From e08b96371625aaa84cb03f51acc4c8e0be27403a Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:20 +0100
Subject: KVM: s390: add parameter for KVM_CREATE_VM

This patch introduces a new config option for user controlled kernel
virtual machines. It introduces a parameter to KVM_CREATE_VM that
allows to set bits that alter the capabilities of the newly created
virtual machine.
The parameter is passed to kvm_arch_init_vm for all architectures.
The only valid modifier bit for now is KVM_VM_S390_UCONTROL.
This requires CAP_SYS_ADMIN privileges and creates a user controlled
virtual machine on s390 architectures.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/Kconfig    |  9 +++++++++
 arch/s390/kvm/kvm-s390.c | 24 +++++++++++++++++++-----
 arch/s390/kvm/kvm-s390.h | 10 ++++++++++
 3 files changed, 38 insertions(+), 5 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index a21634173a66..78eb9847008f 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -34,6 +34,15 @@ config KVM
 
 	  If unsure, say N.
 
+config KVM_S390_UCONTROL
+	bool "Userspace controlled virtual machines"
+	depends on KVM
+	---help---
+	  Allow CAP_SYS_ADMIN users to create KVM virtual machines that are
+	  controlled by userspace.
+
+	  If unsure, say N.
+
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/vhost/Kconfig
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d1c445732451..f0937552175b 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -171,11 +171,22 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	return r;
 }
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	int rc;
 	char debug_name[16];
 
+	rc = -EINVAL;
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (type & ~KVM_VM_S390_UCONTROL)
+		goto out_err;
+	if ((type & KVM_VM_S390_UCONTROL) && (!capable(CAP_SYS_ADMIN)))
+		goto out_err;
+#else
+	if (type)
+		goto out_err;
+#endif
+
 	rc = s390_enable_sie();
 	if (rc)
 		goto out_err;
@@ -198,10 +209,13 @@ int kvm_arch_init_vm(struct kvm *kvm)
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
 	VM_EVENT(kvm, 3, "%s", "vm created");
 
-	kvm->arch.gmap = gmap_alloc(current->mm);
-	if (!kvm->arch.gmap)
-		goto out_nogmap;
-
+	if (type & KVM_VM_S390_UCONTROL) {
+		kvm->arch.gmap = NULL;
+	} else {
+		kvm->arch.gmap = gmap_alloc(current->mm);
+		if (!kvm->arch.gmap)
+			goto out_nogmap;
+	}
 	return 0;
 out_nogmap:
 	debug_unregister(kvm->arch.dbf);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 99b0b7597115..45b236a7c730 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -47,6 +47,16 @@ static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
 	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
 }
 
+static inline int kvm_is_ucontrol(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (kvm->arch.gmap)
+		return 0;
+	return 1;
+#else
+	return 0;
+#endif
+}
 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);
-- 
cgit v1.2.3


From 27e0393f15fc8bc855c6a888387ff5ffd2181089 Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:21 +0100
Subject: KVM: s390: ucontrol: per vcpu address spaces

This patch introduces two ioctls for virtual cpus, that are only
valid for kernel virtual machines that are controlled by userspace.
Each virtual cpu has its individual address space in this mode of
operation, and each address space is backed by the gmap
implementation just like the address space for regular KVM guests.
KVM_S390_UCAS_MAP allows to map a part of the user's virtual address
space to the vcpu. Starting offset and length in both the user and
the vcpu address space need to be aligned to 1M.
KVM_S390_UCAS_UNMAP can be used to unmap a range of memory from a
virtual cpu in a similar way.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 38 +++++++++++++++++++++++++++++
 arch/s390/kvm/kvm-s390.c          | 50 ++++++++++++++++++++++++++++++++++++++-
 include/linux/kvm.h               | 10 ++++++++
 3 files changed, 97 insertions(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 579d40b26a5a..ee394b263261 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1496,6 +1496,44 @@ following algorithm:
 Some guests configure the LINT1 NMI input to cause a panic, aiding in
 debugging.
 
+4.64 KVM_S390_UCAS_MAP
+
+Capability: KVM_CAP_S390_UCONTROL
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_ucas_mapping (in)
+Returns: 0 in case of success
+
+The parameter is defined like this:
+	struct kvm_s390_ucas_mapping {
+		__u64 user_addr;
+		__u64 vcpu_addr;
+		__u64 length;
+	};
+
+This ioctl maps the memory at "user_addr" with the length "length" to
+the vcpu's address space starting at "vcpu_addr". All parameters need to
+be alligned by 1 megabyte.
+
+4.65 KVM_S390_UCAS_UNMAP
+
+Capability: KVM_CAP_S390_UCONTROL
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_ucas_mapping (in)
+Returns: 0 in case of success
+
+The parameter is defined like this:
+	struct kvm_s390_ucas_mapping {
+		__u64 user_addr;
+		__u64 vcpu_addr;
+		__u64 length;
+	};
+
+This ioctl unmaps the memory in the vcpu's address space starting at
+"vcpu_addr" with the length "length". The field "user_addr" is ignored.
+All parameters need to be alligned by 1 megabyte.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f0937552175b..2d3248895def 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -233,6 +233,10 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 		(__u64) vcpu->arch.sie_block)
 		vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
 	smp_mb();
+
+	if (kvm_is_ucontrol(vcpu->kvm))
+		gmap_free(vcpu->arch.gmap);
+
 	free_page((unsigned long)(vcpu->arch.sie_block));
 	kvm_vcpu_uninit(vcpu);
 	kfree(vcpu);
@@ -263,12 +267,20 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_vcpus(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	debug_unregister(kvm->arch.dbf);
-	gmap_free(kvm->arch.gmap);
+	if (!kvm_is_ucontrol(kvm))
+		gmap_free(kvm->arch.gmap);
 }
 
 /* Section: vcpu related */
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	if (kvm_is_ucontrol(vcpu->kvm)) {
+		vcpu->arch.gmap = gmap_alloc(current->mm);
+		if (!vcpu->arch.gmap)
+			return -ENOMEM;
+		return 0;
+	}
+
 	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
 	return 0;
 }
@@ -687,6 +699,42 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_S390_INITIAL_RESET:
 		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
 		break;
+#ifdef CONFIG_KVM_S390_UCONTROL
+	case KVM_S390_UCAS_MAP: {
+		struct kvm_s390_ucas_mapping ucasmap;
+
+		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
+			r = -EFAULT;
+			break;
+		}
+
+		if (!kvm_is_ucontrol(vcpu->kvm)) {
+			r = -EINVAL;
+			break;
+		}
+
+		r = gmap_map_segment(vcpu->arch.gmap, ucasmap.user_addr,
+				     ucasmap.vcpu_addr, ucasmap.length);
+		break;
+	}
+	case KVM_S390_UCAS_UNMAP: {
+		struct kvm_s390_ucas_mapping ucasmap;
+
+		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
+			r = -EFAULT;
+			break;
+		}
+
+		if (!kvm_is_ucontrol(vcpu->kvm)) {
+			r = -EINVAL;
+			break;
+		}
+
+		r = gmap_unmap_segment(vcpu->arch.gmap, ucasmap.vcpu_addr,
+			ucasmap.length);
+		break;
+	}
+#endif
 	default:
 		r = -EINVAL;
 	}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index bba393a6760f..0a66c1072691 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -658,6 +658,16 @@ struct kvm_clock_data {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+
+/* enable ucontrol for s390 */
+struct kvm_s390_ucas_mapping {
+	__u64 user_addr;
+	__u64 vcpu_addr;
+	__u64 length;
+};
+#define KVM_S390_UCAS_MAP        _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
+#define KVM_S390_UCAS_UNMAP      _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
+
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP        _IO(KVMIO,   0x60)
 #define KVM_IRQ_LINE              _IOW(KVMIO,  0x61, struct kvm_irq_level)
-- 
cgit v1.2.3


