[PATCH 03/12] KVM: PPC: Book3S HV: Provide a way for userspace to get/set per-vCPU areas

From: Paul Mackerras <paulus@samba.org>
To: Alexander Graf <agraf@suse.de>
Cc: kvm-ppc@vger.kernel.org, kvm@vger.kernel.org
Subject: [PATCH 03/12] KVM: PPC: Book3S HV: Provide a way for userspace to get/set per-vCPU areas
Date: Tue, 28 Aug 2012 22:33:12 +1000	[thread overview]
Message-ID: <20120828123312.GD7258@bloggs.ozlabs.ibm.com> (raw)
In-Reply-To: <20120828123043.GA7258@bloggs.ozlabs.ibm.com>

The PAPR paravirtualization interface lets guests register three
different types of per-vCPU buffer areas in its memory for communication
with the hypervisor.  These are called virtual processor areas (VPAs).
Currently the hypercalls to register and unregister VPAs are handled
by KVM in the kernel, and userspace has no way to know about or save
and restore these registrations across a migration.

This adds get and set ioctls to allow userspace to see what addresses
have been registered, and to register or unregister them.  This will
be needed for guest hibernation and migration, and is also needed so
that userspace can unregister them on reset (otherwise we corrupt
guest memory after reboot by writing to the VPAs registered by the
previous kernel).  We also add a capability to indicate that the
ioctls are supported.

This also fixes a bug where we were calling init_vpa unconditionally,
leading to an oops when unregistering the VPA.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_ppc.h |    2 ++
 arch/powerpc/kvm/book3s_hv.c       |   54 +++++++++++++++++++++++++++++++++++-
 arch/powerpc/kvm/powerpc.c         |   23 +++++++++++++++
 include/linux/kvm.h                |   12 ++++++++
 4 files changed, 90 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 41a00ea..4e0bc22 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -201,6 +201,8 @@ int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
 int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
 int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
+int kvm_vcpu_get_vpa_info(struct kvm_vcpu *vcpu, struct kvm_ppc_vpa *vpa);
+int kvm_vcpu_set_vpa_info(struct kvm_vcpu *vcpu, struct kvm_ppc_vpa *vpa);
 
 void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 817837d..53d950b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -143,6 +143,57 @@ static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
 	vpa->yield_count = 1;
 }
 
+int kvm_vcpu_get_vpa_info(struct kvm_vcpu *vcpu, struct kvm_ppc_vpa *vpa)
+{
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	vpa->vpa_addr = vcpu->arch.vpa.next_gpa;
+	vpa->slb_shadow_addr = vcpu->arch.slb_shadow.next_gpa;
+	vpa->slb_shadow_size = vcpu->arch.slb_shadow.len;
+	vpa->dtl_addr = vcpu->arch.dtl.next_gpa;
+	vpa->dtl_size = vcpu->arch.dtl.len;
+	spin_unlock(&vcpu->arch.vpa_update_lock);
+	return 0;
+}
+
+static inline void set_vpa(struct kvmppc_vpa *v, unsigned long addr,
+			   unsigned long len)
+{
+	if (v->next_gpa != addr || v->len != len) {
+		v->next_gpa = addr;
+		v->len = addr ? len : 0;
+		v->update_pending = 1;
+	}
+}
+
+int kvm_vcpu_set_vpa_info(struct kvm_vcpu *vcpu, struct kvm_ppc_vpa *vpa)
+{
+	/* check that addresses are cacheline aligned */
+	if ((vpa->vpa_addr & (L1_CACHE_BYTES - 1)) ||
+	    (vpa->slb_shadow_addr & (L1_CACHE_BYTES - 1)) ||
+	    (vpa->dtl_addr & (L1_CACHE_BYTES - 1)))
+		return -EINVAL;
+
+	/* DTL must be at least 1 entry long, if being set */
+	if (vpa->dtl_addr) {
+		if (vpa->dtl_size < sizeof(struct dtl_entry))
+			return -EINVAL;
+		vpa->dtl_size -= vpa->dtl_size % sizeof(struct dtl_entry);
+	}
+
+	/* DTL and SLB shadow require VPA */
+	if (!vpa->vpa_addr && (vpa->slb_shadow_addr || vpa->dtl_addr))
+		return -EINVAL;
+
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	set_vpa(&vcpu->arch.vpa, vpa->vpa_addr, sizeof(struct lppaca));
+	set_vpa(&vcpu->arch.slb_shadow, vpa->slb_shadow_addr,
+		vpa->slb_shadow_size);
+	set_vpa(&vcpu->arch.dtl, vpa->dtl_addr, vpa->dtl_size);
+	spin_unlock(&vcpu->arch.vpa_update_lock);
+
+	return 0;
+}
+
 /* Length for a per-processor buffer is passed in at offset 4 in the buffer */
 struct reg_vpa {
 	u32 dummy;
@@ -321,7 +372,8 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	if (vcpu->arch.vpa.update_pending) {
 		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
-		init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
+		if (vcpu->arch.vpa.pinned_addr)
+			init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
 	}
 	if (vcpu->arch.dtl.update_pending) {
 		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 10e4dfb..72764ba 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -341,6 +341,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 		if (cpu_has_feature(CPU_FTR_ARCH_201))
 			r = 2;
 		break;
+	case KVM_CAP_PPC_VPA:
+		r = 1;
+		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
 #ifdef CONFIG_KVM_BOOK3S_64_HV
@@ -821,6 +824,26 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 #endif
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	case KVM_PPC_GET_VPA_INFO: {
+		struct kvm_ppc_vpa vpa;
+		r = kvm_vcpu_get_vpa_info(vcpu, &vpa);
+		if (r)
+			break;
+		r = -EFAULT;
+		if (copy_to_user(argp, &vpa, sizeof(vpa)))
+			break;
+		r = 0;
+	}
+	case KVM_PPC_SET_VPA_INFO: {
+		struct kvm_ppc_vpa vpa;
+		r = -EFAULT;
+		if (copy_from_user(&vpa, argp, sizeof(vpa)))
+			break;
+		r = kvm_vcpu_set_vpa_info(vcpu, &vpa);
+		break;
+	}
+#endif
 	default:
 		r = -EINVAL;
 	}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index f4f5be8..4a8bb4f 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -622,6 +622,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_S390_COW 79
 #define KVM_CAP_PPC_ALLOC_HTAB 80
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 81
+#define KVM_CAP_PPC_VPA 83
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -959,4 +960,15 @@ struct kvm_assigned_msix_entry {
 	__u16 padding[3];
 };
 
+struct kvm_ppc_vpa {
+	__u64 vpa_addr;
+	__u64 slb_shadow_addr;
+	__u64 dtl_addr;
+	__u32 slb_shadow_size;
+	__u32 dtl_size;
+};
+
+#define KVM_PPC_GET_VPA_INFO	_IOR(KVMIO, 0xae, struct kvm_ppc_vpa)
+#define KVM_PPC_SET_VPA_INFO	_IOW(KVMIO, 0xaf, struct kvm_ppc_vpa)
+
 #endif /* __LINUX_KVM_H */
-- 
1.7.10.rc3.219.g53414

