Merge tag 'kvm-4.20-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "ARM:
   - Improved guest IPA space support (32 to 52 bits)

   - RAS event delivery for 32bit

   - PMU fixes

   - Guest entry hardening

   - Various cleanups

   - Port of dirty_log_test selftest

  PPC:
   - Nested HV KVM support for radix guests on POWER9. The performance
     is much better than with PR KVM. Migration and arbitrary level of
     nesting is supported.

   - Disable nested HV-KVM on early POWER9 chips that need a particular
     hardware bug workaround

   - One VM per core mode to prevent potential data leaks

   - PCI pass-through optimization

   - merge ppc-kvm topic branch and kvm-ppc-fixes to get a better base

  s390:
   - Initial version of AP crypto virtualization via vfio-mdev

   - Improvement for vfio-ap

   - Set the host program identifier

   - Optimize page table locking

  x86:
   - Enable nested virtualization by default

   - Implement Hyper-V IPI hypercalls

   - Improve #PF and #DB handling

   - Allow guests to use Enlightened VMCS

   - Add migration selftests for VMCS and Enlightened VMCS

   - Allow coalesced PIO accesses

   - Add an option to perform nested VMCS host state consistency check
     through hardware

   - Automatic tuning of lapic_timer_advance_ns

   - Many fixes, minor improvements, and cleanups"

* tag 'kvm-4.20-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  KVM/nVMX: Do not validate that posted_intr_desc_addr is page aligned
  Revert "kvm: x86: optimize dr6 restore"
  KVM: PPC: Optimize clearing TCEs for sparse tables
  x86/kvm/nVMX: tweak shadow fields
  selftests/kvm: add missing executables to .gitignore
  KVM: arm64: Safety check PSTATE when entering guest and handle IL
  KVM: PPC: Book3S HV: Don't use streamlined entry path on early POWER9 chips
  arm/arm64: KVM: Enable 32 bits kvm vcpu events support
  arm/arm64: KVM: Rename function kvm_arch_dev_ioctl_check_extension()
  KVM: arm64: Fix caching of host MDCR_EL2 value
  KVM: VMX: enable nested virtualization by default
  KVM/x86: Use 32bit xor to clear registers in svm.c
  kvm: x86: Introduce KVM_CAP_EXCEPTION_PAYLOAD
  kvm: vmx: Defer setting of DR6 until #DB delivery
  kvm: x86: Defer setting of CR2 until #PF delivery
  kvm: x86: Add payload operands to kvm_multiple_exception
  kvm: x86: Add exception payload fields to kvm_vcpu_events
  kvm: x86: Add has_payload and payload to kvm_queued_exception
  KVM: Documentation: Fix omission in struct kvm_vcpu_events
  KVM: selftests: add Enlightened VMCS test
  ...