From e168bf8de33e16a909df2401af1f7d419c5780de Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:22 +0100
Subject: KVM: s390: ucontrol: export page faults to user

This patch introduces a new exit reason in the kvm_run structure
named KVM_EXIT_S390_UCONTROL. This exit indicates, that a virtual cpu
has regognized a fault on the host page table. The idea is that
userspace can handle this fault by mapping memory at the fault
location into the cpu's address space and then continue to run the
virtual cpu.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 14 ++++++++++++++
 arch/s390/kvm/kvm-s390.c          | 32 +++++++++++++++++++++++++++-----
 arch/s390/kvm/kvm-s390.h          |  1 +
 include/linux/kvm.h               |  6 ++++++
 4 files changed, 48 insertions(+), 5 deletions(-)

(limited to 'arch/s390')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index ee394b263261..6e53ff51422f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1694,6 +1694,20 @@ s390 specific.
 
 s390 specific.
 
+		/* KVM_EXIT_S390_UCONTROL */
+		struct {
+			__u64 trans_exc_code;
+			__u32 pgm_code;
+		} s390_ucontrol;
+
+s390 specific. A page fault has occurred for a user controlled virtual
+machine (KVM_VM_S390_UNCONTROL) on it's host page table that cannot be
+resolved by the kernel.
+The program code and the translation exception code that were placed
+in the cpu's lowcore are presented here as defined by the z Architecture
+Principles of Operation Book in the Chapter for Dynamic Address Translation
+(DAT)
+
 		/* KVM_EXIT_DCR */
 		struct {
 			__u32 dcrn;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2d3248895def..af05328aca25 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -493,8 +493,10 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return -EINVAL; /* not implemented yet */
 }
 
-static void __vcpu_run(struct kvm_vcpu *vcpu)
+static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
+	int rc;
+
 	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);
 
 	if (need_resched())
@@ -511,9 +513,15 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
-	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
-		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
-		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs);
+	if (rc) {
+		if (kvm_is_ucontrol(vcpu->kvm)) {
+			rc = SIE_INTERCEPT_UCONTROL;
+		} else {
+			VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+			kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+			rc = 0;
+		}
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
@@ -522,6 +530,7 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 
 	memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16);
+	return rc;
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -542,6 +551,7 @@ rerun_vcpu:
 	case KVM_EXIT_UNKNOWN:
 	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
+	case KVM_EXIT_S390_UCONTROL:
 		break;
 	default:
 		BUG();
@@ -553,7 +563,9 @@ rerun_vcpu:
 	might_fault();
 
 	do {
-		__vcpu_run(vcpu);
+		rc = __vcpu_run(vcpu);
+		if (rc)
+			break;
 		rc = kvm_handle_sie_intercept(vcpu);
 	} while (!signal_pending(current) && !rc);
 
@@ -565,6 +577,16 @@ rerun_vcpu:
 		rc = -EINTR;
 	}
 
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (rc == SIE_INTERCEPT_UCONTROL) {
+		kvm_run->exit_reason = KVM_EXIT_S390_UCONTROL;
+		kvm_run->s390_ucontrol.trans_exc_code =
+			current->thread.gmap_addr;
+		kvm_run->s390_ucontrol.pgm_code = 0x10;
+		rc = 0;
+	}
+#endif
+
 	if (rc == -EOPNOTSUPP) {
 		/* intercept cannot be handled in-kernel, prepare kvm-run */
 		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 45b236a7c730..62aa5f19bb98 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -26,6 +26,7 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
 /* negativ values are error codes, positive values for internal conditions */
 #define SIE_INTERCEPT_RERUNVCPU		(1<<0)
+#define SIE_INTERCEPT_UCONTROL		(1<<1)
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
 
 #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 0a66c1072691..7f686f6708b0 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -162,6 +162,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_INTERNAL_ERROR   17
 #define KVM_EXIT_OSI              18
 #define KVM_EXIT_PAPR_HCALL	  19
+#define KVM_EXIT_S390_UCONTROL	  20
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1
@@ -249,6 +250,11 @@ struct kvm_run {
 #define KVM_S390_RESET_CPU_INIT  8
 #define KVM_S390_RESET_IPL       16
 		__u64 s390_reset_flags;
+		/* KVM_EXIT_S390_UCONTROL */
+		struct {
+			__u64 trans_exc_code;
+			__u32 pgm_code;
+		} s390_ucontrol;
 		/* KVM_EXIT_DCR */
 		struct {
 			__u32 dcrn;
-- 
cgit v1.2.3


From 5b1c1493afe8d69909f9df3221bb2fffdf479f4a Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:23 +0100
Subject: KVM: s390: ucontrol: export SIE control block to user

This patch exports the s390 SIE hardware control block to userspace
via the mapping of the vcpu file descriptor. In order to do so,
a new arch callback named kvm_arch_vcpu_fault  is introduced for all
architectures. It allows to map architecture specific pages.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 Documentation/virtual/kvm/api.txt |  5 +++++
 arch/ia64/kvm/kvm-ia64.c          |  5 +++++
 arch/powerpc/kvm/powerpc.c        |  5 +++++
 arch/s390/kvm/kvm-s390.c          | 13 +++++++++++++
 arch/x86/kvm/x86.c                |  5 +++++
 include/linux/kvm.h               |  2 ++
 include/linux/kvm_host.h          |  1 +
 virt/kvm/kvm_main.c               |  2 +-
 8 files changed, 37 insertions(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6e53ff51422f..5ebf47d99e56 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -218,6 +218,11 @@ 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
+cpu's hardware control block.
+
 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
 
 Capability: basic
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index df6b14194051..8ca7261e7b3d 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1566,6 +1566,11 @@ out:
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		struct kvm_memory_slot *memslot,
 		struct kvm_memory_slot old,
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 83f244569874..a5671616af86 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -659,6 +659,11 @@ out:
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
 static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
 {
 	u32 inst_lis = 0x3c000000;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index af05328aca25..d6bc65aeb950 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -763,6 +763,19 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if ((vmf->pgoff == KVM_S390_SIE_PAGE_OFFSET)
+		 && (kvm_is_ucontrol(vcpu->kvm))) {
+		vmf->page = virt_to_page(vcpu->arch.sie_block);
+		get_page(vmf->page);
+		return 0;
+	}
+#endif
+	return VM_FAULT_SIGBUS;
+}
+
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 06925b4bcc27..a3ce196d21fe 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2814,6 +2814,11 @@ out:
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+	return VM_FAULT_SIGBUS;
+}
+
 static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr)
 {
 	int ret;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 7f686f6708b0..8f888df206a2 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -440,6 +440,8 @@ struct kvm_ppc_pvinfo {
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
 #define KVM_VM_S390_UCONTROL	1
 
+#define KVM_S390_SIE_PAGE_OFFSET 1
+
 /*
  * ioctls for /dev/kvm fds:
  */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 82375e145e64..d4d4d7092110 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -450,6 +450,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg);
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
 
 int kvm_dev_ioctl_check_extension(long ext);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 32e3b048a6cf..64be836f3348 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1657,7 +1657,7 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
 #endif
 	else
-		return VM_FAULT_SIGBUS;
+		return kvm_arch_vcpu_fault(vcpu, vmf);
 	get_page(page);
 	vmf->page = page;
 	return 0;
-- 
cgit v1.2.3


