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

Pull KVM updates from Paolo Bonzini:
 "4.11 is going to be a relatively large release for KVM, with a little
  over 200 commits and noteworthy changes for most architectures.

  ARM:
   - GICv3 save/restore
   - cache flushing fixes
   - working MSI injection for GICv3 ITS
   - physical timer emulation

  MIPS:
   - various improvements under the hood
   - support for SMP guests
   - a large rewrite of MMU emulation. KVM MIPS can now use MMU
     notifiers to support copy-on-write, KSM, idle page tracking,
     swapping, ballooning and everything else. KVM_CAP_READONLY_MEM is
     also supported, so that writes to some memory regions can be
     treated as MMIO. The new MMU also paves the way for hardware
     virtualization support.

  PPC:
   - support for POWER9 using the radix-tree MMU for host and guest
   - resizable hashed page table
   - bugfixes.

  s390:
   - expose more features to the guest
   - more SIMD extensions
   - instruction execution protection
   - ESOP2

  x86:
   - improved hashing in the MMU
   - faster PageLRU tracking for Intel CPUs without EPT A/D bits
   - some refactoring of nested VMX entry/exit code, preparing for live
     migration support of nested hypervisors
   - expose yet another AVX512 CPUID bit
   - host-to-guest PTP support
   - refactoring of interrupt injection, with some optimizations thrown
     in and some duct tape removed.
   - remove lazy FPU handling
   - optimizations of user-mode exits
   - optimizations of vcpu_is_preempted() for KVM guests

  generic:
   - alternative signaling mechanism that doesn't pound on
     tsk->sighand->siglock"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (195 commits)
  x86/kvm: Provide optimized version of vcpu_is_preempted() for x86-64
  x86/paravirt: Change vcp_is_preempted() arg type to long
  KVM: VMX: use correct vmcs_read/write for guest segment selector/base
  x86/kvm/vmx: Defer TR reload after VM exit
  x86/asm/64: Drop __cacheline_aligned from struct x86_hw_tss
  x86/kvm/vmx: Simplify segment_base()
  x86/kvm/vmx: Get rid of segment_base() on 64-bit kernels
  x86/kvm/vmx: Don't fetch the TSS base from the GDT
  x86/asm: Define the kernel TSS limit in a macro
  kvm: fix page struct leak in handle_vmon
  KVM: PPC: Book3S HV: Disable HPT resizing on POWER9 for now
  KVM: Return an error code only as a constant in kvm_get_dirty_log()
  KVM: Return an error code only as a constant in kvm_get_dirty_log_protect()
  KVM: Return directly after a failed copy_from_user() in kvm_vm_compat_ioctl()
  KVM: x86: remove code for lazy FPU handling
  KVM: race-free exit from KVM_RUN without POSIX signals
  KVM: PPC: Book3S HV: Turn "KVM guest htab" message into a debug message
  KVM: PPC: Book3S PR: Ratelimit copy data failure error messages
  KVM: Support vCPU-based gfn->hva cache
  KVM: use separate generations for each address space
  ...

8 files changed, 224 insertions, 57 deletions

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 4aa8a7e2a1da..4492c9363178 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -373,7 +373,7 @@ void ipte_unlock(struct kvm_vcpu *vcpu)
 		ipte_unlock_simple(vcpu);
 }
 
-static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
+static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, u8 ar,
 			  enum gacc_mode mode)
 {
 	union alet alet;
@@ -465,7 +465,9 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
 struct trans_exc_code_bits {
 	unsigned long addr : 52; /* Translation-exception Address */
 	unsigned long fsi  : 2;  /* Access Exception Fetch/Store Indication */
-	unsigned long	   : 6;
+	unsigned long	   : 2;
+	unsigned long b56  : 1;
+	unsigned long	   : 3;
 	unsigned long b60  : 1;
 	unsigned long b61  : 1;
 	unsigned long as   : 2;  /* ASCE Identifier */
@@ -485,7 +487,7 @@ enum prot_type {
 };
 