1 files changed, 1291 insertions, 0 deletions

diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
new file mode 100644
index 000000000000..401d2ecbebc5
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -0,0 +1,1291 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corporation, 2018
+ * Authors Suraj Jitindar Singh <sjitindarsingh@gmail.com>
+ *	   Paul Mackerras <paulus@ozlabs.org>
+ *
+ * Description: KVM functions specific to running nested KVM-HV guests
+ * on Book3S processors (specifically POWER9 and later).
+ */
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/llist.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/pte-walk.h>
+#include <asm/reg.h>
+
+static struct patb_entry *pseries_partition_tb;
+
+static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp);
+static void kvmhv_free_memslot_nest_rmap(struct kvm_memory_slot *free);
+
+void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	hr->pcr = vc->pcr;
+	hr->dpdes = vc->dpdes;
+	hr->hfscr = vcpu->arch.hfscr;
+	hr->tb_offset = vc->tb_offset;
+	hr->dawr0 = vcpu->arch.dawr;
+	hr->dawrx0 = vcpu->arch.dawrx;
+	hr->ciabr = vcpu->arch.ciabr;
+	hr->purr = vcpu->arch.purr;
+	hr->spurr = vcpu->arch.spurr;
+	hr->ic = vcpu->arch.ic;
+	hr->vtb = vc->vtb;
+	hr->srr0 = vcpu->arch.shregs.srr0;
+	hr->srr1 = vcpu->arch.shregs.srr1;
+	hr->sprg[0] = vcpu->arch.shregs.sprg0;
+	hr->sprg[1] = vcpu->arch.shregs.sprg1;
+	hr->sprg[2] = vcpu->arch.shregs.sprg2;
+	hr->sprg[3] = vcpu->arch.shregs.sprg3;
+	hr->pidr = vcpu->arch.pid;
+	hr->cfar = vcpu->arch.cfar;
+	hr->ppr = vcpu->arch.ppr;
+}
+
+static void byteswap_pt_regs(struct pt_regs *regs)
+{
+	unsigned long *addr = (unsigned long *) regs;
+
+	for (; addr < ((unsigned long *) (regs + 1)); addr++)
+		*addr = swab64(*addr);
+}
+
+static void byteswap_hv_regs(struct hv_guest_state *hr)
+{
+	hr->version = swab64(hr->version);
+	hr->lpid = swab32(hr->lpid);
+	hr->vcpu_token = swab32(hr->vcpu_token);
+	hr->lpcr = swab64(hr->lpcr);
+	hr->pcr = swab64(hr->pcr);
+	hr->amor = swab64(hr->amor);
+	hr->dpdes = swab64(hr->dpdes);
+	hr->hfscr = swab64(hr->hfscr);
+	hr->tb_offset = swab64(hr->tb_offset);
+	hr->dawr0 = swab64(hr->dawr0);
+	hr->dawrx0 = swab64(hr->dawrx0);
+	hr->ciabr = swab64(hr->ciabr);
+	hr->hdec_expiry = swab64(hr->hdec_expiry);
+	hr->purr = swab64(hr->purr);
+	hr->spurr = swab64(hr->spurr);
+	hr->ic = swab64(hr->ic);
+	hr->vtb = swab64(hr->vtb);
+	hr->hdar = swab64(hr->hdar);
+	hr->hdsisr = swab64(hr->hdsisr);
+	hr->heir = swab64(hr->heir);
+	hr->asdr = swab64(hr->asdr);
+	hr->srr0 = swab64(hr->srr0);
+	hr->srr1 = swab64(hr->srr1);
+	hr->sprg[0] = swab64(hr->sprg[0]);
+	hr->sprg[1] = swab64(hr->sprg[1]);
+	hr->sprg[2] = swab64(hr->sprg[2]);
+	hr->sprg[3] = swab64(hr->sprg[3]);
+	hr->pidr = swab64(hr->pidr);
+	hr->cfar = swab64(hr->cfar);
+	hr->ppr = swab64(hr->ppr);
+}
+
+static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
+				 struct hv_guest_state *hr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	hr->dpdes = vc->dpdes;
+	hr->hfscr = vcpu->arch.hfscr;
+	hr->purr = vcpu->arch.purr;
+	hr->spurr = vcpu->arch.spurr;
+	hr->ic = vcpu->arch.ic;
+	hr->vtb = vc->vtb;
+	hr->srr0 = vcpu->arch.shregs.srr0;
+	hr->srr1 = vcpu->arch.shregs.srr1;
+	hr->sprg[0] = vcpu->arch.shregs.sprg0;
+	hr->sprg[1] = vcpu->arch.shregs.sprg1;
+	hr->sprg[2] = vcpu->arch.shregs.sprg2;
+	hr->sprg[3] = vcpu->arch.shregs.sprg3;
+	hr->pidr = vcpu->arch.pid;
+	hr->cfar = vcpu->arch.cfar;
+	hr->ppr = vcpu->arch.ppr;
+	switch (trap) {
+	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
+		hr->hdar = vcpu->arch.fault_dar;
+		hr->hdsisr = vcpu->arch.fault_dsisr;
+		hr->asdr = vcpu->arch.fault_gpa;
+		break;
+	case BOOK3S_INTERRUPT_H_INST_STORAGE:
+		hr->asdr = vcpu->arch.fault_gpa;
+		break;
+	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
+		hr->heir = vcpu->arch.emul_inst;
+		break;
+	}
+}
+
+static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+{
+	/*
+	 * Don't let L1 enable features for L2 which we've disabled for L1,
+	 * but preserve the interrupt cause field.
+	 */
+	hr->hfscr &= (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
+
+	/* Don't let data address watchpoint match in hypervisor state */
