KVM: arm64: Exclude host_debug_data from vcpu_arch

Keeping host_debug_state on a per-vcpu basis is completely
pointless. The lifetime of this data is only that of the inner
run-loop, which means it is never accessed outside of the core
EL2 code.

Move the structure into kvm_host_data, and save over 500 bytes
per vcpu.
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/kvm_host.h

@@ -543,6 +543,19 @@ struct kvm_cpu_context {
  */
 struct kvm_host_data {
 	struct kvm_cpu_context host_ctxt;
+
+	/*
+	 * host_debug_state contains the host registers which are
+	 * saved and restored during world switches.
+	 */
+	 struct {
+		/* {Break,watch}point registers */
+		struct kvm_guest_debug_arch regs;
+		/* Statistical profiling extension */
+		u64 pmscr_el1;
+		/* Self-hosted trace */
+		u64 trfcr_el1;
+	} host_debug_state;
 };
 
 struct kvm_host_psci_config {
@@ -638,11 +651,10 @@ struct kvm_vcpu_arch {
 	 * We maintain more than a single set of debug registers to support
 	 * debugging the guest from the host and to maintain separate host and
 	 * guest state during world switches. vcpu_debug_state are the debug
-	 * registers of the vcpu as the guest sees them.  host_debug_state are
-	 * the host registers which are saved and restored during
-	 * world switches. external_debug_state contains the debug
-	 * values we want to debug the guest. This is set via the
-	 * KVM_SET_GUEST_DEBUG ioctl.
+	 * registers of the vcpu as the guest sees them.
+	 *
+	 * external_debug_state contains the debug values we want to debug the
+	 * guest. This is set via the KVM_SET_GUEST_DEBUG ioctl.
 	 *
 	 * debug_ptr points to the set of debug registers that should be loaded
 	 * onto the hardware when running the guest.
@@ -654,15 +666,6 @@ struct kvm_vcpu_arch {
 	struct user_fpsimd_state *host_fpsimd_state;	/* hyp VA */
 	struct task_struct *parent_task;
 
-	struct {
-		/* {Break,watch}point registers */
-		struct kvm_guest_debug_arch regs;
-		/* Statistical profiling extension */
-		u64 pmscr_el1;
-		/* Self-hosted trace */
-		u64 trfcr_el1;
-	} host_debug_state;
-
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
 	struct arch_timer_cpu timer_cpu;

arch/arm64/kvm/hyp/include/hyp/debug-sr.h

@@ -137,7 +137,7 @@ static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 
 	host_ctxt = host_data_ptr(host_ctxt);
 	guest_ctxt = &vcpu->arch.ctxt;
-	host_dbg = &vcpu->arch.host_debug_state.regs;
+	host_dbg = host_data_ptr(host_debug_state.regs);
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
 	__debug_save_state(host_dbg, host_ctxt);
@@ -156,7 +156,7 @@ static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 
 	host_ctxt = host_data_ptr(host_ctxt);
 	guest_ctxt = &vcpu->arch.ctxt;
-	host_dbg = &vcpu->arch.host_debug_state.regs;
+	host_dbg = host_data_ptr(host_debug_state.regs);
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
 	__debug_save_state(guest_dbg, guest_ctxt);

arch/arm64/kvm/hyp/nvhe/debug-sr.c

@@ -83,10 +83,10 @@ void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
 	/* Disable and flush SPE data generation */
 	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE))
-		__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+		__debug_save_spe(host_data_ptr(host_debug_state.pmscr_el1));
 	/* Disable and flush Self-Hosted Trace generation */
 	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE))
-		__debug_save_trace(&vcpu->arch.host_debug_state.trfcr_el1);
+		__debug_save_trace(host_data_ptr(host_debug_state.trfcr_el1));
 }
 
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
@@ -97,9 +97,9 @@ void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
 void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE))
-		__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+		__debug_restore_spe(*host_data_ptr(host_debug_state.pmscr_el1));
 	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE))
-		__debug_restore_trace(vcpu->arch.host_debug_state.trfcr_el1);
+		__debug_restore_trace(*host_data_ptr(host_debug_state.trfcr_el1));
 }
 
 void __debug_switch_to_host(struct kvm_vcpu *vcpu)