mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Colton Lewis <coltonlewis@google.com>
To: Marc Zyngier <maz@kernel.org>, Oliver Upton <oupton@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	 Mark Rutland <mark.rutland@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	 Ingo Molnar <mingo@redhat.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	 Russell King <linux@armlinux.org.uk>,
	Jonathan Corbet <corbet@lwn.net>,
	 Fuad Tabba <fuad.tabba@linux.dev>,
	Joey Gouly <joey.gouly@arm.com>,
	 Suzuki K Poulose <suzuki.poulose@arm.com>,
	Zenghui Yu <yuzenghui@huawei.com>,
	 Shuah Khan <skhan@linuxfoundation.org>,
	James Clark <james.clark@linaro.org>,
	 Alexandru Elisei <alexandru.elisei@arm.com>,
	Mingwei Zhang <mizhang@google.com>,
	 Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>,
	kvmarm@lists.linux.dev,  linux-arm-kernel@lists.infradead.org,
	kvm@vger.kernel.org,  linux-perf-users@vger.kernel.org,
	linux-kselftest@vger.kernel.org,  linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH v10 07/33] perf: arm_pmuv3: Move counter allocation mask to per-CPU struct pmu_hw_events
Date: Thu, 19 Nov 2026 18:51:49 +0000	[thread overview]
Message-ID: <20261119185215.632334-8-coltonlewis@google.com> (raw)
In-Reply-To: <20261119185215.632334-1-coltonlewis@google.com>

In preparation for dynamic per-CPU PMU counter reservations when running
KVM guests with a partitioned PMU, move the counter allocation mask from
the global struct arm_pmu to per-CPU struct pmu_hw_events.

Initialize cpuc->cntr_mask from the static cpu_pmu->cntr_mask during PMU
probe and CPU hotplug startup, and update event counter allocation
helpers (armv8pmu_get_single_idx(), armv8pmu_get_chain_idx(), and
armv8pmu_get_event_idx()) to query the per-CPU mask.

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Colton Lewis <coltonlewis@google.com>
---
 drivers/perf/arm_pmu.c       |  9 +++++++--
 drivers/perf/arm_pmuv3.c     | 28 +++++++++++++++++-----------
 include/linux/perf/arm_pmu.h |  1 +
 3 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 1150695653892..b1851d1c594b1 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -408,9 +408,11 @@ validate_group(struct perf_event *event)
 
 	/*
 	 * Initialise the fake PMU. We only need to populate the
-	 * used_mask for the purposes of validation.
+	 * used_mask and cntr_mask for the purposes of validation.
 	 */
 	memset(&fake_pmu.used_mask, 0, sizeof(fake_pmu.used_mask));
+	bitmap_copy(fake_pmu.cntr_mask, to_arm_pmu(event->pmu)->cntr_mask,
+		    ARMPMU_MAX_HWEVENTS);
 
 	if (!validate_event(event->pmu, &fake_pmu, leader))
 		return -EINVAL;
@@ -717,6 +719,7 @@ bool arm_pmu_irq_is_nmi(void)
 static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct arm_pmu *pmu = hlist_entry_safe(node, struct arm_pmu, node);
+	struct pmu_hw_events *cpuc = per_cpu_ptr(pmu->hw_events, cpu);
 	int irq;
 
 	if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
@@ -724,6 +727,8 @@ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
 	if (pmu->reset)
 		pmu->reset(pmu);
 
+	bitmap_copy(cpuc->cntr_mask, pmu->cntr_mask, ARMPMU_MAX_HWEVENTS);
+
 	irq = armpmu_get_cpu_irq(pmu, cpu);
 	if (irq)
 		per_cpu(cpu_irq_ops, cpu)->enable_pmuirq(irq);
@@ -753,7 +758,7 @@ static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd)
 	struct perf_event *event;
 	int idx;
 
-	for_each_set_bit(idx, armpmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
+	for_each_set_bit(idx, hw_events->cntr_mask, ARMPMU_MAX_HWEVENTS) {
 		event = hw_events->events[idx];
 		if (!event)
 			continue;
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 4a6c1f3bcea1f..973d4abcb3a6e 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -813,7 +813,7 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
 		write_pmuacr(mask);
 	} else {
 		/* Clear any unused counters to avoid leaking their contents */
-		for_each_andnot_bit(i, cpu_pmu->cntr_mask, cpuc->used_mask,
+		for_each_andnot_bit(i, cpuc->cntr_mask, cpuc->used_mask,
 				    ARMPMU_MAX_HWEVENTS) {
 			if (i == ARMV8_PMU_CYCLE_IDX)
 				write_pmccntr(0);
@@ -917,7 +917,7 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	 * to prevent skews in group events.
 	 */
 	armv8pmu_stop(cpu_pmu);
-	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
+	for_each_set_bit(idx, cpuc->cntr_mask, ARMPMU_MAX_HWEVENTS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
@@ -953,20 +953,18 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	return IRQ_HANDLED;
 }
 
