] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them kan.liang
2019-03-22 16:37 ` [PATCH V3 06/23] perf/x86: Support constraint ranges kan.liang
2019-03-22 16:37 ` [PATCH V3 07/23] perf/x86/intel: Add Icelake support kan.liang
2019-03-22 16:37 ` [PATCH V3 08/23] perf/x86/intel/cstate: " kan.liang
2019-03-22 16:37 ` [PATCH V3 09/23] perf/x86/intel/rapl: " kan.liang
2019-03-22 16:37 ` [PATCH V3 10/23] perf/x86/msr: " kan.liang
2019-03-22 16:37 ` [PATCH V3 11/23] perf/x86/intel/uncore: Add Intel Icelake uncore support kan.liang
2019-03-22 16:37 ` [PATCH V3 12/23] perf/core: Support a REMOVE transaction kan.liang
2019-03-22 16:37 ` [PATCH V3 13/23] perf/x86/intel: Basic support for metrics counters kan.liang
2019-03-22 16:37 ` [PATCH V3 14/23] perf/x86/intel: Support overflows on SLOTS kan.liang
2019-03-22 16:37 ` [PATCH V3 15/23] perf/x86/intel: Support hardware TopDown metrics kan.liang
2019-03-22 16:37 ` [PATCH V3 16/23] perf/x86/intel: Set correct weight for topdown subevent counters kan.liang
2019-03-22 16:37 ` [PATCH V3 17/23] perf/x86/intel: Export new top down events for Icelake kan.liang
2019-03-22 16:37 ` [PATCH V3 18/23] perf/x86/intel: Disable sampling read slots and topdown kan.liang
2019-03-22 16:37 ` kan.liang [this message]
2019-03-22 16:37 ` [PATCH V3 20/23] perf, tools: Add support for recording and printing XMM registers kan.liang
2019-03-22 16:37 ` [PATCH 21/23] perf, tools, stat: Support new per thread TopDown metrics kan.liang
2019-03-22 16:37 ` [PATCH V3 22/23] perf, tools: Add documentation for topdown metrics kan.liang
2019-03-22 16:37 ` [PATCH V3 23/23] perf vendor events intel: Add JSON files for Icelake kan.liang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190322163718.2191-20-kan.liang@linux.intel.com \
--to=kan.liang@linux.intel.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=eranian@google.com \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.