From c0d744a9c8aae81b624e0650e6fbbbb83db1a145 Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:24 +0100
Subject: KVM: s390: ucontrol: disable in-kernel handling of SIE intercepts

This patch disables in-kernel handling of SIE intercepts for user
controlled virtual machines. All intercepts are passed to userspace
via KVM_EXIT_SIE exit reason just like SIE intercepts that cannot be
handled in-kernel for regular KVM guests.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d6bc65aeb950..02510946864e 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -566,7 +566,10 @@ rerun_vcpu:
 		rc = __vcpu_run(vcpu);
 		if (rc)
 			break;
-		rc = kvm_handle_sie_intercept(vcpu);
+		if (kvm_is_ucontrol(vcpu->kvm))
+			rc = -EOPNOTSUPP;
+		else
+			rc = kvm_handle_sie_intercept(vcpu);
 	} while (!signal_pending(current) && !rc);
 
 	if (rc == SIE_INTERCEPT_RERUNVCPU)
-- 
cgit v1.2.3


From d6b6d166864fa97ca3b1ed1a5c62fd3b53d4606f Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:25 +0100
Subject: KVM: s390: ucontrol: disable in-kernel irq stack

This patch disables the in-kernel interrupt stack for KVM virtual
machines that are controlled by user. Userspace has to take care
of handling interrupts on its own.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 02510946864e..5b5c28e471df 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -505,7 +505,8 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	if (test_thread_flag(TIF_MCCK_PENDING))
 		s390_handle_mcck();
 
-	kvm_s390_deliver_pending_interrupts(vcpu);
+	if (!kvm_is_ucontrol(vcpu->kvm))
+		kvm_s390_deliver_pending_interrupts(vcpu);
 
 	vcpu->arch.sie_block->icptcode = 0;
 	local_irq_disable();
-- 
cgit v1.2.3


From ccc7910fe564d99415def7c041fa261e62a43011 Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:26 +0100
Subject: KVM: s390: ucontrol: interface to inject faults on a vcpu page table

This patch allows the user to fault in pages on a virtual cpus
address space for user controlled virtual machines. Typically this
is superfluous because userspace can just create a mapping and
let the kernel's page fault logic take are of it. There is one
exception: SIE won't start if the lowcore is not present. Normally
the kernel takes care of this [handle_validity() in
arch/s390/kvm/intercept.c] but since the kernel does not handle
intercepts for user controlled virtual machines, userspace needs to
be able to handle this condition.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 16 ++++++++++++++++
 arch/s390/kvm/kvm-s390.c          |  6 ++++++
 include/linux/kvm.h               |  1 +
 3 files changed, 23 insertions(+)

(limited to 'arch/s390')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 5ebf47d99e56..a67fb35993fa 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1539,6 +1539,22 @@ This ioctl unmaps the memory in the vcpu's address space starting at
 "vcpu_addr" with the length "length". The field "user_addr" is ignored.
 All parameters need to be alligned by 1 megabyte.
 
+4.66 KVM_S390_VCPU_FAULT
+
+Capability: KVM_CAP_S390_UCONTROL
+Architectures: s390
+Type: vcpu ioctl
+Parameters: vcpu absolute address (in)
+Returns: 0 in case of success
+
+This call creates a page table entry on the virtual cpu's address space
+(for user controlled virtual machines) or the virtual machine's address
+space (for regular virtual machines). This only works for minor faults,
+thus it's recommended to access subject memory page via the user page
+table upfront. This is useful to handle validity intercepts for user
+controlled virtual machines to fault in the virtual cpu's lowcore pages
+prior to calling the KVM_RUN ioctl.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 5b5c28e471df..8489edf80c89 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -761,6 +761,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 #endif
+	case KVM_S390_VCPU_FAULT: {
+		r = gmap_fault(arg, vcpu->arch.gmap);
+		if (!IS_ERR_VALUE(r))
+			r = 0;
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 8f888df206a2..778e748927b4 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -675,6 +675,7 @@ struct kvm_s390_ucas_mapping {
 };
 #define KVM_S390_UCAS_MAP        _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
 #define KVM_S390_UCAS_UNMAP      _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
+#define KVM_S390_VCPU_FAULT	 _IOW(KVMIO, 0x52, unsigned long)
 
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP        _IO(KVMIO,   0x60)
-- 
cgit v1.2.3


From 58f9460ba1cc9de67e6591bfd08dccded43d27bd Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:27 +0100
Subject: KVM: s390: ucontrol: disable sca

This patch makes sure user controlled virtual machines do not use a
system control area (sca). This is needed in order to create
virtual machines with more cpus than the size of the sca [64].

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8489edf80c89..abf784d8c680 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -228,10 +228,13 @@ out_err:
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
-	clear_bit(63 - vcpu->vcpu_id, (unsigned long *) &vcpu->kvm->arch.sca->mcn);
-	if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
-		(__u64) vcpu->arch.sie_block)
-		vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
+	if (!kvm_is_ucontrol(vcpu->kvm)) {
+		clear_bit(63 - vcpu->vcpu_id,
+			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
+		if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
+		    (__u64) vcpu->arch.sie_block)
+			vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
+	}
 	smp_mb();
 
 	if (kvm_is_ucontrol(vcpu->kvm))
@@ -368,12 +371,19 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 		goto out_free_cpu;
 
 	vcpu->arch.sie_block->icpua = id;
-	BUG_ON(!kvm->arch.sca);
-	if (!kvm->arch.sca->cpu[id].sda)
-		kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
-	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
-	vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
-	set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
+	if (!kvm_is_ucontrol(kvm)) {
+		if (!kvm->arch.sca) {
+			WARN_ON_ONCE(1);
+			goto out_free_cpu;
+		}
+		if (!kvm->arch.sca->cpu[id].sda)
+			kvm->arch.sca->cpu[id].sda =
+				(__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh =
+			(__u32)(((__u64)kvm->arch.sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
+		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
+	}
 
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
-- 
cgit v1.2.3


From 3777594d5a75b704312544a59094beecd820e12b Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:28 +0100
Subject: KVM: s390: fix assumption for KVM_MAX_VCPUS

This patch fixes definition of the idle_mask and the local_int array
in kvm_s390_float_interrupt. Previous definition had 64 cpus max
hardcoded instead of using KVM_MAX_VCPUS.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/include/asm/kvm_host.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index b0c235cb6ad5..e34fb2ba76c1 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -220,8 +220,9 @@ struct kvm_s390_float_interrupt {
 	struct list_head list;
 	atomic_t active;
 	int next_rr_cpu;
-	unsigned long idle_mask [(64 + sizeof(long) - 1) / sizeof(long)];
-	struct kvm_s390_local_interrupt *local_int[64];
+	unsigned long idle_mask[(KVM_MAX_VCPUS + sizeof(long) - 1)
+				/ sizeof(long)];
+	struct kvm_s390_local_interrupt *local_int[KVM_MAX_VCPUS];
 };
 
 
-- 
cgit v1.2.3


From 1efd0f595ab9d10fef1486dfdef952107c91f3db Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:29 +0100
Subject: KVM: s390: ucontrol: announce capability for user controlled vms

This patch announces a new capability KVM_CAP_S390_UCONTROL that
indicates that kvm can now support virtual machines that are
controlled by userspace.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 3 +++
 include/linux/kvm.h      | 1 +
 2 files changed, 4 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index abf784d8c680..a1061b361c43 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -129,6 +129,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_S390_PSW:
 	case KVM_CAP_S390_GMAP:
 	case KVM_CAP_SYNC_MMU:
+#ifdef CONFIG_KVM_S390_UCONTROL
+	case KVM_CAP_S390_UCONTROL:
+#endif
 		r = 1;
 		break;
 	default:
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 778e748927b4..6cf048d9604b 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -569,6 +569,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_PAPR 68
 #define KVM_CAP_S390_GMAP 71
 #define KVM_CAP_TSC_DEADLINE_TIMER 72
+#define KVM_CAP_S390_UCONTROL 73
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 3e6afcf1d8ce6bca6bfa62a49c1d70d2f16162eb Mon Sep 17 00:00:00 2001
From: Carsten Otte <cotte@de.ibm.com>
Date: Wed, 4 Jan 2012 10:25:30 +0100
Subject: KVM: s390: Fix return code for unknown ioctl numbers

This patch fixes the return code of kvm_arch_vcpu_ioctl in case
of an unkown ioctl number.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index a1061b361c43..a33b44487540 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -781,7 +781,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 	default:
-		r = -EINVAL;
+		r = -ENOTTY;
 	}
 	return r;
 }
-- 
cgit v1.2.3


From 8d26cf7b40b1648c39e77a113dac07ad31363120 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Wed, 11 Jan 2012 11:19:32 +0100
Subject: KVM: s390: rework code that sets the prefix

There are several places in the kvm module, which set the prefix register.
Since we need to flush the cpu, lets combine this operation into a helper
function. This helper will also explicitely mask out the unused bits.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/interrupt.c | 3 +--
 arch/s390/kvm/kvm-s390.c  | 3 +--
 arch/s390/kvm/kvm-s390.h  | 7 +++++++
 arch/s390/kvm/priv.c      | 3 +--
 4 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 278ee009ce65..c6366cfb3bf0 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -236,8 +236,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
 			   inti->prefix.address);
 		vcpu->stat.deliver_prefix_signal++;
-		vcpu->arch.sie_block->prefix = inti->prefix.address;
-		vcpu->arch.sie_block->ihcpu = 0xffff;
+		kvm_s390_set_prefix(vcpu, inti->prefix.address);
 		break;
 
 	case KVM_S390_RESTART:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index a33b44487540..1868b89a840f 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -322,8 +322,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	/* this equals initial cpu reset in pop, but we don't switch to ESA */
 	vcpu->arch.sie_block->gpsw.mask = 0UL;
 	vcpu->arch.sie_block->gpsw.addr = 0UL;
-	vcpu->arch.sie_block->prefix    = 0UL;
-	vcpu->arch.sie_block->ihcpu     = 0xffff;
+	kvm_s390_set_prefix(vcpu, 0);
 	vcpu->arch.sie_block->cputm     = 0UL;
 	vcpu->arch.sie_block->ckc       = 0UL;
 	vcpu->arch.sie_block->todpr     = 0;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 62aa5f19bb98..ff28f9d1c9eb 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -58,6 +58,13 @@ static inline int kvm_is_ucontrol(struct kvm *kvm)
 	return 0;
 #endif
 }
+
+static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
+{
+	vcpu->arch.sie_block->prefix = prefix & 0x7fffe000u;
+	vcpu->arch.sie_block->ihcpu  = 0xffff;
+}
+
 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 d02638959922..9c83b8a53843 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -56,8 +56,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	vcpu->arch.sie_block->prefix = address;
-	vcpu->arch.sie_block->ihcpu = 0xffff;
+	kvm_s390_set_prefix(vcpu, address);
 
 	VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
 out:
-- 
cgit v1.2.3


From b9e5dc8d4511e6a00862a795319569e7fe7f60f4 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Wed, 11 Jan 2012 11:20:30 +0100
Subject: KVM: provide synchronous registers in kvm_run

On some cpus the overhead for virtualization instructions is in the same
range as a system call. Having to call multiple ioctls to get set registers
will make certain userspace handled exits more expensive than necessary.
Lets provide a section in kvm_run that works as a shared save area
for guest registers.
We also provide two 64bit flags fields (architecture specific), that will
specify
1. which parts of these fields are valid.
2. which registers were modified by userspace

Each bit for these flag fields will define a group of registers (like
general purpose) or a single register.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 23 +++++++++++++++++++++++
 arch/ia64/include/asm/kvm.h       |  4 ++++
 arch/powerpc/include/asm/kvm.h    |  4 ++++
 arch/s390/include/asm/kvm.h       |  3 +++
 arch/x86/include/asm/kvm.h        |  4 ++++
 include/linux/kvm.h               | 15 +++++++++++++++
 6 files changed, 53 insertions(+)

(limited to 'arch/s390')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a67fb35993fa..7ca696227d3a 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1771,6 +1771,29 @@ developer registration required to access it).
 		/* Fix the size of the union. */
 		char padding[256];
 	};
+
+	/*
+	 * shared registers between kvm and userspace.
+	 * kvm_valid_regs specifies the register classes set by the host
+	 * kvm_dirty_regs specified the register classes dirtied by userspace
+	 * struct kvm_sync_regs is architecture specific, as well as the
+	 * bits for kvm_valid_regs and kvm_dirty_regs
+	 */
+	__u64 kvm_valid_regs;
+	__u64 kvm_dirty_regs;
+	union {
+		struct kvm_sync_regs regs;
+		char padding[1024];
+	} s;
+
+If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
+certain guest registers without having to call SET/GET_*REGS. Thus we can
+avoid some system call overhead if userspace has to handle the exit.
+Userspace can query the validity of the structure by checking
+kvm_valid_regs for specific bits. These bits are architecture specific
+and usually define the validity of a groups of registers. (e.g. one bit
+ for general purpose registers)
+
 };
 
 6. Capabilities that can be enabled
diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h
index bc90c75adf67..b9f82c84f093 100644
--- a/arch/ia64/include/asm/kvm.h
+++ b/arch/ia64/include/asm/kvm.h
@@ -261,4 +261,8 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
 #endif
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index f7727d91ac6b..7d9d4de057ef 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -265,6 +265,10 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
 #define KVM_REG_MASK		0x001f
 #define KVM_REG_EXT_MASK	0xffe0
 #define KVM_REG_GPR		0x0000
diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index 82b32a100c7d..325560afb77e 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -41,4 +41,7 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
 #endif
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 4d8dcbdfc120..e7d1c194d272 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -321,4 +321,8 @@ struct kvm_xcrs {
 	__u64 padding[16];
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 6cf048d9604b..245bcb3a0fcd 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -279,6 +279,20 @@ struct kvm_run {
 		/* Fix the size of the union. */
 		char padding[256];
 	};
+
+	/*
+	 * shared registers between kvm and userspace.
+	 * kvm_valid_regs specifies the register classes set by the host
+	 * kvm_dirty_regs specified the register classes dirtied by userspace
+	 * struct kvm_sync_regs is architecture specific, as well as the
+	 * bits for kvm_valid_regs and kvm_dirty_regs
+	 */
+	__u64 kvm_valid_regs;
+	__u64 kvm_dirty_regs;
+	union {
+		struct kvm_sync_regs regs;
+		char padding[1024];
+	} s;
 };
 
