From: Peter Zijlstra <peterz@infradead.org>
To: kan.liang@linux.intel.com
Cc: acme@kernel.org, mingo@redhat.com, linux-kernel@vger.kernel.org,
tglx@linutronix.de, jolsa@kernel.org, eranian@google.com,
alexander.shishkin@linux.intel.com, ak@linux.intel.com
Subject: Re: [RESEND PATCH V3 2/8] perf/x86/intel: Basic support for metrics counters
Date: Wed, 28 Aug 2019 11:02:17 +0200 [thread overview]
Message-ID: <20190828090217.GN2386@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20190828084416.GC2369@hirez.programming.kicks-ass.net>
On Wed, Aug 28, 2019 at 10:44:16AM +0200, Peter Zijlstra wrote:
> Let me clean up this mess for you.
Here, how's that. Now we don't check is_metric_idx() _3_ times on the
enable/disable path and all the topdown crud is properly placed in the
fixed counter functions.
Please think; don't tinker.
---
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1033,22 +1033,34 @@ static inline void x86_assign_hw_event(s
struct cpu_hw_events *cpuc, int i)
{
struct hw_perf_event *hwc = &event->hw;
+ int idx;
- hwc->idx = cpuc->assign[i];
+ idx = hwc->idx = cpuc->assign[i];
hwc->last_cpu = smp_processor_id();
hwc->last_tag = ++cpuc->tags[i];
- if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
+ switch (hwc->idx) {
+ case INTEL_PMC_IDX_FIXED_BTS:
hwc->config_base = 0;
hwc->event_base = 0;
- } else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
+ break;
+
+ case INTEL_PMC_IDX_FIXED_METRIC_BASE ... INTEL_PMC_IDX_FIXED_METRIC_BASE+3:
+ /* All METRIC events are mapped onto the fixed SLOTS event */
+ idx = INTEL_PMC_IDX_FIXED_SLOTS;
+
+ case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1:
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;
- } else {
+ hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
+ (idx - INTEL_PMC_IDX_FIXED);
+ hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | 1<<30;
+ break;
+
+ default:
hwc->config_base = x86_pmu_config_addr(hwc->idx);
hwc->event_base = x86_pmu_event_addr(hwc->idx);
hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx);
+ break;
}
}
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2128,27 +2128,61 @@ static inline void intel_pmu_ack_status(
wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
}
-static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static inline bool event_is_checkpointed(struct perf_event *event)
+{
+ return unlikely(event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
+static inline void intel_set_masks(struct perf_event *event, int idx)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ if (event->attr.exclude_host)
+ __set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+ if (event->attr.exclude_guest)
+ __set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+ if (event_is_checkpointed(event))
+ __set_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static inline void intel_clear_masks(struct perf_event *event, int idx)
{
- int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ __clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+ __clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+ __clear_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static void intel_pmu_disable_fixed(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
u64 ctrl_val, mask;
+ int idx = hwc->idx;
- mask = 0xfULL << (idx * 4);
+ if (is_topdown_idx(idx)) {
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ /*
+ * When there are other Top-Down events still active; don't
+ * disable the SLOTS counter.
+ */
+ if (*(u64 *)cpuc->active_mask & INTEL_PMC_OTHER_TOPDOWN_BITS(idx))
+ return;
+
+ idx = INTEL_PMC_IDX_FIXED_SLOTS;
+ }
+ intel_clear_masks(event, idx);
+
+ mask = 0xfULL << ((idx - INTEL_PMC_IDX_FIXED) * 4);
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
wrmsrl(hwc->config_base, ctrl_val);
}
-static inline bool event_is_checkpointed(struct perf_event *event)
-{
- return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
-}
-
static void intel_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
intel_pmu_disable_bts();
@@ -2156,18 +2190,19 @@ static void intel_pmu_disable_event(stru
return;
}
- cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
- cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
- cpuc->intel_cp_status &= ~(1ull << hwc->idx);
-
- if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL))
- intel_pmu_disable_fixed(hwc);
- else
+ if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+ intel_pmu_disable_fixed(event);
+ } else {
+ intel_clear_masks(event, hwc->idx);
x86_pmu_disable_event(event);
+ }
/*
* Needs to be called after x86_pmu_disable_event,
* so we don't trigger the event without PEBS bit set.
+ *
+ * Metric stuff doesn't do PEBS (I hope?); and so the early exit from
+ * intel_pmu_disable_fixed() is OK.
*/
if (unlikely(event->attr.precise_ip))
intel_pmu_pebs_disable(event);
@@ -2192,8 +2227,22 @@ static void intel_pmu_read_event(struct
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;
u64 ctrl_val, mask, bits = 0;
+ int idx = hwc->idx;
+
+ if (is_topdown_idx(idx)) {
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ /*
+ * When there are other Top-Down events already active; don't
+ * enable the SLOTS counter.
