From 77975357956c6450dd7ac3dfe572c1a8f0014c54 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Thu, 20 Dec 2012 15:32:06 +0100
Subject: KVM: s390: Constify intercept handler tables.

These tables are never modified.

Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/s390/kvm/intercept.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/s390/kvm/intercept.c')

diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 22798ec33fd1..0c08b3f1c1c5 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -104,7 +104,7 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static intercept_handler_t instruction_handlers[256] = {
+static const intercept_handler_t instruction_handlers[256] = {
 	[0x01] = kvm_s390_handle_01,
 	[0x83] = kvm_s390_handle_diag,
 	[0xae] = kvm_s390_handle_sigp,
-- 
cgit v1.2.3


From b1c571a50dfacf25a24c23271e9b8bf18ff6b102 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Thu, 20 Dec 2012 15:32:07 +0100
Subject: KVM: s390: Decoding helper functions.

Introduce helper functions for decoding the various base/displacement
instruction formats.

Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/s390/kvm/intercept.c | 21 ++++++---------------
 arch/s390/kvm/kvm-s390.h  | 37 +++++++++++++++++++++++++++++++++++++
 arch/s390/kvm/priv.c      | 42 +++++++++++-------------------------------
 arch/s390/kvm/sigp.c      |  6 +-----
 4 files changed, 55 insertions(+), 51 deletions(-)

(limited to 'arch/s390/kvm/intercept.c')

diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 0c08b3f1c1c5..df6c0ad085aa 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -26,9 +26,6 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 {
 	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
-			((vcpu->arch.sie_block->ipb & 0xff00) << 4);
 	u64 useraddr;
 	int reg, rc;
 
@@ -36,17 +33,15 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 	if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f)
 		return -EOPNOTSUPP;
 
-	useraddr = disp2;
-	if (base2)
-		useraddr += vcpu->run->s.regs.gprs[base2];
+	useraddr = kvm_s390_get_base_disp_rsy(vcpu);
 
 	if (useraddr & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	reg = reg1;
 
-	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
-		   disp2);
+	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3,
+		   useraddr);
 	trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, useraddr);
 
 	do {
@@ -68,23 +63,19 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 {
 	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 useraddr;
 	u32 val = 0;
 	int reg, rc;
 
 	vcpu->stat.instruction_lctl++;
 
-	useraddr = disp2;
-	if (base2)
-		useraddr += vcpu->run->s.regs.gprs[base2];
+	useraddr = kvm_s390_get_base_disp_rs(vcpu);
 
 	if (useraddr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
-		   disp2);
+	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3,
+		   useraddr);
 	trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, useraddr);
 
 	reg = reg1;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index d75bc5e92c5b..dccc0242b7ca 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -65,6 +65,43 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
 	vcpu->arch.sie_block->ihcpu  = 0xffff;
 }
 
+static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu)
+{
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
+					      u64 *address1, u64 *address2)
+{
+	int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
+	int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
+	int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
+	int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
+
+	*address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1;
+	*address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu)
+{
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+			((vcpu->arch.sie_block->ipb & 0xff00) << 4);
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu)
+{
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
 void kvm_s390_tasklet(unsigned long parm);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 1aeb9335f9e2..d715842f56ca 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -24,17 +24,13 @@
 
 static int handle_set_prefix(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	u32 address = 0;
 	u8 tmp;
 
 	vcpu->stat.instruction_spx++;
 
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -67,15 +63,12 @@ out:
 
 static int handle_store_prefix(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	u32 address;
 
 	vcpu->stat.instruction_stpx++;
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -100,15 +93,12 @@ out:
 
 static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 useraddr;
 	int rc;
 
 	vcpu->stat.instruction_stap++;
-	useraddr = disp2;
-	if (base2)
-		useraddr += vcpu->run->s.regs.gprs[base2];
+
+	useraddr = kvm_s390_get_base_disp_s(vcpu);
 
 	if (useraddr & 1) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -178,15 +168,12 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 
 static int handle_stidp(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	int rc;
 
 	vcpu->stat.instruction_stidp++;
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	if (operand2 & 7) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -240,17 +227,13 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28;
 	int sel1 = vcpu->run->s.regs.gprs[0] & 0xff;
 	int sel2 = vcpu->run->s.regs.gprs[1] & 0xffff;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	unsigned long mem;
 
 	vcpu->stat.instruction_stsi++;
 	VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
 