-static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc,
-				    struct arm_pmu *cpu_pmu)
+static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc)
 {
 	int idx;
 
-	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
+	for_each_set_bit(idx, cpuc->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
 		if (!test_and_set_bit(idx, cpuc->used_mask))
 			return idx;
 	}
 	return -EAGAIN;
 }
 
-static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
-				   struct arm_pmu *cpu_pmu)
+static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc)
 {
 	int idx;
 
@@ -974,7 +972,7 @@ static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
 	 * Chaining requires two consecutive event counters, where
 	 * the lower idx must be even.
 	 */
-	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
+	for_each_set_bit(idx, cpuc->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
 		if (!(idx & 0x1))
 			continue;
 		if (!test_and_set_bit(idx, cpuc->used_mask)) {
@@ -1042,7 +1040,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	 */
 	if ((evtype == ARMV8_PMUV3_PERFCTR_INST_RETIRED) &&
 	    !armv8pmu_event_get_threshold(&event->attr) &&
-	    test_bit(ARMV8_PMU_INSTR_IDX, cpu_pmu->cntr_mask) &&
+	    test_bit(ARMV8_PMU_INSTR_IDX, cpuc->cntr_mask) &&
 	    !armv8pmu_event_want_user_access(event)) {
 		if (!test_and_set_bit(ARMV8_PMU_INSTR_IDX, cpuc->used_mask))
 			return ARMV8_PMU_INSTR_IDX;
@@ -1052,9 +1050,9 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	 * Otherwise use events counters
 	 */
 	if (armv8pmu_event_is_chained(event))
-		return	armv8pmu_get_chain_idx(cpuc, cpu_pmu);
+		return armv8pmu_get_chain_idx(cpuc);
 	else
-		return armv8pmu_get_single_idx(cpuc, cpu_pmu);
+		return armv8pmu_get_single_idx(cpuc);
 }
 
 static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc,
@@ -1426,6 +1424,7 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
 		.present = false,
 	};
 	int ret;
+	int cpu;
 
 	ret = smp_call_function_any(&cpu_pmu->supported_cpus,
 				    __armv8pmu_probe_pmu,
@@ -1441,6 +1440,13 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
 		if (ret)
 			return ret;
 	}
+
+	for_each_possible_cpu(cpu) {
+		struct pmu_hw_events *cpuc = per_cpu_ptr(cpu_pmu->hw_events, cpu);
+
+		bitmap_copy(cpuc->cntr_mask, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS);
+	}
+
 	return 0;
 }
 
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 02d2c7f45b527..be1e345e99a77 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -62,6 +62,7 @@ struct pmu_hw_events {
 	 * an event. A 0 means that the counter can be used.
 	 */
 	DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS);
+	DECLARE_BITMAP(cntr_mask, ARMPMU_MAX_HWEVENTS);
 
 	/*
 	 * When using percpu IRQs, we need a percpu dev_id. Place it here as we
-- 
2.56.1.708.g77570a6a1d-goog


