Re: [RFC PATCH v3 5/8] KVM: arm64: Introduce module param to partition the PMU

Colton Lewis coltonlewis@google.com writes:

For PMUv3, the register MDCR_EL2.HPMN partitiones the PMU counters into two ranges where counters 0..HPMN-1 are accessible by EL1 and, if allowed, EL0 while counters HPMN..N are only accessible by EL2.

Introduce a module parameter in KVM to set this register. The name reserved_host_counters reflects the intent to reserve some counters for the host so the guest may eventually be allowed direct access to a subset of PMU functionality for increased performance.

Track HPMN and whether the pmu is partitioned in struct arm_pmu because both KVM and the PMUv3 driver will need to know that to handle guests correctly.

Due to the difficulty this feature would create for the driver running at EL1 on the host, partitioning is only allowed in VHE mode. Working on nVHE mode would require a hypercall for every register access because the counters reserved for the host by HPMN are now only accessible to EL2.

The parameter is only configurable at boot time. Making the parameter configurable on a running system is dangerous due to the difficulty of knowing for sure no counters are in use anywhere so it is safe to reporgram HPMN.

Signed-off-by: Colton Lewis coltonlewis@google.com

arch/arm64/include/asm/kvm_pmu.h | 4 +++ arch/arm64/kvm/Makefile | 2 +- arch/arm64/kvm/debug.c | 9 ++++-- arch/arm64/kvm/pmu-part.c | 47 ++++++++++++++++++++++++++++++++ arch/arm64/kvm/pmu.c | 2 ++ include/linux/perf/arm_pmu.h | 2 ++ 6 files changed, 62 insertions(+), 4 deletions(-) create mode 100644 arch/arm64/kvm/pmu-part.c

diff --git a/arch/arm64/include/asm/kvm_pmu.h b/arch/arm64/include/asm/kvm_pmu.h index 613cddbdbdd8..174b7f376d95 100644 --- a/arch/arm64/include/asm/kvm_pmu.h +++ b/arch/arm64/include/asm/kvm_pmu.h @@ -22,6 +22,10 @@ bool kvm_set_pmuserenr(u64 val); void kvm_vcpu_pmu_resync_el0(void); void kvm_host_pmu_init(struct arm_pmu *pmu);

+u8 kvm_pmu_get_reserved_counters(void); +u8 kvm_pmu_hpmn(u8 nr_counters); +void kvm_pmu_partition(struct arm_pmu *pmu);

• #else

static inline void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) {} diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 3cf7adb2b503..065a6b804c84 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -25,7 +25,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \ vgic/vgic-its.o vgic/vgic-debug.o

-kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o pmu.o +kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o pmu-part.o pmu.o kvm-$(CONFIG_ARM64_PTR_AUTH) += pauth.o kvm-$(CONFIG_PTDUMP_STAGE2_DEBUGFS) += ptdump.o

diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 7fb1d9e7180f..b5ac5a213877 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -31,15 +31,18 @@ */ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) {

• u8 counters = *host_data_ptr(nr_event_counters);
• u8 hpmn = kvm_pmu_hpmn(counters);
• preempt_disable();

/* * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK * to disable guest access to the profiling and trace buffers */

• vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN,

• 			 *host_data_ptr(nr_event_counters));
  

• vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM |

• vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN, hpmn);
• vcpu->arch.mdcr_el2 |= (MDCR_EL2_HPMD |

• 		MDCR_EL2_TPM |
  	MDCR_EL2_TPMS |
  	MDCR_EL2_TTRF |
  	MDCR_EL2_TPMCR |
  

diff --git a/arch/arm64/kvm/pmu-part.c b/arch/arm64/kvm/pmu-part.c new file mode 100644 index 000000000000..e74fecc67e37 --- /dev/null +++ b/arch/arm64/kvm/pmu-part.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0-only +/*

• • Copyright (C) 2025 Google LLC
• • Author: Colton Lewis coltonlewis@google.com
• */

+#include <linux/kvm_host.h> +#include <linux/perf/arm_pmu.h>

+#include <asm/kvm_pmu.h>

+static u8 reserved_host_counters __read_mostly;

+module_param(reserved_host_counters, byte, 0); +MODULE_PARM_DESC(reserved_host_counters,

•  "Partition the PMU into host and guest counters");
  

+u8 kvm_pmu_get_reserved_counters(void) +{

• return reserved_host_counters;

+}

+u8 kvm_pmu_hpmn(u8 nr_counters) +{

• if (reserved_host_counters >= nr_counters) {

• if (this_cpu_has_cap(ARM64_HAS_HPMN0))
  

• 	return 0;
  

• return 1;
  

• }
• return nr_counters - reserved_host_counters;

+}

+void kvm_pmu_partition(struct arm_pmu *pmu) +{

• u8 nr_counters = *host_data_ptr(nr_event_counters);
• u8 hpmn = kvm_pmu_hpmn(nr_counters);
• if (hpmn < nr_counters) {

• pmu->hpmn = hpmn;
  

• pmu->partitioned = true;
  

• } else {

• pmu->hpmn = nr_counters;
  

• pmu->partitioned = false;
  

• }

+}

There should be a VHE check in here. I thought I wouldn't need it with moving MDCR_EL2 writes out of the driver but I just remembered there are two spots in patch 7 I still need to write that register.

diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index 85b5cb432c4f..7169c1a24dd6 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -243,6 +243,8 @@ void kvm_host_pmu_init(struct arm_pmu *pmu) entry->arm_pmu = pmu; list_add_tail(&entry->entry, &arm_pmus);

• kvm_pmu_partition(pmu);
• if (list_is_singular(&arm_pmus)) static_branch_enable(&kvm_arm_pmu_available);

diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 35c3a85bee43..ee4fc2e26bff 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -125,6 +125,8 @@ struct arm_pmu {

/* Only to be used by ACPI probing code */ unsigned long acpi_cpuid;

• u8 hpmn; /* MDCR_EL2.HPMN: counter partition pivot */
• bool partitioned; };

#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))

2.48.1.601.g30ceb7b040-goog