From: Oliver Upton <oliver.upton@linux.dev>
To: kvmarm@lists.linux.dev
Cc: Marc Zyngier <maz@kernel.org>, James Morse <james.morse@arm.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
Zenghui Yu <yuzenghui@huawei.com>,
Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>,
Oliver Upton <oliver.upton@linux.dev>
Subject: [PATCH v2 12/12] KVM: arm64: nv: Reprogram PMU events affected by nested transition
Date: Tue, 27 Aug 2024 00:22:35 +0000 [thread overview]
Message-ID: <20240827002235.1753237-13-oliver.upton@linux.dev> (raw)
In-Reply-To: <20240827002235.1753237-1-oliver.upton@linux.dev>
Start reprogramming PMU events at nested boundaries now that everything
is in place to handle the EL2 event filter. Only repaint events where
the filter differs between EL1 and EL2 as a slight optimization.
PMU now 'works' for nested VMs, albeit slow.
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
arch/arm64/kvm/emulate-nested.c | 4 ++++
arch/arm64/kvm/pmu-emul.c | 24 ++++++++++++++++++++++++
include/kvm/arm_pmu.h | 3 +++
3 files changed, 31 insertions(+)
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index ae183dea79b7..6f748c4257f5 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -2411,6 +2411,8 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
kvm_arch_vcpu_load(vcpu, smp_processor_id());
preempt_enable();
+
+ kvm_pmu_reprogram_events(vcpu);
}
static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2,
@@ -2493,6 +2495,8 @@ static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2,
kvm_arch_vcpu_load(vcpu, smp_processor_id());
preempt_enable();
+ kvm_pmu_reprogram_events(vcpu);
+
return 1;
}
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 3dee669c0674..0cd0426892be 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -1180,3 +1180,27 @@ u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N);
}
+
+void kvm_pmu_reprogram_events(struct kvm_vcpu *vcpu)
+{
+ unsigned long mask;
+ int i;
+
+ if (!kvm_vcpu_has_pmu(vcpu))
+ return;
+
+ mask = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+ for_each_set_bit(i, &mask, 32) {
+ struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
+
+ /*
+ * We only need to reconfigure events where the filter is
+ * different at EL1 vs. EL2, as we're multiplexing the true EL1
+ * event filter bit for nested.
+ */
+ if (kvm_pmc_counts_at_el1(pmc) == kvm_pmc_counts_at_el2(pmc))
+ continue;
+
+ kvm_pmu_create_perf_event(pmc);
+ }
+}
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 25017e72c562..4e3f35b00bf8 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -97,6 +97,7 @@ int kvm_arm_set_default_pmu(struct kvm *kvm);
u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm);
u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu);
+void kvm_pmu_reprogram_events(struct kvm_vcpu *vcpu);
#else
struct kvm_pmu {
};
@@ -192,6 +193,8 @@ static inline u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
return 0;
}
+static inline void kvm_pmu_reprogram_events(struct kvm_vcpu *vcpu) {}
+
#endif
#endif
--
2.46.0.295.g3b9ea8a38a-goog
prev parent reply other threads:[~2024-08-27 0:23 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-27 0:22 [PATCH v2 00/12] KVM: arm64: nv: More complete support for FEAT_PMUv3 Oliver Upton
2024-08-27 0:22 ` [PATCH v2 01/12] KVM: arm64: Rename kvm_pmu_valid_counter_mask() Oliver Upton
2024-08-27 0:22 ` [PATCH v2 02/12] KVM: arm64: nv: Adjust range of accessible PMCs according to HPMN Oliver Upton
2024-08-27 0:22 ` [PATCH v2 03/12] KVM: arm64: nv: Rename BEHAVE_FORWARD_ANY Oliver Upton
2024-08-27 0:22 ` [PATCH v2 04/12] KVM: arm64: nv: Add support for describing traps that affect Host EL0 Oliver Upton
2024-08-27 16:24 ` Marc Zyngier
2024-08-27 0:22 ` [PATCH v2 05/12] KVM: arm64: nv: Reinject traps that take effect in " Oliver Upton
2024-08-27 0:22 ` [PATCH v2 06/12] KVM: arm64: nv: Honor MDCR_EL2.{TPM, TPMCR} " Oliver Upton
2024-08-27 0:22 ` [PATCH v2 07/12] KVM: arm64: nv: Allow coarse-grained trap combos to use complex traps Oliver Upton
2024-08-27 0:22 ` [PATCH v2 08/12] KVM: arm64: nv: Describe trap behaviour of MDCR_EL2.HPMN Oliver Upton
2024-08-27 0:22 ` [PATCH v2 09/12] KVM: arm64: nv: Advertise support for FEAT_HPMN0 Oliver Upton
2024-08-27 16:40 ` Marc Zyngier
2024-08-27 0:22 ` [PATCH v2 10/12] KVM: arm64: Add helpers to determine if PMC counts at a given EL Oliver Upton
2024-08-27 0:22 ` [PATCH v2 11/12] KVM: arm64: nv: Honor NSH filter when in hyp context Oliver Upton
2024-08-27 0:22 ` Oliver Upton [this message]
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=20240827002235.1753237-13-oliver.upton@linux.dev \
--to=oliver.upton@linux.dev \
--cc=gankulkarni@os.amperecomputing.com \
--cc=james.morse@arm.com \
--cc=kvmarm@lists.linux.dev \
--cc=maz@kernel.org \
--cc=suzuki.poulose@arm.com \
--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 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.