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	if (operand2 & 0xfff && fc > 0)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -335,17 +318,14 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 
 static int handle_tprot(struct kvm_vcpu *vcpu)
 {
-	int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
-	int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
-	int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
-	int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
-	u64 address1 = disp1 + base1 ? vcpu->run->s.regs.gprs[base1] : 0;
-	u64 address2 = disp2 + base2 ? vcpu->run->s.regs.gprs[base2] : 0;
+	u64 address1, address2;
 	struct vm_area_struct *vma;
 	unsigned long user_address;
 
 	vcpu->stat.instruction_tprot++;
 
+	kvm_s390_get_base_disp_sse(vcpu, &address1, &address2);
+
 	/* we only handle the Linux memory detection case:
 	 * access key == 0
 	 * guest DAT == off
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 566ddf6e8dfb..461e84179db1 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -324,8 +324,6 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 {
 	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int r3 = vcpu->arch.sie_block->ipa & 0x000f;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u32 parameter;
 	u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
 	u8 order_code;
@@ -336,9 +334,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu,
 						   PGM_PRIVILEGED_OPERATION);
 
-	order_code = disp2;
-	if (base2)
-		order_code += vcpu->run->s.regs.gprs[base2];
+	order_code = kvm_s390_get_base_disp_rs(vcpu);
 
 	if (r1 % 2)
 		parameter = vcpu->run->s.regs.gprs[r1];
-- 
cgit v1.2.3


From 48a3e950f4cee6a345ffbe9baf599f1e9a54c479 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Thu, 20 Dec 2012 15:32:09 +0100
Subject: KVM: s390: Add support for machine checks.

Add support for injecting machine checks (only repressible
conditions for now).

This is a bit more involved than I/O interrupts, for these reasons:

- Machine checks come in both floating and cpu varieties.
- We don't have a bit for machine checks enabling, but have to use
  a roundabout approach with trapping PSW changing instructions and
  watching for opened machine checks.

Reviewed-by: Alexander Graf <agraf@suse.de>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 Documentation/virtual/kvm/api.txt |   4 ++
 arch/s390/include/asm/kvm_host.h  |   8 +++
 arch/s390/kvm/intercept.c         |   2 +
 arch/s390/kvm/interrupt.c         | 112 +++++++++++++++++++++++++++++++
 arch/s390/kvm/kvm-s390.h          |   3 +
 arch/s390/kvm/priv.c              | 135 ++++++++++++++++++++++++++++++++++++++
 arch/s390/kvm/trace-s390.h        |   6 +-
 include/uapi/linux/kvm.h          |   1 +
 8 files changed, 268 insertions(+), 3 deletions(-)

(limited to 'arch/s390/kvm/intercept.c')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 83bd92b52936..8a0de309932f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2073,6 +2073,10 @@ KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an
     I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
     I/O interruption parameters in parm (subchannel) and parm64 (intparm,
     interruption subclass)
+KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
+                           machine check interrupt code in parm64 (note that
+                           machine checks needing further payload are not
+                           supported by this ioctl)
 
 Note that the vcpu ioctl is asynchronous to vcpu execution.
 
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index a8e35c43df78..29363d155cd5 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -75,8 +75,10 @@ struct kvm_s390_sie_block {
 	__u8	reserved40[4];		/* 0x0040 */
 #define LCTL_CR0	0x8000
 #define LCTL_CR6	0x0200
+#define LCTL_CR14	0x0002
 	__u16   lctl;			/* 0x0044 */
 	__s16	icpua;			/* 0x0046 */
+#define ICTL_LPSW 0x00400000
 	__u32	ictl;			/* 0x0048 */
 	__u32	eca;			/* 0x004c */
 	__u8	icptcode;		/* 0x0050 */
@@ -187,6 +189,11 @@ struct kvm_s390_emerg_info {
 	__u16 code;
 };
 
+struct kvm_s390_mchk_info {
+	__u64 cr14;
+	__u64 mcic;
+};
+
 struct kvm_s390_interrupt_info {
 	struct list_head list;
 	u64	type;
@@ -197,6 +204,7 @@ struct kvm_s390_interrupt_info {
 		struct kvm_s390_emerg_info emerg;
 		struct kvm_s390_extcall_info extcall;
 		struct kvm_s390_prefix_info prefix;
+		struct kvm_s390_mchk_info mchk;
 	};
 };
 
