| 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: Tue, 26 Mar 2019 09:08:51 -0700
From: kan.liang@...ux.intel.com
To: peterz@...radead.org, acme@...nel.org, mingo@...hat.com,
linux-kernel@...r.kernel.org
Cc: tglx@...utronix.de, jolsa@...nel.org, eranian@...gle.com,
alexander.shishkin@...ux.intel.com, ak@...ux.intel.com,
Kan Liang <kan.liang@...ux.intel.com>
Subject: [PATCH V4 13/23] perf/x86/intel: Basic support for metrics counters
From: Andi Kleen <ak@...ux.intel.com>
Metrics counters (hardware counters containing multiple metrics)
are modelled as separate registers for each sub-event, with an
extra reg being used for coordinating access to the underlying
register in the scheduler.
This patch adds the basic infrastructure to separate the scheduler
register indexes from the actual hardware register indexes. In
most cases the MSR address is already used correctly, but for
code using indexes we need a separate reg_idx field in the event
to indicate the correct underlying register.
Signed-off-by: Andi Kleen <ak@...ux.intel.com>
Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
---
No changes since V3.
arch/x86/events/core.c | 18 ++++++++++++++++--
arch/x86/events/intel/core.c | 29 ++++++++++++++++++++---------
arch/x86/events/perf_event.h | 15 +++++++++++++++
arch/x86/include/asm/msr-index.h | 1 +
arch/x86/include/asm/perf_event.h | 30 ++++++++++++++++++++++++++++++
include/linux/perf_event.h | 1 +
6 files changed, 83 insertions(+), 11 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 9c14b4b3e457..d24f8d009529 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1006,16 +1006,30 @@ static inline void x86_assign_hw_event(struct perf_event *event,
struct hw_perf_event *hwc = &event->hw;
hwc->idx = cpuc->assign[i];
+ hwc->reg_idx = hwc->idx;
hwc->last_cpu = smp_processor_id();
hwc->last_tag = ++cpuc->tags[i];
+ /*
+ * Metrics counters use different indexes in the scheduler
+ * versus the hardware.
+ *
+ * Map metrics to fixed counter 3 (which is the base count),
+ * but the update event callback reads the extra metric register
+ * and converts to the right metric.
+ */
+ if (is_metric_idx(hwc->idx))
+ hwc->reg_idx = INTEL_PMC_IDX_FIXED_SLOTS;
+
if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
hwc->config_base = 0;
hwc->event_base = 0;
} else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
- hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED);
- hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30;
+ hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
+ (hwc->reg_idx - INTEL_PMC_IDX_FIXED);
+ hwc->event_base_rdpmc = (hwc->reg_idx - INTEL_PMC_IDX_FIXED)
+ | 1<<30;
} else {
hwc->config_base = x86_pmu_config_addr(hwc->idx);
hwc->event_base = x86_pmu_event_addr(hwc->idx);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ef95d73ef4f0..5c8f0df137bc 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2090,7 +2090,7 @@ static inline void intel_pmu_ack_status(u64 ack)
static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
{
- int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
+ int idx = hwc->reg_idx - INTEL_PMC_IDX_FIXED;
u64 ctrl_val, mask;
mask = 0xfULL << (idx * 4);
@@ -2116,9 +2116,19 @@ static void intel_pmu_disable_event(struct perf_event *event)
return;
}
- cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
- cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
- cpuc->intel_cp_status &= ~(1ull << hwc->idx);
+ __clear_bit(hwc->idx, cpuc->enabled_events);
+
+ /*
+ * When any other slots sharing event is still enabled,
+ * cancel the disabling.
+ */
+ if (is_any_slots_idx(hwc->idx) &&
+ (*(u64 *)&cpuc->enabled_events & INTEL_PMC_MSK_ANY_SLOTS))
+ return;
+
+ cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->reg_idx);
+ cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->reg_idx);
+ cpuc->intel_cp_status &= ~(1ull << hwc->reg_idx);
if (unlikely(event->attr.precise_ip))
intel_pmu_pebs_disable(event);
@@ -2150,7 +2160,7 @@ static void intel_pmu_read_event(struct perf_event *event)
static void intel_pmu_enable_fixed(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
+ int idx = hwc->reg_idx - INTEL_PMC_IDX_FIXED;
u64 ctrl_val, mask, bits = 0;
/*
@@ -2194,18 +2204,19 @@ static void intel_pmu_enable_event(struct perf_event *event)
}
if (event->attr.exclude_host)
- cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
+ cpuc->intel_ctrl_guest_mask |= (1ull << hwc->reg_idx);
if (event->attr.exclude_guest)
- cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
+ cpuc->intel_ctrl_host_mask |= (1ull << hwc->reg_idx);
if (unlikely(event_is_checkpointed(event)))
- cpuc->intel_cp_status |= (1ull << hwc->idx);
+ cpuc->intel_cp_status |= (1ull << hwc->reg_idx);
if (unlikely(event->attr.precise_ip))
intel_pmu_pebs_enable(event);
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
- intel_pmu_enable_fixed(event);
+ if (!__test_and_set_bit(hwc->idx, cpuc->enabled_events))
+ intel_pmu_enable_fixed(event);
return;
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index e4503e6a6b97..bd6ab970c73f 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -185,6 +185,7 @@ struct cpu_hw_events {
unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
int enabled;
+ unsigned long enabled_events[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
int n_events; /* the # of events in the below arrays */
int n_added; /* the # last events in the below arrays;
@@ -348,6 +349,20 @@ struct cpu_hw_events {
#define FIXED_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, (1ULL << (32+n)), FIXED_EVENT_FLAGS)
+/*
+ * Special metric counters do not actually exist, but get remapped
+ * to a combination of FxCtr3 + MSR_PERF_METRICS
+ *
+ * This allocates them to a dummy offset for the scheduler.
