All of lore.kernel.org
 help / color / mirror / Atom feed
From: Like Xu <like.xu@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Paolo Bonzini <pbonzini@redhat.com>
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	Sean Christopherson <sean.j.christopherson@intel.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	ak@linux.intel.com, wei.w.wang@intel.com,
	Like Xu <like.xu@linux.intel.com>
Subject: [PATCH v11 02/11] perf/x86/core: Refactor hw->idx checks and cleanup
Date: Thu, 14 May 2020 16:30:45 +0800	[thread overview]
Message-ID: <20200514083054.62538-3-like.xu@linux.intel.com> (raw)
In-Reply-To: <20200514083054.62538-1-like.xu@linux.intel.com>

For intel_pmu_en/disable_event(), reorder the branches checks for
hw->idx and make them sorted by probability: gp,fixed,bts,others.

Clean up the x86_assign_hw_event() by converting multiple if-else
statements to a switch statement.

To skip x86_perf_event_update() and x86_perf_event_set_period(),
it's generic to replace "idx == INTEL_PMC_IDX_FIXED_BTS" check with
'!hwc->event_base' because that should be 0 for all non-gp/fixed cases.

Wrap related bit operations into intel_set/clear_masks() and
make the main path more cleaner and readable.

No functional changes.

Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Original-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
---
 arch/x86/events/core.c       | 25 +++++++----
 arch/x86/events/intel/core.c | 85 +++++++++++++++++++-----------------
 2 files changed, 62 insertions(+), 48 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index a619763e96e1..f7a259dcbb06 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -71,10 +71,9 @@ u64 x86_perf_event_update(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
-	int idx = hwc->idx;
 	u64 delta;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
@@ -1097,22 +1096,30 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 				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 ... 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;
 	}
 }
 
@@ -1233,7 +1240,7 @@ int x86_perf_event_set_period(struct perf_event *event)
 	s64 period = hwc->sample_period;
 	int ret = 0, idx = hwc->idx;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 332954cccece..f1439acbf7e6 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2136,8 +2136,35 @@ static inline void intel_pmu_ack_status(u64 ack)
 	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)
 {
+	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;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
 
@@ -2148,31 +2175,22 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 	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);
+	int idx = hwc->idx;
 
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_clear_masks(event, idx);
+		x86_pmu_disable_event(event);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_clear_masks(event, idx);
+		intel_pmu_disable_fixed(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
-		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
-		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.
@@ -2238,33 +2256,22 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 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))
-			return;
-
-		intel_pmu_enable_bts(hwc->config);
-		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);
+	int idx = hwc->idx;
 
 	if (unlikely(event->attr.precise_ip))
 		intel_pmu_pebs_enable(event);
 
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_set_masks(event, idx);
+		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_set_masks(event, idx);
 		intel_pmu_enable_fixed(event);
-		return;
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
+		if (!__this_cpu_read(cpu_hw_events.enabled))
+			return;
+		intel_pmu_enable_bts(hwc->config);
 	}
-
-	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
 static void intel_pmu_add_event(struct perf_event *event)
-- 
2.21.3


  parent reply	other threads:[~2020-05-14  8:31 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-14  8:30 [PATCH v11 00/11] Guest Last Branch Recording Enabling Like Xu
2020-05-14  8:30 ` [PATCH v11 01/11] perf/x86: Fix variable types for LBR registers Like Xu
2020-05-14  8:30 ` Like Xu [this message]
2020-05-14  8:30 ` [PATCH v11 03/11] perf/x86/lbr: Add interface to get basic information about LBR stack Like Xu
2020-05-14  8:30 ` [PATCH v11 04/11] perf/x86: Add constraint to create guest LBR event without hw counter Like Xu
2020-05-18 11:43   ` Peter Zijlstra
2020-07-03  8:01   ` [tip: perf/core] " tip-bot2 for Like Xu
2020-05-14  8:30 ` [PATCH v11 05/11] perf/x86: Keep LBR stack unchanged in host context for guest LBR event Like Xu
2020-05-18 11:59   ` Peter Zijlstra
2020-05-18 12:02   ` Peter Zijlstra
2020-05-19  3:08     ` Like Xu
2020-05-19 10:45       ` Peter Zijlstra
2020-05-19 13:25         ` Xu, Like
2020-07-03  8:01   ` [tip: perf/core] perf/x86: Keep LBR records unchanged in host context for guest usage tip-bot2 for Like Xu
2020-05-14  8:30 ` [PATCH v11 06/11] KVM: x86/pmu: Tweak kvm_pmu_get_msr to pass 'struct msr_data' in Like Xu
2020-05-14  8:30 ` [PATCH v11 07/11] KVM: x86: Expose MSR_IA32_PERF_CAPABILITIES for LBR record format Like Xu
2020-05-19 10:53   ` Peter Zijlstra
2020-05-19 12:19     ` Xu, Like
2020-05-19 15:12     ` Sean Christopherson
2020-05-14  8:30 ` [PATCH v11 08/11] KVM: x86/pmu: Emulate LBR feature via guest LBR event Like Xu
2020-05-19 11:00   ` Peter Zijlstra
2020-05-19 12:24     ` Xu, Like
2020-05-19 11:01   ` Peter Zijlstra
2020-05-19 12:28     ` Xu, Like
2020-05-19 11:03   ` Peter Zijlstra
2020-05-19 12:40     ` Xu, Like
2020-05-14  8:30 ` [PATCH v11 09/11] KVM: x86/pmu: Release guest LBR event via vPMU lazy release mechanism Like Xu
2020-05-14  8:30 ` [PATCH v11 10/11] KVM: x86/pmu: Check guest LBR availability in case host reclaims them Like Xu
2020-05-19 11:15   ` Peter Zijlstra
2020-05-19 13:10     ` Xu, Like
2020-05-19 14:57       ` Peter Zijlstra
2020-05-20  2:01         ` Xu, Like
2020-05-27  8:17           ` Like Xu
2020-05-14  8:30 ` [PATCH v11 11/11] KVM: x86/pmu: Reduce the overhead of LBR passthrough or cancellation Like Xu
2020-05-27  8:28 ` [PATCH v11 00/11] Guest Last Branch Recording Enabling Xu, Like

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=20200514083054.62538-3-like.xu@linux.intel.com \
    --to=like.xu@linux.intel.com \
    --cc=ak@linux.intel.com \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=sean.j.christopherson@intel.com \
    --cc=tglx@linutronix.de \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.com \
    --cc=wei.w.wang@intel.com \
    /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.