From d8346b7d9bab37e6cc712ff1622c65ff98bdfef8 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Thu, 20 Dec 2012 15:32:08 +0100
Subject: KVM: s390: Support for I/O interrupts.

Add support for handling I/O interrupts (standard, subchannel-related
ones and rudimentary adapter interrupts).

The subchannel-identifying parameters are encoded into the interrupt
type.

I/O interrupts are floating, so they can't be injected on a specific
vcpu.

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 ++++
 1 file changed, 4 insertions(+)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a4df5535996b..83bd92b52936 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2069,6 +2069,10 @@ KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
 KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
 KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm
 KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
+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)
 
 Note that the vcpu ioctl is asynchronous to vcpu execution.
 
-- 
cgit v1.2.3-59-g8ed1b


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 'Documentation')

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 v1.2.3-59-g8ed1b


From d6712df95bcfea597fc3ea2405ec13e8b69a7b8c Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Thu, 20 Dec 2012 15:32:11 +0100
Subject: KVM: s390: Base infrastructure for enabling capabilities.

Make s390 support KVM_ENABLE_CAP.

Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Acked-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 |  2 +-
 arch/s390/kvm/kvm-s390.c          | 26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 8a0de309932f..73bd159c5559 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -913,7 +913,7 @@ documentation when it pops into existence).
 4.37 KVM_ENABLE_CAP
 
 Capability: KVM_CAP_ENABLE_CAP
-Architectures: ppc
+Architectures: ppc, s390
 Type: vcpu ioctl
 Parameters: struct kvm_enable_cap (in)
 Returns: 0 on success; -1 on error
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f718bc65835c..5ff26033825c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -140,6 +140,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif
 	case KVM_CAP_SYNC_REGS:
 	case KVM_CAP_ONE_REG:
+	case KVM_CAP_ENABLE_CAP:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -808,6 +809,22 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	return 0;
 }
 
+static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
+				     struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -894,6 +911,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			r = 0;
 		break;
 	}
+	case KVM_ENABLE_CAP:
+	{
+		struct kvm_enable_cap cap;
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			break;
+		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
-- 
cgit v1.2.3-59-g8ed1b


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 'Documentation')

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 v1.2.3-59-g8ed1b


From 68e2ffed358c92341c126e606b500098fc72f5f7 Mon Sep 17 00:00:00 2001
From: Mihai Caraman <mihai.caraman@freescale.com>
Date: Tue, 11 Dec 2012 03:38:23 +0000
Subject: KVM: PPC: Fix SREGS documentation reference

Reflect the uapi folder change in SREGS API documentation.

Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com>
Reviewed-by: Amos Kong <kongjianjun@gmail.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index f2d6391178b9..4fc2bfcb16d5 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -345,7 +345,7 @@ struct kvm_sregs {
 	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
 };
 
-/* ppc -- see arch/powerpc/include/asm/kvm.h */
+/* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
 
 interrupt_bitmap is a bitmap of pending external interrupts.  At most
 one bit may be set.  This interrupt has been acknowledged by the APIC
-- 
cgit v1.2.3-59-g8ed1b


From 1c810636556c8d53a37406b34a64d9b9b0161aa6 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 4 Jan 2013 18:12:48 +0100
Subject: KVM: PPC: BookE: Implement EPR exit

The External Proxy Facility in FSL BookE chips allows the interrupt
controller to automatically acknowledge an interrupt as soon as a
core gets its pending external interrupt delivered.

Today, user space implements the interrupt controller, so we need to
check on it during such a cycle.

This patch implements logic for user space to enable EPR exiting,
disable EPR exiting and EPR exiting itself, so that user space can
acknowledge an interrupt when an external interrupt has successfully
been delivered into the guest vcpu.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt   | 40 +++++++++++++++++++++++++++++++++++--
 arch/powerpc/include/asm/kvm_host.h |  2 ++
 arch/powerpc/include/asm/kvm_ppc.h  |  9 +++++++++
 arch/powerpc/kvm/booke.c            | 14 ++++++++++++-
 arch/powerpc/kvm/powerpc.c          | 10 ++++++++++
 include/linux/kvm_host.h            |  1 +
 include/uapi/linux/kvm.h            |  6 ++++++
 7 files changed, 79 insertions(+), 3 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 4fc2bfcb16d5..a98ed09269d7 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2246,8 +2246,8 @@ executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.
 
-NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR
-      and KVM_EXIT_PAPR the corresponding
+NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR,
+      KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding
 operations are complete (and guest state is consistent) only after userspace
 has re-entered the kernel with KVM_RUN.  The kernel side will first finish
 incomplete operations and then check for pending signals.  Userspace
@@ -2366,6 +2366,25 @@ 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.
 