+	hr->dawrx0 &= ~DAWRX_HYP;
+
+	/* Don't let completed instruction address breakpt match in HV state */
+	if ((hr->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+		hr->ciabr &= ~CIABR_PRIV;
+}
+
+static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	vc->pcr = hr->pcr;
+	vc->dpdes = hr->dpdes;
+	vcpu->arch.hfscr = hr->hfscr;
+	vcpu->arch.dawr = hr->dawr0;
+	vcpu->arch.dawrx = hr->dawrx0;
+	vcpu->arch.ciabr = hr->ciabr;
+	vcpu->arch.purr = hr->purr;
+	vcpu->arch.spurr = hr->spurr;
+	vcpu->arch.ic = hr->ic;
+	vc->vtb = hr->vtb;
+	vcpu->arch.shregs.srr0 = hr->srr0;
+	vcpu->arch.shregs.srr1 = hr->srr1;
+	vcpu->arch.shregs.sprg0 = hr->sprg[0];
+	vcpu->arch.shregs.sprg1 = hr->sprg[1];
+	vcpu->arch.shregs.sprg2 = hr->sprg[2];
+	vcpu->arch.shregs.sprg3 = hr->sprg[3];
+	vcpu->arch.pid = hr->pidr;
+	vcpu->arch.cfar = hr->cfar;
+	vcpu->arch.ppr = hr->ppr;
+}
+
+void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
+				   struct hv_guest_state *hr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	vc->dpdes = hr->dpdes;
+	vcpu->arch.hfscr = hr->hfscr;
+	vcpu->arch.purr = hr->purr;
+	vcpu->arch.spurr = hr->spurr;
+	vcpu->arch.ic = hr->ic;
+	vc->vtb = hr->vtb;
+	vcpu->arch.fault_dar = hr->hdar;
+	vcpu->arch.fault_dsisr = hr->hdsisr;
+	vcpu->arch.fault_gpa = hr->asdr;
+	vcpu->arch.emul_inst = hr->heir;
+	vcpu->arch.shregs.srr0 = hr->srr0;
+	vcpu->arch.shregs.srr1 = hr->srr1;
+	vcpu->arch.shregs.sprg0 = hr->sprg[0];
+	vcpu->arch.shregs.sprg1 = hr->sprg[1];
+	vcpu->arch.shregs.sprg2 = hr->sprg[2];
+	vcpu->arch.shregs.sprg3 = hr->sprg[3];
+	vcpu->arch.pid = hr->pidr;
+	vcpu->arch.cfar = hr->cfar;
+	vcpu->arch.ppr = hr->ppr;
+}
+
+long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
+{
+	long int err, r;
+	struct kvm_nested_guest *l2;
+	struct pt_regs l2_regs, saved_l1_regs;
+	struct hv_guest_state l2_hv, saved_l1_hv;
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	u64 hv_ptr, regs_ptr;
+	u64 hdec_exp;
+	s64 delta_purr, delta_spurr, delta_ic, delta_vtb;
+	u64 mask;
+	unsigned long lpcr;
+
+	if (vcpu->kvm->arch.l1_ptcr == 0)
+		return H_NOT_AVAILABLE;
+
+	/* copy parameters in */
+	hv_ptr = kvmppc_get_gpr(vcpu, 4);
+	err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv,
+				  sizeof(struct hv_guest_state));
+	if (err)
+		return H_PARAMETER;
+	if (kvmppc_need_byteswap(vcpu))
+		byteswap_hv_regs(&l2_hv);
+	if (l2_hv.version != HV_GUEST_STATE_VERSION)
+		return H_P2;
+
+	regs_ptr = kvmppc_get_gpr(vcpu, 5);
+	err = kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs,
+				  sizeof(struct pt_regs));
+	if (err)
+		return H_PARAMETER;
+	if (kvmppc_need_byteswap(vcpu))
+		byteswap_pt_regs(&l2_regs);
+	if (l2_hv.vcpu_token >= NR_CPUS)
+		return H_PARAMETER;
+
+	/* translate lpid */
+	l2 = kvmhv_get_nested(vcpu->kvm, l2_hv.lpid, true);
+	if (!l2)
+		return H_PARAMETER;
+	if (!l2->l1_gr_to_hr) {
+		mutex_lock(&l2->tlb_lock);
+		kvmhv_update_ptbl_cache(l2);
+		mutex_unlock(&l2->tlb_lock);
+	}
+
+	/* save l1 values of things */
+	vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
+	saved_l1_regs = vcpu->arch.regs;
+	kvmhv_save_hv_regs(vcpu, &saved_l1_hv);
+
+	/* convert TB values/offsets to host (L0) values */
+	hdec_exp = l2_hv.hdec_expiry - vc->tb_offset;
+	vc->tb_offset += l2_hv.tb_offset;
+
+	/* set L1 state to L2 state */
+	vcpu->arch.nested = l2;
+	vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token;
+	vcpu->arch.regs = l2_regs;
+	vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
+	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
+		LPCR_LPES | LPCR_MER;
+	lpcr = (vc->lpcr & ~mask) | (l2_hv.lpcr & mask);
+	sanitise_hv_regs(vcpu, &l2_hv);
+	restore_hv_regs(vcpu, &l2_hv);
+
+	vcpu->arch.ret = RESUME_GUEST;
+	vcpu->arch.trap = 0;
+	do {
+		if (mftb() >= hdec_exp) {
+			vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER;
+			r = RESUME_HOST;
+			break;
+		}
+		r = kvmhv_run_single_vcpu(vcpu->arch.kvm_run, vcpu, hdec_exp,
+					  lpcr);
+	} while (is_kvmppc_resume_guest(r));
+
+	/* save L2 state for return */
+	l2_regs = vcpu->arch.regs;
+	l2_regs.msr = vcpu->arch.shregs.msr;
+	delta_purr = vcpu->arch.purr - l2_hv.purr;
