[PATCH v2 45/60] KVM: PPC: Book3S HV P9: Demand fault TM facility registers

[Nicholas Piggin]

Use HFSCR facility disabling to implement demand faulting for TM, 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          | 26 ++++++++++++++++++++------
 arch/powerpc/kvm/book3s_hv_p9_entry.c | 15 +++++++++++----
 3 files changed, 32 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c8d8bd90bf14..ef60f5cce251 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -581,6 +581,7 @@ struct kvm_vcpu_arch {
 	ulong ppr;
 	u32 pspb;
 	u8 load_ebb;
+	u8 load_tm;
 	ulong fscr;
 	ulong shadow_fscr;
 	ulong ebbhr;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 99d4fd84f0b2..2254101a7760 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1446,6 +1446,16 @@ static int kvmppc_ebb_unavailable(struct kvm_vcpu *vcpu)
 	return RESUME_GUEST;
 }
 
+static int kvmppc_tm_unavailable(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.hfscr_permitted & HFSCR_TM))
+		return EMULATE_FAIL;
+
+	vcpu->arch.hfscr |= HFSCR_TM;
+
+	return RESUME_GUEST;
+}
+
 static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 				 struct task_struct *tsk)
 {
@@ -1742,6 +1752,8 @@ XXX benchmark guest exits
 				r = kvmppc_pmu_unavailable(vcpu);
 			if (cause == FSCR_EBB_LG)
 				r = kvmppc_ebb_unavailable(vcpu);
+			if (cause == FSCR_TM_LG)
+				r = kvmppc_tm_unavailable(vcpu);
 		}
 		if (r == EMULATE_FAIL) {
 			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
@@ -2786,9 +2798,9 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	vcpu->arch.hfscr_permitted = vcpu->arch.hfscr;
 
 	/*
-	 * PM, EBB is demand-faulted so start with it clear.
+	 * PM, EBB, TM are demand-faulted so start with it clear.
 	 */
-	vcpu->arch.hfscr &= ~(HFSCR_PM | HFSCR_EBB);
+	vcpu->arch.hfscr &= ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM);
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
@@ -3858,8 +3870,9 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns
 		msr |= MSR_VEC;
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr |= MSR_VSX;
-	if (cpu_has_feature(CPU_FTR_TM) ||
-	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+	if ((cpu_has_feature(CPU_FTR_TM) ||
+	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) &&
+			(vcpu->arch.hfscr & HFSCR_TM))
 		msr |= MSR_TM;
 	msr = msr_check_and_set(msr);
 
@@ -4575,8 +4588,9 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 		msr |= MSR_VEC;
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr |= MSR_VSX;
-	if (cpu_has_feature(CPU_FTR_TM) ||
-	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+	if ((cpu_has_feature(CPU_FTR_TM) ||
+	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) &&
+			(vcpu->arch.hfscr & HFSCR_TM))
 		msr |= MSR_TM;
 	msr = msr_check_and_set(msr);
 
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index d196642061aa..ae5832a0836f 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -309,7 +309,7 @@ bool load_vcpu_state(struct kvm_vcpu *vcpu,
 		if (MSR_TM_ACTIVE(guest_msr)) {
 			kvmppc_restore_tm_hv(vcpu, guest_msr, true);
 			ret = true;
-		} else {
+		} else if (vcpu->arch.hfscr & HFSCR_TM) {
 			mtspr(SPRN_TEXASR, vcpu->arch.texasr);
 			mtspr(SPRN_TFHAR, vcpu->arch.tfhar);
 			mtspr(SPRN_TFIAR, vcpu->arch.tfiar);
@@ -343,10 +343,16 @@ void store_vcpu_state(struct kvm_vcpu *vcpu)
 		unsigned long guest_msr = vcpu->arch.shregs.msr;
 		if (MSR_TM_ACTIVE(guest_msr)) {
 			kvmppc_save_tm_hv(vcpu, guest_msr, true);
-		} else {
+		} else if (vcpu->arch.hfscr & HFSCR_TM) {
 			vcpu->arch.texasr = mfspr(SPRN_TEXASR);
 			vcpu->arch.tfhar = mfspr(SPRN_TFHAR);
 			vcpu->arch.tfiar = mfspr(SPRN_TFIAR);
+
+			if (!vcpu->arch.nested) {
+				vcpu->arch.load_tm++; /* see load_ebb comment */
+				if (!vcpu->arch.load_tm)
+					vcpu->arch.hfscr &= ~HFSCR_TM;
+			}
 		}
 	}
 }
@@ -637,8 +643,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 		msr |= MSR_VEC;
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr |= MSR_VSX;
-	if (cpu_has_feature(CPU_FTR_TM) ||
-	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+	if ((cpu_has_feature(CPU_FTR_TM) ||
+	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) &&
+			(vcpu->arch.hfscr & HFSCR_TM))
 		msr |= MSR_TM;
 	msr = msr_check_and_set(msr);
 	/* Save MSR for restore. This is after hard disable, so EE is clear. */
-- 
2.23.0