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

Pull KVM fixes from Radim Krčmář:
 "ARM:
   - fix incorrect huge page mappings on systems using the contiguous
     hint for hugetlbfs
   - support alternative GICv4 init sequence
   - correctly implement the ARM SMCC for HVC and SMC handling

  PPC:
   - add KVM IOCTL for reporting vulnerability and workaround status

  s390:
   - provide userspace interface for branch prediction changes in
     firmware

  x86:
   - use correct macros for bits"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: s390: wire up bpb feature
  KVM: PPC: Book3S: Provide information about hardware/firmware CVE workarounds
  KVM/x86: Fix wrong macro references of X86_CR0_PG_BIT and X86_CR4_PAE_BIT in kvm_valid_sregs()
  arm64: KVM: Fix SMCCC handling of unimplemented SMC/HVC calls
  KVM: arm64: Fix GICv4 init when called from vgic_its_create
  KVM: arm/arm64: Check pagesize when allocating a hugepage at Stage 2

Documentation/virtual/kvm/api.txt

@@ -3403,6 +3403,52 @@ invalid, if invalid pages are written to (e.g. after the end of memory)
 or if no page table is present for the addresses (e.g. when using
 hugepages).
 
+4.108 KVM_PPC_GET_CPU_CHAR
+
+Capability: KVM_CAP_PPC_GET_CPU_CHAR
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_ppc_cpu_char (out)
+Returns: 0 on successful completion
+	 -EFAULT if struct kvm_ppc_cpu_char cannot be written
+
+This ioctl gives userspace information about certain characteristics
+of the CPU relating to speculative execution of instructions and
+possible information leakage resulting from speculative execution (see
+CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754).  The information is
+returned in struct kvm_ppc_cpu_char, which looks like this:
+
+struct kvm_ppc_cpu_char {
+	__u64	character;		/* characteristics of the CPU */
+	__u64	behaviour;		/* recommended software behaviour */
+	__u64	character_mask;		/* valid bits in character */
+	__u64	behaviour_mask;		/* valid bits in behaviour */
+};
+
+For extensibility, the character_mask and behaviour_mask fields
+indicate which bits of character and behaviour have been filled in by
+the kernel.  If the set of defined bits is extended in future then
+userspace will be able to tell whether it is running on a kernel that
+knows about the new bits.
+
+The character field describes attributes of the CPU which can help
+with preventing inadvertent information disclosure - specifically,
+whether there is an instruction to flash-invalidate the L1 data cache
+(ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether the L1 data cache is set
+to a mode where entries can only be used by the thread that created
+them, whether the bcctr[l] instruction prevents speculation, and
+whether a speculation barrier instruction (ori 31,31,0) is provided.
+
+The behaviour field describes actions that software should take to
+prevent inadvertent information disclosure, and thus describes which
+vulnerabilities the hardware is subject to; specifically whether the
+L1 data cache should be flushed when returning to user mode from the
+kernel, and whether a speculation barrier should be placed between an
+array bounds check and the array access.
+
+These fields use the same bit definitions as the new
+H_GET_CPU_CHARACTERISTICS hypercall.
+
 5. The kvm_run structure
 ------------------------
 

arch/arm64/kvm/handle_exit.c

@@ -45,7 +45,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
-		kvm_inject_undefined(vcpu);
+		vcpu_set_reg(vcpu, 0, ~0UL);
 		return 1;
 	}
 
@@ -54,7 +54,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	kvm_inject_undefined(vcpu);
+	vcpu_set_reg(vcpu, 0, ~0UL);
 	return 1;
 }
 

arch/powerpc/include/uapi/asm/kvm.h

@@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info {
 	__u32	ap_encodings[8];
 };
 
+/* For KVM_PPC_GET_CPU_CHAR */
+struct kvm_ppc_cpu_char {
+	__u64	character;		/* characteristics of the CPU */
+	__u64	behaviour;		/* recommended software behaviour */
+	__u64	character_mask;		/* valid bits in character */
+	__u64	behaviour_mask;		/* valid bits in behaviour */
+};
+
+/*
+ * Values for character and character_mask.
+ * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
+ */
+#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31		(1ULL << 63)
+#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED	(1ULL << 62)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30	(1ULL << 61)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2	(1ULL << 60)
+#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV	(1ULL << 59)
+#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
+#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
+#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+
+#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
+#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
+#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
 

arch/powerpc/kvm/powerpc.c

@@ -39,6 +39,10 @@
 #include <asm/iommu.h>
 #include <asm/switch_to.h>
 #include <asm/xive.h>
+#ifdef CONFIG_PPC_PSERIES
+#include <asm/hvcall.h>
+#include <asm/plpar_wrappers.h>
+#endif
 
 #include "timing.h"
 #include "irq.h"
@@ -548,6 +552,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #ifdef CONFIG_KVM_XICS
 	case KVM_CAP_IRQ_XICS:
 #endif
+	case KVM_CAP_PPC_GET_CPU_CHAR:
 		r = 1;
 		break;
 
@@ -1759,6 +1764,124 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return r;
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * These functions check whether the underlying hardware is safe
+ * against attacks based on observing the effects of speculatively
+ * executed instructions, and whether it supplies instructions for
+ * use in workarounds.  The information comes from firmware, either
+ * via the device tree on powernv platforms or from an hcall on
+ * pseries platforms.
+ */
+#ifdef CONFIG_PPC_PSERIES
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	struct h_cpu_char_result c;
+	unsigned long rc;
+
+	if (!machine_is(pseries))
+		return -ENOTTY;
+
+	rc = plpar_get_cpu_characteristics(&c);
+	if (rc == H_SUCCESS) {
+		cp->character = c.character;
+		cp->behaviour = c.behaviour;
+		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+			KVM_PPC_CPU_CHAR_BR_HINT_HONOURED |
+			KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF |
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+	}
+	return 0;
+}
+#else
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	return -ENOTTY;
+}
+#endif
+
+static inline bool have_fw_feat(struct device_node *fw_features,
+				const char *state, const char *name)
+{
+	struct device_node *np;
+	bool r = false;
+
+	np = of_get_child_by_name(fw_features, name);
+	if (np) {
+		r = of_property_read_bool(np, state);
+		of_node_put(np);
+	}
+	return r;
+}
+
+static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	struct device_node *np, *fw_features;
+	int r;
+
+	memset(cp, 0, sizeof(*cp));
+	r = pseries_get_cpu_char(cp);
+	if (r != -ENOTTY)
+		return r;
+
+	np = of_find_node_by_name(NULL, "ibm,opal");
+	if (np) {
+		fw_features = of_get_child_by_name(np, "fw-features");
+		of_node_put(np);
+		if (!fw_features)
+			return 0;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-spec-barrier-ori31,31,0"))
+			cp->character |= KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-bcctrl-serialized"))
+			cp->character |= KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-l1d-flush-ori30,30,0"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-l1d-flush-trig2"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-l1d-thread-split"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-count-cache-disabled"))
+			cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+
+		if (have_fw_feat(fw_features, "enabled",
+				 "speculation-policy-favor-security"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY;
+		if (!have_fw_feat(fw_features, "disabled",
+				  "needs-l1d-flush-msr-pr-0-to-1"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR;
+		if (!have_fw_feat(fw_features, "disabled",
+				  "needs-spec-barrier-for-bound-checks"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+
+		of_node_put(fw_features);
+	}
+
+	return 0;
+}
+#endif
+
 long kvm_arch_vm_ioctl(struct file *filp,
                        unsigned int ioctl, unsigned long arg)
 {
@@ -1861,6 +1984,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+	case KVM_PPC_GET_CPU_CHAR: {
+		struct kvm_ppc_cpu_char cpuchar;
+
+		r = kvmppc_get_cpu_char(&cpuchar);
+		if (r >= 0 && copy_to_user(argp, &cpuchar, sizeof(cpuchar)))
+			r = -EFAULT;
+		break;
+	}
 	default: {
 		struct kvm *kvm = filp->private_data;
 		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);

arch/s390/include/asm/kvm_host.h

@@ -207,7 +207,8 @@ struct kvm_s390_sie_block {
 	__u16	ipa;			/* 0x0056 */
 	__u32	ipb;			/* 0x0058 */
 	__u32	scaoh;			/* 0x005c */
-	__u8	reserved60;		/* 0x0060 */
+#define FPF_BPBC 	0x20
+	__u8	fpf;			/* 0x0060 */
 #define ECB_GS		0x40
 #define ECB_TE		0x10
 #define ECB_SRSI	0x04

arch/s390/include/uapi/asm/kvm.h

@@ -224,6 +224,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_RICCB  (1UL << 7)
 #define KVM_SYNC_FPRS   (1UL << 8)
 #define KVM_SYNC_GSCB   (1UL << 9)
+#define KVM_SYNC_BPBC   (1UL << 10)
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
@@ -247,7 +248,9 @@ struct kvm_sync_regs {
 	};
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
-	__u8 padding1[52];	/* riccb needs to be 64byte aligned */
+	__u8 bpbc : 1;		/* bp mode */
+	__u8 reserved2 : 7;
+	__u8 padding1[51];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
 	__u8 padding2[192];	/* sdnx needs to be 256byte aligned */
 	union {

arch/s390/kvm/kvm-s390.c

@@ -421,6 +421,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_GS:
 		r = test_facility(133);
 		break;
+	case KVM_CAP_S390_BPB:
+		r = test_facility(82);
+		break;
 	default:
 		r = 0;
 	}
@@ -2198,6 +2201,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	kvm_s390_set_prefix(vcpu, 0);
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
+	if (test_kvm_facility(vcpu->kvm, 82))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
 	if (test_kvm_facility(vcpu->kvm, 133))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
 	/* fprs can be synchronized via vrs, even if the guest has no vx. With
@@ -2339,6 +2344,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
+	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
@@ -3298,6 +3304,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
 		vcpu->arch.gs_enabled = 1;
 	}
+	if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) &&
+	    test_kvm_facility(vcpu->kvm, 82)) {
+		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
+	}
 	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	/* save host (userspace) fprs/vrs */
@@ -3344,6 +3355,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
 	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
 	/* Save guest register state */

arch/s390/kvm/vsie.c

@@ -223,6 +223,12 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	memcpy(scb_o->gcr, scb_s->gcr, 128);
 	scb_o->pp = scb_s->pp;
 
+	/* branch prediction */
+	if (test_kvm_facility(vcpu->kvm, 82)) {
+		scb_o->fpf &= ~FPF_BPBC;
+		scb_o->fpf |= scb_s->fpf & FPF_BPBC;
+	}
+
 	/* interrupt intercept */
 	switch (scb_s->icptcode) {
 	case ICPT_PROGI:
@@ -265,6 +271,7 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	scb_s->ecb3 = 0;
 	scb_s->ecd = 0;
 	scb_s->fac = 0;
+	scb_s->fpf = 0;
 
 	rc = prepare_cpuflags(vcpu, vsie_page);
 	if (rc)
@@ -324,6 +331,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			prefix_unmapped(vsie_page);
 		scb_s->ecb |= scb_o->ecb & ECB_TE;
 	}
+	/* branch prediction */
+	if (test_kvm_facility(vcpu->kvm, 82))
+		scb_s->fpf |= scb_o->fpf & FPF_BPBC;
 	/* SIMD */
 	if (test_kvm_facility(vcpu->kvm, 129)) {
 		scb_s->eca |= scb_o->eca & ECA_VX;

arch/x86/kvm/x86.c

@@ -7496,13 +7496,13 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);
 
 int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
-	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) {
+	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
 		/*
 		 * When EFER.LME and CR0.PG are set, the processor is in
 		 * 64-bit mode (though maybe in a 32-bit code segment).
 		 * CR4.PAE and EFER.LMA must be set.
 		 */
-		if (!(sregs->cr4 & X86_CR4_PAE_BIT)
+		if (!(sregs->cr4 & X86_CR4_PAE)
 		    || !(sregs->efer & EFER_LMA))
 			return -EINVAL;
 	} else {

include/uapi/linux/kvm.h

@@ -932,6 +932,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_SYNIC2 148
 #define KVM_CAP_HYPERV_VP_INDEX 149
 #define KVM_CAP_S390_AIS_MIGRATION 150
+#define KVM_CAP_PPC_GET_CPU_CHAR 151
+#define KVM_CAP_S390_BPB 152
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1261,6 +1263,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
 /* Available with KVM_CAP_PPC_RADIX_MMU */
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
+/* Available with KVM_CAP_PPC_GET_CPU_CHAR */
+#define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)

virt/kvm/arm/mmu.c

@@ -1310,7 +1310,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
-	if (is_vm_hugetlb_page(vma) && !logging_active) {
+	if (vma_kernel_pagesize(vma) == PMD_SIZE && !logging_active) {
 		hugetlb = true;
 		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
 	} else {

virt/kvm/arm/vgic/vgic-init.c

@@ -285,9 +285,11 @@ int vgic_init(struct kvm *kvm)
 	if (ret)
 		goto out;
 
-	ret = vgic_v4_init(kvm);
-	if (ret)
-		goto out;
+	if (vgic_has_its(kvm)) {
+		ret = vgic_v4_init(kvm);
+		if (ret)
+			goto out;
+	}
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_vgic_vcpu_enable(vcpu);

virt/kvm/arm/vgic/vgic-v4.c

@@ -118,7 +118,7 @@ int vgic_v4_init(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	int i, nr_vcpus, ret;
 
-	if (!vgic_supports_direct_msis(kvm))
+	if (!kvm_vgic_global_state.has_gicv4)
 		return 0; /* Nothing to see here... move along. */
 
 	if (dist->its_vm.vpes)