+	delta_spurr = vcpu->arch.spurr - l2_hv.spurr;
+	delta_ic = vcpu->arch.ic - l2_hv.ic;
+	delta_vtb = vc->vtb - l2_hv.vtb;
+	save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv);
+
+	/* restore L1 state */
+	vcpu->arch.nested = NULL;
+	vcpu->arch.regs = saved_l1_regs;
+	vcpu->arch.shregs.msr = saved_l1_regs.msr & ~MSR_TS_MASK;
+	/* set L1 MSR TS field according to L2 transaction state */
+	if (l2_regs.msr & MSR_TS_MASK)
+		vcpu->arch.shregs.msr |= MSR_TS_S;
+	vc->tb_offset = saved_l1_hv.tb_offset;
+	restore_hv_regs(vcpu, &saved_l1_hv);
+	vcpu->arch.purr += delta_purr;
+	vcpu->arch.spurr += delta_spurr;
+	vcpu->arch.ic += delta_ic;
+	vc->vtb += delta_vtb;
+
+	kvmhv_put_nested(l2);
+
+	/* copy l2_hv_state and regs back to guest */
+	if (kvmppc_need_byteswap(vcpu)) {
+		byteswap_hv_regs(&l2_hv);
+		byteswap_pt_regs(&l2_regs);
+	}
+	err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv,
+				   sizeof(struct hv_guest_state));
+	if (err)
+		return H_AUTHORITY;
+	err = kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs,
+				   sizeof(struct pt_regs));
+	if (err)
+		return H_AUTHORITY;
+
+	if (r == -EINTR)
+		return H_INTERRUPT;
+
+	return vcpu->arch.trap;
+}
+
+long kvmhv_nested_init(void)
+{
+	long int ptb_order;
+	unsigned long ptcr;
+	long rc;
+
+	if (!kvmhv_on_pseries())
+		return 0;
+	if (!radix_enabled())
+		return -ENODEV;
+
+	/* find log base 2 of KVMPPC_NR_LPIDS, rounding up */
+	ptb_order = __ilog2(KVMPPC_NR_LPIDS - 1) + 1;
+	if (ptb_order < 8)
+		ptb_order = 8;
+	pseries_partition_tb = kmalloc(sizeof(struct patb_entry) << ptb_order,
+				       GFP_KERNEL);
+	if (!pseries_partition_tb) {
+		pr_err("kvm-hv: failed to allocated nested partition table\n");
+		return -ENOMEM;
+	}
+
+	ptcr = __pa(pseries_partition_tb) | (ptb_order - 8);
+	rc = plpar_hcall_norets(H_SET_PARTITION_TABLE, ptcr);
+	if (rc != H_SUCCESS) {
+		pr_err("kvm-hv: Parent hypervisor does not support nesting (rc=%ld)\n",
+		       rc);
+		kfree(pseries_partition_tb);
+		pseries_partition_tb = NULL;
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+void kvmhv_nested_exit(void)
+{
+	/*
+	 * N.B. the kvmhv_on_pseries() test is there because it enables
+	 * the compiler to remove the call to plpar_hcall_norets()
+	 * when CONFIG_PPC_PSERIES=n.
+	 */
+	if (kvmhv_on_pseries() && pseries_partition_tb) {
+		plpar_hcall_norets(H_SET_PARTITION_TABLE, 0);
+		kfree(pseries_partition_tb);
+		pseries_partition_tb = NULL;
+	}
+}
+
+static void kvmhv_flush_lpid(unsigned int lpid)
+{
+	long rc;
+
+	if (!kvmhv_on_pseries()) {
+		radix__flush_tlb_lpid(lpid);
+		return;
+	}
+
+	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
+				lpid, TLBIEL_INVAL_SET_LPID);
+	if (rc)
+		pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc);
+}
+
+void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1)
+{
+	if (!kvmhv_on_pseries()) {
+		mmu_partition_table_set_entry(lpid, dw0, dw1);
+		return;
+	}
+
+	pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
+	pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
+	/* L0 will do the necessary barriers */
+	kvmhv_flush_lpid(lpid);
+}
+
+static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp)
+{
+	unsigned long dw0;
+
+	dw0 = PATB_HR | radix__get_tree_size() |
+		__pa(gp->shadow_pgtable) | RADIX_PGD_INDEX_SIZE;
+	kvmhv_set_ptbl_entry(gp->shadow_lpid, dw0, gp->process_table);
+}
+
+void kvmhv_vm_nested_init(struct kvm *kvm)
+{
+	kvm->arch.max_nested_lpid = -1;
+}
+
+/*
+ * Handle the H_SET_PARTITION_TABLE hcall.
+ * r4 = guest real address of partition table + log_2(size) - 12
+ * (formatted as for the PTCR).
+ */
+long kvmhv_set_partition_table(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long ptcr = kvmppc_get_gpr(vcpu, 4);
+	int srcu_idx;
+	long ret = H_SUCCESS;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	/*
+	 * Limit the partition table to 4096 entries (because that's what
+	 * hardware supports), and check the base address.
+	 */
+	if ((ptcr & PRTS_MASK) > 12 - 8 ||
+	    !kvm_is_visible_gfn(vcpu->kvm, (ptcr & PRTB_MASK) >> PAGE_SHIFT))
+		ret = H_PARAMETER;
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	if (ret == H_SUCCESS)
+		kvm->arch.l1_ptcr = ptcr;