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index df6c0ad085aa..950c13ecaf60 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -97,10 +97,12 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 
 static const intercept_handler_t instruction_handlers[256] = {
 	[0x01] = kvm_s390_handle_01,
+	[0x82] = kvm_s390_handle_lpsw,
 	[0x83] = kvm_s390_handle_diag,
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
 	[0xb7] = handle_lctl,
+	[0xb9] = kvm_s390_handle_b9,
 	[0xe5] = kvm_s390_handle_e5,
 	[0xeb] = handle_lctlg,
 };
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 52cdf20906ab..b3b4748485ee 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -41,6 +41,11 @@ static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
 	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
 }
 
+static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
+}
+
 static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
 {
 	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) ||
@@ -82,6 +87,12 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 	case KVM_S390_SIGP_SET_PREFIX:
 	case KVM_S390_RESTART:
 		return 1;
+	case KVM_S390_MCHK:
+		if (psw_mchk_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14)
+			return 1;
+		return 0;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
 		if (psw_ioint_disabled(vcpu))
 			return 0;
@@ -116,6 +127,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 		CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
 		&vcpu->arch.sie_block->cpuflags);
 	vcpu->arch.sie_block->lctl = 0x0000;
+	vcpu->arch.sie_block->ictl &= ~ICTL_LPSW;
 }
 
 static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
@@ -139,6 +151,12 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
 	case KVM_S390_SIGP_STOP:
 		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
 		break;
+	case KVM_S390_MCHK:
+		if (psw_mchk_disabled(vcpu))
+			vcpu->arch.sie_block->ictl |= ICTL_LPSW;
+		else
+			vcpu->arch.sie_block->lctl |= LCTL_CR14;
+		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
 		if (psw_ioint_disabled(vcpu))
 			__set_cpuflag(vcpu, CPUSTAT_IO_INT);
@@ -326,6 +344,32 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 			exception = 1;
 		break;
 
+	case KVM_S390_MCHK:
+		VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
+			   inti->mchk.mcic);
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->mchk.cr14,
+						 inti->mchk.mcic);
+		rc = kvm_s390_vcpu_store_status(vcpu,
+						KVM_S390_STORE_STATUS_PREFIXED);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u64(vcpu, __LC_MCCK_CODE, inti->mchk.mcic);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_to_guest(vcpu, __LC_MCK_OLD_PSW,
+				   &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				     __LC_MCK_NEW_PSW, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
 	{
 		__u32 param0 = ((__u32)inti->io.subchannel_id << 16) |
@@ -588,6 +632,61 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 	}
 }
 
+void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct kvm_s390_interrupt_info  *n, *inti = NULL;
+	int deliver;
+
+	__reset_intercept_indicators(vcpu);
+	if (atomic_read(&li->active)) {
+		do {
+			deliver = 0;
+			spin_lock_bh(&li->lock);
+			list_for_each_entry_safe(inti, n, &li->list, list) {
+				if ((inti->type == KVM_S390_MCHK) &&
+				    __interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&li->list))
+				atomic_set(&li->active, 0);
+			spin_unlock_bh(&li->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+
+	if (atomic_read(&fi->active)) {
+		do {
+			deliver = 0;
+			spin_lock(&fi->lock);
+			list_for_each_entry_safe(inti, n, &fi->list, list) {
+				if ((inti->type == KVM_S390_MCHK) &&
+				    __interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&fi->list))
+				atomic_set(&fi->active, 0);
+			spin_unlock(&fi->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+}
+
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -641,6 +740,13 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	case KVM_S390_INT_EMERGENCY:
 		kfree(inti);
 		return -EINVAL;
+	case KVM_S390_MCHK:
+		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
+			 s390int->parm64);
+		inti->type = s390int->type;
+		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
+		inti->mchk.mcic = s390int->parm64;
+		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
 		if (s390int->type & IOINT_AI_MASK)
 			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
@@ -749,6 +855,12 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		inti->type = s390int->type;
 		inti->emerg.code = s390int->parm;
 		break;
+	case KVM_S390_MCHK:
+		VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
+			   s390int->parm64);
+		inti->type = s390int->type;
+		inti->mchk.mcic = s390int->parm64;
+		break;
 	case KVM_S390_INT_VIRTIO:
 	case KVM_S390_INT_SERVICE:
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index dccc0242b7ca..1f7cc6ccf102 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -106,6 +106,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
 void kvm_s390_tasklet(unsigned long parm);
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
+void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu);
 int kvm_s390_inject_vm(struct kvm *kvm,
 		struct kvm_s390_interrupt *s390int);
 int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
@@ -117,6 +118,8 @@ int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_01(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_b9(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu);
 