+		/* KVM_EXIT_EPR */
+		struct {
+			__u32 epr;
+		} epr;
+
+On FSL BookE PowerPC chips, the interrupt controller has a fast patch
+interrupt acknowledge path to the core. When the core successfully
+delivers an interrupt, it automatically populates the EPR register with
+the interrupt vector number and acknowledges the interrupt inside
+the interrupt controller.
+
+In case the interrupt controller lives in user space, we need to do
+the interrupt acknowledge cycle through it to fetch the next to be
+delivered interrupt vector using this exit.
+
+It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
+external interrupt has just been delivered into the guest. User space
+should put the acknowledged interrupt vector into the 'epr' field.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -2501,3 +2520,20 @@ 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.
+
+6.5 KVM_CAP_PPC_EPR
+
+Architectures: ppc
+Parameters: args[0] defines whether the proxy facility is active
+Returns: 0 on success; -1 on error
+
+This capability enables or disables the delivery of interrupts through the
+external proxy facility.
+
+When enabled (args[0] != 0), every time the guest gets an external interrupt
+delivered, it automatically exits into user space with a KVM_EXIT_EPR exit
+to receive the topmost interrupt vector.
+
+When disabled (args[0] == 0), behavior is as if this facility is unsupported.
+
+When this capability is enabled, KVM_EXIT_EPR can occur.
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index ab49c6cf891c..8a72d59467eb 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -520,6 +520,8 @@ struct kvm_vcpu_arch {
 	u8 sane;
 	u8 cpu_type;
 	u8 hcall_needed;
+	u8 epr_enabled;
+	u8 epr_needed;
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 5f5f69abd281..493630e209c8 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -264,6 +264,15 @@ static inline void kvm_linear_init(void)
 {}
 #endif
 
+static inline void kvmppc_set_epr(struct kvm_vcpu *vcpu, u32 epr)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_GEPR, epr);
+#elif defined(CONFIG_BOOKE)
+	vcpu->arch.epr = epr;
+#endif
+}
+
 int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 			      struct kvm_config_tlb *cfg);
 int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 964f4475f55c..940ec806187e 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -306,7 +306,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 {
 	int allowed = 0;
 	ulong msr_mask = 0;
-	bool update_esr = false, update_dear = false;
+	bool update_esr = false, update_dear = false, update_epr = false;
 	ulong crit_raw = vcpu->arch.shared->critical;
 	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
 	bool crit;
@@ -330,6 +330,9 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		keep_irq = true;
 	}
 
+	if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_enabled)
+		update_epr = true;
+
 	switch (priority) {
 	case BOOKE_IRQPRIO_DTLB_MISS:
 	case BOOKE_IRQPRIO_DATA_STORAGE:
@@ -408,6 +411,8 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 			set_guest_esr(vcpu, vcpu->arch.queued_esr);
 		if (update_dear == true)
 			set_guest_dear(vcpu, vcpu->arch.queued_dear);
+		if (update_epr == true)
+			kvm_make_request(KVM_REQ_EPR_EXIT, vcpu);
 
 		new_msr &= msr_mask;
 #if defined(CONFIG_64BIT)
@@ -615,6 +620,13 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 		r = 0;
 	}
 
+	if (kvm_check_request(KVM_REQ_EPR_EXIT, vcpu)) {
+		vcpu->run->epr.epr = 0;
+		vcpu->arch.epr_needed = true;
+		vcpu->run->exit_reason = KVM_EXIT_EPR;
+		r = 0;
+	}
+
 	return r;
 }
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index e2225e5b8a4c..934413cd3a1b 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -306,6 +306,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_BOOKE
 	case KVM_CAP_PPC_BOOKE_SREGS:
 	case KVM_CAP_PPC_BOOKE_WATCHDOG:
+	case KVM_CAP_PPC_EPR:
 #else
 	case KVM_CAP_PPC_SEGSTATE:
 	case KVM_CAP_PPC_HIOR:
@@ -721,6 +722,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		for (i = 0; i < 9; ++i)
 			kvmppc_set_gpr(vcpu, 4 + i, run->papr_hcall.args[i]);
 		vcpu->arch.hcall_needed = 0;
+#ifdef CONFIG_BOOKE
+	} else if (vcpu->arch.epr_needed) {
+		kvmppc_set_epr(vcpu, run->epr.epr);
+		vcpu->arch.epr_needed = 0;
+#endif
 	}
 
