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

Pull kvm updates from Paolo Bonzini:
 "S390:

   - ultravisor communication device driver

   - fix TEID on terminating storage key ops

  RISC-V:

   - Added Sv57x4 support for G-stage page table

   - Added range based local HFENCE functions

   - Added remote HFENCE functions based on VCPU requests

   - Added ISA extension registers in ONE_REG interface

   - Updated KVM RISC-V maintainers entry to cover selftests support

  ARM:

   - Add support for the ARMv8.6 WFxT extension

   - Guard pages for the EL2 stacks

   - Trap and emulate AArch32 ID registers to hide unsupported features

   - Ability to select and save/restore the set of hypercalls exposed to
     the guest

   - Support for PSCI-initiated suspend in collaboration with userspace

   - GICv3 register-based LPI invalidation support

   - Move host PMU event merging into the vcpu data structure

   - GICv3 ITS save/restore fixes

   - The usual set of small-scale cleanups and fixes

  x86:

   - New ioctls to get/set TSC frequency for a whole VM

   - Allow userspace to opt out of hypercall patching

   - Only do MSR filtering for MSRs accessed by rdmsr/wrmsr

  AMD SEV improvements:

   - Add KVM_EXIT_SHUTDOWN metadata for SEV-ES

   - V_TSC_AUX support

  Nested virtualization improvements for AMD:

   - Support for "nested nested" optimizations (nested vVMLOAD/VMSAVE,
     nested vGIF)

   - Allow AVIC to co-exist with a nested guest running

   - Fixes for LBR virtualizations when a nested guest is running, and
     nested LBR virtualization support

   - PAUSE filtering for nested hypervisors

  Guest support:

   - Decoupling of vcpu_is_preempted from PV spinlocks"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (199 commits)
  KVM: x86: Fix the intel_pt PMI handling wrongly considered from guest
  KVM: selftests: x86: Sync the new name of the test case to .gitignore
  Documentation: kvm: reorder ARM-specific section about KVM_SYSTEM_EVENT_SUSPEND
  x86, kvm: use correct GFP flags for preemption disabled
  KVM: LAPIC: Drop pending LAPIC timer injection when canceling the timer
  x86/kvm: Alloc dummy async #PF token outside of raw spinlock
  KVM: x86: avoid calling x86 emulator without a decoded instruction
  KVM: SVM: Use kzalloc for sev ioctl interfaces to prevent kernel data leak
  x86/fpu: KVM: Set the base guest FPU uABI size to sizeof(struct kvm_xsave)
  s390/uv_uapi: depend on CONFIG_S390
  KVM: selftests: x86: Fix test failure on arch lbr capable platforms
  KVM: LAPIC: Trace LAPIC timer expiration on every vmentry
  KVM: s390: selftest: Test suppression indication on key prot exception
  KVM: s390: Don't indicate suppression on dirtying, failing memop
  selftests: drivers/s390x: Add uvdevice tests
  drivers/s390/char: Add Ultravisor io device
  MAINTAINERS: Update KVM RISC-V entry to cover selftests support
  RISC-V: KVM: Introduce ISA extension register
  RISC-V: KVM: Cleanup stale TLB entries when host CPU changes
  RISC-V: KVM: Add remote HFENCE functions based on VCPU requests
  ...

3 files changed, 91 insertions, 5 deletions

diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index a2d376b8bce3..cfea7b77a5b8 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -2,7 +2,7 @@
 /*
  * Ultravisor Interfaces
  *
- * Copyright IBM Corp. 2019
+ * Copyright IBM Corp. 2019, 2022
  *
  * Author(s):
  *	Vasily Gorbik <gor@linux.ibm.com>
@@ -52,6 +52,7 @@
 #define UVC_CMD_UNPIN_PAGE_SHARED	0x0342
 #define UVC_CMD_SET_SHARED_ACCESS	0x1000
 #define UVC_CMD_REMOVE_SHARED_ACCESS	0x1001
+#define UVC_CMD_RETR_ATTEST		0x1020
 
 /* Bits in installed uv calls */
 enum uv_cmds_inst {
@@ -76,6 +77,7 @@ enum uv_cmds_inst {
 	BIT_UVC_CMD_UNSHARE_ALL = 20,
 	BIT_UVC_CMD_PIN_PAGE_SHARED = 21,
 	BIT_UVC_CMD_UNPIN_PAGE_SHARED = 22,
+	BIT_UVC_CMD_RETR_ATTEST = 28,
 };
 
 enum uv_feat_ind {
@@ -219,6 +221,25 @@ struct uv_cb_share {
 	u64 reserved28;
 } __packed __aligned(8);
 