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d715842f56ca..d3cbcd3c9ada 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -18,6 +18,8 @@
 #include <asm/debug.h>
 #include <asm/ebcdic.h>
 #include <asm/sysinfo.h>
+#include <asm/ptrace.h>
+#include <asm/compat.h>
 #include "gaccess.h"
 #include "kvm-s390.h"
 #include "trace.h"
@@ -166,6 +168,99 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static void handle_new_psw(struct kvm_vcpu *vcpu)
+{
+	/* Check whether the new psw is enabled for machine checks. */
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK)
+		kvm_s390_deliver_pending_machine_checks(vcpu);
+}
+
+#define PSW_MASK_ADDR_MODE (PSW_MASK_EA | PSW_MASK_BA)
+#define PSW_MASK_UNASSIGNED 0xb80800fe7fffffffUL
+#define PSW_ADDR_24 0x00000000000fffffUL
+#define PSW_ADDR_31 0x000000007fffffffUL
+
+int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
+{
+	u64 addr;
+	psw_compat_t new_psw;
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+
+	if (addr & 7) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw))) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	if (!(new_psw.mask & PSW32_MASK_BASE)) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	vcpu->arch.sie_block->gpsw.mask =
+		(new_psw.mask & ~PSW32_MASK_BASE) << 32;
+	vcpu->arch.sie_block->gpsw.addr = new_psw.addr;
+
+	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_UNASSIGNED) ||
+	    (!(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) &&
+	     (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_24)) ||
+	    ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) ==
+	     PSW_MASK_EA)) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	handle_new_psw(vcpu);
+out:
+	return 0;
+}
+
+static int handle_lpswe(struct kvm_vcpu *vcpu)
+{
+	u64 addr;
+	psw_t new_psw;
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+
+	if (addr & 7) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw))) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	vcpu->arch.sie_block->gpsw.mask = new_psw.mask;
+	vcpu->arch.sie_block->gpsw.addr = new_psw.addr;
+
+	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_UNASSIGNED) ||
+	    (((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) ==
+	      PSW_MASK_BA) &&
+	     (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_31)) ||
+	    (!(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) &&
+	     (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_24)) ||
+	    ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) ==
+	     PSW_MASK_EA)) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	handle_new_psw(vcpu);
+out:
+	return 0;
+}
+
 static int handle_stidp(struct kvm_vcpu *vcpu)
 {
 	u64 operand2;
@@ -292,6 +387,7 @@ static const intercept_handler_t priv_handlers[256] = {
 	[0x5f] = handle_chsc,
 	[0x7d] = handle_stsi,
 	[0xb1] = handle_stfl,
+	[0xb2] = handle_lpswe,
 };
 
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
@@ -316,6 +412,45 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 	return -EOPNOTSUPP;
 }
 
+static int handle_epsw(struct kvm_vcpu *vcpu)
+{
+	int reg1, reg2;
+
+	reg1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 24;
+	reg2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16;
+
+	/* This basically extracts the mask half of the psw. */
+	vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000;
+	vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32;
+	if (reg2) {
+		vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000;
+		vcpu->run->s.regs.gprs[reg2] |=
+			vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffff;
+	}
+	return 0;
+}
+
+static const intercept_handler_t b9_handlers[256] = {
+	[0x8d] = handle_epsw,
+};
+
+int kvm_s390_handle_b9(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	/* This is handled just as for the B2 instructions. */
+	handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	if (handler) {
+		if ((handler != handle_epsw) &&
+		    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE))
+			return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+		else
+			return handler(vcpu);
+	}
+	return -EOPNOTSUPP;
+}
+
 static int handle_tprot(struct kvm_vcpu *vcpu)
 {
 	u64 address1, address2;
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index 90fdf85b5ff7..95fbc1ab88dc 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -141,13 +141,13 @@ TRACE_EVENT(kvm_s390_inject_vcpu,
  * Trace point for the actual delivery of interrupts.
  */
 TRACE_EVENT(kvm_s390_deliver_interrupt,
-	    TP_PROTO(unsigned int id, __u64 type, __u32 data0, __u64 data1),
+	    TP_PROTO(unsigned int id, __u64 type, __u64 data0, __u64 data1),
 	    TP_ARGS(id, type, data0, data1),
 
 	    TP_STRUCT__entry(
 		    __field(int, id)
 		    __field(__u32, inttype)
-		    __field(__u32, data0)
+		    __field(__u64, data0)
 		    __field(__u64, data1)
 		    ),
 