 	r = kvmppc_vcpu_run(run, vcpu);
@@ -762,6 +768,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		r = 0;
 		vcpu->arch.papr_enabled = true;
 		break;
+	case KVM_CAP_PPC_EPR:
+		r = 0;
+		vcpu->arch.epr_enabled = cap->args[0];
+		break;
 #ifdef CONFIG_BOOKE
 	case KVM_CAP_PPC_BOOKE_WATCHDOG:
 		r = 0;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index cbe0d683e2e5..4dd7d7531e69 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -122,6 +122,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_WATCHDOG          18
 #define KVM_REQ_MASTERCLOCK_UPDATE 19
 #define KVM_REQ_MCLOCK_INPROGRESS 20
+#define KVM_REQ_EPR_EXIT          21
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 8bb0bf83afc5..9a2db5767ed5 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -169,6 +169,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_S390_UCONTROL	  20
 #define KVM_EXIT_WATCHDOG         21
 #define KVM_EXIT_S390_TSCH        22
+#define KVM_EXIT_EPR              23
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -295,6 +296,10 @@ struct kvm_run {
 			__u32 ipb;
 			__u8 dequeued;
 		} s390_tsch;
+		/* KVM_EXIT_EPR */
+		struct {
+			__u32 epr;
+		} epr;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -656,6 +661,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 #define KVM_CAP_PPC_HTAB_FD 84
 #define KVM_CAP_S390_CSS_SUPPORT 85
+#define KVM_CAP_PPC_EPR 86
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3-59-g8ed1b


From 324b3e63167bce69e6622c2be182595790bf7e38 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 4 Jan 2013 18:28:51 +0100
Subject: KVM: PPC: BookE: Add EPR ONE_REG sync

We need to be able to read and write the contents of the EPR register
from user space.

This patch implements that logic through the ONE_REG API and declares
its (never implemented) SREGS counterpart as deprecated.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt   |  1 +
 arch/powerpc/include/uapi/asm/kvm.h |  6 +++++-
 arch/powerpc/kvm/booke.c            | 21 +++++++++++++++++++++
 3 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a98ed09269d7..09905cbcbb0b 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1774,6 +1774,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_VPA_SLB   | 128
   PPC   | KVM_REG_PPC_VPA_DTL   | 128
   PPC   | KVM_REG_PPC_EPCR	| 32
+  PPC   | KVM_REG_PPC_EPR	| 32
 
 4.69 KVM_GET_ONE_REG
 
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 2fba8a66fb10..16064d00adb9 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -114,7 +114,10 @@ struct kvm_regs {
 /* Embedded Floating Point (SPE) -- IVOR32-34 if KVM_SREGS_E_IVOR */
 #define KVM_SREGS_E_SPE			(1 << 9)
 
-/* External Proxy (EXP) -- EPR */
+/*
+ * DEPRECATED! USE ONE_REG FOR THIS ONE!
+ * External Proxy (EXP) -- EPR
+ */
 #define KVM_SREGS_EXP			(1 << 10)
 
 /* External PID (E.PD) -- EPSC/EPLC */
@@ -412,5 +415,6 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_VPA_DTL	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x84)
 
 #define KVM_REG_PPC_EPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85)
+#define KVM_REG_PPC_EPR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x86)
 
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 940ec806187e..8779cd4c52d9 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -300,6 +300,15 @@ static void set_guest_esr(struct kvm_vcpu *vcpu, u32 esr)
 #endif
 }
 
+static unsigned long get_guest_epr(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	return mfspr(SPRN_GEPR);
+#else
+	return vcpu->arch.epr;
+#endif
+}
+
 /* Deliver the interrupt of the corresponding priority, if possible. */
 static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                                         unsigned int priority)
@@ -1405,6 +1414,11 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				 &vcpu->arch.dbg_reg.dac[dac], sizeof(u64));
 		break;
 	}
+	case KVM_REG_PPC_EPR: {
+		u32 epr = get_guest_epr(vcpu);
+		r = put_user(epr, (u32 __user *)(long)reg->addr);
+		break;
+	}
 #if defined(CONFIG_64BIT)
 	case KVM_REG_PPC_EPCR:
 		r = put_user(vcpu->arch.epcr, (u32 __user *)(long)reg->addr);
@@ -1437,6 +1451,13 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			     (u64 __user *)(long)reg->addr, sizeof(u64));
 		break;
 	}
+	case KVM_REG_PPC_EPR: {
+		u32 new_epr;
+		r = get_user(new_epr, (u32 __user *)(long)reg->addr);
+		if (!r)
+			kvmppc_set_epr(vcpu, new_epr);
+		break;
+	}
 #if defined(CONFIG_64BIT)
 	case KVM_REG_PPC_EPCR: {
 		u32 new_epcr;
-- 
cgit v1.2.3-59-g8ed1b


From e12091ce7bdd3c82fa392a868d1bdccecee655d5 Mon Sep 17 00:00:00 2001
From: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Date: Tue, 8 Jan 2013 19:45:28 +0900
Subject: KVM: Remove unused slot_bitmap from kvm_mmu_page

Not needed any more.

Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 Documentation/virtual/kvm/mmu.txt |  7 -------
 arch/x86/include/asm/kvm_host.h   |  5 -----
 arch/x86/kvm/mmu.c                | 10 ----------
 3 files changed, 22 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index fa5f1dbc6b23..43fcb761ed16 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -187,13 +187,6 @@ Shadow pages contain the following information:
     perform a reverse map from a pte to a gfn. When role.direct is set, any
     element of this array can be calculated from the gfn field when used, in
     this case, the array of gfns is not allocated. See role.direct and gfn.
-  slot_bitmap:
-    A bitmap containing one bit per memory slot.  If the page contains a pte
-    mapping a page from memory slot n, then bit n of slot_bitmap will be set
-    (if a page is aliased among several slots, then it is not guaranteed that
-    all slots will be marked).
-    Used during dirty logging to avoid scanning a shadow page if none if its
-    pages need tracking.
   root_count:
     A counter keeping track of how many hardware registers (guest cr3 or
     pdptrs) are now pointing at the page.  While this counter is nonzero, the
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c431b33271f3..f75e1feb6ec5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -219,11 +219,6 @@ struct kvm_mmu_page {
 	u64 *spt;
 	/* hold the gfn of each spte inside spt */
 	gfn_t *gfns;
-	/*
-	 * One bit set per slot which has memory
-	 * in this shadow page.
-	 */
-	DECLARE_BITMAP(slot_bitmap, KVM_MEM_SLOTS_NUM);
 	bool unsync;
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index aeb7666eb81e..9c1b2d6158bf 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1522,7 +1522,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
 		sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
-	bitmap_zero(sp->slot_bitmap, KVM_MEM_SLOTS_NUM);
 	sp->parent_ptes = 0;
 	mmu_page_add_parent_pte(vcpu, sp, parent_pte);
 	kvm_mod_used_mmu_pages(vcpu->kvm, +1);
@@ -2183,14 +2182,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
 
-static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
-{
-	int slot = memslot_id(kvm, gfn);
-	struct kvm_mmu_page *sp = page_header(__pa(pte));
-
-	__set_bit(slot, sp->slot_bitmap);
-}
-
 /*
  * The function is based on mtrr_type_lookup() in
  * arch/x86/kernel/cpu/mtrr/generic.c
@@ -2472,7 +2463,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		++vcpu->kvm->stat.lpages;
 
 	if (is_shadow_present_pte(*sptep)) {
-		page_header_update_slot(vcpu->kvm, sptep, gfn);
 		if (!was_rmapped) {
 			rmap_count = rmap_add(vcpu, sptep, gfn);
 			if (rmap_count > RMAP_RECYCLE_THRESHOLD)
-- 
cgit v1.2.3-59-g8ed1b


From 75d61fbcf563373696578570e914f555e12c8d97 Mon Sep 17 00:00:00 2001
From: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Date: Wed, 30 Jan 2013 19:40:41 +0900
Subject: KVM: set_memory_region: Disallow changing read-only attribute later

As Xiao pointed out, there are a few problems with it:
 - kvm_arch_commit_memory_region() write protects the memory slot only
   for GET_DIRTY_LOG when modifying the flags.
 - FNAME(sync_page) uses the old spte value to set a new one without
   checking KVM_MEM_READONLY flag.

Since we flush all shadow pages when creating a new slot, the simplest
fix is to disallow such problematic flag changes: this is safe because
no one is doing such things.

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 12 ++++++------
 virt/kvm/kvm_main.c               | 35 ++++++++++++-----------------------
 2 files changed, 18 insertions(+), 29 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 09905cbcbb0b..0e03b1968272 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -874,12 +874,12 @@ It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
 be identical.  This allows large pages in the guest to be backed by large
 pages in the host.
 
-The flags field supports two flag, KVM_MEM_LOG_DIRTY_PAGES, which instructs
-kvm to keep track of writes to memory within the slot.  See KVM_GET_DIRTY_LOG
-ioctl.  The KVM_CAP_READONLY_MEM capability indicates the availability of the
-KVM_MEM_READONLY flag.  When this flag is set for a memory region, KVM only
-allows read accesses.  Writes will be posted to userspace as KVM_EXIT_MMIO
-exits.
+The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and
+KVM_MEM_READONLY.  The former can be set to instruct KVM to keep track of
+writes to memory within the slot.  See KVM_GET_DIRTY_LOG ioctl to know how to
+use it.  The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
+to make a new slot read-only.  In this case, writes to this memory will be
+posted to userspace as KVM_EXIT_MMIO exits.
 