+ * This does not allow sharing of multiple users of the same
+ * metric without multiplexing, even though the hardware supports that
+ * in principle.
+ */
+
+#define METRIC_EVENT_CONSTRAINT(c, n) \
+ EVENT_CONSTRAINT(c, (1ULL << (INTEL_PMC_IDX_FIXED_METRIC_BASE+n)), \
+ FIXED_EVENT_FLAGS)
+
/*
* Constraint on the Event code + UMask
*/
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1378518cf63f..4310477d6808 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -777,6 +777,7 @@
#define MSR_CORE_PERF_FIXED_CTR0 0x00000309
#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a
#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR3 0x0000030c
#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d
#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e
#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index dcb8bac6fddb..4a59d35a8e1d 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -166,6 +166,10 @@ struct x86_pmu_capability {
#define INTEL_PMC_IDX_FIXED_REF_CYCLES (INTEL_PMC_IDX_FIXED + 2)
#define INTEL_PMC_MSK_FIXED_REF_CYCLES (1ULL << INTEL_PMC_IDX_FIXED_REF_CYCLES)
+#define MSR_ARCH_PERFMON_FIXED_CTR3 0x30c
+#define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3)
+#define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS)
+
/*
* We model BTS tracing as another fixed-mode PMC.
*
@@ -175,6 +179,32 @@ struct x86_pmu_capability {
*/
#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16)
+/*
+ * We model PERF_METRICS as more magic fixed-mode PMCs, one for each metric
+ * and another for the whole slots counter
+ *
+ * Internally they all map to Fixed Ctr 3 (SLOTS), and allocate PERF_METRICS
+ * as an extra_reg. PERF_METRICS has no own configuration, but we fill in
+ * the configuration of FxCtr3 to enforce that all the shared users of SLOTS
+ * have the same configuration.
+ */
+#define INTEL_PMC_IDX_FIXED_METRIC_BASE (INTEL_PMC_IDX_FIXED + 17)
+#define INTEL_PMC_IDX_TD_RETIRING (INTEL_PMC_IDX_FIXED_METRIC_BASE + 0)
+#define INTEL_PMC_IDX_TD_BAD_SPEC (INTEL_PMC_IDX_FIXED_METRIC_BASE + 1)
+#define INTEL_PMC_IDX_TD_FE_BOUND (INTEL_PMC_IDX_FIXED_METRIC_BASE + 2)
+#define INTEL_PMC_IDX_TD_BE_BOUND (INTEL_PMC_IDX_FIXED_METRIC_BASE + 3)
+#define INTEL_PMC_MSK_ANY_SLOTS ((0xfull << INTEL_PMC_IDX_FIXED_METRIC_BASE) | \
+ INTEL_PMC_MSK_FIXED_SLOTS)
+static inline bool is_metric_idx(int idx)
+{
+ return idx >= INTEL_PMC_IDX_FIXED_METRIC_BASE && idx <= INTEL_PMC_IDX_TD_BE_BOUND;
+}
+
+static inline bool is_any_slots_idx(int idx)
+{
+ return is_metric_idx(idx) || idx == INTEL_PMC_IDX_FIXED_SLOTS;
+}
+
#define GLOBAL_STATUS_COND_CHG BIT_ULL(63)
#define GLOBAL_STATUS_BUFFER_OVF BIT_ULL(62)
#define GLOBAL_STATUS_UNC_OVF BIT_ULL(61)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fb258c171b2c..c0cbd714f10e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -127,6 +127,7 @@ struct hw_perf_event {
unsigned long event_base;
int event_base_rdpmc;
int idx;
+ int reg_idx;
int last_cpu;
int flags;
--
2.17.1
Powered by blists - more mailing lists