 static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
-		     ar_t ar, enum gacc_mode mode, enum prot_type prot)
+		     u8 ar, enum gacc_mode mode, enum prot_type prot)
 {
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	struct trans_exc_code_bits *tec;
@@ -497,14 +499,18 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
 	switch (code) {
 	case PGM_PROTECTION:
 		switch (prot) {
+		case PROT_TYPE_LA:
+			tec->b56 = 1;
+			break;
+		case PROT_TYPE_KEYC:
+			tec->b60 = 1;
+			break;
 		case PROT_TYPE_ALC:
 			tec->b60 = 1;
 			/* FALL THROUGH */
 		case PROT_TYPE_DAT:
 			tec->b61 = 1;
 			break;
-		default: /* LA and KEYC set b61 to 0, other params undefined */
-			return code;
 		}
 		/* FALL THROUGH */
 	case PGM_ASCE_TYPE:
@@ -539,7 +545,7 @@ static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
 }
 
 static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
-			 unsigned long ga, ar_t ar, enum gacc_mode mode)
+			 unsigned long ga, u8 ar, enum gacc_mode mode)
 {
 	int rc;
 	struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw);
@@ -771,7 +777,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar,
+static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 			    unsigned long *pages, unsigned long nr_pages,
 			    const union asce asce, enum gacc_mode mode)
 {
@@ -803,7 +809,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar,
 	return 0;
 }
 
-int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
+int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 		 unsigned long len, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -877,7 +883,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
  * Note: The IPTE lock is not taken during this function, so the caller
  * has to take care of this.
  */
-int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
+int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 			    unsigned long *gpa, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -910,7 +916,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
 /**
  * check_gva_range - test a range of guest virtual addresses for accessibility
  */
-int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
+int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode)
 {
 	unsigned long gpa;
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index 8756569ad938..7ce47fd36f28 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -162,11 +162,11 @@ enum gacc_mode {
 };
 
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
-			    ar_t ar, unsigned long *gpa, enum gacc_mode mode);
-int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
+			    u8 ar, unsigned long *gpa, enum gacc_mode mode);
+int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode);
 
-int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
+int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 		 unsigned long len, enum gacc_mode mode);
 
 int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
@@ -218,7 +218,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
  *	 if data has been changed in guest space in case of an exception.
  */
 static inline __must_check
-int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
+int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 		unsigned long len)
 {
 	return access_guest(vcpu, ga, ar, data, len, GACC_STORE);
@@ -238,7 +238,7 @@ int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
  * data will be copied from guest space to kernel space.
  */
 static inline __must_check
-int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
+int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, void *data,
 	       unsigned long len)
 {
 	return access_guest(vcpu, ga, ar, data, len, GACC_FETCH);
@@ -247,10 +247,11 @@ int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 /**
  * read_guest_instr - copy instruction data from guest space to kernel space
  * @vcpu: virtual cpu
+ * @ga: guest address
  * @data: destination address in kernel space
  * @len: number of bytes to copy
  *
- * Copy @len bytes from the current psw address (guest space) to @data (kernel
+ * Copy @len bytes from the given address (guest space) to @data (kernel
  * space).
  *
  * The behaviour of read_guest_instr is identical to read_guest, except that
@@ -258,10 +259,10 @@ int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
  * address-space mode.
  */
 static inline __must_check
-int read_guest_instr(struct kvm_vcpu *vcpu, void *data, unsigned long len)
+int read_guest_instr(struct kvm_vcpu *vcpu, unsigned long ga, void *data,
+		     unsigned long len)
 {
-	return access_guest(vcpu, vcpu->arch.sie_block->gpsw.addr, 0, data, len,
-			    GACC_IFETCH);
+	return access_guest(vcpu, ga, 0, data, len, GACC_IFETCH);
 }
 
 /**
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index d7c6a7f53ced..23d9a4e12da1 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -388,14 +388,13 @@ void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu)
 #define per_write_wp_event(code) \
 			(code & (PER_CODE_STORE | PER_CODE_STORE_REAL))
 