 /* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
@@ -570,6 +584,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_S390_GMAP 71
 #define KVM_CAP_TSC_DEADLINE_TIMER 72
 #define KVM_CAP_S390_UCONTROL 73
+#define KVM_CAP_SYNC_REGS 74
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 60b413c9248495ea400e80e08e4d1e28ed7ee05e Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Wed, 11 Jan 2012 11:20:31 +0100
Subject: KVM: s390: provide the prefix register via kvm_run

Add the prefix register to the synced register field in kvm_run.
While we need the prefix register most of the time read-only, this
patch also adds handling for guest dirtying of the prefix register.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/include/asm/kvm.h | 2 ++
 arch/s390/kvm/kvm-s390.c    | 7 +++++++
 2 files changed, 9 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index 325560afb77e..9fc328c26159 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -41,7 +41,9 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
+#define KVM_SYNC_PREFIX (1UL << 0)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
+	__u64 prefix;	/* prefix register */
 };
 #endif
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1868b89a840f..6962c1b9eec6 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -132,6 +132,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_KVM_S390_UCONTROL
 	case KVM_CAP_S390_UCONTROL:
 #endif
+	case KVM_CAP_SYNC_REGS:
 		r = 1;
 		break;
 	default:
@@ -288,6 +289,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	}
 
 	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX;
 	return 0;
 }
 
@@ -572,6 +574,10 @@ rerun_vcpu:
 
 	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
 	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) {
+		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_PREFIX;
+		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+	}
 
 	might_fault();
 
@@ -620,6 +626,7 @@ rerun_vcpu:
 
 	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
 	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
+	kvm_run->s.regs.prefix = vcpu->arch.sie_block->prefix;
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
-- 
cgit v1.2.3


From 5a32c1af56b3c74212b1de2a1d1658c303dd3516 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Wed, 11 Jan 2012 11:20:32 +0100
Subject: KVM: s390: provide general purpose guest registers via kvm_run

This patch adds the general purpose registers to the kvm_run structure.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/include/asm/kvm.h      |  2 ++
 arch/s390/include/asm/kvm_host.h |  3 +--
 arch/s390/kvm/diag.c             |  6 +++---
 arch/s390/kvm/intercept.c        |  4 ++--
 arch/s390/kvm/kvm-s390.c         | 14 +++++++-------
 arch/s390/kvm/priv.c             | 24 ++++++++++++------------
 arch/s390/kvm/sigp.c             | 20 ++++++++++----------
 7 files changed, 37 insertions(+), 36 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index 9fc328c26159..420dbb7db8dd 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -42,8 +42,10 @@ struct kvm_guest_debug_arch {
 };
 
 #define KVM_SYNC_PREFIX (1UL << 0)
+#define KVM_SYNC_GPRS   (1UL << 1)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
+	__u64 gprs[16];	/* general purpose registers */
 };
 #endif
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index e34fb2ba76c1..ed843cad4194 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -228,7 +228,6 @@ struct kvm_s390_float_interrupt {
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
-	unsigned long	  guest_gprs[16];
 	s390_fp_regs      host_fpregs;
 	unsigned int      host_acrs[NUM_ACRS];
 	s390_fp_regs      guest_fpregs;
@@ -254,5 +253,5 @@ struct kvm_arch{
 	struct gmap *gmap;
 };
 
-extern int sie64a(struct kvm_s390_sie_block *, unsigned long *);
+extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 #endif
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 8943e82cd4d9..a353f0ea45c2 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -20,8 +20,8 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
 	unsigned long start, end;
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
 
-	start = vcpu->arch.guest_gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
-	end = vcpu->arch.guest_gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
+	start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
+	end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
 
 	if (start & ~PAGE_MASK || end & ~PAGE_MASK || start > end
 	    || start < 2 * PAGE_SIZE)
@@ -56,7 +56,7 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 {
 	unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
-	unsigned long subcode = vcpu->arch.guest_gprs[reg] & 0xffff;
+	unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
 
 	VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
 	switch (subcode) {
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 02434543eabb..776ef83c2771 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -36,7 +36,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 
 	useraddr = disp2;
 	if (base2)
-		useraddr += vcpu->arch.guest_gprs[base2];
+		useraddr += vcpu->run->s.regs.gprs[base2];
 
 	if (useraddr & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -75,7 +75,7 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 
 	useraddr = disp2;
 	if (base2)
-		useraddr += vcpu->arch.guest_gprs[base2];
+		useraddr += vcpu->run->s.regs.gprs[base2];
 
 	if (useraddr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6962c1b9eec6..80b12bac6a5b 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -289,7 +289,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	}
 
 	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
-	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX;
+	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX | KVM_SYNC_GPRS;
 	return 0;
 }
 
@@ -428,13 +428,13 @@ static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
-	memcpy(&vcpu->arch.guest_gprs, &regs->gprs, sizeof(regs->gprs));
+	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
-	memcpy(&regs->gprs, &vcpu->arch.guest_gprs, sizeof(regs->gprs));
+	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
 	return 0;
 }
 
@@ -511,7 +511,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int rc;
 
-	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);
+	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
 
 	if (need_resched())
 		schedule();
@@ -528,7 +528,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
-	rc = sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs);
+	rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs);
 	if (rc) {
 		if (kvm_is_ucontrol(vcpu->kvm)) {
 			rc = SIE_INTERCEPT_UCONTROL;
@@ -544,7 +544,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	kvm_guest_exit();
 	local_irq_enable();
 
-	memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16);
+	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
 	return rc;
 }
 
@@ -673,7 +673,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 		return -EFAULT;
 
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs),
-			vcpu->arch.guest_gprs, 128, prefix))
+			vcpu->run->s.regs.gprs, 128, prefix))
 		return -EFAULT;
 
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw),
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 9c83b8a53843..e5a45dbd26ac 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -33,7 +33,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -73,7 +73,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
 	vcpu->stat.instruction_stpx++;
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -105,7 +105,7 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 	vcpu->stat.instruction_stap++;
 	useraddr = disp2;
 	if (base2)
-		useraddr += vcpu->arch.guest_gprs[base2];
+		useraddr += vcpu->run->s.regs.gprs[base2];
 
 	if (useraddr & 1) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -180,7 +180,7 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
 	vcpu->stat.instruction_stidp++;
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	if (operand2 & 7) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -231,9 +231,9 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 
 static int handle_stsi(struct kvm_vcpu *vcpu)
 {
-	int fc = (vcpu->arch.guest_gprs[0] & 0xf0000000) >> 28;
-	int sel1 = vcpu->arch.guest_gprs[0] & 0xff;
-	int sel2 = vcpu->arch.guest_gprs[1] & 0xffff;
+	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;
@@ -244,14 +244,14 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	if (operand2 & 0xfff && fc > 0)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	switch (fc) {
 	case 0:
-		vcpu->arch.guest_gprs[0] = 3 << 28;
+		vcpu->run->s.regs.gprs[0] = 3 << 28;
 		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
 		return 0;
 	case 1: /* same handling for 1 and 2 */
@@ -280,7 +280,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	}
 	free_page(mem);
 	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.guest_gprs[0] = 0;
+	vcpu->run->s.regs.gprs[0] = 0;
 	return 0;
 out_mem:
 	free_page(mem);
@@ -332,8 +332,8 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
 	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->arch.guest_gprs[base1] : 0;
-	u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
+	u64 address1 = disp1 + base1 ? vcpu->run->s.regs.gprs[base1] : 0;
+	u64 address2 = disp2 + base2 ? vcpu->run->s.regs.gprs[base2] : 0;
 	struct vm_area_struct *vma;
 	unsigned long user_address;
 