+	return ret;
+}
+
+/*
+ * Reload the partition table entry for a guest.
+ * Caller must hold gp->tlb_lock.
+ */
+static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp)
+{
+	int ret;
+	struct patb_entry ptbl_entry;
+	unsigned long ptbl_addr;
+	struct kvm *kvm = gp->l1_host;
+
+	ret = -EFAULT;
+	ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4);
+	if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8)))
+		ret = kvm_read_guest(kvm, ptbl_addr,
+				     &ptbl_entry, sizeof(ptbl_entry));
+	if (ret) {
+		gp->l1_gr_to_hr = 0;
+		gp->process_table = 0;
+	} else {
+		gp->l1_gr_to_hr = be64_to_cpu(ptbl_entry.patb0);
+		gp->process_table = be64_to_cpu(ptbl_entry.patb1);
+	}
+	kvmhv_set_nested_ptbl(gp);
+}
+
+struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
+{
+	struct kvm_nested_guest *gp;
+	long shadow_lpid;
+
+	gp = kzalloc(sizeof(*gp), GFP_KERNEL);
+	if (!gp)
+		return NULL;
+	gp->l1_host = kvm;
+	gp->l1_lpid = lpid;
+	mutex_init(&gp->tlb_lock);
+	gp->shadow_pgtable = pgd_alloc(kvm->mm);
+	if (!gp->shadow_pgtable)
+		goto out_free;
+	shadow_lpid = kvmppc_alloc_lpid();
+	if (shadow_lpid < 0)
+		goto out_free2;
+	gp->shadow_lpid = shadow_lpid;
+
+	memset(gp->prev_cpu, -1, sizeof(gp->prev_cpu));
+
+	return gp;
+
+ out_free2:
+	pgd_free(kvm->mm, gp->shadow_pgtable);
+ out_free:
+	kfree(gp);
+	return NULL;
+}
+
+/*
+ * Free up any resources allocated for a nested guest.
+ */
+static void kvmhv_release_nested(struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = gp->l1_host;
+
+	if (gp->shadow_pgtable) {
+		/*
+		 * No vcpu is using this struct and no call to
+		 * kvmhv_get_nested can find this struct,
+		 * so we don't need to hold kvm->mmu_lock.
+		 */
+		kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
+					  gp->shadow_lpid);
+		pgd_free(kvm->mm, gp->shadow_pgtable);
+	}
+	kvmhv_set_ptbl_entry(gp->shadow_lpid, 0, 0);
+	kvmppc_free_lpid(gp->shadow_lpid);
+	kfree(gp);
+}
+
+static void kvmhv_remove_nested(struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = gp->l1_host;
+	int lpid = gp->l1_lpid;
+	long ref;
+
+	spin_lock(&kvm->mmu_lock);
+	if (gp == kvm->arch.nested_guests[lpid]) {
+		kvm->arch.nested_guests[lpid] = NULL;
+		if (lpid == kvm->arch.max_nested_lpid) {
+			while (--lpid >= 0 && !kvm->arch.nested_guests[lpid])
+				;
+			kvm->arch.max_nested_lpid = lpid;
+		}
+		--gp->refcnt;
+	}
+	ref = gp->refcnt;
+	spin_unlock(&kvm->mmu_lock);
+	if (ref == 0)
+		kvmhv_release_nested(gp);
+}
+
+/*
+ * Free up all nested resources allocated for this guest.
+ * This is called with no vcpus of the guest running, when
+ * switching the guest to HPT mode or when destroying the
+ * guest.
+ */
+void kvmhv_release_all_nested(struct kvm *kvm)
+{
+	int i;
+	struct kvm_nested_guest *gp;
+	struct kvm_nested_guest *freelist = NULL;
+	struct kvm_memory_slot *memslot;
+	int srcu_idx;
+
+	spin_lock(&kvm->mmu_lock);
+	for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
+		gp = kvm->arch.nested_guests[i];
+		if (!gp)
+			continue;
+		kvm->arch.nested_guests[i] = NULL;
+		if (--gp->refcnt == 0) {
+			gp->next = freelist;
+			freelist = gp;
+		}
+	}
+	kvm->arch.max_nested_lpid = -1;
+	spin_unlock(&kvm->mmu_lock);
+	while ((gp = freelist) != NULL) {
+		freelist = gp->next;
+		kvmhv_release_nested(gp);
+	}
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	kvm_for_each_memslot(memslot, kvm_memslots(kvm))
+		kvmhv_free_memslot_nest_rmap(memslot);
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+}
+
+/* caller must hold gp->tlb_lock */
+static void kvmhv_flush_nested(struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = gp->l1_host;
+
+	spin_lock(&kvm->mmu_lock);
+	kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable, gp->shadow_lpid);
+	spin_unlock(&kvm->mmu_lock);
+	kvmhv_flush_lpid(gp->shadow_lpid);
+	kvmhv_update_ptbl_cache(gp);
+	if (gp->l1_gr_to_hr == 0)
+		kvmhv_remove_nested(gp);
+}
+
+struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
+					  bool create)
+{
+	struct kvm_nested_guest *gp, *newgp;
+
+	if (l1_lpid >= KVM_MAX_NESTED_GUESTS ||
+	    l1_lpid >= (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 12 - 4)))
+		return NULL;