-static int debug_exit_required(struct kvm_vcpu *vcpu)
+static int debug_exit_required(struct kvm_vcpu *vcpu, u8 perc,
+			       unsigned long peraddr)
 {
-	u8 perc = vcpu->arch.sie_block->perc;
 	struct kvm_debug_exit_arch *debug_exit = &vcpu->run->debug.arch;
 	struct kvm_hw_wp_info_arch *wp_info = NULL;
 	struct kvm_hw_bp_info_arch *bp_info = NULL;
 	unsigned long addr = vcpu->arch.sie_block->gpsw.addr;
-	unsigned long peraddr = vcpu->arch.sie_block->peraddr;
 
 	if (guestdbg_hw_bp_enabled(vcpu)) {
 		if (per_write_wp_event(perc) &&
@@ -437,36 +436,118 @@ exit_required:
 	return 1;
 }
 
+static int per_fetched_addr(struct kvm_vcpu *vcpu, unsigned long *addr)
+{
+	u8 exec_ilen = 0;
+	u16 opcode[3];
+	int rc;
+
+	if (vcpu->arch.sie_block->icptcode == ICPT_PROGI) {
+		/* PER address references the fetched or the execute instr */
+		*addr = vcpu->arch.sie_block->peraddr;
+		/*
+		 * Manually detect if we have an EXECUTE instruction. As
+		 * instructions are always 2 byte aligned we can read the
+		 * first two bytes unconditionally
+		 */
+		rc = read_guest_instr(vcpu, *addr, &opcode, 2);
+		if (rc)
+			return rc;
+		if (opcode[0] >> 8 == 0x44)
+			exec_ilen = 4;
+		if ((opcode[0] & 0xff0f) == 0xc600)
+			exec_ilen = 6;
+	} else {
+		/* instr was suppressed, calculate the responsible instr */
+		*addr = __rewind_psw(vcpu->arch.sie_block->gpsw,
+				     kvm_s390_get_ilen(vcpu));
+		if (vcpu->arch.sie_block->icptstatus & 0x01) {
+			exec_ilen = (vcpu->arch.sie_block->icptstatus & 0x60) >> 4;
+			if (!exec_ilen)
+				exec_ilen = 4;
+		}
+	}
+
+	if (exec_ilen) {
+		/* read the complete EXECUTE instr to detect the fetched addr */
+		rc = read_guest_instr(vcpu, *addr, &opcode, exec_ilen);
+		if (rc)
+			return rc;
+		if (exec_ilen == 6) {
+			/* EXECUTE RELATIVE LONG - RIL-b format */
+			s32 rl = *((s32 *) (opcode + 1));
+
+			/* rl is a _signed_ 32 bit value specifying halfwords */
+			*addr += (u64)(s64) rl * 2;
+		} else {
+			/* EXECUTE - RX-a format */
+			u32 base = (opcode[1] & 0xf000) >> 12;
+			u32 disp = opcode[1] & 0x0fff;
+			u32 index = opcode[0] & 0x000f;
+
+			*addr = base ? vcpu->run->s.regs.gprs[base] : 0;
+			*addr += index ? vcpu->run->s.regs.gprs[index] : 0;
+			*addr += disp;
+		}
+		*addr = kvm_s390_logical_to_effective(vcpu, *addr);
+	}
+	return 0;
+}
+
 #define guest_per_enabled(vcpu) \
 			     (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER)
 
 int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu)
 {
+	const u64 cr10 = vcpu->arch.sie_block->gcr[10];
+	const u64 cr11 = vcpu->arch.sie_block->gcr[11];
 	const u8 ilen = kvm_s390_get_ilen(vcpu);
 	struct kvm_s390_pgm_info pgm_info = {
 		.code = PGM_PER,
 		.per_code = PER_CODE_IFETCH,
 		.per_address = __rewind_psw(vcpu->arch.sie_block->gpsw, ilen),
 	};
+	unsigned long fetched_addr;
+	int rc;
 