@@ -159,7 +159,7 @@ TRACE_EVENT(kvm_s390_deliver_interrupt,
 		    ),
 
 	    TP_printk("deliver interrupt (vcpu %d): type:%x (%s) "	\
-		      "data:%08x %016llx",
+		      "data:%08llx %016llx",
 		      __entry->id, __entry->inttype,
 		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
 		      __entry->data0, __entry->data1)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 54540bdd3340..80bb3b801116 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -397,6 +397,7 @@ struct kvm_s390_psw {
 #define KVM_S390_PROGRAM_INT		0xfffe0001u
 #define KVM_S390_SIGP_SET_PREFIX	0xfffe0002u
 #define KVM_S390_RESTART		0xfffe0003u
+#define KVM_S390_MCHK			0xfffe1000u
 #define KVM_S390_INT_VIRTIO		0xffff2603u
 #define KVM_S390_INT_SERVICE		0xffff2401u
 #define KVM_S390_INT_EMERGENCY		0xffff1201u
-- 
cgit v1.2.3


From f379aae558b8daff0f7a1c5fc225af5d35c741f7 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Thu, 20 Dec 2012 15:32:10 +0100
Subject: KVM: s390: In-kernel handling of I/O instructions.

Explicitely catch all channel I/O related instructions intercepts
in the kernel and set condition code 3 for them.

This paves the way for properly handling these instructions later
on.

Note: This is not architecture compliant (the previous code wasn't
either) since setting cc 3 is not the correct thing to do for some
of these instructions. For Linux guests, however, it still has the
intended effect of stopping css probing.

Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/s390/kvm/intercept.c | 19 +++++++++++++---
 arch/s390/kvm/kvm-s390.h  |  1 +
 arch/s390/kvm/priv.c      | 56 +++++++++++++++++++++++++++++++++--------------
 3 files changed, 56 insertions(+), 20 deletions(-)

(limited to 'arch/s390/kvm/intercept.c')

diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 950c13ecaf60..71af87dbb42c 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -30,8 +30,6 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 	int reg, rc;
 
 	vcpu->stat.instruction_lctlg++;
-	if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f)
-		return -EOPNOTSUPP;
 
 	useraddr = kvm_s390_get_base_disp_rsy(vcpu);
 
@@ -95,6 +93,21 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static const intercept_handler_t eb_handlers[256] = {
+	[0x2f] = handle_lctlg,
+	[0x8a] = kvm_s390_handle_priv_eb,
+};
+
+static int handle_eb(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
+
 static const intercept_handler_t instruction_handlers[256] = {
 	[0x01] = kvm_s390_handle_01,
 	[0x82] = kvm_s390_handle_lpsw,
@@ -104,7 +117,7 @@ static const intercept_handler_t instruction_handlers[256] = {
 	[0xb7] = handle_lctl,
 	[0xb9] = kvm_s390_handle_b9,
 	[0xe5] = kvm_s390_handle_e5,
-	[0xeb] = handle_lctlg,
+	[0xeb] = handle_eb,
 };
 
 static int handle_noop(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 1f7cc6ccf102..211b340385a7 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -120,6 +120,7 @@ int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_01(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_b9(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu);
 
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d3cbcd3c9ada..8ad776f87856 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -127,20 +127,9 @@ static int handle_skey(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int handle_stsch(struct kvm_vcpu *vcpu)
+static int handle_io_inst(struct kvm_vcpu *vcpu)
 {
-	vcpu->stat.instruction_stsch++;
-	VCPU_EVENT(vcpu, 4, "%s", "store subchannel - CC3");
-	/* condition code 3 */
-	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
-	return 0;
-}
-
-static int handle_chsc(struct kvm_vcpu *vcpu)
-{
-	vcpu->stat.instruction_chsc++;
-	VCPU_EVENT(vcpu, 4, "%s", "channel subsystem call - CC3");
+	VCPU_EVENT(vcpu, 4, "%s", "I/O instruction");
 	/* condition code 3 */
 	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
 	vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
@@ -375,7 +364,7 @@ out_fail:
 	return 0;
 }
 
-static const intercept_handler_t priv_handlers[256] = {
+static const intercept_handler_t b2_handlers[256] = {
 	[0x02] = handle_stidp,
 	[0x10] = handle_set_prefix,
 	[0x11] = handle_store_prefix,
@@ -383,8 +372,22 @@ static const intercept_handler_t priv_handlers[256] = {
 	[0x29] = handle_skey,
 	[0x2a] = handle_skey,
 	[0x2b] = handle_skey,
-	[0x34] = handle_stsch,
-	[0x5f] = handle_chsc,
+	[0x30] = handle_io_inst,
+	[0x31] = handle_io_inst,
+	[0x32] = handle_io_inst,
+	[0x33] = handle_io_inst,
+	[0x34] = handle_io_inst,
+	[0x35] = handle_io_inst,
+	[0x36] = handle_io_inst,
+	[0x37] = handle_io_inst,
+	[0x38] = handle_io_inst,
+	[0x39] = handle_io_inst,
+	[0x3a] = handle_io_inst,
+	[0x3b] = handle_io_inst,
+	[0x3c] = handle_io_inst,
+	[0x5f] = handle_io_inst,
+	[0x74] = handle_io_inst,
+	[0x76] = handle_io_inst,
 	[0x7d] = handle_stsi,
 	[0xb1] = handle_stfl,
 	[0xb2] = handle_lpswe,
@@ -401,7 +404,7 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 	 * state bit and (a) handle the instruction or (b) send a code 2
 	 * program check.
 	 * Anything else goes to userspace.*/
-	handler = priv_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
 	if (handler) {
 		if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 			return kvm_s390_inject_program_int(vcpu,
@@ -432,6 +435,7 @@ static int handle_epsw(struct kvm_vcpu *vcpu)
 
 static const intercept_handler_t b9_handlers[256] = {
 	[0x8d] = handle_epsw,
+	[0x9c] = handle_io_inst,
 };
 
 int kvm_s390_handle_b9(struct kvm_vcpu *vcpu)
@@ -451,6 +455,24 @@ int kvm_s390_handle_b9(struct kvm_vcpu *vcpu)
 	return -EOPNOTSUPP;
 }
 
+static const intercept_handler_t eb_handlers[256] = {
+	[0x8a] = handle_io_inst,
+};
+
+int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	/* All eb instructions that end up here are privileged. */
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
+
 static int handle_tprot(struct kvm_vcpu *vcpu)
 {
 	u64 address1, address2;
-- 
cgit v1.2.3


From fa6b7fe9928d50444c29b29c8563746c6b0c6299 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Thu, 20 Dec 2012 15:32:12 +0100
Subject: KVM: s390: Add support for channel I/O instructions.

Add a new capability, KVM_CAP_S390_CSS_SUPPORT, which will pass
intercepts for channel I/O instructions to userspace. Only I/O
instructions interacting with I/O interrupts need to be handled
in-kernel:

- TEST PENDING INTERRUPTION (tpi) dequeues and stores pending
  interrupts entirely in-kernel.
- TEST SUBCHANNEL (tsch) dequeues pending interrupts in-kernel
  and exits via KVM_EXIT_S390_TSCH to userspace for subchannel-
  related processing.

Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 30 +++++++++++++
 arch/s390/include/asm/kvm_host.h  |  1 +
 arch/s390/kvm/intercept.c         |  1 +
 arch/s390/kvm/interrupt.c         | 37 ++++++++++++++++
 arch/s390/kvm/kvm-s390.c          | 12 ++++++
 arch/s390/kvm/kvm-s390.h          |  2 +
 arch/s390/kvm/priv.c              | 91 +++++++++++++++++++++++++++++++++++++--
 arch/s390/kvm/trace-s390.h        | 20 +++++++++
 include/trace/events/kvm.h        |  2 +-
 include/uapi/linux/kvm.h          | 11 +++++
 10 files changed, 202 insertions(+), 5 deletions(-)

(limited to 'arch/s390/kvm/intercept.c')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 73bd159c5559..f2d6391178b9 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2350,6 +2350,22 @@ The possible hypercalls are defined in the Power Architecture Platform
 Requirements (PAPR) document available from www.power.org (free
 developer registration required to access it).
 
+		/* KVM_EXIT_S390_TSCH */
+		struct {
+			__u16 subchannel_id;
+			__u16 subchannel_nr;
+			__u32 io_int_parm;
+			__u32 io_int_word;
+			__u32 ipb;
+			__u8 dequeued;
+		} s390_tsch;
+
+s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled
+and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O
+interrupt for the target subchannel has been dequeued and subchannel_id,
+subchannel_nr, io_int_parm and io_int_word contain the parameters for that
+interrupt. ipb is needed for instruction parameter decoding.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -2471,3 +2487,17 @@ For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
    where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
  - The tsize field of mas1 shall be set to 4K on TLB0, even though the
    hardware ignores this value for TLB0.
+
+6.4 KVM_CAP_S390_CSS_SUPPORT
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success; -1 on error
+
+This capability enables support for handling of channel I/O instructions.
+
+TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are
+handled in-kernel, while the other I/O instructions are passed to userspace.
+
+When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
+SUBCHANNEL intercepts.
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 29363d155cd5..16bd5d169cdb 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -262,6 +262,7 @@ struct kvm_arch{
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
 	struct gmap *gmap;
+	int css_support;
 };
 
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 71af87dbb42c..f26ff1e31bdb 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -264,6 +264,7 @@ static const intercept_handler_t intercept_funcs[] = {
 	[0x0C >> 2] = handle_instruction_and_prog,
 	[0x10 >> 2] = handle_noop,
 	[0x14 >> 2] = handle_noop,
+	[0x18 >> 2] = handle_noop,
 	[0x1C >> 2] = kvm_s390_handle_wait,
 	[0x20 >> 2] = handle_validity,
 	[0x28 >> 2] = handle_stop,
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index b3b4748485ee..9a128357fd15 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -709,6 +709,43 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 	return 0;
 }
 
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
+						    u64 cr6, u64 schid)
+{
+	struct kvm_s390_float_interrupt *fi;
+	struct kvm_s390_interrupt_info *inti, *iter;
+
+	if ((!schid && !cr6) || (schid && cr6))
+		return NULL;
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+	inti = NULL;
+	list_for_each_entry(iter, &fi->list, list) {
+		if (!is_ioint(iter->type))
+			continue;
+		if (cr6 && ((cr6 & iter->io.io_int_word) == 0))
+			continue;
+		if (schid) {
+			if (((schid & 0x00000000ffff0000) >> 16) !=
+			    iter->io.subchannel_id)
+				continue;
+			if ((schid & 0x000000000000ffff) !=
+			    iter->io.subchannel_nr)
+				continue;
+		}
+		inti = iter;
+		break;
+	}
+	if (inti)
+		list_del_init(&inti->list);
+	if (list_empty(&fi->list))
+		atomic_set(&fi->active, 0);
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+	return inti;
+}
+
 int kvm_s390_inject_vm(struct kvm *kvm,
 		       struct kvm_s390_interrupt *s390int)
 {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 5ff26033825c..5b01f0953900 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -141,6 +141,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_SYNC_REGS:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
+	case KVM_CAP_S390_CSS_SUPPORT:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -235,6 +236,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		if (!kvm->arch.gmap)
 			goto out_nogmap;
 	}
+
+	kvm->arch.css_support = 0;
+
 	return 0;
 out_nogmap:
 	debug_unregister(kvm->arch.dbf);
@@ -658,6 +662,7 @@ rerun_vcpu:
 	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
 	case KVM_EXIT_S390_UCONTROL:
+	case KVM_EXIT_S390_TSCH:
 		break;
 	default:
 		BUG();
@@ -818,6 +823,13 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	switch (cap->cap) {
+	case KVM_CAP_S390_CSS_SUPPORT:
+		if (!vcpu->kvm->arch.css_support) {
+			vcpu->kvm->arch.css_support = 1;
+			trace_kvm_s390_enable_css(vcpu->kvm);
+		}
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 211b340385a7..3e05deff21b6 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -113,6 +113,8 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		struct kvm_s390_interrupt *s390int);
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
+						    u64 cr6, u64 schid);
 
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 8ad776f87856..0ef9894606e5 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -127,15 +127,98 @@ static int handle_skey(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int handle_io_inst(struct kvm_vcpu *vcpu)
+static int handle_tpi(struct kvm_vcpu *vcpu)
 {
-	VCPU_EVENT(vcpu, 4, "%s", "I/O instruction");
-	/* condition code 3 */
+	u64 addr;
+	struct kvm_s390_interrupt_info *inti;
+	int cc;
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+
+	inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->run->s.regs.crs[6], 0);
+	if (inti) {
+		if (addr) {
+			/*
+			 * Store the two-word I/O interruption code into the
+			 * provided area.
+			 */
+			put_guest_u16(vcpu, addr, inti->io.subchannel_id);
+			put_guest_u16(vcpu, addr + 2, inti->io.subchannel_nr);
+			put_guest_u32(vcpu, addr + 4, inti->io.io_int_parm);
+		} else {
+			/*
+			 * Store the three-word I/O interruption code into
+			 * the appropriate lowcore area.
+			 */
+			put_guest_u16(vcpu, 184, inti->io.subchannel_id);
+			put_guest_u16(vcpu, 186, inti->io.subchannel_nr);
+			put_guest_u32(vcpu, 188, inti->io.io_int_parm);
+			put_guest_u32(vcpu, 192, inti->io.io_int_word);
+		}
+		cc = 1;
+	} else
+		cc = 0;
+	kfree(inti);
+	/* Set condition code and we're done. */
 	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+	vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44;
 	return 0;
 }
 