+ */
+ if (*(u64 *)cpuc->active_mask & INTEL_PMC_OTHER_TOPDOWN_BITS(idx))
+ return;
+
+ idx = INTEL_PMC_IDX_FIXED_SLOTS;
+ }
+
+ intel_set_masks(event, hwc->idx);
/*
* Enable IRQ generation (0x8), if not PEBS,
@@ -2213,6 +2262,7 @@ static void intel_pmu_enable_fixed(struc
if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
bits |= 0x4;
+ idx -= INTEL_PMC_IDX_FIXED;
bits <<= (idx * 4);
mask = 0xfULL << (idx * 4);
@@ -2230,7 +2280,6 @@ static void intel_pmu_enable_fixed(struc
static void intel_pmu_enable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
if (!__this_cpu_read(cpu_hw_events.enabled))
@@ -2240,23 +2289,16 @@ static void intel_pmu_enable_event(struc
return;
}
- if (event->attr.exclude_host)
- cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
- if (event->attr.exclude_guest)
- cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
-
- if (unlikely(event_is_checkpointed(event)))
- cpuc->intel_cp_status |= (1ull << hwc->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);
- return;
+ } else {
+ intel_set_masks(event, hwc->idx);
+ __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
-
- __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
static void intel_pmu_add_event(struct perf_event *event)
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -349,6 +349,20 @@ struct cpu_hw_events {
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
*/
#define INTEL_UEVENT_CONSTRAINT(c, n) \
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -795,6 +795,7 @@
#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
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -175,11 +175,39 @@ struct x86_pmu_capability {
/*
* We model BTS tracing as another fixed-mode PMC.
*
- * We choose a value in the middle of the fixed event range, since lower
+ * We choose value 47 for the fixed index of BTS, since lower
* values are used by actual fixed events and higher values are used
* to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr.
*/
-#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16)
+#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 15)
+
+/*
+ * We model PERF_METRICS as more magic fixed-mode PMCs, one for each metric
+ *
+ * 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 + 16)
+#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_TOPDOWN ((0xfull << INTEL_PMC_IDX_FIXED_METRIC_BASE) | \
+ INTEL_PMC_MSK_FIXED_SLOTS)
+
+static inline bool is_metric_idx(int idx)
+{
+ return (unsigned)(idx - INTEL_PMC_IDX_FIXED_METRIC_BASE) < 4;
+}
+
+static inline bool is_topdown_idx(int idx)
+{
+ return is_metric_idx(idx) || idx == INTEL_PMC_IDX_FIXED_SLOTS;
+}
+
+#define INTEL_PMC_OTHER_TOPDOWN_BITS(bit) (~(0x1ull << bit) & INTEL_PMC_MSK_TOPDOWN)
#define GLOBAL_STATUS_COND_CHG BIT_ULL(63)
#define GLOBAL_STATUS_BUFFER_OVF BIT_ULL(62)
next prev parent reply other threads:[~2019-08-28 9:02 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-26 14:47 [RESEND PATCH V3 0/8] TopDown metrics support for Icelake kan.liang
2019-08-26 14:47 ` [RESEND PATCH V3 1/8] perf/x86/intel: Set correct mask for TOPDOWN.SLOTS kan.liang
2019-08-28 7:48 ` Peter Zijlstra
2019-08-26 14:47 ` [RESEND PATCH V3 2/8] perf/x86/intel: Basic support for metrics counters kan.liang
2019-08-28 7:48 ` Peter Zijlstra
2019-08-28 7:52 ` Peter Zijlstra
2019-08-28 13:59 ` Liang, Kan
2019-08-28 8:44 ` Peter Zijlstra
2019-08-28 9:02 ` Peter Zijlstra [this message]
2019-08-28 9:37 ` Peter Zijlstra
2019-08-28 13:51 ` Liang, Kan
2019-08-28 8:52 ` Peter Zijlstra
2019-08-26 14:47 ` [RESEND PATCH V3 3/8] perf/x86/intel: Support hardware TopDown metrics kan.liang
2019-08-28 15:02 ` Peter Zijlstra
2019-08-28 19:04 ` Andi Kleen
2019-08-31 9:19 ` Peter Zijlstra
2019-09-09 13:40 ` Liang, Kan
2019-08-28 19:35 ` Liang, Kan
2019-08-28 15:19 ` Peter Zijlstra
2019-08-28 16:11 ` [PATCH] x86/math64: Provide a sane mul_u64_u32_div() implementation for x86_64 Peter Zijlstra
2019-08-29 9:30 ` Peter Zijlstra
2019-08-28 16:17 ` [RESEND PATCH V3 3/8] perf/x86/intel: Support hardware TopDown metrics Andi Kleen
2019-08-28 16:28 ` Peter Zijlstra
2019-08-29 3:11 ` Andi Kleen
2019-08-29 9:17 ` Peter Zijlstra
2019-08-29 13:31 ` Liang, Kan
2019-08-29 13:52 ` Peter Zijlstra
2019-08-29 16:56 ` Liang, Kan
2019-08-31 9:18 ` Peter Zijlstra
2019-08-30 23:18 ` Stephane Eranian
2019-08-31 0:31 ` Andi Kleen
2019-08-31 9:13 ` Stephane Eranian
2019-08-31 9:29 ` Peter Zijlstra
2019-08-31 17:53 ` Andi Kleen
2019-08-26 14:47 ` [RESEND PATCH V3 4/8] perf/x86/intel: Support per thread RDPMC " kan.liang
2019-08-26 14:47 ` [RESEND PATCH V3 5/8] perf/x86/intel: Export TopDown events for Icelake kan.liang
2019-08-26 14:47 ` [RESEND PATCH V3 6/8] perf/x86/intel: Disable sampling read slots and topdown kan.liang
2019-08-26 14:47 ` [RESEND PATCH V3 7/8] perf, tools, stat: Support new per thread TopDown metrics kan.liang
2019-08-26 14:47 ` [RESEND PATCH V3 8/8] perf, tools: Add documentation for topdown metrics 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=20190828090217.GN2386@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=eranian@google.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).