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

Pull KVM fixes from Radim Krčmář:
 "ARM:
   - a fix for a build failure introduced in -rc1 when tracepoints are
     enabled on 32-bit ARM.

   - disable use of stack pointer protection in the hyp code which can
     cause panics.

   - a handful of VGIC fixes.

   - a fix to the init of the redistributors on GICv3 systems that
     prevented boot with kvmtool on GICv3 systems introduced in -rc1.

   - a number of race conditions fixed in our MMU handling code.

   - a fix for the guest being able to program the debug extensions for
     the host on the 32-bit side.

  PPC:
   - fixes for build failures with PR KVM configurations.

   - a fix for a host crash that can occur on POWER9 with radix guests.

  x86:
   - fixes for nested PML and nested EPT.

   - a fix for crashes caused by reserved bits in SSE MXCSR that could
     have been set by userspace.

   - an optimization of halt polling that fixes high CPU overhead.

   - fixes for four reports from Dan Carpenter's static checker.

   - a protection around code that shouldn't have been preemptible.

   - a fix for port IO emulation"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (27 commits)
  KVM: x86: prevent uninitialized variable warning in check_svme()
  KVM: x86/vPMU: fix undefined shift in intel_pmu_refresh()
  KVM: x86: zero base3 of unusable segments
  KVM: X86: Fix read out-of-bounds vulnerability in kvm pio emulation
  KVM: x86: Fix potential preemption when get the current kvmclock timestamp
  KVM: Silence underflow warning in avic_get_physical_id_entry()
  KVM: arm/arm64: Hold slots_lock when unregistering kvm io bus devices
  KVM: arm/arm64: Fix bug when registering redist iodevs
  KVM: x86: lower default for halt_poll_ns
  kvm: arm/arm64: Fix use after free of stage2 page table
  kvm: arm/arm64: Force reading uncached stage2 PGD
  KVM: nVMX: fix EPT permissions as reported in exit qualification
  KVM: VMX: Don't enable EPT A/D feature if EPT feature is disabled
  KVM: x86: Fix load damaged SSEx MXCSR register
  kvm: nVMX: off by one in vmx_write_pml_buffer()
  KVM: arm: rename pm_fake handler to trap_raz_wi
  KVM: arm: plug potential guest hardware debug leakage
  kvm: arm/arm64: Fix race in resetting stage2 PGD
  KVM: arm/arm64: vgic-v3: Use PREbits to infer the number of ICH_APxRn_EL2 registers
  KVM: arm/arm64: vgic-v3: Do not use Active+Pending state for a HW interrupt
  ...

8 files changed, 62 insertions, 32 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9c761fea0c98..695605eb1dfb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -43,7 +43,7 @@
 #define KVM_PRIVATE_MEM_SLOTS 3
 #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 
-#define KVM_HALT_POLL_NS_DEFAULT 400000
+#define KVM_HALT_POLL_NS_DEFAULT 200000
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index c2f8dde3255c..d5d44c452624 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -90,6 +90,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
  * Boot time FPU feature detection code:
  */
 unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
 
 static void __init fpu__init_system_mxcsr(void)
 {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c25cfaf584e7..0816ab2e8adc 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4173,7 +4173,7 @@ static int check_dr_write(struct x86_emulate_ctxt *ctxt)
 
 static int check_svme(struct x86_emulate_ctxt *ctxt)
 {
-	u64 efer;
+	u64 efer = 0;
 
 	ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 56241746abbd..b0454c7e4cff 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -283,11 +283,13 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	pt_element_t pte;
 	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
-	unsigned index, pt_access, pte_access, accessed_dirty, pte_pkey;
+	u64 pt_access, pte_access;
+	unsigned index, accessed_dirty, pte_pkey;
 	unsigned nested_access;
 	gpa_t pte_gpa;
 	bool have_ad;
 	int offset;
+	u64 walk_nx_mask = 0;
 	const int write_fault = access & PFERR_WRITE_MASK;
 	const int user_fault  = access & PFERR_USER_MASK;
 	const int fetch_fault = access & PFERR_FETCH_MASK;
@@ -302,6 +304,7 @@ retry_walk:
 	have_ad       = PT_HAVE_ACCESSED_DIRTY(mmu);
 
 #if PTTYPE == 64
+	walk_nx_mask = 1ULL << PT64_NX_SHIFT;
 	if (walker->level == PT32E_ROOT_LEVEL) {
 		pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
 		trace_kvm_mmu_paging_element(pte, walker->level);
@@ -313,8 +316,6 @@ retry_walk:
 	walker->max_level = walker->level;
 	ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
 
-	accessed_dirty = have_ad ? PT_GUEST_ACCESSED_MASK : 0;
-
 	/*
 	 * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging
 	 * by the MOV to CR instruction are treated as reads and do not cause the
@@ -322,14 +323,14 @@ retry_walk:
 	 */
 	nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK;
 
-	pt_access = pte_access = ACC_ALL;
+	pte_access = ~0;
 	++walker->level;
 
 	do {
 		gfn_t real_gfn;
 		unsigned long host_addr;
 
-		pt_access &= pte_access;
+		pt_access = pte_access;
 		--walker->level;
 
 		index = PT_INDEX(addr, walker->level);
@@ -371,6 +372,12 @@ retry_walk:
 
 		trace_kvm_mmu_paging_element(pte, walker->level);
 
+		/*
+		 * Inverting the NX it lets us AND it like other
+		 * permission bits.
+		 */
+		pte_access = pt_access & (pte ^ walk_nx_mask);
+
 		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
@@ -379,14 +386,16 @@ retry_walk:
 			goto error;
 		}
 