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 0a7941d74bc6..30eb0f73f9d5 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -48,7 +48,7 @@
 
 
 static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
-			unsigned long *reg)
+			u64 *reg)
 {
 	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	int rc;
@@ -220,7 +220,7 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 }
 
 static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
-			     unsigned long *reg)
+			     u64 *reg)
 {
 	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	struct kvm_s390_local_interrupt *li = NULL;
@@ -278,7 +278,7 @@ out_fi:
 }
 
 static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
-				unsigned long *reg)
+				u64 *reg)
 {
 	int rc;
 	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
@@ -316,7 +316,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 	int base2 = vcpu->arch.sie_block->ipb >> 28;
 	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u32 parameter;
-	u16 cpu_addr = vcpu->arch.guest_gprs[r3];
+	u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
 	u8 order_code;
 	int rc;
 
@@ -327,18 +327,18 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 
 	order_code = disp2;
 	if (base2)
-		order_code += vcpu->arch.guest_gprs[base2];
+		order_code += vcpu->run->s.regs.gprs[base2];
 
 	if (r1 % 2)
-		parameter = vcpu->arch.guest_gprs[r1];
+		parameter = vcpu->run->s.regs.gprs[r1];
 	else
-		parameter = vcpu->arch.guest_gprs[r1 + 1];
+		parameter = vcpu->run->s.regs.gprs[r1 + 1];
 
 	switch (order_code) {
 	case SIGP_SENSE:
 		vcpu->stat.instruction_sigp_sense++;
 		rc = __sigp_sense(vcpu, cpu_addr,
-				  &vcpu->arch.guest_gprs[r1]);
+				  &vcpu->run->s.regs.gprs[r1]);
 		break;
 	case SIGP_EXTERNAL_CALL:
 		vcpu->stat.instruction_sigp_external_call++;
@@ -363,12 +363,12 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 	case SIGP_SET_PREFIX:
 		vcpu->stat.instruction_sigp_prefix++;
 		rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
-				       &vcpu->arch.guest_gprs[r1]);
+				       &vcpu->run->s.regs.gprs[r1]);
 		break;
 	case SIGP_SENSE_RUNNING:
 		vcpu->stat.instruction_sigp_sense_running++;
 		rc = __sigp_sense_running(vcpu, cpu_addr,
-					  &vcpu->arch.guest_gprs[r1]);
+					  &vcpu->run->s.regs.gprs[r1]);
 		break;
 	case SIGP_RESTART:
 		vcpu->stat.instruction_sigp_restart++;
-- 
cgit v1.2.3


From 59674c1a6a35d56ae5197cbc9abe7bfec6762ba9 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Wed, 11 Jan 2012 11:20:33 +0100
Subject: KVM: s390: provide access guest registers via kvm_run

This patch adds the access registers to the kvm_run structure.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/include/asm/kvm.h      |  2 ++
 arch/s390/include/asm/kvm_host.h |  1 -
 arch/s390/kvm/kvm-s390.c         | 16 +++++++++-------
 3 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index 420dbb7db8dd..9acbde4af297 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -43,9 +43,11 @@ struct kvm_guest_debug_arch {
 
 #define KVM_SYNC_PREFIX (1UL << 0)
 #define KVM_SYNC_GPRS   (1UL << 1)
+#define KVM_SYNC_ACRS   (1UL << 2)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
 	__u64 gprs[16];	/* general purpose registers */
+	__u32 acrs[16];	/* access registers */
 };
 #endif
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index ed843cad4194..e6304268ea28 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -231,7 +231,6 @@ struct kvm_vcpu_arch {
 	s390_fp_regs      host_fpregs;
 	unsigned int      host_acrs[NUM_ACRS];
 	s390_fp_regs      guest_fpregs;
-	unsigned int      guest_acrs[NUM_ACRS];
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct tasklet_struct tasklet;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 80b12bac6a5b..0b91679369bc 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -289,7 +289,9 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	}
 
 	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
-	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX | KVM_SYNC_GPRS;
+	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
+				    KVM_SYNC_GPRS |
+				    KVM_SYNC_ACRS;
 	return 0;
 }
 
@@ -304,7 +306,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	save_access_regs(vcpu->arch.host_acrs);
 	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
-	restore_access_regs(vcpu->arch.guest_acrs);
+	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.gmap);
 	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 }
@@ -314,7 +316,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 	save_fp_regs(&vcpu->arch.guest_fpregs);
-	save_access_regs(vcpu->arch.guest_acrs);
+	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_fp_regs(&vcpu->arch.host_fpregs);
 	restore_access_regs(vcpu->arch.host_acrs);
 }
@@ -441,16 +443,16 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs));
+	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
 	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
-	restore_access_regs(vcpu->arch.guest_acrs);
+	restore_access_regs(vcpu->run->s.regs.acrs);
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	memcpy(&sregs->acrs, &vcpu->arch.guest_acrs, sizeof(sregs->acrs));
+	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
 	memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
 	return 0;
 }
@@ -702,7 +704,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 		return -EFAULT;
 
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
-			&vcpu->arch.guest_acrs, 64, prefix))
+			&vcpu->run->s.regs.acrs, 64, prefix))
 		return -EFAULT;
 
 	if (__guestcopy(vcpu,
-- 
cgit v1.2.3


From 851755871c1f3184f4124c466e85881f17fa3226 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Mon, 6 Feb 2012 10:59:02 +0100
Subject: KVM: s390: Sanitize fpc registers for KVM_SET_FPU

commit 7eef87dc99e419b1cc051e4417c37e4744d7b661 (KVM: s390: fix
register setting) added a load of the floating point control register
to the KVM_SET_FPU path. Lets make sure that the fpc is valid.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0b91679369bc..121316ef2e15 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -460,7 +460,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
-	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
+	vcpu->arch.guest_fpregs.fpc = fpu->fpc & FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
 	return 0;
 }
-- 
cgit v1.2.3


From 9e0d5473e2f0ba2d2fe9dab9408edef3060b710e Mon Sep 17 00:00:00 2001
From: Jens Freimann <jfrei@linux.vnet.ibm.com>
Date: Mon, 6 Feb 2012 10:59:03 +0100
Subject: KVM: s390: do store status after handling STOP_ON_STOP bit

In handle_stop() handle the stop bit before doing the store status as
described for "Stop and Store Status" in the Principles of Operation.
We have to give up the local_int.lock before calling kvm store status
since it calls gmap_fault() which might sleep. Since local_int.lock
only protects local_int.* and not guest memory we can give up the lock.

Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/intercept.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 776ef83c2771..361456577c6f 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -133,13 +133,6 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 
 	vcpu->stat.exit_stop_request++;
 	spin_lock_bh(&vcpu->arch.local_int.lock);
-	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
-		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
-		rc = kvm_s390_vcpu_store_status(vcpu,
-						  KVM_S390_STORE_STATUS_NOADDR);
-		if (rc >= 0)
-			rc = -EOPNOTSUPP;
-	}
 
 	if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) {
 		vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP;
@@ -155,7 +148,18 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 		rc = -EOPNOTSUPP;
 	}
 
-	spin_unlock_bh(&vcpu->arch.local_int.lock);
+	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
+		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
+		/* store status must be called unlocked. Since local_int.lock
+		 * only protects local_int.* and not guest memory we can give
+		 * up the lock here */
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
+		rc = kvm_s390_vcpu_store_status(vcpu,
+						KVM_S390_STORE_STATUS_NOADDR);
+		if (rc >= 0)
+			rc = -EOPNOTSUPP;
+	} else
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
 	return rc;
 }
 
-- 
cgit v1.2.3


From 151104a7b3a82f9c56d636595ae58084049d2559 Mon Sep 17 00:00:00 2001
From: Jens Freimann <jfrei@linux.vnet.ibm.com>
Date: Wed, 8 Feb 2012 08:28:29 +0100
Subject: KVM: s390: make sigp restart return busy when stop pending

On reboot the guest sends in smp_send_stop() a sigp stop to all CPUs
except for current CPU.  Then the guest switches to the IPL cpu by
sending a restart to the IPL CPU, followed by a sigp stop to the
current cpu. Since restart is handled by userspace it's possible that
the restart is delivered before the old stop.  This means that the IPL
CPU isn't restarted and we have no running CPUs. So let's make sure
that there is no stop action pending when we do the restart.

Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/sigp.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 30eb0f73f9d5..c703b1cbb0aa 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -309,6 +309,34 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
 	return rc;
 }
 
+static int __sigp_restart(struct kvm_vcpu *vcpu, u16 cpu_addr)
+{
+	int rc = 0;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return 3; /* not operational */
+
+	spin_lock(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = 3; /* not operational */
+		goto out;
+	}
+
+	spin_lock_bh(&li->lock);
+	if (li->action_bits & ACTION_STOP_ON_STOP)
+		rc = 2; /* busy */
+	else
+		VCPU_EVENT(vcpu, 4, "sigp restart %x to handle userspace",
+			cpu_addr);
+	spin_unlock_bh(&li->lock);
+out:
+	spin_unlock(&fi->lock);
+	return rc;
+}
+
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 {
 	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
@@ -372,6 +400,9 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		break;
 	case SIGP_RESTART:
 		vcpu->stat.instruction_sigp_restart++;
+		rc = __sigp_restart(vcpu, cpu_addr);
+		if (rc == 2) /* busy */
+			break;
 		/* user space must know about restart */
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 24a13044a84be51a6a4885a72ac9d5f4ed0742d0 Mon Sep 17 00:00:00 2001
From: Jens Freimann <jfrei@linux.vnet.ibm.com>
Date: Mon, 6 Feb 2012 10:59:05 +0100
Subject: KVM: s390: ignore sigp stop overinitiative

In __inject_sigp_stop() do nothing when the CPU is already in stopped
state.

Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/sigp.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index c703b1cbb0aa..f3d5cc297012 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -160,12 +160,15 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 	inti->type = KVM_S390_SIGP_STOP;
 
 	spin_lock_bh(&li->lock);
+	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED))
+		goto out;
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
 	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
 	li->action_bits |= action;
 	if (waitqueue_active(&li->wq))
 		wake_up_interruptible(&li->wq);
+out:
 	spin_unlock_bh(&li->lock);
 
 	return 0; /* order accepted */
-- 
cgit v1.2.3


From 9ec2d6dc6c4d4792b85dec2f09d39387fb7157d1 Mon Sep 17 00:00:00 2001
From: Jens Freimann <jfrei@linux.vnet.ibm.com>
Date: Mon, 6 Feb 2012 10:59:06 +0100
Subject: KVM: s390: add stop_on_stop flag when doing stop and store

When we do a stop and store status we need to pass ACTION_STOP_ON_STOP
flag to __sigp_stop().

Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/kvm/sigp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index f3d5cc297012..0ad4cf238391 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -385,7 +385,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		break;
 	case SIGP_STOP_STORE_STATUS:
 		vcpu->stat.instruction_sigp_stop++;
-		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP);
+		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP |
+						 ACTION_STOP_ON_STOP);
 		break;
 	case SIGP_SET_ARCH:
 		vcpu->stat.instruction_sigp_arch++;
-- 
cgit v1.2.3


From 9eed0735ca6a5cf386a4998ad4b6d52d1e29353f Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Mon, 6 Feb 2012 10:59:07 +0100
Subject: KVM: s390: provide control registers via kvm_run

There are several cases were we need the control registers for
userspace. Lets also provide those in kvm_run.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/s390/include/asm/kvm.h | 2 ++
 arch/s390/kvm/kvm-s390.c    | 9 ++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'arch/s390')

diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index 9acbde4af297..96076676e224 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -44,10 +44,12 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_PREFIX (1UL << 0)
 #define KVM_SYNC_GPRS   (1UL << 1)
 #define KVM_SYNC_ACRS   (1UL << 2)
+#define KVM_SYNC_CRS    (1UL << 3)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
 	__u64 gprs[16];	/* general purpose registers */
 	__u32 acrs[16];	/* access registers */
+	__u64 crs[16];	/* control registers */
 };
 #endif
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 121316ef2e15..cf3c0a91d046 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -291,7 +291,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
 	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
 				    KVM_SYNC_GPRS |
-				    KVM_SYNC_ACRS;
+				    KVM_SYNC_ACRS |
+				    KVM_SYNC_CRS;
 	return 0;
 }
 
@@ -580,6 +581,11 @@ rerun_vcpu:
 		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_PREFIX;
 		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
 	}
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
+		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_CRS;
+		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
+		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+	}
 
 	might_fault();
 
@@ -629,6 +635,7 @@ rerun_vcpu:
 	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
 	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
 	kvm_run->s.regs.prefix = vcpu->arch.sie_block->prefix;
+	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
-- 
cgit v1.2.3


From db3fe4eb45f3555d91a7124e18cf3a2f2a30eb90 Mon Sep 17 00:00:00 2001
From: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Date: Wed, 8 Feb 2012 13:02:18 +0900
Subject: KVM: Introduce kvm_memory_slot::arch and move lpage_info into it

Some members of kvm_memory_slot are not used by every architecture.

This patch is the first step to make this difference clear by
introducing kvm_memory_slot::arch;  lpage_info is moved into it.

Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/ia64/include/asm/kvm_host.h    |  3 ++
 arch/ia64/kvm/kvm-ia64.c            | 10 ++++++
 arch/powerpc/include/asm/kvm_host.h |  3 ++
 arch/powerpc/kvm/powerpc.c          | 10 ++++++
 arch/s390/include/asm/kvm_host.h    |  3 ++
 arch/s390/kvm/kvm-s390.c            | 10 ++++++
 arch/x86/include/asm/kvm_host.h     |  9 +++++
 arch/x86/kvm/mmu.c                  |  2 +-
 arch/x86/kvm/x86.c                  | 59 +++++++++++++++++++++++++++++++
 include/linux/kvm_host.h            | 11 +++---
 virt/kvm/kvm_main.c                 | 70 +++++--------------------------------
 11 files changed, 122 insertions(+), 68 deletions(-)

(limited to 'arch/s390')

diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 2689ee54a1c9..e35b3a84a40b 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -459,6 +459,9 @@ struct kvm_sal_data {
 	unsigned long boot_gp;
 };
 
+struct kvm_arch_memory_slot {
+};
+
 struct kvm_arch {
 	spinlock_t dirty_log_lock;
 
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 8ca7261e7b3d..d8ddbba6fe7d 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1571,6 +1571,16 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	return 0;
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		struct kvm_memory_slot *memslot,
 		struct kvm_memory_slot old,
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1843d5d2a3be..52eb9c1f4fe0 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -213,6 +213,9 @@ struct revmap_entry {
 #define KVMPPC_PAGE_WRITETHRU	HPTE_R_W	/* 0x40 */
 #define KVMPPC_GOT_PAGE		0x80
 