+
+	spin_lock(&kvm->mmu_lock);
+	gp = kvm->arch.nested_guests[l1_lpid];
+	if (gp)
+		++gp->refcnt;
+	spin_unlock(&kvm->mmu_lock);
+
+	if (gp || !create)
+		return gp;
+
+	newgp = kvmhv_alloc_nested(kvm, l1_lpid);
+	if (!newgp)
+		return NULL;
+	spin_lock(&kvm->mmu_lock);
+	if (kvm->arch.nested_guests[l1_lpid]) {
+		/* someone else beat us to it */
+		gp = kvm->arch.nested_guests[l1_lpid];
+	} else {
+		kvm->arch.nested_guests[l1_lpid] = newgp;
+		++newgp->refcnt;
+		gp = newgp;
+		newgp = NULL;
+		if (l1_lpid > kvm->arch.max_nested_lpid)
+			kvm->arch.max_nested_lpid = l1_lpid;
+	}
+	++gp->refcnt;
+	spin_unlock(&kvm->mmu_lock);
+
+	if (newgp)
+		kvmhv_release_nested(newgp);
+
+	return gp;
+}
+
+void kvmhv_put_nested(struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = gp->l1_host;
+	long ref;
+
+	spin_lock(&kvm->mmu_lock);
+	ref = --gp->refcnt;
+	spin_unlock(&kvm->mmu_lock);
+	if (ref == 0)
+		kvmhv_release_nested(gp);
+}
+
+static struct kvm_nested_guest *kvmhv_find_nested(struct kvm *kvm, int lpid)
+{
+	if (lpid > kvm->arch.max_nested_lpid)
+		return NULL;
+	return kvm->arch.nested_guests[lpid];
+}
+
+static inline bool kvmhv_n_rmap_is_equal(u64 rmap_1, u64 rmap_2)
+{
+	return !((rmap_1 ^ rmap_2) & (RMAP_NESTED_LPID_MASK |
+				       RMAP_NESTED_GPA_MASK));
+}
+
+void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
+			    struct rmap_nested **n_rmap)
+{
+	struct llist_node *entry = ((struct llist_head *) rmapp)->first;
+	struct rmap_nested *cursor;
+	u64 rmap, new_rmap = (*n_rmap)->rmap;
+
+	/* Are there any existing entries? */
+	if (!(*rmapp)) {
+		/* No -> use the rmap as a single entry */
+		*rmapp = new_rmap | RMAP_NESTED_IS_SINGLE_ENTRY;
+		return;
+	}
+
+	/* Do any entries match what we're trying to insert? */
+	for_each_nest_rmap_safe(cursor, entry, &rmap) {
+		if (kvmhv_n_rmap_is_equal(rmap, new_rmap))
+			return;
+	}
+
+	/* Do we need to create a list or just add the new entry? */
+	rmap = *rmapp;
+	if (rmap & RMAP_NESTED_IS_SINGLE_ENTRY) /* Not previously a list */
+		*rmapp = 0UL;
+	llist_add(&((*n_rmap)->list), (struct llist_head *) rmapp);
+	if (rmap & RMAP_NESTED_IS_SINGLE_ENTRY) /* Not previously a list */
+		(*n_rmap)->list.next = (struct llist_node *) rmap;
+
+	/* Set NULL so not freed by caller */
+	*n_rmap = NULL;
+}
+
+static void kvmhv_remove_nest_rmap(struct kvm *kvm, u64 n_rmap,
+				   unsigned long hpa, unsigned long mask)
+{
+	struct kvm_nested_guest *gp;
+	unsigned long gpa;
+	unsigned int shift, lpid;
+	pte_t *ptep;
+
+	gpa = n_rmap & RMAP_NESTED_GPA_MASK;
+	lpid = (n_rmap & RMAP_NESTED_LPID_MASK) >> RMAP_NESTED_LPID_SHIFT;
+	gp = kvmhv_find_nested(kvm, lpid);
+	if (!gp)
+		return;
+
+	/* Find and invalidate the pte */
+	ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
+	/* Don't spuriously invalidate ptes if the pfn has changed */
+	if (ptep && pte_present(*ptep) && ((pte_val(*ptep) & mask) == hpa))
+		kvmppc_unmap_pte(kvm, ptep, gpa, shift, NULL, gp->shadow_lpid);
+}
+
+static void kvmhv_remove_nest_rmap_list(struct kvm *kvm, unsigned long *rmapp,
+					unsigned long hpa, unsigned long mask)
+{
+	struct llist_node *entry = llist_del_all((struct llist_head *) rmapp);
+	struct rmap_nested *cursor;
+	unsigned long rmap;
+
+	for_each_nest_rmap_safe(cursor, entry, &rmap) {
+		kvmhv_remove_nest_rmap(kvm, rmap, hpa, mask);
+		kfree(cursor);
+	}
+}
+
+/* called with kvm->mmu_lock held */
+void kvmhv_remove_nest_rmap_range(struct kvm *kvm,
+				  struct kvm_memory_slot *memslot,
+				  unsigned long gpa, unsigned long hpa,
+				  unsigned long nbytes)
+{
+	unsigned long gfn, end_gfn;
+	unsigned long addr_mask;
+
+	if (!memslot)
+		return;
+	gfn = (gpa >> PAGE_SHIFT) - memslot->base_gfn;
+	end_gfn = gfn + (nbytes >> PAGE_SHIFT);
+
+	addr_mask = PTE_RPN_MASK & ~(nbytes - 1);
+	hpa &= addr_mask;
+
+	for (; gfn < end_gfn; gfn++) {
+		unsigned long *rmap = &memslot->arch.rmap[gfn];
+		kvmhv_remove_nest_rmap_list(kvm, rmap, hpa, addr_mask);
+	}
+}
+
+static void kvmhv_free_memslot_nest_rmap(struct kvm_memory_slot *free)
+{
+	unsigned long page;
+
+	for (page = 0; page < free->npages; page++) {
+		unsigned long rmap, *rmapp = &free->arch.rmap[page];
