[S390] kvm: handle tprot intercepts

When running a kvm guest we can get intercepts for tprot, if the host
page table is read-only or not populated. This patch implements the
most common case (linux memory detection).
This also allows host copy on write for guest memory on newer systems.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

5 files changed, 53 insertions, 0 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index cef7dbf69df..e9bcdca32a3 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -138,6 +138,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_chsc;
 	u32 instruction_stsi;
 	u32 instruction_stfl;
+	u32 instruction_tprot;
 	u32 instruction_sigp_sense;
 	u32 instruction_sigp_emergency;
 	u32 instruction_sigp_stop;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index f7b6df45d8b..b5312050b22 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -105,6 +105,7 @@ static intercept_handler_t instruction_handlers[256] = {
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
 	[0xb7] = handle_lctl,
+	[0xe5] = kvm_s390_handle_e5,
 	[0xeb] = handle_lctlg,
 };
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 67345ae7ce8..123ebea7228 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -62,6 +62,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
 	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
 	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
+	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
 	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
 	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
 	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index a7b7586626d..65e2201a555 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -87,6 +87,7 @@ static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
 
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_e5(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 73c47bd95db..39162636108 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -326,3 +326,52 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 	}
 	return -EOPNOTSUPP;
 }
+
+static int handle_tprot(struct kvm_vcpu *vcpu)
+{
+	int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
+	int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
+	int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
+	int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
+	u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0;
+	u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
+	struct vm_area_struct *vma;
+
+	vcpu->stat.instruction_tprot++;
+
+	/* we only handle the Linux memory detection case:
+	 * access key == 0
+	 * guest DAT == off
+	 * everything else goes to userspace. */
+	if (address2 & 0xf0)
+		return -EOPNOTSUPP;
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
+		return -EOPNOTSUPP;
+
+
+	down_read(&current->mm->mmap_sem);
+	vma = find_vma(current->mm,
+			(unsigned long) __guestaddr_to_user(vcpu, address1));
+	if (!vma) {
+		up_read(&current->mm->mmap_sem);
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	}
+
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	if (!(vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_READ))
+		vcpu->arch.sie_block->gpsw.mask |= (1ul << 44);
+	if (!(vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_READ))
+		vcpu->arch.sie_block->gpsw.mask |= (2ul << 44);
+
+	up_read(&current->mm->mmap_sem);
+	return 0;
+}
+
+int kvm_s390_handle_e5(struct kvm_vcpu *vcpu)
+{
+	/* For e5xx... instructions we only handle TPROT */
+	if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01)
+		return handle_tprot(vcpu);
+	return -EOPNOTSUPP;
+}
+