+struct kvm_arch_memory_slot {
+};
+
 struct kvm_arch {
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	unsigned long hpt_virt;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 0e21d155eea7..00d7e345b3fe 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -281,6 +281,16 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	return 0;
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
                                    struct kvm_memory_slot *memslot,
                                    struct kvm_memory_slot old,
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index e6304268ea28..7343872890a2 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -245,6 +245,9 @@ struct kvm_vm_stat {
 	u32 remote_tlb_flush;
 };
 
+struct kvm_arch_memory_slot {
+};
+
 struct kvm_arch{
 	struct sca_block *sca;
 	debug_info_t *dbf;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index cf3c0a91d046..17ad69d596fd 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -814,6 +814,16 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	return 0;
+}
+
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c24125cd0c63..74c9edf2bb18 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -483,6 +483,15 @@ struct kvm_vcpu_arch {
 	} osvw;
 };
 
+struct kvm_lpage_info {
+	unsigned long rmap_pde;
+	int write_count;
+};
+
+struct kvm_arch_memory_slot {
+	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
+};
+
 struct kvm_arch {
 	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 37e7f100a0e0..ff053ca32303 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -689,7 +689,7 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
 	unsigned long idx;
 
 	idx = gfn_to_index(gfn, slot->base_gfn, level);
-	return &slot->lpage_info[level - 2][idx];
+	return &slot->arch.lpage_info[level - 2][idx];
 }
 
 static void account_shadowed(struct kvm *kvm, gfn_t gfn)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3df0b7a140b0..ca74c1dadf3a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6239,6 +6239,65 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		put_page(kvm->arch.ept_identity_pagetable);
 }
 
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+	int i;
+
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) {
+			vfree(free->arch.lpage_info[i]);
+			free->arch.lpage_info[i] = NULL;
+		}
+	}
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	int i;
+
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		unsigned long ugfn;
+		int lpages;
+		int level = i + 2;
+
+		lpages = gfn_to_index(slot->base_gfn + npages - 1,
+				      slot->base_gfn, level) + 1;
+
+		slot->arch.lpage_info[i] =
+			vzalloc(lpages * sizeof(*slot->arch.lpage_info[i]));
+		if (!slot->arch.lpage_info[i])
+			goto out_free;
+
+		if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
+			slot->arch.lpage_info[i][0].write_count = 1;
+		if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
+			slot->arch.lpage_info[i][lpages - 1].write_count = 1;
+		ugfn = slot->userspace_addr >> PAGE_SHIFT;
+		/*
+		 * If the gfn and userspace address are not aligned wrt each
+		 * other, or if explicitly asked to, disable large page
+		 * support for this slot
+		 */
+		if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) ||
+		    !kvm_largepages_enabled()) {
+			unsigned long j;
+
+			for (j = 0; j < lpages; ++j)
+				slot->arch.lpage_info[i][j].write_count = 1;
+		}
+	}
+
+	return 0;
+
+out_free:
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		vfree(slot->arch.lpage_info[i]);
+		slot->arch.lpage_info[i] = NULL;
+	}
+	return -ENOMEM;
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_memory_slot old,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7a08496b974a..355e44555c39 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -171,11 +171,6 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
  */
 #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)
 
-struct kvm_lpage_info {
-	unsigned long rmap_pde;
-	int write_count;
-};
-
 struct kvm_memory_slot {
 	gfn_t base_gfn;
 	unsigned long npages;
@@ -184,7 +179,7 @@ struct kvm_memory_slot {
 	unsigned long *dirty_bitmap;
 	unsigned long *dirty_bitmap_head;
 	unsigned long nr_dirty_pages;
-	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
+	struct kvm_arch_memory_slot arch;
 	unsigned long userspace_addr;
 	int user_alloc;
 	int id;
@@ -376,6 +371,9 @@ int kvm_set_memory_region(struct kvm *kvm,
 int __kvm_set_memory_region(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem,
 			    int user_alloc);
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont);
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_memory_slot old,
@@ -385,6 +383,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
 				int user_alloc);
+bool kvm_largepages_enabled(void);
 void kvm_disable_largepages(void);
 void kvm_arch_flush_shadow(struct kvm *kvm);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a30447c5eb4a..8340e0e62034 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -535,21 +535,13 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 				  struct kvm_memory_slot *dont)
 {
-	int i;
-
 	if (!dont || free->rmap != dont->rmap)
 		vfree(free->rmap);
 
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		kvm_destroy_dirty_bitmap(free);
 
-
-	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
-		if (!dont || free->lpage_info[i] != dont->lpage_info[i]) {
-			vfree(free->lpage_info[i]);
-			free->lpage_info[i] = NULL;
-		}
-	}
+	kvm_arch_free_memslot(free, dont);
 
 	free->npages = 0;
 	free->rmap = NULL;
@@ -685,53 +677,6 @@ void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new)
 	slots->generation++;
 }
 
-#ifndef CONFIG_S390
-static int create_lpage_info(struct kvm_memory_slot *slot, unsigned long npages)
-{
-	int i;
-
-	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
-		unsigned long ugfn;
-		int lpages;
-		int level = i + 2;
-
-		lpages = gfn_to_index(slot->base_gfn + npages - 1,
-				      slot->base_gfn, level) + 1;
-
-		slot->lpage_info[i] = vzalloc(lpages * sizeof(*slot->lpage_info[i]));
-		if (!slot->lpage_info[i])
-			goto out_free;
-
-		if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
-			slot->lpage_info[i][0].write_count = 1;
-		if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
-			slot->lpage_info[i][lpages - 1].write_count = 1;
-		ugfn = slot->userspace_addr >> PAGE_SHIFT;
-		/*
-		 * If the gfn and userspace address are not aligned wrt each
-		 * other, or if explicitly asked to, disable large page
-		 * support for this slot
-		 */
-		if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) ||
-		    !largepages_enabled) {
-			unsigned long j;
-
-			for (j = 0; j < lpages; ++j)
-				slot->lpage_info[i][j].write_count = 1;
-		}
-	}
-
-	return 0;
-
-out_free:
-	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
-		vfree(slot->lpage_info[i]);
-		slot->lpage_info[i] = NULL;
-	}
-	return -ENOMEM;
-}
-#endif /* not defined CONFIG_S390 */
-
 /*
  * Allocate some memory and give it an address in the guest physical address
  * space.
@@ -819,10 +764,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		new.rmap = vzalloc(npages * sizeof(*new.rmap));
 		if (!new.rmap)
 			goto out_free;
-
-		if (create_lpage_info(&new, npages))
-			goto out_free;
 #endif /* not defined CONFIG_S390 */
+		if (kvm_arch_create_memslot(&new, npages))
+			goto out_free;
 	}
 
 	/* Allocate page dirty bitmap if needed */
@@ -880,8 +824,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (!npages) {
 		new.rmap = NULL;
 		new.dirty_bitmap = NULL;
-		for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i)
-			new.lpage_info[i] = NULL;
+		memset(&new.arch, 0, sizeof(new.arch));
 	}
 
 	update_memslots(slots, &new);
@@ -968,6 +911,11 @@ out:
 	return r;
 }
 
+bool kvm_largepages_enabled(void)
+{
+	return largepages_enabled;
+}
+
 void kvm_disable_largepages(void)
 {
 	largepages_enabled = false;
-- 
cgit v1.2.3