  parent reply	other threads:[~2026-11-19 18:52 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-19 18:51 [PATCH v10 00/33] ARM64 PMU Partitioning Colton Lewis
2026-11-19 18:51 ` [PATCH v10 01/33] arm64: cpufeature: Add cpucap for HPMN0 Colton Lewis
2026-11-19 18:51 ` [PATCH v10 02/33] KVM: arm64: Reorganize PMU includes Colton Lewis
2026-11-19 18:51 ` [PATCH v10 03/33] KVM: arm64: Reorganize PMU functions Colton Lewis
2026-11-19 18:51 ` [PATCH v10 04/33] KVM: arm64: Use nr_pmu_counters in kvm_pmu_implemented_counter_mask() Colton Lewis
2026-11-19 18:51 ` [PATCH v10 05/33] KVM: arm64: Ignore HPMN for userspace PMU register access Colton Lewis
2026-11-19 18:51 ` [PATCH v10 06/33] perf: arm_pmuv3: Generalize counter bitmasks Colton Lewis
2026-11-19 18:51 ` Colton Lewis [this message]
2026-11-19 18:51 ` [PATCH v10 08/33] perf: arm_pmuv3: Check cntr_mask before using pmccntr Colton Lewis
2026-11-19 18:51 ` [PATCH v10 09/33] perf: arm_pmuv3: Allocate counter indices from high to low Colton Lewis
2026-11-19 18:51 ` [PATCH v10 10/33] perf: arm_pmuv3: Expose number of general-purpose counters in sysfs Colton Lewis
2026-11-19 18:51 ` [PATCH v10 11/33] KVM: arm64: Add initial scaffolding for Partitioned PMU Colton Lewis
2026-11-19 18:51 ` [PATCH v10 12/33] KVM: arm64: Set up FGT " Colton Lewis
2026-11-19 18:51 ` [PATCH v10 13/33] KVM: arm64: Make __vcpu_rmw_sys_reg() atomic Colton Lewis
2026-11-19 18:51 ` [PATCH v10 14/33] KVM: arm64: Add Partitioned PMU register trap handlers Colton Lewis
2026-11-19 18:51 ` [PATCH v10 15/33] KVM: arm64: Construct mdcr_el2 in a local variable in kvm_arm_setup_mdcr_el2() Colton Lewis
2026-11-19 18:51 ` [PATCH v10 16/33] KVM: arm64: Set up MDCR_EL2 to handle a Partitioned PMU Colton Lewis
2026-11-19 18:51 ` [PATCH v10 17/33] KVM: arm64: Context swap Partitioned PMU guest registers Colton Lewis
2026-11-19 18:52 ` [PATCH v10 18/33] KVM: arm64: Enforce PMU event filter at vcpu_load() Colton Lewis
2026-11-19 18:52 ` [PATCH v10 19/33] perf: Add perf_pmu_resched_update() Colton Lewis
2026-11-19 18:52 ` [PATCH v10 20/33] perf/core: Prioritize kernel-owned pinned events when scheduling groups Colton Lewis
2026-11-19 18:52 ` [PATCH v10 21/33] KVM: arm64: Allow kvm_vcpu_pmu_resync_el0() to resync filters in process context Colton Lewis
2026-11-19 18:52 ` [PATCH v10 22/33] KVM: arm64: Apply dynamic guest counter reservations Colton Lewis
2026-11-19 18:52 ` [PATCH v10 23/33] KVM: arm64: Implement lazy PMU context swaps Colton Lewis
2026-11-19 18:52 ` [PATCH v10 24/33] perf: arm_pmuv3: Handle IRQs for Partitioned PMU guest counters Colton Lewis
2026-11-19 18:52 ` [PATCH v10 25/33] KVM: arm64: Detect overflows for the Partitioned PMU Colton Lewis
2026-11-19 18:52 ` [PATCH v10 26/33] KVM: arm64: Multiplex PMCR_EL0.E and MDCR_EL2.HPME for sub-partitioned L1 Colton Lewis
2026-11-19 18:52 ` [PATCH v10 27/33] KVM: arm64: Emulate mismatched LP and HLP overflow widths " Colton Lewis
2026-11-19 18:52 ` [PATCH v10 28/33] KVM: arm64: Emulate trapped PMSWINC_EL0 writes for Partitioned PMU Colton Lewis
2026-11-19 18:52 ` [PATCH v10 29/33] KVM: arm64: Forward FGT traps for PMXEVTYPER_EL0 and PMXEVCNTR_EL0 Colton Lewis
2026-11-19 18:52 ` [PATCH v10 30/33] KVM: arm64: Support zero event counters on Partitioned PMU without HPMN0 Colton Lewis
2026-11-19 18:52 ` [PATCH v10 31/33] KVM: arm64: Add vCPU device attr to partition the PMU Colton Lewis
2026-11-19 18:52 ` [PATCH v10 32/33] KVM: selftests: Add find_bit to KVM library Colton Lewis
2026-11-19 18:52 ` [PATCH v10 33/33] KVM: arm64: selftests: Add test case for Partitioned PMU Colton Lewis

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=20261119185215.632334-8-coltonlewis@google.com \
    --to=coltonlewis@google.com \
    --cc=alexandru.elisei@arm.com \
    --cc=catalin.marinas@arm.com \
    --cc=corbet@lwn.net \
    --cc=fuad.tabba@linux.dev \
    --cc=gankulkarni@os.amperecomputing.com \
    --cc=james.clark@linaro.org \
    --cc=joey.gouly@arm.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=mark.rutland@arm.com \
    --cc=maz@kernel.org \
    --cc=mingo@redhat.com \
    --cc=mizhang@google.com \
    --cc=oupton@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=skhan@linuxfoundation.org \
    --cc=suzuki.poulose@arm.com \
    --cc=will@kernel.org \
    --cc=yuzenghui@huawei.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®