[PATCH v3 36/52] KVM: PPC: Book3S HV P9: Demand fault EBB facility registers

[Nicholas Piggin]

Use HFSCR facility disabling to implement demand faulting for EBB, with
a hysteresis counter similar to the load_fp etc counters in context
switching that implement the equivalent demand faulting for userspace
facilities.

This speeds up guest entry/exit by avoiding the register save/restore
when a guest is not frequently using them. When a guest does use them
often, there will be some additional demand fault overhead, but these
are not commonly used facilities.

Reviewed-by: Fabiano Rosas <farosas at linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---
 arch/powerpc/include/asm/kvm_host.h   |  1 +
 arch/powerpc/kvm/book3s_hv.c          | 16 +++++++++++++--
 arch/powerpc/kvm/book3s_hv_p9_entry.c | 28 +++++++++++++++++++++------
 3 files changed, 37 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c5fc4d016695..9c63eff35812 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -579,6 +579,7 @@ struct kvm_vcpu_arch {
 	ulong cfar;
 	ulong ppr;
 	u32 pspb;
+	u8 load_ebb;
 	ulong fscr;
 	ulong shadow_fscr;
 	ulong ebbhr;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6fb941aa77f1..070469867bf5 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1436,6 +1436,16 @@ static int kvmppc_pmu_unavailable(struct kvm_vcpu *vcpu)
 	return RESUME_GUEST;
 }
 
+static int kvmppc_ebb_unavailable(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.hfscr_permitted & HFSCR_EBB))
+		return EMULATE_FAIL;
+
+	vcpu->arch.hfscr |= HFSCR_EBB;
+
+	return RESUME_GUEST;
+}
+
 static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 				 struct task_struct *tsk)
 {
@@ -1727,6 +1737,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 				r = kvmppc_emulate_doorbell_instr(vcpu);
 			if (cause == FSCR_PM_LG)
 				r = kvmppc_pmu_unavailable(vcpu);
+			if (cause == FSCR_EBB_LG)
+				r = kvmppc_ebb_unavailable(vcpu);
 		}
 		if (r == EMULATE_FAIL) {
 			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
@@ -2771,9 +2783,9 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	vcpu->arch.hfscr_permitted = vcpu->arch.hfscr;
 
 	/*
-	 * PM is demand-faulted so start with it clear.
+	 * PM, EBB is demand-faulted so start with it clear.
 	 */
-	vcpu->arch.hfscr &= ~HFSCR_PM;
+	vcpu->arch.hfscr &= ~(HFSCR_PM | HFSCR_EBB);
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index a23f09fa7d2d..929a7c336b09 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -232,9 +232,12 @@ static void load_spr_state(struct kvm_vcpu *vcpu,
 				struct p9_host_os_sprs *host_os_sprs)
 {
 	mtspr(SPRN_TAR, vcpu->arch.tar);
-	mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
-	mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
-	mtspr(SPRN_BESCR, vcpu->arch.bescr);
+
+	if (vcpu->arch.hfscr & HFSCR_EBB) {
+		mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
+		mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
+		mtspr(SPRN_BESCR, vcpu->arch.bescr);
+	}
 
 	if (cpu_has_feature(CPU_FTR_P9_TIDR))
 		mtspr(SPRN_TIDR, vcpu->arch.tid);
@@ -265,9 +268,22 @@ static void load_spr_state(struct kvm_vcpu *vcpu,
 static void store_spr_state(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.tar = mfspr(SPRN_TAR);
-	vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
-	vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
-	vcpu->arch.bescr = mfspr(SPRN_BESCR);
+
+	if (vcpu->arch.hfscr & HFSCR_EBB) {
+		vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
+		vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
+		vcpu->arch.bescr = mfspr(SPRN_BESCR);
+		/*
+		 * This is like load_fp in context switching, turn off the
+		 * facility after it wraps the u8 to try avoiding saving
+		 * and restoring the registers each partition switch.
+		 */
+		if (!vcpu->arch.nested) {
+			vcpu->arch.load_ebb++;
+			if (!vcpu->arch.load_ebb)
+				vcpu->arch.hfscr &= ~HFSCR_EBB;
+		}
+	}
 
 	if (cpu_has_feature(CPU_FTR_P9_TIDR))
 		vcpu->arch.tid = mfspr(SPRN_TIDR);
-- 
2.23.0