+		struct rmap_nested *cursor;
+		struct llist_node *entry;
+
+		entry = llist_del_all((struct llist_head *) rmapp);
+		for_each_nest_rmap_safe(cursor, entry, &rmap)
+			kfree(cursor);
+	}
+}
+
+static bool kvmhv_invalidate_shadow_pte(struct kvm_vcpu *vcpu,
+					struct kvm_nested_guest *gp,
+					long gpa, int *shift_ret)
+{
+	struct kvm *kvm = vcpu->kvm;
+	bool ret = false;
+	pte_t *ptep;
+	int shift;
+
+	spin_lock(&kvm->mmu_lock);
+	ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
+	if (!shift)
+		shift = PAGE_SHIFT;
+	if (ptep && pte_present(*ptep)) {
+		kvmppc_unmap_pte(kvm, ptep, gpa, shift, NULL, gp->shadow_lpid);
+		ret = true;
+	}
+	spin_unlock(&kvm->mmu_lock);
+
+	if (shift_ret)
+		*shift_ret = shift;
+	return ret;
+}
+
+static inline int get_ric(unsigned int instr)
+{
+	return (instr >> 18) & 0x3;
+}
+
+static inline int get_prs(unsigned int instr)
+{
+	return (instr >> 17) & 0x1;
+}
+
+static inline int get_r(unsigned int instr)
+{
+	return (instr >> 16) & 0x1;
+}
+
+static inline int get_lpid(unsigned long r_val)
+{
+	return r_val & 0xffffffff;
+}
+
+static inline int get_is(unsigned long r_val)
+{
+	return (r_val >> 10) & 0x3;
+}
+
+static inline int get_ap(unsigned long r_val)
+{
+	return (r_val >> 5) & 0x7;
+}
+
+static inline long get_epn(unsigned long r_val)
+{
+	return r_val >> 12;
+}
+
+static int kvmhv_emulate_tlbie_tlb_addr(struct kvm_vcpu *vcpu, int lpid,
+					int ap, long epn)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *gp;
+	long npages;
+	int shift, shadow_shift;
+	unsigned long addr;
+
+	shift = ap_to_shift(ap);
+	addr = epn << 12;
+	if (shift < 0)
+		/* Invalid ap encoding */
+		return -EINVAL;
+
+	addr &= ~((1UL << shift) - 1);
+	npages = 1UL << (shift - PAGE_SHIFT);
+
+	gp = kvmhv_get_nested(kvm, lpid, false);
+	if (!gp) /* No such guest -> nothing to do */
+		return 0;
+	mutex_lock(&gp->tlb_lock);
+
+	/* There may be more than one host page backing this single guest pte */
+	do {
+		kvmhv_invalidate_shadow_pte(vcpu, gp, addr, &shadow_shift);
+
+		npages -= 1UL << (shadow_shift - PAGE_SHIFT);
+		addr += 1UL << shadow_shift;
+	} while (npages > 0);
+
+	mutex_unlock(&gp->tlb_lock);
+	kvmhv_put_nested(gp);
+	return 0;
+}
+
+static void kvmhv_emulate_tlbie_lpid(struct kvm_vcpu *vcpu,
+				     struct kvm_nested_guest *gp, int ric)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	mutex_lock(&gp->tlb_lock);
+	switch (ric) {
+	case 0:
+		/* Invalidate TLB */
+		spin_lock(&kvm->mmu_lock);
+		kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
+					  gp->shadow_lpid);
+		kvmhv_flush_lpid(gp->shadow_lpid);
+		spin_unlock(&kvm->mmu_lock);
+		break;
+	case 1:
+		/*
+		 * Invalidate PWC
+		 * We don't cache this -> nothing to do
+		 */
+		break;
+	case 2:
+		/* Invalidate TLB, PWC and caching of partition table entries */
+		kvmhv_flush_nested(gp);
+		break;
+	default:
+		break;
+	}
+	mutex_unlock(&gp->tlb_lock);
+}
+
+static void kvmhv_emulate_tlbie_all_lpid(struct kvm_vcpu *vcpu, int ric)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *gp;
+	int i;
+
+	spin_lock(&kvm->mmu_lock);
+	for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
+		gp = kvm->arch.nested_guests[i];
+		if (gp) {
+			spin_unlock(&kvm->mmu_lock);
+			kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
+			spin_lock(&kvm->mmu_lock);
+		}
+	}
+	spin_unlock(&kvm->mmu_lock);
+}
+
+static int kvmhv_emulate_priv_tlbie(struct kvm_vcpu *vcpu, unsigned int instr,
+				    unsigned long rsval, unsigned long rbval)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *gp;
+	int r, ric, prs, is, ap;
+	int lpid;
+	long epn;
+	int ret = 0;
+
+	ric = get_ric(instr);
+	prs = get_prs(instr);
+	r = get_r(instr);
+	lpid = get_lpid(rsval);
+	is = get_is(rbval);
+
+	/*
+	 * These cases are invalid and are not handled:
+	 * r   != 1 -> Only radix supported
+	 * prs == 1 -> Not HV privileged
+	 * ric == 3 -> No cluster bombs for radix
+	 * is  == 1 -> Partition scoped translations not associated with pid
+	 * (!is) && (ric == 1 || ric == 2) -> Not supported by ISA
+	 */
+	if ((!r) || (prs) || (ric == 3) || (is == 1) ||
+	    ((!is) && (ric == 1 || ric == 2)))
+		return -EINVAL;
+
+	switch (is) {
