Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "For x86, there is a new alternative and (in the future) more scalable
  implementation of extended page tables that does not need a reverse
  map from guest physical addresses to host physical addresses.

  For now it is disabled by default because it is still lacking a few of
  the existing MMU's bells and whistles. However it is a very solid
  piece of work and it is already available for people to hammer on it.

  Other updates:

  ARM:
   - New page table code for both hypervisor and guest stage-2
   - Introduction of a new EL2-private host context
   - Allow EL2 to have its own private per-CPU variables
   - Support of PMU event filtering
   - Complete rework of the Spectre mitigation

  PPC:
   - Fix for running nested guests with in-kernel IRQ chip
   - Fix race condition causing occasional host hard lockup
   - Minor cleanups and bugfixes

  x86:
   - allow trapping unknown MSRs to userspace
   - allow userspace to force #GP on specific MSRs
   - INVPCID support on AMD
   - nested AMD cleanup, on demand allocation of nested SVM state
   - hide PV MSRs and hypercalls for features not enabled in CPUID
   - new test for MSR_IA32_TSC writes from host and guest
   - cleanups: MMU, CPUID, shared MSRs
   - LAPIC latency optimizations ad bugfixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (232 commits)
  kvm: x86/mmu: NX largepage recovery for TDP MMU
  kvm: x86/mmu: Don't clear write flooding count for direct roots
  kvm: x86/mmu: Support MMIO in the TDP MMU
  kvm: x86/mmu: Support write protection for nesting in tdp MMU
  kvm: x86/mmu: Support disabling dirty logging for the tdp MMU
  kvm: x86/mmu: Support dirty logging for the TDP MMU
  kvm: x86/mmu: Support changed pte notifier in tdp MMU
  kvm: x86/mmu: Add access tracking for tdp_mmu
  kvm: x86/mmu: Support invalidate range MMU notifier for TDP MMU
  kvm: x86/mmu: Allocate struct kvm_mmu_pages for all pages in TDP MMU
  kvm: x86/mmu: Add TDP MMU PF handler
  kvm: x86/mmu: Remove disallowed_hugepage_adjust shadow_walk_iterator arg
  kvm: x86/mmu: Support zapping SPTEs in the TDP MMU
  KVM: Cache as_id in kvm_memory_slot
  kvm: x86/mmu: Add functions to handle changed TDP SPTEs
  kvm: x86/mmu: Allocate and free TDP MMU roots
  kvm: x86/mmu: Init / Uninit the TDP MMU
  kvm: x86/mmu: Introduce tdp_iter
  KVM: mmu: extract spte.h and spte.c
  KVM: mmu: Separate updating a PTE from kvm_set_pte_rmapp
  ...

1 files changed, 20 insertions, 4 deletions

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3bd3118c7633..e3b1839fc251 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -111,7 +111,7 @@ module_param(one_vm_per_core, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires indep_threads_mode=N)");
 
 #ifdef CONFIG_KVM_XICS
-static struct kernel_param_ops module_param_ops = {
+static const struct kernel_param_ops module_param_ops = {
 	.set = param_set_int,
 	.get = param_get_int,
 };
@@ -3442,9 +3442,19 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	unsigned long host_psscr = mfspr(SPRN_PSSCR);
 	unsigned long host_pidr = mfspr(SPRN_PID);
 
+	/*
+	 * P8 and P9 suppress the HDEC exception when LPCR[HDICE] = 0,
+	 * so set HDICE before writing HDEC.
+	 */
+	mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr | LPCR_HDICE);
+	isync();
+
 	hdec = time_limit - mftb();
-	if (hdec < 0)
+	if (hdec < 0) {
+		mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr);
+		isync();
 		return BOOK3S_INTERRUPT_HV_DECREMENTER;
+	}
 	mtspr(SPRN_HDEC, hdec);
 
 	if (vc->tb_offset) {
@@ -3565,7 +3575,7 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
  * Virtual-mode guest entry for POWER9 and later when the host and
  * guest are both using the radix MMU.  The LPIDR has already been set.
  */
-int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
+static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 			 unsigned long lpcr)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -3579,7 +3589,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	dec = mfspr(SPRN_DEC);
 	tb = mftb();
-	if (dec < 512)
+	if (dec < 0)
 		return BOOK3S_INTERRUPT_HV_DECREMENTER;
 	local_paca->kvm_hstate.dec_expires = dec + tb;
 	if (local_paca->kvm_hstate.dec_expires < time_limit)
@@ -5257,6 +5267,12 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp,
 	case KVM_PPC_ALLOCATE_HTAB: {
 		u32 htab_order;
 
+		/* If we're a nested hypervisor, we currently only support radix */
+		if (kvmhv_on_pseries()) {
+			r = -EOPNOTSUPP;
+			break;
+		}
+
 		r = -EFAULT;
 		if (get_user(htab_order, (u32 __user *)argp))
 			break;