+/* Retrieve Attestation Measurement */
+struct uv_cb_attest {
+	struct uv_cb_header header;	/* 0x0000 */
+	u64 reserved08[2];		/* 0x0008 */
+	u64 arcb_addr;			/* 0x0018 */
+	u64 cont_token;			/* 0x0020 */
+	u8  reserved28[6];		/* 0x0028 */
+	u16 user_data_len;		/* 0x002e */
+	u8  user_data[256];		/* 0x0030 */
+	u32 reserved130[3];		/* 0x0130 */
+	u32 meas_len;			/* 0x013c */
+	u64 meas_addr;			/* 0x0140 */
+	u8  config_uid[16];		/* 0x0148 */
+	u32 reserved158;		/* 0x0158 */
+	u32 add_data_len;		/* 0x015c */
+	u64 add_data_addr;		/* 0x0160 */
+	u64 reserved168[4];		/* 0x0168 */
+} __packed __aligned(8);
+
 static inline int __uv_call(unsigned long r1, unsigned long r2)
 {
 	int cc;
diff --git a/arch/s390/include/uapi/asm/uvdevice.h b/arch/s390/include/uapi/asm/uvdevice.h
new file mode 100644
index 000000000000..10a5ac918e02
--- /dev/null
+++ b/arch/s390/include/uapi/asm/uvdevice.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ *  Copyright IBM Corp. 2022
+ *  Author(s): Steffen Eiden <seiden@linux.ibm.com>
+ */
+#ifndef __S390_ASM_UVDEVICE_H
+#define __S390_ASM_UVDEVICE_H
+
+#include <linux/types.h>
+
+struct uvio_ioctl_cb {
+	__u32 flags;
+	__u16 uv_rc;			/* UV header rc value */
+	__u16 uv_rrc;			/* UV header rrc value */
+	__u64 argument_addr;		/* Userspace address of uvio argument */
+	__u32 argument_len;
+	__u8  reserved14[0x40 - 0x14];	/* must be zero */
+};
+
+#define UVIO_ATT_USER_DATA_LEN		0x100
+#define UVIO_ATT_UID_LEN		0x10
+struct uvio_attest {
+	__u64 arcb_addr;				/* 0x0000 */
+	__u64 meas_addr;				/* 0x0008 */
+	__u64 add_data_addr;				/* 0x0010 */
+	__u8  user_data[UVIO_ATT_USER_DATA_LEN];	/* 0x0018 */
+	__u8  config_uid[UVIO_ATT_UID_LEN];		/* 0x0118 */
+	__u32 arcb_len;					/* 0x0128 */
+	__u32 meas_len;					/* 0x012c */
+	__u32 add_data_len;				/* 0x0130 */
+	__u16 user_data_len;				/* 0x0134 */
+	__u16 reserved136;				/* 0x0136 */
+};
+
+/*
+ * The following max values define an upper length for the IOCTL in/out buffers.
+ * However, they do not represent the maximum the Ultravisor allows which is
+ * often way smaller. By allowing larger buffer sizes we hopefully do not need
+ * to update the code with every machine update. It is therefore possible for
+ * userspace to request more memory than actually used by kernel/UV.
+ */
+#define UVIO_ATT_ARCB_MAX_LEN		0x100000
+#define UVIO_ATT_MEASUREMENT_MAX_LEN	0x8000
+#define UVIO_ATT_ADDITIONAL_MAX_LEN	0x8000
+
+#define UVIO_DEVICE_NAME "uv"
+#define UVIO_TYPE_UVC 'u'
+
+#define UVIO_IOCTL_ATT _IOWR(UVIO_TYPE_UVC, 0x01, struct uvio_ioctl_cb)
+
+#endif /* __S390_ASM_UVDEVICE_H */
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index d53a183c2005..227ed0009354 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -491,8 +491,8 @@ enum prot_type {
 	PROT_TYPE_IEP  = 4,
 };
 
-static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
-		     u8 ar, enum gacc_mode mode, enum prot_type prot)
+static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, u8 ar,
+			    enum gacc_mode mode, enum prot_type prot, bool terminate)
 {
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	struct trans_exc_code_bits *tec;
@@ -520,6 +520,11 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
 			tec->b61 = 1;
 			break;
 		}
+		if (terminate) {
+			tec->b56 = 0;
+			tec->b60 = 0;
+			tec->b61 = 0;
+		}
 		fallthrough;
 	case PGM_ASCE_TYPE:
 	case PGM_PAGE_TRANSLATION:
@@ -552,6 +557,12 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
 	return code;
 }
 
+static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva, u8 ar,
+		     enum gacc_mode mode, enum prot_type prot)
+{
+	return trans_exc_ending(vcpu, code, gva, ar, mode, prot, false);
+}
+
 static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
 			 unsigned long ga, u8 ar, enum gacc_mode mode)
 {
@@ -1109,8 +1120,11 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 		data += fragment_len;
 		ga = kvm_s390_logical_to_effective(vcpu, ga + fragment_len);
 	}
-	if (rc > 0)
-		rc = trans_exc(vcpu, rc, ga, ar, mode, prot);
+	if (rc > 0) {
+		bool terminate = (mode == GACC_STORE) && (idx > 0);
+
+		rc = trans_exc_ending(vcpu, rc, ga, ar, mode, prot, terminate);
+	}
 out_unlock:
 	if (need_ipte_lock)
 		ipte_unlock(vcpu);