Merge branch 'topic/ppc-kvm' into next

Merge our topic branch containing KVM related patches.

8 files changed, 107 insertions, 39 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 4f527d09c92b..3e1e2a698c9e 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -302,6 +302,7 @@ void kvmhv_nested_exit(void);
 void kvmhv_vm_nested_init(struct kvm *kvm);
 long kvmhv_set_partition_table(struct kvm_vcpu *vcpu);
 long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu);
+void kvmhv_flush_lpid(u64 lpid);
 void kvmhv_set_ptbl_entry(u64 lpid, u64 dw0, u64 dw1);
 void kvmhv_release_all_nested(struct kvm *kvm);
 long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
@@ -593,13 +594,17 @@ static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
 
 
 KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64, KVMPPC_GSID_VTB)
-KVMPPC_BOOK3S_VCORE_ACCESSOR(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
 KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(arch_compat, 32, KVMPPC_GSID_LOGICAL_PVR)
 KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(lpcr, 64, KVMPPC_GSID_LPCR)
+KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
+
+static inline u64 kvmppc_get_tb_offset(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.vcore->tb_offset;
+}
 
 static inline u64 kvmppc_get_dec_expires(struct kvm_vcpu *vcpu)
 {
-	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_TB_OFFSET) < 0);
 	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB) < 0);
 	return vcpu->arch.dec_expires;
 }
@@ -607,7 +612,6 @@ static inline u64 kvmppc_get_dec_expires(struct kvm_vcpu *vcpu)
 static inline void kvmppc_set_dec_expires(struct kvm_vcpu *vcpu, u64 val)
 {
 	vcpu->arch.dec_expires = val;
-	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_TB_OFFSET) < 0);
 	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB);
 }
 
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 2477021bff54..d8729ec81ca0 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -682,6 +682,7 @@ void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *i
 int kvmhv_nestedv2_flush_vcpu(struct kvm_vcpu *vcpu, u64 time_limit);
 int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1);
 int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu);
+int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa);
 
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 6cd20ab9e94e..8acec144120e 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -302,11 +302,11 @@ static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
 
 	switch (priority) {
 	case BOOK3S_IRQPRIO_DECREMENTER:
-		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
+		deliver = !kvmhv_is_nestedv2() && (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
-		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
+		deliver = !kvmhv_is_nestedv2() && (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
 	case BOOK3S_IRQPRIO_SYSTEM_RESET:
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 175a8eb2681f..4a1abb9f7c05 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -40,6 +40,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	unsigned long quadrant, ret = n;
 	bool is_load = !!to;
 
+	if (kvmhv_is_nestedv2())
+		return H_UNSUPPORTED;
+
 	/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
 	if (kvmhv_on_pseries())
 		return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
@@ -97,7 +100,7 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 					  void *to, void *from, unsigned long n)
 {
 	int lpid = vcpu->kvm->arch.lpid;
-	int pid = kvmppc_get_pid(vcpu);
+	int pid;
 
 	/* This would cause a data segment intr so don't allow the access */
 	if (eaddr & (0x3FFUL << 52))
@@ -110,6 +113,8 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* If accessing quadrant 3 then pid is expected to be 0 */
 	if (((eaddr >> 62) & 0x3) == 0x3)
 		pid = 0;
+	else
+		pid = kvmppc_get_pid(vcpu);
 
 	eaddr &= ~(0xFFFUL << 52);
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1ed6ec140701..e48126a59ba7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -650,7 +650,8 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 	return err;
 }
 
-static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
+static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap,
+			       struct kvmppc_vpa *old_vpap)
 {
 	struct kvm *kvm = vcpu->kvm;
 	void *va;
@@ -690,9 +691,8 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
 		kvmppc_unpin_guest_page(kvm, va, gpa, false);
 		va = NULL;
 	}
-	if (vpap->pinned_addr)
-		kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
-					vpap->dirty);
+	*old_vpap = *vpap;
+
 	vpap->gpa = gpa;
 	vpap->pinned_addr = va;
 	vpap->dirty = false;
@@ -702,6 +702,9 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
 
 static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
+	struct kvmppc_vpa old_vpa = { 0 };
+
 	if (!(vcpu->arch.vpa.update_pending ||
 	      vcpu->arch.slb_shadow.update_pending ||
 	      vcpu->arch.dtl.update_pending))
@@ -709,17 +712,34 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	if (vcpu->arch.vpa.update_pending) {
-		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
-		if (vcpu->arch.vpa.pinned_addr)
+		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa, &old_vpa);
+		if (old_vpa.pinned_addr) {
+			if (kvmhv_is_nestedv2())
+				kvmhv_nestedv2_set_vpa(vcpu, ~0ull);
+			kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+						old_vpa.dirty);
+		}
+		if (vcpu->arch.vpa.pinned_addr) {
 			init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
+			if (kvmhv_is_nestedv2())
+				kvmhv_nestedv2_set_vpa(vcpu, __pa(vcpu->arch.vpa.pinned_addr));
+		}
 	}
 	if (vcpu->arch.dtl.update_pending) {
-		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
+		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl, &old_vpa);
+		if (old_vpa.pinned_addr)
+			kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+						old_vpa.dirty);
 		vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
 		vcpu->arch.dtl_index = 0;
 	}
-	if (vcpu->arch.slb_shadow.update_pending)
-		kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
+	if (vcpu->arch.slb_shadow.update_pending) {
+		kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow, &old_vpa);
+		if (old_vpa.pinned_addr)
+			kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+						old_vpa.dirty);
+	}
+
 	spin_unlock(&vcpu->arch.vpa_update_lock);
 }
 
@@ -1597,7 +1617,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 	 * That can happen due to a bug, or due to a machine check
 	 * occurring at just the wrong time.
 	 */
-	if (__kvmppc_get_msr_hv(vcpu) & MSR_HV) {
+	if (!kvmhv_is_nestedv2() && (__kvmppc_get_msr_hv(vcpu) & MSR_HV)) {
 		printk(KERN_EMERG "KVM trap in HV mode!\n");
 		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
 			vcpu->arch.trap, kvmppc_get_pc(vcpu),
@@ -1688,7 +1708,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 	{
 		int i;
 
-		if (unlikely(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
+		if (!kvmhv_is_nestedv2() && unlikely(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
 			/*
 			 * Guest userspace executed sc 1. This can only be
 			 * reached by the P9 path because the old path
@@ -4084,6 +4104,8 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
 	if (rc < 0)
 		return -EINVAL;
 
+	kvmppc_gse_put_u64(io->vcpu_run_input, KVMPPC_GSID_LPCR, lpcr);
+
 	accumulate_time(vcpu, &vcpu->arch.in_guest);
 	rc = plpar_guest_run_vcpu(0, vcpu->kvm->arch.lpid, vcpu->vcpu_id,
 				  &trap, &i);
@@ -4736,13 +4758,19 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	if (!nested) {
 		kvmppc_core_prepare_to_enter(vcpu);
-		if (__kvmppc_get_msr_hv(vcpu) & MSR_EE) {
-			if (xive_interrupt_pending(vcpu))
+		if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
+			     &vcpu->arch.pending_exceptions) ||
+		    xive_interrupt_pending(vcpu)) {
+			/*
+			 * For nested HV, don't synthesize but always pass MER,
+			 * the L0 will be able to optimise that more
+			 * effectively than manipulating registers directly.
+			 */
+			if (!kvmhv_on_pseries() && (__kvmppc_get_msr_hv(vcpu) & MSR_EE))
 				kvmppc_inject_interrupt_hv(vcpu,
-						BOOK3S_INTERRUPT_EXTERNAL, 0);
-		} else if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
-			     &vcpu->arch.pending_exceptions)) {
-			lpcr |= LPCR_MER;
+							   BOOK3S_INTERRUPT_EXTERNAL, 0);
+			else
+				lpcr |= LPCR_MER;
 		}
 	} else if (vcpu->arch.pending_exceptions ||
 		   vcpu->arch.doorbell_request ||
@@ -4806,7 +4834,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	 * entering a nested guest in which case the decrementer is now owned
 	 * by L2 and the L1 decrementer is provided in hdec_expires
 	 */
-	if (kvmppc_core_pending_dec(vcpu) &&
+	if (!kvmhv_is_nestedv2() && kvmppc_core_pending_dec(vcpu) &&
 			((tb < kvmppc_dec_expires_host_tb(vcpu)) ||
 			 (trap == BOOK3S_INTERRUPT_SYSCALL &&
 			  kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED)))
@@ -4949,7 +4977,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 		if (run->exit_reason == KVM_EXIT_PAPR_HCALL) {
 			accumulate_time(vcpu, &vcpu->arch.hcall);
 