 	/*
 	 * The PSW points to the next instruction, therefore the intercepted
 	 * instruction generated a PER i-fetch event. PER address therefore
 	 * points at the previous PSW address (could be an EXECUTE function).
 	 */
-	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+	if (!guestdbg_enabled(vcpu))
+		return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+
+	if (debug_exit_required(vcpu, pgm_info.per_code, pgm_info.per_address))
+		vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING;
+
+	if (!guest_per_enabled(vcpu) ||
+	    !(vcpu->arch.sie_block->gcr[9] & PER_EVENT_IFETCH))
+		return 0;
+
+	rc = per_fetched_addr(vcpu, &fetched_addr);
+	if (rc < 0)
+		return rc;
+	if (rc)
+		/* instruction-fetching exceptions */
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	if (in_addr_range(fetched_addr, cr10, cr11))
+		return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+	return 0;
 }
 
-static void filter_guest_per_event(struct kvm_vcpu *vcpu)
+static int filter_guest_per_event(struct kvm_vcpu *vcpu)
 {
 	const u8 perc = vcpu->arch.sie_block->perc;
-	u64 peraddr = vcpu->arch.sie_block->peraddr;
 	u64 addr = vcpu->arch.sie_block->gpsw.addr;
 	u64 cr9 = vcpu->arch.sie_block->gcr[9];
 	u64 cr10 = vcpu->arch.sie_block->gcr[10];
 	u64 cr11 = vcpu->arch.sie_block->gcr[11];
 	/* filter all events, demanded by the guest */
 	u8 guest_perc = perc & (cr9 >> 24) & PER_CODE_MASK;
+	unsigned long fetched_addr;
+	int rc;
 
 	if (!guest_per_enabled(vcpu))
 		guest_perc = 0;
@@ -478,9 +559,17 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 		guest_perc &= ~PER_CODE_BRANCH;
 
 	/* filter "instruction-fetching" events */
-	if (guest_perc & PER_CODE_IFETCH &&
-	    !in_addr_range(peraddr, cr10, cr11))
-		guest_perc &= ~PER_CODE_IFETCH;
+	if (guest_perc & PER_CODE_IFETCH) {
+		rc = per_fetched_addr(vcpu, &fetched_addr);
+		if (rc < 0)
+			return rc;
+		/*
+		 * Don't inject an irq on exceptions. This would make handling
+		 * on icpt code 8 very complex (as PSW was already rewound).
+		 */
+		if (rc || !in_addr_range(fetched_addr, cr10, cr11))
+			guest_perc &= ~PER_CODE_IFETCH;
+	}
 
 	/* All other PER events will be given to the guest */
 	/* TODO: Check altered address/address space */
@@ -489,6 +578,7 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 
 	if (!guest_perc)
 		vcpu->arch.sie_block->iprcc &= ~PGM_PER;
+	return 0;
 }
 
 #define pssec(vcpu) (vcpu->arch.sie_block->gcr[1] & _ASCE_SPACE_SWITCH)
@@ -496,14 +586,17 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 #define old_ssec(vcpu) ((vcpu->arch.sie_block->tecmc >> 31) & 0x1)
 #define old_as_is_home(vcpu) !(vcpu->arch.sie_block->tecmc & 0xffff)
 
-void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
+int kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
 {
-	int new_as;
+	int rc, new_as;
 
-	if (debug_exit_required(vcpu))
+	if (debug_exit_required(vcpu, vcpu->arch.sie_block->perc,
+				vcpu->arch.sie_block->peraddr))
 		vcpu->guest_debug |= KVM_GUESTDBG_EXIT_PENDING;
 
-	filter_guest_per_event(vcpu);
+	rc = filter_guest_per_event(vcpu);
+	if (rc)
+		return rc;
 
 	/*
 	 * Only RP, SAC, SACF, PT, PTI, PR, PC instructions can trigger
@@ -532,4 +625,5 @@ void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu)
 		    (pssec(vcpu) || old_ssec(vcpu)))
 			vcpu->arch.sie_block->iprcc = PGM_SPACE_SWITCH;
 	}
+	return 0;
 }
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 7a27eebab28a..59920f96ebc0 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -238,7 +238,9 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 	vcpu->stat.exit_program_interruption++;
 
 	if (guestdbg_enabled(vcpu) && per_event(vcpu)) {
-		kvm_s390_handle_per_event(vcpu);
+		rc = kvm_s390_handle_per_event(vcpu);
+		if (rc)
+			return rc;
 		/* the interrupt might have been filtered out completely */
 		if (vcpu->arch.sie_block->iprcc == 0)
 			return 0;
@@ -359,6 +361,9 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu)
 
 static int handle_operexc(struct kvm_vcpu *vcpu)
 {
+	psw_t oldpsw, newpsw;
+	int rc;
+
 	vcpu->stat.exit_operation_exception++;
 	trace_kvm_s390_handle_operexc(vcpu, vcpu->arch.sie_block->ipa,
 				      vcpu->arch.sie_block->ipb);
@@ -369,6 +374,24 @@ static int handle_operexc(struct kvm_vcpu *vcpu)
 
 	if (vcpu->arch.sie_block->ipa == 0 && vcpu->kvm->arch.user_instr0)
 		return -EOPNOTSUPP;
+	rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &newpsw, sizeof(psw_t));
+	if (rc)
+		return rc;
+	/*
+	 * Avoid endless loops of operation exceptions, if the pgm new
+	 * PSW will cause a new operation exception.
+	 * The heuristic checks if the pgm new psw is within 6 bytes before
+	 * the faulting psw address (with same DAT, AS settings) and the
+	 * new psw is not a wait psw and the fault was not triggered by
+	 * problem state.
+	 */
+	oldpsw = vcpu->arch.sie_block->gpsw;
+	if (oldpsw.addr - newpsw.addr <= 6 &&
+	    !(newpsw.mask & PSW_MASK_WAIT) &&
+	    !(oldpsw.mask & PSW_MASK_PSTATE) &&
+	    (newpsw.mask & PSW_MASK_ASC) == (oldpsw.mask & PSW_MASK_ASC) &&
+	    (newpsw.mask & PSW_MASK_DAT) == (oldpsw.mask & PSW_MASK_DAT))
+		return -EOPNOTSUPP;
 
 	return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
 }
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b604854df02c..f5694838234d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -218,7 +218,7 @@ static void allow_cpu_feat(unsigned long nr)
 static inline int plo_test_bit(unsigned char nr)
 {
 	register unsigned long r0 asm("0") = (unsigned long) nr | 0x100;
-	int cc = 3; /* subfunction not available */
+	int cc;
 
 	asm volatile(
 		/* Parameter registers are ignored for "test bit" */
@@ -371,6 +371,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_IRQCHIP:
 	case KVM_CAP_VM_ATTRIBUTES:
 	case KVM_CAP_MP_STATE:
+	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_S390_INJECT_IRQ:
 	case KVM_CAP_S390_USER_SIGP:
 	case KVM_CAP_S390_USER_STSI:
@@ -443,6 +444,9 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	struct kvm_memory_slot *memslot;
 	int is_dirty = 0;
 
+	if (kvm_is_ucontrol(kvm))
+		return -EINVAL;
+
 	mutex_lock(&kvm->slots_lock);
 