+static int handle_tsch(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_interrupt_info *inti;
+
+	inti = kvm_s390_get_io_int(vcpu->kvm, 0,
+				   vcpu->run->s.regs.gprs[1]);
+
+	/*
+	 * Prepare exit to userspace.
+	 * We indicate whether we dequeued a pending I/O interrupt
+	 * so that userspace can re-inject it if the instruction gets
+	 * a program check. While this may re-order the pending I/O
+	 * interrupts, this is no problem since the priority is kept
+	 * intact.
+	 */
+	vcpu->run->exit_reason = KVM_EXIT_S390_TSCH;
+	vcpu->run->s390_tsch.dequeued = !!inti;
+	if (inti) {
+		vcpu->run->s390_tsch.subchannel_id = inti->io.subchannel_id;
+		vcpu->run->s390_tsch.subchannel_nr = inti->io.subchannel_nr;
+		vcpu->run->s390_tsch.io_int_parm = inti->io.io_int_parm;
+		vcpu->run->s390_tsch.io_int_word = inti->io.io_int_word;
+	}
+	vcpu->run->s390_tsch.ipb = vcpu->arch.sie_block->ipb;
+	kfree(inti);
+	return -EREMOTE;
+}
+
+static int handle_io_inst(struct kvm_vcpu *vcpu)
+{
+	VCPU_EVENT(vcpu, 4, "%s", "I/O instruction");
+
+	if (vcpu->kvm->arch.css_support) {
+		/*
+		 * Most I/O instructions will be handled by userspace.
+		 * Exceptions are tpi and the interrupt portion of tsch.
+		 */
+		if (vcpu->arch.sie_block->ipa == 0xb236)
+			return handle_tpi(vcpu);
+		if (vcpu->arch.sie_block->ipa == 0xb235)
+			return handle_tsch(vcpu);
+		/* Handle in userspace. */
+		return -EOPNOTSUPP;
+	} else {
+		/*
+		 * Set condition code 3 to stop the guest from issueing channel
+		 * I/O instructions.
+		 */
+		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+		vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+		return 0;
+	}
+}
+
 static int handle_stfl(struct kvm_vcpu *vcpu)
 {
 	unsigned int facility_list;
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index 95fbc1ab88dc..13f30f58a2df 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -204,6 +204,26 @@ TRACE_EVENT(kvm_s390_stop_request,
 	);
 
 
+/*
+ * Trace point for enabling channel I/O instruction support.
+ */
+TRACE_EVENT(kvm_s390_enable_css,
+	    TP_PROTO(void *kvm),
+	    TP_ARGS(kvm),
+
+	    TP_STRUCT__entry(
+		    __field(void *, kvm)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->kvm = kvm;
+		    ),
+
+	    TP_printk("enabling channel I/O support (kvm @ %p)\n",
+		      __entry->kvm)
+	);
+
+
 #endif /* _TRACE_KVMS390_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 7ef9e759f499..a23f47c884cf 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -14,7 +14,7 @@
 	ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR),	\
 	ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\
 	ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL),	\
-	ERSN(S390_UCONTROL)
+	ERSN(S390_UCONTROL), ERSN(S390_TSCH)
 
 TRACE_EVENT(kvm_userspace_exit,
 	    TP_PROTO(__u32 reason, int errno),
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 80bb3b801116..8bb0bf83afc5 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -168,6 +168,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_PAPR_HCALL	  19
 #define KVM_EXIT_S390_UCONTROL	  20
 #define KVM_EXIT_WATCHDOG         21
+#define KVM_EXIT_S390_TSCH        22
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -285,6 +286,15 @@ struct kvm_run {
 			__u64 ret;
 			__u64 args[9];
 		} papr_hcall;
+		/* KVM_EXIT_S390_TSCH */
+		struct {
+			__u16 subchannel_id;
+			__u16 subchannel_nr;
+			__u32 io_int_parm;
+			__u32 io_int_word;
+			__u32 ipb;
+			__u8 dequeued;
+		} s390_tsch;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -645,6 +655,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 #define KVM_CAP_PPC_HTAB_FD 84
+#define KVM_CAP_S390_CSS_SUPPORT 85
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3