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

Pull kvm fixes from Paolo Bonzini:
 "Bugfixes and a one-liner patch to silence a sparse warning"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: arm64: Stop clobbering x0 for HVC_SOFT_RESTART
  KVM: arm64: PMU: Fix per-CPU access in preemptible context
  KVM: VMX: Use KVM_POSSIBLE_CR*_GUEST_BITS to initialize guest/host masks
  KVM: x86: Mark CR4.TSD as being possibly owned by the guest
  KVM: x86: Inject #GP if guest attempts to toggle CR4.LA57 in 64-bit mode
  kvm: use more precise cast and do not drop __user
  KVM: x86: bit 8 of non-leaf PDPEs is not reserved
  KVM: X86: Fix async pf caused null-ptr-deref
  KVM: arm64: vgic-v4: Plug race between non-residency and v4.1 doorbell
  KVM: arm64: pvtime: Ensure task delay accounting is enabled
  KVM: arm64: Fix kvm_reset_vcpu() return code being incorrect with SVE
  KVM: arm64: Annotate hyp NMI-related functions as __always_inline
  KVM: s390: reduce number of IO pins to 1

arch/arm64/include/asm/arch_gicv3.h

@@ -109,7 +109,7 @@ static inline u32 gic_read_pmr(void)
 	return read_sysreg_s(SYS_ICC_PMR_EL1);
 }
 
-static inline void gic_write_pmr(u32 val)
+static __always_inline void gic_write_pmr(u32 val)
 {
 	write_sysreg_s(val, SYS_ICC_PMR_EL1);
 }

arch/arm64/include/asm/cpufeature.h

@@ -675,7 +675,7 @@ static inline bool system_supports_generic_auth(void)
 		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
 }
 
-static inline bool system_uses_irq_prio_masking(void)
+static __always_inline bool system_uses_irq_prio_masking(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
 	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);

arch/arm64/kvm/hyp-init.S

@@ -136,11 +136,15 @@ SYM_CODE_START(__kvm_handle_stub_hvc)
 
 1:	cmp	x0, #HVC_RESET_VECTORS
 	b.ne	1f
-reset:
+
 	/*
-	 * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
-	 * case we coming via HVC_SOFT_RESTART.
+	 * Set the HVC_RESET_VECTORS return code before entering the common
+	 * path so that we do not clobber x0-x2 in case we are coming via
+	 * HVC_SOFT_RESTART.
 	 */
+	mov	x0, xzr
+reset:
+	/* Reset kvm back to the hyp stub. */
 	mrs	x5, sctlr_el2
 	mov_q	x6, SCTLR_ELx_FLAGS
 	bic	x5, x5, x6		// Clear SCTL_M and etc
@@ -151,7 +155,6 @@ reset:
 	/* Install stub vectors */
 	adr_l	x5, __hyp_stub_vectors
 	msr	vbar_el2, x5
-	mov	x0, xzr
 	eret
 
 1:	/* Bad stub call */

arch/arm64/kvm/pmu.c

@@ -159,7 +159,10 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events)
 }
 
 /*
- * On VHE ensure that only guest events have EL0 counting enabled
+ * On VHE ensure that only guest events have EL0 counting enabled.
+ * This is called from both vcpu_{load,put} and the sysreg handling.
+ * Since the latter is preemptible, special care must be taken to
+ * disable preemption.
  */
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
 {
@@ -169,12 +172,14 @@ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
 	if (!has_vhe())
 		return;
 
+	preempt_disable();
 	host = this_cpu_ptr(&kvm_host_data);
 	events_guest = host->pmu_events.events_guest;
 	events_host = host->pmu_events.events_host;
 
 	kvm_vcpu_pmu_enable_el0(events_guest);
 	kvm_vcpu_pmu_disable_el0(events_host);
+	preempt_enable();
 }
 
 /*

arch/arm64/kvm/pvtime.c

@@ -3,6 +3,7 @@
 
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
+#include <linux/sched/stat.h>
 
 #include <asm/kvm_mmu.h>
 #include <asm/pvclock-abi.h>
@@ -73,6 +74,11 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	return base;
 }
 
+static bool kvm_arm_pvtime_supported(void)
+{
+	return !!sched_info_on();
+}
+
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr)
 {
@@ -82,7 +88,8 @@ int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 	int ret = 0;
 	int idx;
 
-	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+	if (!kvm_arm_pvtime_supported() ||
+	    attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
 		return -ENXIO;
 
 	if (get_user(ipa, user))
@@ -110,7 +117,8 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
 	u64 __user *user = (u64 __user *)attr->addr;
 	u64 ipa;
 
-	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+	if (!kvm_arm_pvtime_supported() ||
+	    attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
 		return -ENXIO;
 
 	ipa = vcpu->arch.steal.base;
@@ -125,6 +133,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 {
 	switch (attr->attr) {
 	case KVM_ARM_VCPU_PVTIME_IPA:
+		if (kvm_arm_pvtime_supported())
 			return 0;
 	}
 	return -ENXIO;

arch/arm64/kvm/reset.c

@@ -245,7 +245,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
-	int ret = -EINVAL;
+	int ret;
 	bool loaded;
 	u32 pstate;
 
@@ -269,15 +269,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
 	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
-		if (kvm_vcpu_enable_ptrauth(vcpu))
+		if (kvm_vcpu_enable_ptrauth(vcpu)) {
+			ret = -EINVAL;
 			goto out;
 		}
+	}
 
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
+			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) {
+				ret = -EINVAL;
 				goto out;
+			}
 			pstate = VCPU_RESET_PSTATE_SVC;
 		} else {
 			pstate = VCPU_RESET_PSTATE_EL1;

arch/arm64/kvm/vgic/vgic-v4.c

@@ -90,7 +90,15 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 	    !irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
 		disable_irq_nosync(irq);
 
+	/*
+	 * The v4.1 doorbell can fire concurrently with the vPE being
+	 * made non-resident. Ensure we only update pending_last
+	 * *after* the non-residency sequence has completed.
+	 */
+	raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
+	raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
+
 	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
 

arch/s390/include/asm/kvm_host.h

@@ -31,12 +31,12 @@
 #define KVM_USER_MEM_SLOTS 32
 
 /*
- * These seem to be used for allocating ->chip in the routing table,
- * which we don't use. 4096 is an out-of-thin-air value. If we need
- * to look at ->chip later on, we'll need to revisit this.
+ * These seem to be used for allocating ->chip in the routing table, which we
+ * don't use. 1 is as small as we can get to reduce the needed memory. If we
+ * need to look at ->chip later on, we'll need to revisit this.
  */
 #define KVM_NR_IRQCHIPS 1
-#define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_IRQCHIP_NUM_PINS 1
 #define KVM_HALT_POLL_NS_DEFAULT 50000
 
 /* s390-specific vcpu->requests bit members */

arch/x86/kvm/kvm_cache_regs.h

@@ -7,7 +7,7 @@
 #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
 #define KVM_POSSIBLE_CR4_GUEST_BITS				  \
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
+	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD)
 
 #define BUILD_KVM_GPR_ACCESSORS(lname, uname)				      \
 static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\

arch/x86/kvm/mmu/mmu.c

@@ -4449,7 +4449,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | gbpages_bit_rsvd |
+			gbpages_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);

arch/x86/kvm/vmx/nested.c

@@ -4109,7 +4109,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	 * CR0_GUEST_HOST_MASK is already set in the original vmcs01
 	 * (KVM doesn't change it);
 	 */
-	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
 	vmx_set_cr0(vcpu, vmcs12->host_cr0);
 
 	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
@@ -4259,7 +4259,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 	 */
 	vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));
 
-	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
 	vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));
 
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);

arch/x86/kvm/vmx/vmx.c

@@ -133,9 +133,6 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
 #define KVM_VM_CR0_ALWAYS_ON				\
 	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | 	\
 	 X86_CR0_WP | X86_CR0_PG | X86_CR0_PE)
-#define KVM_CR4_GUEST_OWNED_BITS				      \
-	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR      \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD)
 
 #define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
@@ -4034,9 +4031,9 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 
 void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
 {
-	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
-	if (enable_ept)
-		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
+	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS;
+	if (!enable_ept)
+		vmx->vcpu.arch.cr4_guest_owned_bits &= ~X86_CR4_PGE;
 	if (is_guest_mode(&vmx->vcpu))
 		vmx->vcpu.arch.cr4_guest_owned_bits &=
 			~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask;
@@ -4333,8 +4330,8 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	/* 22.2.1, 20.8.1 */
 	vm_entry_controls_set(vmx, vmx_vmentry_ctrl());
 
-	vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS;
-	vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS);
+	vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
+	vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits);
 
 	set_cr4_guest_host_mask(vmx);
 

arch/x86/kvm/x86.c

@@ -975,6 +975,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE))
 			return 1;
+		if ((cr4 ^ old_cr4) & X86_CR4_LA57)
+			return 1;
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
@@ -2693,6 +2695,9 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 	if (data & 0x30)
 		return 1;
 
+	if (!lapic_in_kernel(vcpu))
+		return 1;
+
 	vcpu->arch.apf.msr_en_val = data;
 
 	if (!kvm_pv_async_pf_enabled(vcpu)) {

drivers/irqchip/irq-gic-v3-its.c

@@ -4054,16 +4054,24 @@ static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
 	u64 val;
 
 	if (info->req_db) {
+		unsigned long flags;
+
 		/*
 		 * vPE is going to block: make the vPE non-resident with
 		 * PendingLast clear and DB set. The GIC guarantees that if
 		 * we read-back PendingLast clear, then a doorbell will be
 		 * delivered when an interrupt comes.
+		 *
+		 * Note the locking to deal with the concurrent update of
+		 * pending_last from the doorbell interrupt handler that can
+		 * run concurrently.
 		 */
+		raw_spin_lock_irqsave(&vpe->vpe_lock, flags);
 		val = its_clear_vpend_valid(vlpi_base,
 					    GICR_VPENDBASER_PendingLast,
 					    GICR_VPENDBASER_4_1_DB);
 		vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
+		raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags);
 	} else {
 		/*
 		 * We're not blocking, so just make the vPE non-resident

virt/kvm/kvm_main.c

@@ -3350,7 +3350,8 @@ static long kvm_vcpu_compat_ioctl(struct file *filp,
 			if (kvm_sigmask.len != sizeof(compat_sigset_t))
 				goto out;
 			r = -EFAULT;
-			if (get_compat_sigset(&sigset, (void *)sigmask_arg->sigset))
+			if (get_compat_sigset(&sigset,
+					      (compat_sigset_t __user *)sigmask_arg->sigset))
 				goto out;
 			r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset);
 		} else