-		accessed_dirty &= pte;
-		pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
-
 		walker->ptes[walker->level - 1] = pte;
 	} while (!is_last_gpte(mmu, walker->level, pte));
 
 	pte_pkey = FNAME(gpte_pkeys)(vcpu, pte);
-	errcode = permission_fault(vcpu, mmu, pte_access, pte_pkey, access);
+	accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;
+
+	/* Convert to ACC_*_MASK flags for struct guest_walker.  */
+	walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask);
+	walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask);
+	errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access);
 	if (unlikely(errcode))
 		goto error;
 
@@ -403,7 +412,7 @@ retry_walk:
 	walker->gfn = real_gpa >> PAGE_SHIFT;
 
 	if (!write_fault)
-		FNAME(protect_clean_gpte)(mmu, &pte_access, pte);
+		FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte);
 	else
 		/*
 		 * On a write fault, fold the dirty bit into accessed_dirty.
@@ -421,10 +430,8 @@ retry_walk:
 			goto retry_walk;
 	}
 
-	walker->pt_access = pt_access;
-	walker->pte_access = pte_access;
 	pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
-		 __func__, (u64)pte, pte_access, pt_access);
+		 __func__, (u64)pte, walker->pte_access, walker->pt_access);
 	return 1;
 
 error:
@@ -452,7 +459,7 @@ error:
 	 */
 	if (!(errcode & PFERR_RSVD_MASK)) {
 		vcpu->arch.exit_qualification &= 0x187;
-		vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+		vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3;
 	}
 #endif
 	walker->fault.address = addr;
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c
index 9d4a8504a95a..5ab4a364348e 100644
--- a/arch/x86/kvm/pmu_intel.c
+++ b/arch/x86/kvm/pmu_intel.c
@@ -294,7 +294,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
 
-	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+	pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c27ac6923a18..183ddb235fb4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1272,7 +1272,8 @@ static void init_vmcb(struct vcpu_svm *svm)
 
 }
 
-static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, int index)
+static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
+				       unsigned int index)
 {
 	u64 *avic_physical_id_table;
 	struct kvm_arch *vm_data = &vcpu->kvm->arch;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c6f4ad44aa95..72f78396bc09 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6504,7 +6504,7 @@ static __init int hardware_setup(void)
 		enable_ept_ad_bits = 0;
 	}
 
-	if (!cpu_has_vmx_ept_ad_bits())
+	if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
 		enable_ept_ad_bits = 0;
 
 	if (!cpu_has_vmx_unrestricted_guest())
@@ -11213,7 +11213,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
 		if (!nested_cpu_has_pml(vmcs12))
 			return 0;
 
-		if (vmcs12->guest_pml_index > PML_ENTITY_NUM) {
+		if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
 			vmx->nested.pml_full = true;
 			return 1;
 		}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 464da936c53d..02363e37d4a6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1763,6 +1763,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 {
 	struct kvm_arch *ka = &kvm->arch;
 	struct pvclock_vcpu_time_info hv_clock;
+	u64 ret;
 
 	spin_lock(&ka->pvclock_gtod_sync_lock);
 	if (!ka->use_master_clock) {
@@ -1774,10 +1775,17 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
 	spin_unlock(&ka->pvclock_gtod_sync_lock);
 
+	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
+	get_cpu();
+
 	kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
 			   &hv_clock.tsc_shift,
 			   &hv_clock.tsc_to_system_mul);
-	return __pvclock_read_cycles(&hv_clock, rdtsc());
+	ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+
+	put_cpu();
+
+	return ret;
 }
 
 static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
@@ -3288,11 +3296,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 	}
 }
 
+#define XSAVE_MXCSR_OFFSET 24
+
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+	u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
 
 	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		/*
@@ -3300,11 +3311,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
 		 * with old userspace.
 		 */
-		if (xstate_bv & ~kvm_supported_xcr0())
+		if (xstate_bv & ~kvm_supported_xcr0() ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		load_xsave(vcpu, (u8 *)guest_xsave->region);
 	} else {
-		if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+		if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state.fxsave,
 			guest_xsave->region, sizeof(struct fxregs_state));
@@ -4818,16 +4831,20 @@ emul_write:
 
 static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 {
-	/* TODO: String I/O for in kernel device */
-	int r;
+	int r = 0, i;
 
-	if (vcpu->arch.pio.in)
-		r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
-				    vcpu->arch.pio.size, pd);
-	else
-		r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
-				     vcpu->arch.pio.port, vcpu->arch.pio.size,
-				     pd);
+	for (i = 0; i < vcpu->arch.pio.count; i++) {
+		if (vcpu->arch.pio.in)
+			r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
+					    vcpu->arch.pio.size, pd);
+		else
+			r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
+					     vcpu->arch.pio.port, vcpu->arch.pio.size,
+					     pd);
+		if (r)
+			break;
+		pd += vcpu->arch.pio.size;
+	}
 	return r;
 }
 
@@ -4865,6 +4882,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 	if (vcpu->arch.pio.count)
 		goto data_avail;
 
+	memset(vcpu->arch.pio_data, 0, size * count);
+
 	ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
 	if (ret) {
 data_avail:
@@ -5048,6 +5067,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
 
 	if (var.unusable) {
 		memset(desc, 0, sizeof(*desc));
+		if (base3)
+			*base3 = 0;
 		return false;
 	}