Received-SPF: pass (google.com: domain of linux-kernel+bounces-43530-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Date: Mon, 29 Jan 2024 21:39:17 +0000
Precedence: bulk
Mime-Version: 1.0
Message-ID: <20240129213918.3124494-1-coltonlewis@google.com>
Subject: [PATCH] KVM: arm64: Add capability for unconditional WFx passthrough
From: Colton Lewis <coltonlewis@google.com>
To: kvm@vger.kernel.org
Cc: Marc Zyngier <maz@kernel.org>, Oliver Upton <oliver.upton@linux.dev>, 
	James Morse <james.morse@arm.com>, Suzuki K Poulose <suzuki.poulose@arm.com>, 
	Zenghui Yu <yuzenghui@huawei.com>, Catalin Marinas <catalin.marinas@arm.com>, 
	Will Deacon <will@kernel.org>, Paolo Bonzini <pbonzini@redhat.com>, 
	linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev, 
	linux-kernel@vger.kernel.org, Colton Lewis <coltonlewis@google.com>
Content-Type: text/plain; charset="UTF-8"

Add KVM_CAP_ARM_WFX_PASSTHROUGH capability to always allow WFE/WFI
instructions to run without trapping. Current behavior is to only
allow this if the vcpu is the only task running. This commit keeps the
old behavior when the capability is not set.

This allows userspace to set deterministic behavior and increase
efficiency for platforms with direct interrupt injection support.

The implementation adds a new flag
KVM_ARCH_FLAG_WFX_PASSTHROUGH_ENABLED to kvm.arch.flags.

Signed-off-by: Colton Lewis <coltonlewis@google.com>
---
 arch/arm64/include/asm/kvm_host.h | 2 ++
 arch/arm64/kvm/arm.c              | 7 ++++++-
 include/uapi/linux/kvm.h          | 1 +
 3 files changed, 9 insertions(+), 1 deletion(-)

This patch is based on v6.8-rc1
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 21c57b812569..e0d5ec2983fa 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -274,6 +274,8 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE		6
 	/* Initial ID reg values loaded */
 #define KVM_ARCH_FLAG_ID_REGS_INITIALIZED		7
+	/* Never trap WFE/WFI instructions */
+#define KVM_ARCH_FLAG_WFX_PASSTHROUGH_ENABLED		8
 	unsigned long flags;

 	/* VM-wide vCPU feature set */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a25265aca432..6d993991bd7a 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -116,6 +116,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		}
 		mutex_unlock(&kvm->slots_lock);
 		break;
+	case KVM_CAP_ARM_WFX_PASSTHROUGH:
+		r = 0;
+		set_bit(KVM_ARCH_FLAG_WFX_PASSTHROUGH_ENABLED, &kvm->arch.flags);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -456,7 +460,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
 		kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu);

-	if (single_task_running())
+	if (single_task_running() ||
+	    test_bit(KVM_ARCH_FLAG_WFX_PASSTHROUGH_ENABLED, &vcpu->kvm->arch.flags))
 		vcpu_clear_wfx_traps(vcpu);
 	else
 		vcpu_set_wfx_traps(vcpu);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index c3308536482b..7635b5cd2b3b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1155,6 +1155,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_MEMORY_ATTRIBUTES 233
 #define KVM_CAP_GUEST_MEMFD 234
 #define KVM_CAP_VM_TYPES 235
+#define KVM_CAP_ARM_WFX_PASSTHROUGH 236

 #ifdef KVM_CAP_IRQ_ROUTING

--
2.43.0.429.g432eaa2c6b-goog