KVM: arm64: vgic-v4: Make the doorbell request robust w.r.t preemption

Xiang reports that VMs occasionally fail to boot on GICv4.1 systems when
running a preemptible kernel, as it is possible that a vCPU is blocked
without requesting a doorbell interrupt.

The issue is that any preemption that occurs between vgic_v4_put() and
schedule() on the block path will mark the vPE as nonresident and *not*
request a doorbell irq. This occurs because when the vcpu thread is
resumed on its way to block, vcpu_load() will make the vPE resident
again. Once the vcpu actually blocks, we don't request a doorbell
anymore, and the vcpu won't be woken up on interrupt delivery.

Fix it by tracking that we're entering WFI, and key the doorbell
request on that flag. This allows us not to make the vPE resident
when going through a preempt/schedule cycle, meaning we don't lose
any state.

Cc: stable@vger.kernel.org
Fixes: 8e01d9a396e6 ("KVM: arm64: vgic-v4: Move the GICv4 residency flow to be driven by vcpu_load/put")
Reported-by: Xiang Chen <chenxiang66@hisilicon.com>
Suggested-by: Zenghui Yu <yuzenghui@huawei.com>
Tested-by: Xiang Chen <chenxiang66@hisilicon.com>
Co-developed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20230713070657.3873244-1-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

4 files changed, 12 insertions, 5 deletions

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 8b6096753740..d3dd05bbfe23 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -727,6 +727,8 @@ struct kvm_vcpu_arch {
 #define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))
 /* PMUSERENR for the guest EL0 is on physical CPU */
 #define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(6))
+/* WFI instruction trapped */
+#define IN_WFI			__vcpu_single_flag(sflags, BIT(7))
 
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a402ea5511f3..72dc53a75d1c 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -718,13 +718,15 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu)
 	 */
 	preempt_disable();
 	kvm_vgic_vmcr_sync(vcpu);
-	vgic_v4_put(vcpu, true);
+	vcpu_set_flag(vcpu, IN_WFI);
+	vgic_v4_put(vcpu);
 	preempt_enable();
 
 	kvm_vcpu_halt(vcpu);
 	vcpu_clear_flag(vcpu, IN_WFIT);
 
 	preempt_disable();
+	vcpu_clear_flag(vcpu, IN_WFI);
 	vgic_v4_load(vcpu);
 	preempt_enable();
 }
@@ -792,7 +794,7 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) {
 			/* The distributor enable bits were changed */
 			preempt_disable();
-			vgic_v4_put(vcpu, false);
+			vgic_v4_put(vcpu);
 			vgic_v4_load(vcpu);
 			preempt_enable();
 		}
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index c3b8e132d599..3dfc8b84e03e 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -749,7 +749,7 @@ void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	WARN_ON(vgic_v4_put(vcpu, false));
+	WARN_ON(vgic_v4_put(vcpu));
 
 	vgic_v3_vmcr_sync(vcpu);
 
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index c1c28fe680ba..339a55194b2c 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -336,14 +336,14 @@ void vgic_v4_teardown(struct kvm *kvm)
 	its_vm->vpes = NULL;
 }
 
-int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db)
+int vgic_v4_put(struct kvm_vcpu *vcpu)
 {
 	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
 
 	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	return its_make_vpe_non_resident(vpe, need_db);
+	return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI));
 }
 
 int vgic_v4_load(struct kvm_vcpu *vcpu)
@@ -354,6 +354,9 @@ int vgic_v4_load(struct kvm_vcpu *vcpu)
 	if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident)
 		return 0;
 
+	if (vcpu_get_flag(vcpu, IN_WFI))
+		return 0;
+
 	/*
 	 * Before making the VPE resident, make sure the redistributor
 	 * corresponding to our current CPU expects us here. See the