 When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
 the memory region are automatically reflected into the guest.  For example, an
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 64c5dc37c6a1..2e93630b4add 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -754,7 +754,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	struct kvm_memory_slot *slot;
 	struct kvm_memory_slot old, new;
 	struct kvm_memslots *slots = NULL, *old_memslots;
-	bool old_iommu_mapped;
 	enum kvm_mr_change change;
 
 	r = check_memory_region_flags(mem);
@@ -797,15 +796,14 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new.npages = npages;
 	new.flags = mem->flags;
 
-	old_iommu_mapped = old.npages;
-
 	r = -EINVAL;
 	if (npages) {
 		if (!old.npages)
 			change = KVM_MR_CREATE;
 		else { /* Modify an existing slot. */
 			if ((mem->userspace_addr != old.userspace_addr) ||
-			    (npages != old.npages))
+			    (npages != old.npages) ||
+			    ((new.flags ^ old.flags) & KVM_MEM_READONLY))
 				goto out;
 
 			if (base_gfn != old.base_gfn)
@@ -867,7 +865,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 		/* slot was deleted or moved, clear iommu mapping */
 		kvm_iommu_unmap_pages(kvm, &old);
-		old_iommu_mapped = false;
 		/* From this point no new shadow pages pointing to a deleted,
 		 * or moved, memslot will be created.
 		 *
@@ -898,25 +895,17 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	/*
 	 * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
-	 * un-mapped and re-mapped if their base changes or if flags that the
-	 * iommu cares about change (read-only).  Base change unmapping is
-	 * handled above with slot deletion, so we only unmap incompatible
-	 * flags here.  Anything else the iommu might care about for existing
-	 * slots (size changes, userspace addr changes) is disallowed above,
-	 * so any other attribute changes getting here can be skipped.
+	 * un-mapped and re-mapped if their base changes.  Since base change
+	 * unmapping is handled above with slot deletion, mapping alone is
+	 * needed here.  Anything else the iommu might care about for existing
+	 * slots (size changes, userspace addr changes and read-only flag
+	 * changes) is disallowed above, so any other attribute changes getting
+	 * here can be skipped.
 	 */
-	if (change != KVM_MR_DELETE) {
-		if (old_iommu_mapped &&
-		    ((new.flags ^ old.flags) & KVM_MEM_READONLY)) {
-			kvm_iommu_unmap_pages(kvm, &old);
-			old_iommu_mapped = false;
-		}
-
-		if (!old_iommu_mapped) {
-			r = kvm_iommu_map_pages(kvm, &new);
-			if (r)
-				goto out_slots;
-		}
+	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+		r = kvm_iommu_map_pages(kvm, &new);
+		if (r)
+			goto out_slots;
 	}
 
 	/* actual memory is freed via old in kvm_free_physmem_slot below */
-- 
cgit v1.2.3-59-g8ed1b


From 4293b5e5a68074431cafa74d549c1327ba1d0deb Mon Sep 17 00:00:00 2001
From: Geoff Levand <geoff@infradead.org>
Date: Thu, 31 Jan 2013 12:06:08 -0800
Subject: KVM: Remove duplicate text in api.txt

Signed-off-by: Geoff Levand <geoff@infradead.org>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 13 -------------
 1 file changed, 13 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 0e03b1968272..c2534c300a45 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -219,19 +219,6 @@ allocation of vcpu ids.  For example, if userspace wants
 single-threaded guest vcpus, it should make all vcpu ids be a multiple
 of the number of vcpus per vcore.
 
-On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
-threads in one or more virtual CPU cores.  (This is because the
-hardware requires all the hardware threads in a CPU core to be in the
-same partition.)  The KVM_CAP_PPC_SMT capability indicates the number
-of vcpus per virtual core (vcore).  The vcore id is obtained by
-dividing the vcpu id by the number of vcpus per vcore.  The vcpus in a
-given vcore will always be in the same physical core as each other
-(though that might be a different physical core from time to time).
-Userspace can control the threading (SMT) mode of the guest by its
-allocation of vcpu ids.  For example, if userspace wants
-single-threaded guest vcpus, it should make all vcpu ids be a multiple
-of the number of vcpus per vcore.
-
 For virtual cpus that have been created with S390 user controlled virtual
 machines, the resulting vcpu fd can be memory mapped at page offset
 KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
-- 
cgit v1.2.3-59-g8ed1b