 	r = -EINVAL;
@@ -506,6 +510,14 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		} else if (MACHINE_HAS_VX) {
 			set_kvm_facility(kvm->arch.model.fac_mask, 129);
 			set_kvm_facility(kvm->arch.model.fac_list, 129);
+			if (test_facility(134)) {
+				set_kvm_facility(kvm->arch.model.fac_mask, 134);
+				set_kvm_facility(kvm->arch.model.fac_list, 134);
+			}
+			if (test_facility(135)) {
+				set_kvm_facility(kvm->arch.model.fac_mask, 135);
+				set_kvm_facility(kvm->arch.model.fac_list, 135);
+			}
 			r = 0;
 		} else
 			r = -EINVAL;
@@ -822,6 +834,13 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 		}
 		memcpy(kvm->arch.model.fac_list, proc->fac_list,
 		       S390_ARCH_FAC_LIST_SIZE_BYTE);
+		VM_EVENT(kvm, 3, "SET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx",
+			 kvm->arch.model.ibc,
+			 kvm->arch.model.cpuid);
+		VM_EVENT(kvm, 3, "SET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx",
+			 kvm->arch.model.fac_list[0],
+			 kvm->arch.model.fac_list[1],
+			 kvm->arch.model.fac_list[2]);
 	} else
 		ret = -EFAULT;
 	kfree(proc);
@@ -895,6 +914,13 @@ static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 	proc->ibc = kvm->arch.model.ibc;
 	memcpy(&proc->fac_list, kvm->arch.model.fac_list,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
+	VM_EVENT(kvm, 3, "GET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx",
+		 kvm->arch.model.ibc,
+		 kvm->arch.model.cpuid);
+	VM_EVENT(kvm, 3, "GET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx",
+		 kvm->arch.model.fac_list[0],
+		 kvm->arch.model.fac_list[1],
+		 kvm->arch.model.fac_list[2]);
 	if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
 		ret = -EFAULT;
 	kfree(proc);
@@ -918,6 +944,17 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
 	       sizeof(S390_lowcore.stfle_fac_list));
+	VM_EVENT(kvm, 3, "GET: host ibc:  0x%4.4x, host cpuid:  0x%16.16llx",
+		 kvm->arch.model.ibc,
+		 kvm->arch.model.cpuid);
+	VM_EVENT(kvm, 3, "GET: host facmask:  0x%16.16llx.%16.16llx.%16.16llx",
+		 mach->fac_mask[0],
+		 mach->fac_mask[1],
+		 mach->fac_mask[2]);
+	VM_EVENT(kvm, 3, "GET: host faclist:  0x%16.16llx.%16.16llx.%16.16llx",
+		 mach->fac_list[0],
+		 mach->fac_list[1],
+		 mach->fac_list[2]);
 	if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
 		ret = -EFAULT;
 	kfree(mach);
@@ -1939,6 +1976,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	if (test_kvm_facility(vcpu->kvm, 8) && sclp.has_pfmfi)
 		vcpu->arch.sie_block->ecb2 |= 0x08;
+	if (test_kvm_facility(vcpu->kvm, 130))
+		vcpu->arch.sie_block->ecb2 |= 0x20;
 	vcpu->arch.sie_block->eca = 0x1002000U;
 	if (sclp.has_cei)
 		vcpu->arch.sie_block->eca |= 0x80000000U;
@@ -2579,7 +2618,7 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
 	 * to look up the current opcode to get the length of the instruction
 	 * to be able to forward the PSW.
 	 */
-	rc = read_guest_instr(vcpu, &opcode, 1);
+	rc = read_guest_instr(vcpu, vcpu->arch.sie_block->gpsw.addr, &opcode, 1);
 	ilen = insn_length(opcode);
 	if (rc < 0) {
 		return rc;
@@ -2761,6 +2800,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	int rc;
 	sigset_t sigsaved;
 
+	if (kvm_run->immediate_exit)
+		return -EINTR;
+
 	if (guestdbg_exit_pending(vcpu)) {
 		kvm_s390_prepare_debug_exit(vcpu);
 		return 0;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 3a4e97f1a9e6..af9fa91a0c91 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -86,9 +86,7 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
 	kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
 }
 
-typedef u8 __bitwise ar_t;
-
-static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar)
+static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, u8 *ar)
 {
 	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
 	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
@@ -101,7 +99,7 @@ static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar)
 
 static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
 					      u64 *address1, u64 *address2,
-					      ar_t *ar_b1, ar_t *ar_b2)
+					      u8 *ar_b1, u8 *ar_b2)
 {
 	u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
 	u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
@@ -125,7 +123,7 @@ static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2
 		*r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16;
 }
 