+	case 0:
+		/*
+		 * We know ric == 0
+		 * Invalidate TLB for a given target address
+		 */
+		epn = get_epn(rbval);
+		ap = get_ap(rbval);
+		ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap, epn);
+		break;
+	case 2:
+		/* Invalidate matching LPID */
+		gp = kvmhv_get_nested(kvm, lpid, false);
+		if (gp) {
+			kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
+			kvmhv_put_nested(gp);
+		}
+		break;
+	case 3:
+		/* Invalidate ALL LPIDs */
+		kvmhv_emulate_tlbie_all_lpid(vcpu, ric);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * This handles the H_TLB_INVALIDATE hcall.
+ * Parameters are (r4) tlbie instruction code, (r5) rS contents,
+ * (r6) rB contents.
+ */
+long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	ret = kvmhv_emulate_priv_tlbie(vcpu, kvmppc_get_gpr(vcpu, 4),
+			kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6));
+	if (ret)
+		return H_PARAMETER;
+	return H_SUCCESS;
+}
+
+/* Used to convert a nested guest real address to a L1 guest real address */
+static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
+				       struct kvm_nested_guest *gp,
+				       unsigned long n_gpa, unsigned long dsisr,
+				       struct kvmppc_pte *gpte_p)
+{
+	u64 fault_addr, flags = dsisr & DSISR_ISSTORE;
+	int ret;
+
+	ret = kvmppc_mmu_walk_radix_tree(vcpu, n_gpa, gpte_p, gp->l1_gr_to_hr,
+					 &fault_addr);
+
+	if (ret) {
+		/* We didn't find a pte */
+		if (ret == -EINVAL) {
+			/* Unsupported mmu config */
+			flags |= DSISR_UNSUPP_MMU;
+		} else if (ret == -ENOENT) {
+			/* No translation found */
+			flags |= DSISR_NOHPTE;
+		} else if (ret == -EFAULT) {
+			/* Couldn't access L1 real address */
+			flags |= DSISR_PRTABLE_FAULT;
+			vcpu->arch.fault_gpa = fault_addr;
+		} else {
+			/* Unknown error */
+			return ret;
+		}
+		goto forward_to_l1;
+	} else {
+		/* We found a pte -> check permissions */
+		if (dsisr & DSISR_ISSTORE) {
+			/* Can we write? */
+			if (!gpte_p->may_write) {
+				flags |= DSISR_PROTFAULT;
+				goto forward_to_l1;
+			}
+		} else if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
+			/* Can we execute? */
+			if (!gpte_p->may_execute) {
+				flags |= SRR1_ISI_N_OR_G;
+				goto forward_to_l1;
+			}
+		} else {
+			/* Can we read? */
+			if (!gpte_p->may_read && !gpte_p->may_write) {
+				flags |= DSISR_PROTFAULT;
+				goto forward_to_l1;
+			}
+		}
+	}
+
+	return 0;
+
+forward_to_l1:
+	vcpu->arch.fault_dsisr = flags;
+	if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
+		vcpu->arch.shregs.msr &= ~0x783f0000ul;
+		vcpu->arch.shregs.msr |= flags;
+	}
+	return RESUME_HOST;
+}
+
+static long kvmhv_handle_nested_set_rc(struct kvm_vcpu *vcpu,
+				       struct kvm_nested_guest *gp,
+				       unsigned long n_gpa,
+				       struct kvmppc_pte gpte,
+				       unsigned long dsisr)
+{
+	struct kvm *kvm = vcpu->kvm;
+	bool writing = !!(dsisr & DSISR_ISSTORE);
+	u64 pgflags;
+	bool ret;
+
+	/* Are the rc bits set in the L1 partition scoped pte? */
+	pgflags = _PAGE_ACCESSED;
+	if (writing)
+		pgflags |= _PAGE_DIRTY;
+	if (pgflags & ~gpte.rc)
+		return RESUME_HOST;
+
+	spin_lock(&kvm->mmu_lock);
+	/* Set the rc bit in the pte of our (L0) pgtable for the L1 guest */
+	ret = kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable, writing,
+				     gpte.raddr, kvm->arch.lpid);
+	spin_unlock(&kvm->mmu_lock);
+	if (!ret)
+		return -EINVAL;
+
+	/* Set the rc bit in the pte of the shadow_pgtable for the nest guest */
+	ret = kvmppc_hv_handle_set_rc(kvm, gp->shadow_pgtable, writing, n_gpa,
+				      gp->shadow_lpid);
+	if (!ret)
+		return -EINVAL;
+	return 0;
+}
+
+static inline int kvmppc_radix_level_to_shift(int level)
+{
+	switch (level) {
+	case 2:
+		return PUD_SHIFT;
+	case 1:
+		return PMD_SHIFT;
+	default:
+		return PAGE_SHIFT;
+	}
+}
+
+static inline int kvmppc_radix_shift_to_level(int shift)
+{
+	if (shift == PUD_SHIFT)
+		return 2;
+	if (shift == PMD_SHIFT)
+		return 1;
+	if (shift == PAGE_SHIFT)
+		return 0;
+	WARN_ON_ONCE(1);
+	return 0;
+}
+
+/* called with gp->tlb_lock held */
+static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
+					  struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm