Merge tag 'kvm-s390-next-20141128' of...

Merge tag 'kvm-s390-next-20141128' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Several fixes,cleanups and reworks

Here is a bunch of fixes that deal mostly with architectural compliance:
- interrupt priorities
- interrupt handling
- intruction exit handling

We also provide a helper function for getting the guest visible storage key.

arch/s390/include/asm/kvm_host.h

@@ -123,7 +123,7 @@ struct kvm_s390_sie_block {
 #define ICPT_PARTEXEC	0x38
 #define ICPT_IOINST	0x40
 	__u8	icptcode;		/* 0x0050 */
-	__u8	reserved51;		/* 0x0051 */
+	__u8	icptstatus;		/* 0x0051 */
 	__u16	ihcpu;			/* 0x0052 */
 	__u8	reserved54[2];		/* 0x0054 */
 	__u16	ipa;			/* 0x0056 */
@@ -295,6 +295,79 @@ struct kvm_vcpu_stat {
 #define PGM_PER				0x80
 #define PGM_CRYPTO_OPERATION		0x119
 
+/* irq types in order of priority */
+enum irq_types {
+	IRQ_PEND_MCHK_EX = 0,
+	IRQ_PEND_SVC,
+	IRQ_PEND_PROG,
+	IRQ_PEND_MCHK_REP,
+	IRQ_PEND_EXT_IRQ_KEY,
+	IRQ_PEND_EXT_MALFUNC,
+	IRQ_PEND_EXT_EMERGENCY,
+	IRQ_PEND_EXT_EXTERNAL,
+	IRQ_PEND_EXT_CLOCK_COMP,
+	IRQ_PEND_EXT_CPU_TIMER,
+	IRQ_PEND_EXT_TIMING,
+	IRQ_PEND_EXT_SERVICE,
+	IRQ_PEND_EXT_HOST,
+	IRQ_PEND_PFAULT_INIT,
+	IRQ_PEND_PFAULT_DONE,
+	IRQ_PEND_VIRTIO,
+	IRQ_PEND_IO_ISC_0,
+	IRQ_PEND_IO_ISC_1,
+	IRQ_PEND_IO_ISC_2,
+	IRQ_PEND_IO_ISC_3,
+	IRQ_PEND_IO_ISC_4,
+	IRQ_PEND_IO_ISC_5,
+	IRQ_PEND_IO_ISC_6,
+	IRQ_PEND_IO_ISC_7,
+	IRQ_PEND_SIGP_STOP,
+	IRQ_PEND_RESTART,
+	IRQ_PEND_SET_PREFIX,
+	IRQ_PEND_COUNT
+};
+
+/*
+ * Repressible (non-floating) machine check interrupts
+ * subclass bits in MCIC
+ */
+#define MCHK_EXTD_BIT 58
+#define MCHK_DEGR_BIT 56
+#define MCHK_WARN_BIT 55
+#define MCHK_REP_MASK ((1UL << MCHK_DEGR_BIT) | \
+		       (1UL << MCHK_EXTD_BIT) | \
+		       (1UL << MCHK_WARN_BIT))
+
+/* Exigent machine check interrupts subclass bits in MCIC */
+#define MCHK_SD_BIT 63
+#define MCHK_PD_BIT 62
+#define MCHK_EX_MASK ((1UL << MCHK_SD_BIT) | (1UL << MCHK_PD_BIT))
+
+#define IRQ_PEND_EXT_MASK ((1UL << IRQ_PEND_EXT_IRQ_KEY)    | \
+			   (1UL << IRQ_PEND_EXT_CLOCK_COMP) | \
+			   (1UL << IRQ_PEND_EXT_CPU_TIMER)  | \
+			   (1UL << IRQ_PEND_EXT_MALFUNC)    | \
+			   (1UL << IRQ_PEND_EXT_EMERGENCY)  | \
+			   (1UL << IRQ_PEND_EXT_EXTERNAL)   | \
+			   (1UL << IRQ_PEND_EXT_TIMING)     | \
+			   (1UL << IRQ_PEND_EXT_HOST)       | \
+			   (1UL << IRQ_PEND_EXT_SERVICE)    | \
+			   (1UL << IRQ_PEND_VIRTIO)         | \
+			   (1UL << IRQ_PEND_PFAULT_INIT)    | \
+			   (1UL << IRQ_PEND_PFAULT_DONE))
+
+#define IRQ_PEND_IO_MASK ((1UL << IRQ_PEND_IO_ISC_0) | \
+			  (1UL << IRQ_PEND_IO_ISC_1) | \
+			  (1UL << IRQ_PEND_IO_ISC_2) | \
+			  (1UL << IRQ_PEND_IO_ISC_3) | \
+			  (1UL << IRQ_PEND_IO_ISC_4) | \
+			  (1UL << IRQ_PEND_IO_ISC_5) | \
+			  (1UL << IRQ_PEND_IO_ISC_6) | \
+			  (1UL << IRQ_PEND_IO_ISC_7))
+
+#define IRQ_PEND_MCHK_MASK ((1UL << IRQ_PEND_MCHK_REP) | \
+			    (1UL << IRQ_PEND_MCHK_EX))
+
 struct kvm_s390_interrupt_info {
 	struct list_head list;
 	u64	type;
@@ -313,14 +386,25 @@ struct kvm_s390_interrupt_info {
 #define ACTION_STORE_ON_STOP		(1<<0)
 #define ACTION_STOP_ON_STOP		(1<<1)
 
+struct kvm_s390_irq_payload {
+	struct kvm_s390_io_info io;
+	struct kvm_s390_ext_info ext;
+	struct kvm_s390_pgm_info pgm;
+	struct kvm_s390_emerg_info emerg;
+	struct kvm_s390_extcall_info extcall;
+	struct kvm_s390_prefix_info prefix;
+	struct kvm_s390_mchk_info mchk;
+};
+
 struct kvm_s390_local_interrupt {
 	spinlock_t lock;
-	struct list_head list;
-	atomic_t active;
 	struct kvm_s390_float_interrupt *float_int;
 	wait_queue_head_t *wq;
 	atomic_t *cpuflags;
 	unsigned int action_bits;
+	DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
+	struct kvm_s390_irq_payload irq;
+	unsigned long pending_irqs;
 };
 
 struct kvm_s390_float_interrupt {

arch/s390/include/asm/pgalloc.h

@@ -26,6 +26,7 @@ void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long,
 			    bool init_skey);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned long key, bool nq);
+unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr);
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {

arch/s390/kvm/intercept.c

@@ -38,6 +38,19 @@ static const intercept_handler_t instruction_handlers[256] = {
 	[0xeb] = kvm_s390_handle_eb,
 };
 
+void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
+{
+	struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+
+	/* Use the length of the EXECUTE instruction if necessary */
+	if (sie_block->icptstatus & 1) {
+		ilc = (sie_block->icptstatus >> 4) & 0x6;
+		if (!ilc)
+			ilc = 4;
+	}
+	sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilc);
+}
+
 static int handle_noop(struct kvm_vcpu *vcpu)
 {
 	switch (vcpu->arch.sie_block->icptcode) {
@@ -244,7 +257,7 @@ static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)
 static int handle_external_interrupt(struct kvm_vcpu *vcpu)
 {
 	u16 eic = vcpu->arch.sie_block->eic;
-	struct kvm_s390_interrupt irq;
+	struct kvm_s390_irq irq;
 	psw_t newpsw;
 	int rc;
 
@@ -269,7 +282,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
 		if (kvm_s390_si_ext_call_pending(vcpu))
 			return 0;
 		irq.type = KVM_S390_INT_EXTERNAL_CALL;
-		irq.parm = vcpu->arch.sie_block->extcpuaddr;
+		irq.u.extcall.code = vcpu->arch.sie_block->extcpuaddr;
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -288,7 +301,6 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
  */
 static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 {
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
 	unsigned long srcaddr, dstaddr;
 	int reg1, reg2, rc;
 
@@ -310,7 +322,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 	if (rc != 0)
 		return rc;
 
-	psw->addr = __rewind_psw(*psw, 4);
+	kvm_s390_rewind_psw(vcpu, 4);
 
 	return 0;
 }

arch/s390/kvm/kvm-s390.c

@@ -719,7 +719,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	}
 
 	spin_lock_init(&vcpu->arch.local_int.lock);
-	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
@@ -1122,13 +1121,15 @@ static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
 				      unsigned long token)
 {
 	struct kvm_s390_interrupt inti;
-	inti.parm64 = token;
+	struct kvm_s390_irq irq;
 
 	if (start_token) {
-		inti.type = KVM_S390_INT_PFAULT_INIT;
-		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &inti));
+		irq.u.ext.ext_params2 = token;
+		irq.type = KVM_S390_INT_PFAULT_INIT;
+		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
 	} else {
 		inti.type = KVM_S390_INT_PFAULT_DONE;
+		inti.parm64 = token;
 		WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti));
 	}
 }
@@ -1622,11 +1623,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	switch (ioctl) {
 	case KVM_S390_INTERRUPT: {
 		struct kvm_s390_interrupt s390int;
+		struct kvm_s390_irq s390irq;
 
 		r = -EFAULT;
 		if (copy_from_user(&s390int, argp, sizeof(s390int)))
 			break;
-		r = kvm_s390_inject_vcpu(vcpu, &s390int);
+		if (s390int_to_s390irq(&s390int, &s390irq))
+			return -EINVAL;
+		r = kvm_s390_inject_vcpu(vcpu, &s390irq);
 		break;
 	}
 	case KVM_S390_STORE_STATUS:

arch/s390/kvm/kvm-s390.h

@@ -24,8 +24,6 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 /* declare vfacilities extern */
 extern unsigned long *vfacilities;
 
-int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
-
 /* Transactional Memory Execution related macros */
 #define IS_TE_ENABLED(vcpu)	((vcpu->arch.sie_block->ecb & 0x10))
 #define TDB_FORMAT1		1
@@ -144,7 +142,7 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm);
 int __must_check kvm_s390_inject_vm(struct kvm *kvm,
 				    struct kvm_s390_interrupt *s390int);
 int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
-				      struct kvm_s390_interrupt *s390int);
+				      struct kvm_s390_irq *irq);
 int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 						    u64 cr6, u64 schid);
@@ -152,6 +150,10 @@ void kvm_s390_reinject_io_int(struct kvm *kvm,
 			      struct kvm_s390_interrupt_info *inti);
 int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
 
+/* implemented in intercept.c */
+void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc);
+int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+
 /* implemented in priv.c */
 int is_valid_psw(psw_t *psw);
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
@@ -222,6 +224,9 @@ static inline int kvm_s390_inject_prog_cond(struct kvm_vcpu *vcpu, int rc)
 	return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
 }
 
+int s390int_to_s390irq(struct kvm_s390_interrupt *s390int,
+			struct kvm_s390_irq *s390irq);
+
 /* implemented in interrupt.c */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int psw_extint_disabled(struct kvm_vcpu *vcpu);

arch/s390/kvm/priv.c

@@ -176,21 +176,18 @@ static int handle_skey(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	vcpu->arch.sie_block->gpsw.addr =
-		__rewind_psw(vcpu->arch.sie_block->gpsw, 4);
+	kvm_s390_rewind_psw(vcpu, 4);
 	VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
 	return 0;
 }
 
 static int handle_ipte_interlock(struct kvm_vcpu *vcpu)
 {
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-
 	vcpu->stat.instruction_ipte_interlock++;
-	if (psw_bits(*psw).p)
+	if (psw_bits(vcpu->arch.sie_block->gpsw).p)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 	wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu));
-	psw->addr = __rewind_psw(*psw, 4);
+	kvm_s390_rewind_psw(vcpu, 4);
 	VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation");
 	return 0;
 }
@@ -646,10 +643,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
-	if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
-		if (kvm_s390_check_low_addr_protection(vcpu, start))
-			return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
-	}
+	start = kvm_s390_logical_to_effective(vcpu, start);
 
 	switch (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
 	case 0x00000000:
@@ -665,6 +659,12 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 	default:
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 	}
+
+	if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
+		if (kvm_s390_check_low_addr_protection(vcpu, start))
+			return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
+	}
+
 	while (start < end) {
 		unsigned long useraddr, abs_addr;
 
@@ -718,8 +718,7 @@ static int handle_essa(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	/* Rewind PSW to repeat the ESSA instruction */
-	vcpu->arch.sie_block->gpsw.addr =
-		__rewind_psw(vcpu->arch.sie_block->gpsw, 4);
+	kvm_s390_rewind_psw(vcpu, 4);
 	vcpu->arch.sie_block->cbrlo &= PAGE_MASK;	/* reset nceo */
 	cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
 	down_read(&gmap->mm->mmap_sem);

arch/s390/kvm/sigp.c

@@ -49,13 +49,13 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
 static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
 				    struct kvm_vcpu *dst_vcpu)
 {
-	struct kvm_s390_interrupt s390int = {
+	struct kvm_s390_irq irq = {
 		.type = KVM_S390_INT_EMERGENCY,
-		.parm = vcpu->vcpu_id,
+		.u.emerg.code = vcpu->vcpu_id,
 	};
 	int rc = 0;
 
-	rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int);
+	rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
 	if (!rc)
 		VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x",
 			   dst_vcpu->vcpu_id);
@@ -98,13 +98,13 @@ static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu,
 static int __sigp_external_call(struct kvm_vcpu *vcpu,
 				struct kvm_vcpu *dst_vcpu)
 {
-	struct kvm_s390_interrupt s390int = {
+	struct kvm_s390_irq irq = {
 		.type = KVM_S390_INT_EXTERNAL_CALL,
-		.parm = vcpu->vcpu_id,
+		.u.extcall.code = vcpu->vcpu_id,
 	};
 	int rc;
 
-	rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int);
+	rc = kvm_s390_inject_vcpu(dst_vcpu, &irq);
 	if (!rc)
 		VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x",
 			   dst_vcpu->vcpu_id);
@@ -115,29 +115,20 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu,
 static int __inject_sigp_stop(struct kvm_vcpu *dst_vcpu, int action)
 {
 	struct kvm_s390_local_interrupt *li = &dst_vcpu->arch.local_int;
-	struct kvm_s390_interrupt_info *inti;
 	int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 
-	inti = kzalloc(sizeof(*inti), GFP_ATOMIC);
-	if (!inti)
-		return -ENOMEM;
-	inti->type = KVM_S390_SIGP_STOP;
-
 	spin_lock(&li->lock);
 	if (li->action_bits & ACTION_STOP_ON_STOP) {
 		/* another SIGP STOP is pending */
-		kfree(inti);
 		rc = SIGP_CC_BUSY;
 		goto out;
 	}
 	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
-		kfree(inti);
 		if ((action & ACTION_STORE_ON_STOP) != 0)
 			rc = -ESHUTDOWN;
 		goto out;
 	}
-	list_add_tail(&inti->list, &li->list);
-	atomic_set(&li->active, 1);
+	set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
 	li->action_bits |= action;
 	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
 	kvm_s390_vcpu_wakeup(dst_vcpu);
@@ -207,7 +198,6 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
 			     u32 address, u64 *reg)
 {
 	struct kvm_s390_local_interrupt *li;
-	struct kvm_s390_interrupt_info *inti;
 	int rc;
 
 	li = &dst_vcpu->arch.local_int;
@@ -224,25 +214,17 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
 		return SIGP_CC_STATUS_STORED;
 	}
 
-	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
-	if (!inti)
-		return SIGP_CC_BUSY;
-
 	spin_lock(&li->lock);
 	/* cpu must be in stopped state */
 	if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INCORRECT_STATE;
 		rc = SIGP_CC_STATUS_STORED;
-		kfree(inti);
 		goto out_li;
 	}
 
-	inti->type = KVM_S390_SIGP_SET_PREFIX;
-	inti->prefix.address = address;
-
-	list_add_tail(&inti->list, &li->list);
-	atomic_set(&li->active, 1);
+	li->irq.prefix.address = address;
+	set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
 	kvm_s390_vcpu_wakeup(dst_vcpu);
 	rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 

arch/s390/mm/pgtable.c

@@ -980,6 +980,45 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL(set_guest_storage_key);
 
+unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
+{
+	spinlock_t *ptl;
+	pgste_t pgste;
+	pte_t *ptep;
+	uint64_t physaddr;
+	unsigned long key = 0;
+
+	down_read(&mm->mmap_sem);
+	ptep = get_locked_pte(mm, addr, &ptl);
+	if (unlikely(!ptep)) {
+		up_read(&mm->mmap_sem);
+		return -EFAULT;
+	}
+	pgste = pgste_get_lock(ptep);
+
+	if (pte_val(*ptep) & _PAGE_INVALID) {
+		key |= (pgste_val(pgste) & PGSTE_ACC_BITS) >> 56;
+		key |= (pgste_val(pgste) & PGSTE_FP_BIT) >> 56;
+		key |= (pgste_val(pgste) & PGSTE_GR_BIT) >> 48;
+		key |= (pgste_val(pgste) & PGSTE_GC_BIT) >> 48;
+	} else {
+		physaddr = pte_val(*ptep) & PAGE_MASK;
+		key = page_get_storage_key(physaddr);
+
+		/* Reflect guest's logical view, not physical */
+		if (pgste_val(pgste) & PGSTE_GR_BIT)
+			key |= _PAGE_REFERENCED;
+		if (pgste_val(pgste) & PGSTE_GC_BIT)
+			key |= _PAGE_CHANGED;
+	}
+
+	pgste_set_unlock(ptep, pgste);
+	pte_unmap_unlock(ptep, ptl);
+	up_read(&mm->mmap_sem);
+	return key;
+}
+EXPORT_SYMBOL(get_guest_storage_key);
+
 #else /* CONFIG_PGSTE */
 
 static inline int page_table_with_pgste(struct page *page)