-			if (WARN_ON_ONCE(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
+			if (!kvmhv_is_nestedv2() && WARN_ON_ONCE(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
 				/*
 				 * These should have been caught reflected
 				 * into the guest by now. Final sanity check:
@@ -5691,10 +5719,12 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 			kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
 	}
 
-	if (kvmhv_is_nestedv2())
+	if (kvmhv_is_nestedv2()) {
+		kvmhv_flush_lpid(kvm->arch.lpid);
 		plpar_guest_delete(0, kvm->arch.lpid);
-	else
+	} else {
 		kvmppc_free_lpid(kvm->arch.lpid);
+	}
 
 	kvmppc_free_pimap(kvm);
 }
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 3b658b8696bc..5c375ec1a3c6 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -503,7 +503,7 @@ void kvmhv_nested_exit(void)
 	}
 }
 
-static void kvmhv_flush_lpid(u64 lpid)
+void kvmhv_flush_lpid(u64 lpid)
 {
 	long rc;
 
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index fd3c4f2d9480..5378eb40b162 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -856,6 +856,35 @@ free_gsb:
 EXPORT_SYMBOL_GPL(kvmhv_nestedv2_set_ptbl_entry);
 
 /**
+ * kvmhv_nestedv2_set_vpa() - register L2 VPA with L0
+ * @vcpu: vcpu
+ * @vpa: L1 logical real address
+ */
+int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa)
+{
+	struct kvmhv_nestedv2_io *io;
+	struct kvmppc_gs_buff *gsb;
+	int rc = 0;
+
+	io = &vcpu->arch.nestedv2_io;
+	gsb = io->vcpu_run_input;
+
+	kvmppc_gsb_reset(gsb);
+	rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_VPA, vpa);
+	if (rc < 0)
+		goto out;
+
+	rc = kvmppc_gsb_send(gsb, 0);
+	if (rc < 0)
+		pr_err("KVM-NESTEDv2: couldn't register the L2 VPA (rc=%d)\n", rc);
+
+out:
+	kvmppc_gsb_reset(gsb);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(kvmhv_nestedv2_set_vpa);
+
+/**
  * kvmhv_nestedv2_parse_output() - receive values from H_GUEST_RUN_VCPU output
  * @vcpu: vcpu
  *
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 077fd88a0b68..ec60c7979718 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -93,7 +93,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 
 	emulated = EMULATE_FAIL;
 	vcpu->arch.regs.msr = kvmppc_get_msr(vcpu);
-	kvmhv_nestedv2_reload_ptregs(vcpu, &vcpu->arch.regs);
 	if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) {
 		int type = op.type & INSTR_TYPE_MASK;
 		int size = GETSIZE(op.type);
@@ -112,7 +111,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 						op.reg, size, !instr_byte_swap);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
 		}
@@ -132,7 +131,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 					     KVM_MMIO_REG_FPR|op.reg, size, 1);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
 #endif
@@ -224,16 +223,17 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 			break;
 		}
 #endif
-		case STORE:
-			/* if need byte reverse, op.val has been reversed by
-			 * analyse_instr().
-			 */
-			emulated = kvmppc_handle_store(vcpu, op.val, size, 1);
+		case STORE: {
+			int instr_byte_swap = op.type & BYTEREV;
+
+			emulated = kvmppc_handle_store(vcpu, kvmppc_get_gpr(vcpu, op.reg),
+						       size, !instr_byte_swap);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
+		}
 #ifdef CONFIG_PPC_FPU
 		case STORE_FP:
 			if (kvmppc_check_fp_disabled(vcpu))
@@ -254,7 +254,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 					kvmppc_get_fpr(vcpu, op.reg), size, 1);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
 #endif
@@ -358,7 +358,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	}
 
 	trace_kvm_ppc_instr(ppc_inst_val(inst), kvmppc_get_pc(vcpu), emulated);
-	kvmhv_nestedv2_mark_dirty_ptregs(vcpu, &vcpu->arch.regs);
 
 	/* Advance past emulated instruction. */
 	if (emulated != EMULATE_FAIL)