-static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar)
+static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, u8 *ar)
 {
 	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
 	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
@@ -140,7 +138,7 @@ static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar)
 	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2;
 }
 
-static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, ar_t *ar)
+static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, u8 *ar)
 {
 	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
 	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
@@ -379,7 +377,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
 void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
 void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu);
-void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
 
 /* support for Basic/Extended SCA handling */
 static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm)
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 794503516bd4..fb4b494cde9b 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -54,7 +54,7 @@ int kvm_s390_handle_aa(struct kvm_vcpu *vcpu)
 static int handle_set_clock(struct kvm_vcpu *vcpu)
 {
 	int rc;
-	ar_t ar;
+	u8 ar;
 	u64 op2, val;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
@@ -79,7 +79,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 	u64 operand2;
 	u32 address;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_spx++;
 
@@ -117,7 +117,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
 	u64 operand2;
 	u32 address;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stpx++;
 
@@ -147,7 +147,7 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 	u16 vcpu_id = vcpu->vcpu_id;
 	u64 ga;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stap++;
 
@@ -380,7 +380,7 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
 	u32 tpi_data[3];
 	int rc;
 	u64 addr;
-	ar_t ar;
+	u8 ar;
 
 	addr = kvm_s390_get_base_disp_s(vcpu, &ar);
 	if (addr & 3)
@@ -548,7 +548,7 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
 	psw_compat_t new_psw;
 	u64 addr;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	if (gpsw->mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -575,7 +575,7 @@ static int handle_lpswe(struct kvm_vcpu *vcpu)
 	psw_t new_psw;
 	u64 addr;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -597,7 +597,7 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
 	u64 stidp_data = vcpu->kvm->arch.model.cpuid;
 	u64 operand2;
 	int rc;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stidp++;
 
@@ -644,7 +644,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 	ASCEBC(mem->vm[0].cpi, 16);
 }
 
-static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, ar_t ar,
+static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, u8 ar,
 				 u8 fc, u8 sel1, u16 sel2)
 {
 	vcpu->run->exit_reason = KVM_EXIT_S390_STSI;
@@ -663,7 +663,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	unsigned long mem = 0;
 	u64 operand2;
 	int rc = 0;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stsi++;
 	VCPU_EVENT(vcpu, 3, "STSI: fc: %u sel1: %u sel2: %u", fc, sel1, sel2);
@@ -970,7 +970,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
 	int reg, rc, nr_regs;
 	u32 ctl_array[16];
 	u64 ga;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_lctl++;
 
@@ -1009,7 +1009,7 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu)
 	int reg, rc, nr_regs;
 	u32 ctl_array[16];
 	u64 ga;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stctl++;
 
@@ -1043,7 +1043,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 	int reg, rc, nr_regs;
 	u64 ctl_array[16];
 	u64 ga;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_lctlg++;
 
@@ -1081,7 +1081,7 @@ static int handle_stctg(struct kvm_vcpu *vcpu)
 	int reg, rc, nr_regs;
 	u64 ctl_array[16];
 	u64 ga;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_stctg++;
 
@@ -1132,7 +1132,7 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
 	unsigned long hva, gpa;
 	int ret = 0, cc = 0;
 	bool writable;
-	ar_t ar;
+	u8 ar;
 
 	vcpu->stat.instruction_tprot++;
 
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index a9a9d974d9a4..38556e395915 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -324,6 +324,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	/* Run-time-Instrumentation */
 	if (test_kvm_facility(vcpu->kvm, 64))
 		scb_s->ecb3 |= scb_o->ecb3 & 0x01U;
+	/* Instruction Execution Prevention */
+	if (test_kvm_facility(vcpu->kvm, 130))
+		scb_s->ecb2 |= scb_o->ecb2 & 0x20U;
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_SIIF))
 		scb_s->eca |= scb_o->eca & 0x00000001U;
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_IB))