Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 97 insertions, 48 deletions

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 9026119542..074263429f 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -19,13 +19,11 @@ if VIRTUALIZATION
 
 config KVM
 	bool
-	select PREEMPT_NOTIFIERS
-	select HAVE_KVM_EVENTFD
+	select KVM_COMMON
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_VFIO
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
-	select INTERVAL_TREE
 
 config KVM_BOOK3S_HANDLER
 	bool
@@ -42,7 +40,7 @@ config KVM_BOOK3S_64_HANDLER
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 
 config KVM_BOOK3S_HV_POSSIBLE
 	bool
@@ -85,7 +83,7 @@ config KVM_BOOK3S_64_HV
 	tristate "KVM for POWER7 and later using hypervisor mode in host"
 	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select CMA
 	help
 	  Support running unmodified book3s_64 guest kernels in
@@ -194,7 +192,7 @@ config KVM_E500V2
 	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500v2 host processors.
@@ -211,7 +209,7 @@ config KVM_E500MC
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500MC/E5500/E6500 guest kernels in
 	  virtual machines on E500MC/E5500/E6500 host processors.
@@ -225,7 +223,6 @@ config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM && PPC_E500
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	help
@@ -238,7 +235,6 @@ config KVM_XICS
 	bool "KVM in-kernel XICS emulation"
 	depends on KVM_BOOK3S_64 && !KVM_MPIC
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	default y
 	help
 	  Include support for the XICS (eXternal Interrupt Controller
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 6cd20ab9e9..8acec14412 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 175a8eb268..4a1abb9f7c 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_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 14c6d7e318..b569ebaa59 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -20,6 +20,7 @@
 #include <linux/iommu.h>
 #include <linux/file.h>
 #include <linux/mm.h>
+#include <linux/rcupdate_wait.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index b5c6af0bef..0b921704da 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -672,7 +672,8 @@ 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;
@@ -712,9 +713,8 @@ 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;
@@ -724,6 +724,9 @@ 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))
@@ -731,17 +734,34 @@ 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);
 }
 
@@ -1619,7 +1639,7 @@ 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),
@@ -1710,7 +1730,7 @@ 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
@@ -4106,6 +4126,8 @@ 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);
@@ -4834,7 +4856,7 @@ 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)))
@@ -4977,7 +4999,7 @@ 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:
@@ -5719,10 +5741,12 @@ 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);
 }
@@ -6238,7 +6262,7 @@ static int kvmhv_svm_off(struct kvm *kvm)
 	}
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct kvm_memory_slot *memslot;
 		struct kvm_memslots *slots = __kvm_memslots(kvm, i);
 		int bkt;
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 3b658b8696..5c375ec1a3 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 f354af7e85..8e6f5355f0 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -872,6 +872,35 @@ 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/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 9118242063..5b92619a05 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -604,6 +604,7 @@ static void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
 	case PVR_POWER8:
 	case PVR_POWER8E:
 	case PVR_POWER8NVL:
+	case PVR_HX_C2000:
 	case PVR_POWER9:
 		vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
 			BOOK3S_HFLAG_NEW_TLBIE;
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 077fd88a0b..ec60c79797 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)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f6af752698..23407fbd73 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -528,7 +528,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
@@ -578,7 +577,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQFD_RESAMPLE:
 		r = !xive_enabled();
 		break;
@@ -632,13 +631,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-		r = hv_enabled;
-#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+		BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER));
 		r = 1;
-#else
-		r = 0;
-#endif
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD: